Search

Simple Summary: The proper management of prostate cancer requires accurate assessment of patients diagnosed with prostate cancer, a common and often lethal cancer. Current conventional prostate cancer diagnosis relies on: (1) needle biopsy, which can result in side effects such as hemorrhage or infection, as well as misplacement of needles resulting in evaluation inaccuracy, (2) prostate serum antigen detection that can lead to overdiagnosis, or (3) MRI interpretations using the Prostate Imaging-Reporting and Data System (PI-RADS), which is a subjective method that depends on the experience of the radiologist's interpretation of the images. Quantitative analysis of MRI can alleviate the limitations of conventional approaches. Artificial intelligence applied to MRI requires big training datasets, and its application is restricted to patients scanned under certain restricted conditions. More recently, spectral/statistical techniques, adapted from remote sensing, have been applied and tested in spatially registered multi-parametric MRI. The new spectral/statistical techniques require limited training, are flexible regarding patient scanning conditions, and perform well relative to other techniques. This study extends spectral/statistical techniques to make them more independent of the individual radiologist by autonomously finding the appropriate tumor signature within a prostate and, therefore, providing an objective, non-invasive, accurate means for determining prostate tumor aggressiveness. Background: Accurate, reliable, non-invasive assessment of patients diagnosed with prostate cancer is essential for proper disease management. Quantitative assessment of multi-parametric MRI, such as through artificial intelligence or spectral/statistical approaches, can provide a non-invasive objective determination of the prostate tumor aggressiveness without side effects or potential poor sampling from needle biopsy or overdiagnosis from prostate serum antigen measurements. To simplify and expedite prostate tumor evaluation, this study examined the efficacy of autonomously extracting tumor spectral signatures for spectral/statistical algorithms for spatially registered bi-parametric MRI. Methods: Spatially registered hypercubes were digitally constructed by resizing, translating, and cropping from the image sequences (Apparent Diffusion Coefficient (ADC), High B-value, T2) from 42 consecutive patients in the bi-parametric MRI PI-CAI dataset. Prostate cancer blobs exceeded a threshold applied to the registered set from normalizing the registered set into an image that maximizes High B-value, but minimizes the ADC and T2 images, appearing "green" in the color composite. Clinically significant blobs were selected based on size, average normalized green value, sliding window statistics within a blob, and position within the hypercube. The center of mass and maximized sliding window statistics within the blobs identified voxels associated with tumor signatures. We used correlation coefficients (R) and p-values, to evaluate the linear regression fits of the z-score and SCR (with processed covariance matrix) to tumor aggressiveness, as well as Area Under the Curves (AUC) for Receiver Operator Curves (ROC) from logistic probability fits to clinically significant prostate cancer. Results: The highest R (R > 0.45), AUC (>0.90), and lowest p-values (<0.01) were achieved using z-score and modified registration applied to the covariance matrix and tumor signatures selected from the "greenest" parts from the selected blob. Conclusions: The first autonomous tumor signature applied to spatially registered bi-parametric MRI shows promise for determining prostate tumor aggressiveness. [ABSTRACT FROM AUTHOR]

(1) Background: Non-invasive prostate cancer assessments using multi-parametric MRI are essential to the reliable detection of lesions and proper management of patients. While current guidelines call for the administration of Gadolinium-containing intravenous contrast injections, eliminating such injections would simplify scanning and reduce patient risk and costs. However, augmented image analysis is necessary to extract important diagnostic information from MRIs. Purpose: This study aims to extend previous work on the signal to clutter ratio and test whether prostate tumor eccentricity and volume are indicators of tumor aggressiveness using bi-parametric (BP)-MRI. (2) Methods: This study retrospectively processed 42 consecutive prostate cancer patients from the PI-CAI data collection. BP-MRIs (apparent diffusion coefficient, high b-value, and T2 images) were resized, translated, cropped, and stitched to form spatially registered BP-MRIs. The International Society of Urological Pathology (ISUP) grade was used to judge cases of prostate cancer as either clinically significant prostate cancer (CsPCa) (ISUP ≥ 2) or clinically insignificant prostate cancer (CiPCa) (ISUP < 2). The Adaptive Cosine Estimator (ACE) algorithm was applied to the BP-MRIs, followed by thresholding, and then eccentricity and volume computations, from the labeled and blobbed detection maps. Then, univariate and multivariate linear regression fittings of eccentricity and volume were applied to the ISUP grade. The fits were quantitatively evaluated by computing correlation coefficients (R) and p-values. Area under the curve (AUC) and receiver operator characteristic (ROC) curve scores were used to assess the logistic fitting to CsPCa/CiPCa. (3) Results: Modest correlation coefficients (R) (>0.35) and AUC scores (0.70) for the linear and/or logistic fits from the processed prostate tumor eccentricity and volume computations for the spatially registered BP-MRIs exceeded fits using the parameters of prostate serum antigen, prostate volume, and patient age (R~0.17). (4) Conclusions: This is the first study that applied spectral approaches to BP-MRIs to generate tumor eccentricity and volume metrics to assess tumor aggressiveness. This study found significant values of R and AUC (albeit below those from multi-parametric MRI) to fit and relate the metrics to the ISUP grade and CsPCA/CiPCA, respectively. [ABSTRACT FROM AUTHOR]

Background: Current prostate cancer evaluation can be inaccurate and burdensome. Quantitative evaluation of Magnetic Resonance Imaging (MRI) sequences non-invasively helps prostate tumor assessment. However, including Dynamic Contrast Enhancement (DCE) in the examined MRI sequence set can add complications, inducing possible side effects from the IV placement or injected contrast material and prolonging scanning time. More accurate quantitative MRI without DCE and artificial intelligence approaches are needed. Purpose: Predict the risk of developing Clinically Significant (Insignificant) prostate cancer CsPCa (CiPCa) and correlate with the International Society of Urologic Pathology (ISUP) grade using processed Signal to Clutter Ratio (SCR) derived from spatially registered bi-parametric MRI (SRBP-MRI) and thereby enhance non-invasive management of prostate cancer. Methods: This pilot study retrospectively analyzed 42 consecutive prostate cancer patients from the PI-CAI data collection. BP-MRI (Apparent Diffusion Coefficient, High B-value, T2) were resized, translated, cropped, and stitched to form spatially registered SRBP-MRI. Efficacy of noise reduction was tested by regularizing, eliminating principal components (PC), and minimizing elliptical volume from the covariance matrix to optimize the SCR. MRI guided biopsy (MRBx), Systematic Biopsy (SysBx), combination (MRBx + SysBx), or radical prostatectomy determined the ISUP grade for each patient. ISUP grade ≥ 2 (<2) was judged as CsPCa (CiPCa). Linear and logistic regression were fitted to ISUP grade and CsPCa/CiPCa SCR. Correlation Coefficients (R) and Area Under the Curves (AUC) for Receiver Operator Curves (ROC) evaluated the performance. Results: High correlation coefficients (R) (>0.55) and high AUC (=1.0) for linear and/or logistic fit from processed SCR and z-score for SRBP-MRI greatly exceed fits using prostate serum antigen, prostate volume, and patient age (R ~ 0.17). Patients assessed with combined MRBx + SysBx and from individual MRI scanners achieved higher R (DR = 0.207+/−0.118) than all patients used in the fits. Conclusions: In the first study, to date, spectral approaches for assessing tumor aggressiveness on SRBP-MRI have been applied and tested and achieved high values of R and exceptional AUC to fit the ISUP grade and CsPCA/CiPCA, respectively. [ABSTRACT FROM AUTHOR]

Prostate cancer (PCa) is the most common cancer type in males in the Western World. MRI has an established role in diagnosis of PCa through guiding biopsies. Due to multistep complex nature of the MRI-guided PCa diagnosis pathway, diagnostic performance has a big variation. Developing artificial intelligence (AI) models using machine learning, particularly deep learning, has an expanding role in radiology. Specifically, for prostate MRI, several AI approaches have been defined in the literature for prostate segmentation, lesion detection and classification with the aim of improving diagnostic performance and interobserver agreement. In this review article, we summarize the use of radiology applications of AI in prostate MRI. [ABSTRACT FROM AUTHOR]

OATP1B3 is expressed de novo in primary prostate cancer tissue and to a greater degree in prostate cancer metastases. Gadoxetate disodium is a substrate of OATP1B3, and its uptake has been shown to correlate with OATP1B3 expression in other cancers. We aimed to evaluate use of gadoxetate disodium to image prostate cancer and to track its utility as a biomarker. A single center open-label non-randomized pilot study recruited men with (1) localized, and (2) metastatic castration resistant prostate cancer (mCRPC). Gadoxetate disodium-enhanced MRI was performed at four timepoints post-injection. The Wilcoxon signed rank test was used to compare MRI contrast enhancement ratio (CER) pre-injection and post-injection. OATP1B3 expression was evaluated via immunohistochemistry (IHC) and a pharmacogenomic analysis of OATP1B3, NCTP and OATP1B1 was conducted. The mCRPC subgroup (n = 9) demonstrated significant enhancement compared to pre-contrast images at 20-, 40- and 60-min timepoints (p < 0.0078). The localized cancer subgroup (n = 11) demonstrated earlier enhancement compared to the mCRPC group, but no retention over time (p > 0.05). OATP1B3 expression on IHC trended higher contrast enhancement between 20–40 min (p ≤ 0.064) and was associated with contrast enhancement at 60 min (p = 0.0422). OATP1B1 haplotype, with N130D and V174A substitutions, impacted enhancement at 40–60 min (p ≤ 0.038). mCRPC lesions demonstrate enhancement after injection of gadoxetate disodium on MRI and retention over 60 min. As inter-individual variability in OATP1B3 expression and function has both predictive and prognostic significance, gadoxetate disodium has potential as a biomarker in prostate cancer. [ABSTRACT FROM AUTHOR]

The Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) was developed with a consensus-based process using a combination of published data, and expert observations and opinions. In the short time since its release, numerous studies have validated the value of PI-RADS v2 but, as expected, have also identified a number of ambiguities and limitations, some of which have been documented in the literature with potential solutions offered. To address these issues, the PI-RADS Steering Committee, again using a consensus-based process, has recommended several modifications to PI-RADS v2, maintaining the framework of assigning scores to individual sequences and using these scores to derive an overall assessment category. This updated version, described in this article, is termed PI-RADS v2.1. It is anticipated that the adoption of these PI-RADS v2.1 modifications will improve inter-reader variability and simplify PI-RADS assessment of prostate magnetic resonance imaging even further. Research on the value and limitations on all components of PI-RADS v2.1 is strongly encouraged. The Prostate Imaging Reporting and Data System (PI-RADS) Committee, using a consensus-based process, has recommended several modifications to PI-RADS version 2 (v2), maintaining the framework of assigning scores to individual sequences and using these scores to derive an overall assessment category. The updated version is termed PI-RADS v2.1. [ABSTRACT FROM AUTHOR]

Introduction: Prostate cancer (PCa) imaging is a rapidly evolving field. Dramatic improvements in prostate MRI during the last decade will probably change the accuracy of diagnosis. This chapter reviews recent current evidence about MRI diagnostic performance and impact on PCa management.Materials and methods: The International Consultation on Urological Diseases nominated a committee to review the literature on prostate MRI. A search of the PubMed database was conducted to identify articles focussed on MP-MRI detection and staging protocols, reporting and scoring systems, the role of MP-MRI in diagnosing PCa prior to biopsy, in active surveillance, in focal therapy and in detecting local recurrence after treatment.Results: Differences in opinion were reported in the use of the strength of magnets [1.5 Tesla (T) vs. 3T] and coils. More agreement was found regarding the choice of pulse sequences; diffusion-weighted MRI (DW-MRI), dynamic contrast-enhanced MRI (DCE MRI), and/or MR spectroscopy imaging (MRSI) are recommended in addition to conventional T2-weighted anatomical sequences. In 2015, the Prostate Imaging Reporting and Data System (PI-RADS version 2) was described to standardize image acquisition and interpretation. MP-MRI improves detection of clinically significant PCa (csPCa) in the repeat biopsy setting or before the confirmatory biopsy in patients considering active surveillance. It is useful to guide focal treatment and to detect local recurrences after treatment. Its role in biopsy-naive patients or during the course of active surveillance remains debated.Conclusion: MP-MRI is increasingly used to improve detection of csPCa and for the selection of a suitable therapeutic approach. [ABSTRACT FROM AUTHOR]

Dramatic changes in the use of prostate magnetic resonance imaging (MRI) have occurred in the last decade. The recognition that MRI detects and localizes cancers with reasonable accuracy led to the development of directed biopsies. These image-guided biopsies have a higher sensitivity for clinically significant cancers and a lower sensitivity for indolent disease. Prospective trials provide level 1 evidence supporting the use of prostate MRI. For local staging, while the specificity of prostate MRI is high, its sensitivity is lacking for microscopic extraprostatic extension. Computer-aided diagnosis of prostate MRI promises to bring the diagnostic power of MRI to nonexpert readers and thus further integrate MRI into the diagnostic workup. [ABSTRACT FROM AUTHOR]

Imaging is critically important for the diagnosis, staging, and management of men with high-risk prostate cancer. Conventional imaging modalities have been employed for local and metastatic staging with limited performance. Sodium fluoride positron emission tomography is recommended when there is high suspicion of bone metastases despite a negative or indeterminate bone scan. Magnetic resonance imaging has advantages in local staging but its value depends on the extent of disease. Whole-body positron emission tomography/magnetic resonance imaging could provide both local and distant staging. None of the existing positron emission tomography agents are recommended in practice guidelines; however, among them, prostate-specific membrane antigen-based tracers seem to hold the most promise based on sensitivity and specificity. [ABSTRACT FROM AUTHOR]

Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges. Visual Abstract [ABSTRACT FROM AUTHOR]

Objective To describe the detection rate of anteriorly located prostate cancer ( PCa) with the addition of magnetic resonance imaging ( MRI)/ultrasonography ( US) fusion-guided biopsy ( FGB) to the standard transrectal ultrasonography ( TRUS)-guided biopsy. Patients and Methods All patients, regardless of their biopsy history, who were referred for clinical suspicion of PCa (i.e elevated prostate-specific antigen ( PSA) level and abnormal digital rectal examination) underwent 3T multiparametric- MRI ( mpMRI) screening; and those with suspicious lesions in the anterior region of the prostate were identified. Patients then received a FGB of all suspicious lesions in addition to a systematic 12-core extended sextant TRUS-guided biopsy. We conducted a lesion-based analysis comparing cancer detection rates of anterior targets using FGB vs systematic cores taken from the same anatomic sextant within the prostate. Lengths of cancer in the most involved core were also compared between the two biopsy techniques used. Patients with only anterior targets were analysed separately. Results Of 499 patients undergoing FGB, 162 had a total of 241 anterior lesions. The mean age, PSA level and prostate volume in this group were 62 years, 12.7 ng/dL, and 57 mL, respectively. In total, PCa was diagnosed in 121 anterior lesions (50.2%) identified on mpMRI. Sixty-two (25.7%) of these anterior lesions were documented as positive for cancer on systematic 12-core TRUS-guided biopsy cores, while 97 (40.2%) were positive on the targeted FGB cores ( P = 0.001). In lesions that were positive on both FGB and TRUS biopsy, the most involved core was 112% longer on FGB (3.7 vs 1.6 mm, P ≤ 0.01). Forty-two patients had only anterior lesions on mpMRI; of these, 24 (57.1%) were found to have cancer on the FGB + TRUS biopsy platform. Six patients were positive on FGB only and 13 were positive on both biopsy techniques; however, 7/13 patients were upgraded to a higher Gleason score after FGB. All five patients positive on TRUS biopsy only were candidates for active surveillance. Conclusion The results showed that FGB detects significantly more anteriorly located PCa than does TRUS-guided biopsy alone and it may serve as an effective tool for the subset of patients with such tumours. [ABSTRACT FROM AUTHOR]

Imaging has played an important role in the administration of personalized medicine. From diagnosing diseases to guiding therapies, imaging has become an all-encompassing modality. With respect to prostate cancer, personalized management of the disease has been transformed by imaging. Specifically, multiparametric magnetic resonance imaging has emerged as a vital player in the detection, characterization, and localization of the disease thus making the incorporation of imaging in personalized prostate cancer management integral. In this review, the current role of imaging in personalized medicine for the management of prostate cancer is discussed. [ABSTRACT FROM AUTHOR]

Study Type - Diagnosis (case series) Level of Evidence 4 What's known on the subject? and What does the study add? MRI has been shown to improve prostate cancer detection rates. Pinto et al. ( J Urol 2011; 86: 1281-5) reported their outcomes on 101 patients with low, moderate or high suspicion lesions on multiparametric MRI that were subsequently targeted via an MRI/ultrasound fusion biopsy platform. The prostate cancer detection rates were 27%, 66% and 89% respectively. Sciarra et al. ( Clin Cancer Res 2010; 16: 1875-83) performed a prospective trial in 180 patients with prior negative biopsy and persistent PSA elevation. Patients were randomized to either MRI targeted biopsy followed by random 12-core TRUS biopsy vs random TRUS guided biopsy alone. Prostate cancer detection in the MRI targeted group was 45.5% vs 24.4% in the random group. Although MRI has been shown to improve prostate cancer detection rates, there has not previously been any work looking at the ability of MRI to detect prostate cancer localized to the very distal apex of the prostate. This is an important topic in that it might lead clinicians to counsel their patients in treatment decisions if it is felt that a treatment might not treat this section of the prostate well, e.g. high intensity focused ultrasound therapy that might spare the distal apex. OBJECTIVE To describe an undescribed 'very distal' apical prostate cancer on multiparametric MRI (mpMRI) since apical prostate cancer can be difficult to detect in transrectal ultrasound guided biopsy and might therefore be missed in treatment decisions such as high intensity focused ultrasound or surgical therapy., PATIENTS AND METHODS From January 2011 to December 2012 a total of 210 consecutive patients underwent 3 T mpMRI with endorectal coil followed by our previously described MRI/ultrasound image fused and directed TRUS biopsies., Patients also underwent 12-core TRUS sextant biopsies., The inclusion criteria required at least one distal apical prostate lesion visualized on mpMRI and targeted for biopsy., RESULTS A total of 38 men (median age 62 years, median PSA 7.68 ng/dL) were identified as having distal apical prostate cancer on mpMRI., Thirteen patients (34%) had a prior diagnosis of cancer and were on active surveillance protocols while 25 (66%) did not. Of those patients, 21 (55%) had undergone a median of two prior negative biopsies., Twenty-two patients (58%) were positive on biopsy for prostate cancer. On breakdown of patients who were positive, 17 (77%) were positive on TRUS random biopsies and 21 (95%) were positive on MRI targeted biopsies with the majority of patients having multifocal disease., At the distal apical lesions of interest, 80% were positive on MRI targeted biopsy. In addition 33% of these patients were upgraded based on MRI targeted biopsy at the distal lesion., CONCLUSIONS Very distal apical prostate cancer can be accurately detected and sampled with mpMRI and subsequent MRI/ultrasound fusion biopsy., This may aid clinicians and patients in decision making for therapeutic modalities. [ABSTRACT FROM AUTHOR]

Study Type - Diagnosis (case series) Level of Evidence 4 What's known on the subject? and What does the study add? Benign prostatic hyperplasia is the most common symptomatic disorder of the prostate and its severity varies greatly in the population. Various methods have been used to estimate prostate volumes in the past including the digital rectal examination and ultrasound measurements. High-resolution T2 weighted MRI can provide accurate measurements of zonal volumes and total volumes, which can be used to better understand the etiology of lower urinary tract symptoms of men. OBJECTIVE To use ability of magnetic resonance imaging (MRI) to investigate age-related changes in zonal prostate volumes., PATIENTS AND METHODS This Institutional Review Board approved, Health Insurance Portability and Accountability Act-compliant study consisted of 503 patients who underwent 3 T prostate MRI before any treatment for prostate cancer., Whole prostate (WP) and central gland (CG) volumes were manually contoured on T2-weighted MRI using a semi-automated segmentation tool. WP, CG, peripheral zone (PZ) volumes were measured for each patient., WP, CG, PZ volumes were correlated with age, serum prostate-specific antigen (PSA) level, International Prostate Symptom Score (IPSS), Sexual Health Inventory for Men (SHIM) scores., RESULTS Linear regression analysis showed positive correlations between WP, CG volumes and patient age ( P < 0.001); there was no correlation between age and PZ volume ( P= 0.173)., There was a positive correlation between WP, CG volumes and serum PSA level ( P < 0.001), as well as between PZ volume and serum PSA level ( P= 0.002)., At logistic regression analysis, IPSS positively correlated with WP, CG volumes ( P < 0.001)., SHIM positively correlated with WP ( P= 0.015) and CG ( P= 0.023) volumes., As expected, the IPSS of patients with prostate volumes (WP, CG) in first decile for age were significantly lower than those in tenth decile., CONCLUSIONS Prostate MRI is able to document age-related changes in prostate zonal volumes., Changes in WP and CG volumes correlated inversely with changes in lower urinary tract symptoms., These findings suggest a role for MRI in measuring accurate prostate zonal volumes; have interesting implications for study of age-related changes in the prostate. [ABSTRACT FROM AUTHOR]

ARPKD/CHF is an inherited disease characterized by non-obstructive fusiform dilatation of the renal collecting ducts leading to enlarged spongiform kidneys and ductal plate malformation of the liver resulting in congenital hepatic fibrosis. ARPKD/CHF has a broad spectrum of clinical presentations involving the kidney and liver. Imaging plays an important role in the diagnosis and follow-up of ARPKD/CHF. Combined use of conventional and high-resolution US with MR cholangiography in ARPKD/CHF patients allows detailed definition of the extent of kidney and hepatobiliary manifestations without requiring ionizing radiation and contrast agents. [ABSTRACT FROM AUTHOR]

We describe a 10-year-old girl with congenital absence of the portal vein (CAPV) and multiple hyperplastic nodules in the liver. MRI appearances of the liver lesions and the portocaval anastomosis between the inferior mesenteric vein and internal iliac veins are presented. In addition, the relevance of CAPV and nodular lesions of the liver is reviewed. [ABSTRACT FROM AUTHOR]

Artificial intelligence developments are essential to the successful deployment of community-wide, MRI-driven prostate cancer diagnosis. AI systems should ensure that the main benefits of biopsy avoidance are delivered while maintaining consistent high specificities, at a range of disease prevalences. Since all current artificial intelligence / computer-aided detection systems for prostate cancer detection are experimental, multiple developmental efforts are still needed to bring the vision to fruition. Initial work needs to focus on developing systems as diagnostic supporting aids so their results can be integrated into the radiologists' workflow including gland and target outlining tasks for fusion biopsies. Developing AI systems as clinical decision-making tools will require greater efforts. The latter encompass larger multicentric, multivendor datasets where the different needs of patients stratified by diagnostic settings, disease prevalence, patient preference, and clinical setting are considered. AI-based, robust, standard operating procedures will increase the confidence of patients and payers, thus enabling the wider adoption of the MRI-directed approach for prostate cancer diagnosis. Key Points: • AI systems need to ensure that the benefits of biopsy avoidance are delivered with consistent high specificities, at a range of disease prevalence. • Initial work has focused on developing systems as diagnostic supporting aids for outlining tasks, so they can be integrated into the radiologists' workflow to support MRI-directed biopsies. • Decision support tools require a larger body of work including multicentric, multivendor studies where the clinical needs, disease prevalence, patient preferences, and clinical setting are additionally defined. [ABSTRACT FROM AUTHOR]

Introduction: Classification of clear cell renal cell carcinoma (ccRCC) growth rates in patients with Von Hippel–Lindau (VHL) syndrome has several ramifications for tumor monitoring and surgical planning. Using two separate machine-learning algorithms, we sought to produce models to predict ccRCC growth rate classes based on qualitative MRI-derived characteristics. Material and Methods: We used a prospectively maintained database of patients with VHL who underwent surgical resection for ccRCC between January 2015 and June 2022. We employed a threshold growth rate of 0.5 cm per year to categorize ccRCC tumors into two distinct groups—'slow-growing' and 'fast-growing'. Utilizing a questionnaire of qualitative imaging features, two radiologists assessed each lesion on different MRI sequences. Two machine-learning models, a stacked ensemble technique and a decision tree algorithm, were used to predict the tumor growth rate classes. Positive predictive value (PPV), sensitivity, and F1-score were used to evaluate the performance of the models. Results: This study comprises 55 patients with VHL with 128 ccRCC tumors. Patients' median age was 48 years, and 28 patients were males. Each patient had an average of two tumors, with a median size of 2.1 cm and a median growth rate of 0.35 cm/year. The overall performance of the stacked and DT model had 0.77 ± 0.05 and 0.71 ± 0.06 accuracies, respectively. The best stacked model achieved a PPV of 0.92, a sensitivity of 0.91, and an F1-score of 0.90. Conclusion: This study provides valuable insight into the potential of machine-learning analysis for the determination of renal tumor growth rate in patients with VHL. This finding could be utilized as an assistive tool for the individualized screening and follow-up of this population. [ABSTRACT FROM AUTHOR]

To report an initial experience with a novel, "fully" transperineal (TP) prostate fusion biopsy using an unconstrained ultrasound transducer placed on the perineal skin to guide biopsy needles inserted via a TP approach. Conventional TP prostate biopsies for detection of prostate cancer have been performed with transrectal ultrasound, requiring specialized hardware, imposing limitations on needle trajectory, and contributing to patient discomfort. Seventy-six patients with known or suspected prostate cancer underwent 78 TP biopsy sessions in an academic center between June 2018 and April 2022 and were included in this study. These patients underwent TP prostate fusion biopsy using a grid or freehand device with transrectal ultrasound as well as TP prostate fusion biopsy using TP ultrasound in the same session. Per-session and per-lesion cancer detection rates were compared for conventional and fully TP biopsies using Fisher exact and McNemar's tests. After a refinement period in 30 patients, 92 MRI-visible prostate lesions were sampled in 46 subsequent patients, along with repeat biopsies in 2 of the 30 patients from the refinement period. Grade group ≥2 cancer was diagnosed in 24/92 lesions (26%) on conventional TP biopsy (17 lesions with grid, 7 with freehand device), and in 25/92 lesions (27%) on fully TP biopsy (P = 1.00), with a 73/92 (79%) rate of agreement for grade group ≥2 cancer between the two methods. Fully TP biopsy is feasible and may detect prostate cancer with detection rates comparable to conventional TP biopsy. [ABSTRACT FROM AUTHOR]

Background: von Hippel–Lindau syndrome (VHL) is an autosomal dominant hereditary syndrome with an increased predisposition of developing numerous cysts and tumors, almost exclusively clear cell renal cell carcinoma (ccRCC). Considering the lifelong surveillance in such patients to monitor the disease, patients with VHL are preferentially imaged using MRI to eliminate radiation exposure. Purpose: Segmentation of kidney and tumor structures on MRI in VHL patients is useful in lesion characterization (e.g., cyst vs. tumor), volumetric lesion analysis, and tumor growth prediction. However, automated tasks such as ccRCC segmentation on MRI is sparsely studied. We develop segmentation methodology for ccRCC on T1 weighted precontrast, corticomedullary, nephrogenic, and excretory contrast phase MRI. Methods: We applied a new neural network approache using a novel differentiable decision forest, called hinge forest (HF), to segment kidney parenchyma, cyst, and ccRCC tumors in 117 images from 115 patients. This data set represented an unprecedented 504 ccRCCs with 1171 cystic lesions obtained at five different MRI scanners. The HF architecture was compared with U‐Net on 10 randomized splits with 75% used for training and 25% used for testing. Both methods were trained with Adam using default parameters (α=0.001,β1=0.9,β2=0.999$\alpha = 0.001,\ \beta _1 = 0.9,\ \beta _2 = 0.999$) over 1000 epochs. We further demonstrated some interpretability of our HF method by exploiting decision tree structure. Results: The HF achieved an average kidney, cyst, and tumor Dice similarity coefficient (DSC) of 0.75 ± 0.03, 0.44 ± 0.05, 0.53 ± 0.04, respectively, while U‐Net achieved an average kidney, cyst, and tumor DSC of 0.78 ± 0.02, 0.41 ± 0.04, 0.46 ± 0.05, respectively. The HF significantly outperformed U‐Net on tumors while U‐Net significantly outperformed HF when segmenting kidney parenchymas (α<0.01$\alpha < 0.01$). Conclusions: For the task of ccRCC segmentation, the HF can offer better segmentation performance compared to the traditional U‐Net architecture. The leaf maps can glean hints about deep learning features that might prove to be useful in other automated tasks such as tumor characterization. [ABSTRACT FROM AUTHOR]

The article discusses the use of social media to engage and educate patients about prostate imaging. Topics covered include a key challenge in managing prostate cancer (PCa), the effectiveness of multi-parametric magnetic resonance imaging in detecting PCa, and social media alternatives that enable patients to rapidly search and access information regarding their diagnosis and treatment.

Purpose: To evaluate the cancer detection rates of reduced-core biopsy schemes in patients with unilateral mpMRI-visible intraprostatic lesions and to analyze the contribution of systematic biopsy cores in clinically significant prostate cancer (csPCa) detection. Methods: 212 patients with mpMRI-visible unilateral intraprostatic lesions undergoing MRI/TRUS fusion-guided targeted biopsy (TBx) and systematic biopsy (SBx) were included. Cancer detection rates of TBx + SBx, as determined by highest Gleason Grade Group (GG), were compared to 3 reduced-core biopsy schemes: TBx alone, TBx + ipsilateral systematic biopsy (IBx; MRI-positive hemigland), and TBx + contralateral systematic biopsy (CBx; MRI-negative hemigland). Patient-level and biopsy core-level data were analyzed using descriptive statistics with confidence intervals. Univariable and multivariable logistic regression analysis was conducted to identify predictors of csPCa (≥ GG2) detected in MRI-negative hemiglands at p < 0.05. Results: Overall, 43.4% (92/212) of patients had csPCa and 66.0% (140/212) of patients had any PCa detected by TBx + SBx. Of patients with csPCa, 81.5% had exclusively ipsilateral involvement (MRI-positive), 7.6% had only contralateral involvement (MRI-negative), and 10.9% had bilateral involvement. The csPCa detection rates of reduced-core biopsy schemes were 35.4% (75/212), 40.1% (85/212), and 39.6% (84/212) for TBx alone, TBx + IBx, and TBx + CBx, respectively, with detection sensitivities of 81.5%, 92.4%, and 91.3% compared to TBx + SBx. Conclusion: Reduced-core prostate biopsy strategies confined to the ipsilateral hemigland underestimate csPCa burden by at least 8% in patients with unilateral mpMRI-visible intraprostatic lesions. The combined TBx + SBx strategy maximizes csPCa detection. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of the study is to differentiate granulomatous prostatitis (GP) from high-grade prostate cancer (PCa) based on clinical findings and imaging characteristics on multiparametric MRI (MP-MRI). Methods: Pathology from patients undergoing MRI/US fusion-guided prostate biopsies between 2014 and 2015 was reviewed. Five patients with biopsy proven GP were identified as well as 15 patients with biopsy-proven Gleason score ≥4 + 3 = 7 PCa. Patients were matched for age, serum PSA level, and prebiopsy-assigned MP-MRI cancer suspicion scores. MP-MRI studies were reviewed to identify findings that would differentiate GP from PCa in patients who had equally high suspicion scores based upon imaging characteristics. Results: All five patients with GP on MR/US fusion-targeted biopsies were assigned a PIRADS 4 or 5 suspicion score. There were equally high suspicion scores on MP-MRI for both groups ( p = 0.57). Re-evaluation of the MRI characteristics of the 5 GP patients and 15 matched controls who had pathologically proven Gleason score ≥4 + 3 = 7 PCa on targeted biopsy demonstrated statistically lower mean ADC values within the index targeted lesion for PCa vs. GP ( p = 0.002) Qualitatively, no patients with GP on biopsy had imaging evidence of higher-staged disease, while 33% of patients in the high-risk PCa cohort demonstrated at least one high-stage feature ( p = 0.003). Conclusion: Patients with GP routinely have MRIs with moderate to high levels of suspicion for harboring PCa. Re-evaluation of these patients' imaging demonstrated characteristics including significantly higher ADC values and absence of high-stage features, which may help differentiate areas of GP from PCa in the future. [ABSTRACT FROM AUTHOR]

Purpose: Hereditary leiomyomatosis and renal cell carcinoma (HLRCC) syndrome is associated with an aggressive form of renal cell carcinoma with high risk of metastasis, even in small primary tumors with unequivocal imaging findings. In this study, we compare the performance of ultra-high b-value diffusion-weighted imaging (DWI) sequence (b = 2000 s/mm2) to standard DWI (b = 800 s/mm2) sequence in identifying malignant lesions in patients with HLRCC. Methods: Twenty-eight patients (n = 18 HLRCC patients with 22 lesions, n = 10 controls) were independently evaluated by three abdominal radiologists with different levels of experience using four combinations of MRI sequences in two separate sessions (session 1: DWI with b-800, session 2: DWI with b-2000). T1 precontrast, T2-weighted (T2WI), and apparent diffusion coefficient (ADC) sequences were similar in both sessions. Each identified lesion was subjectively assessed using a six-point cancer likelihood score based on individual sequences and overall impression. Results: The ability to distinguish benign versus malignant renal lesions improved with the use of b-2000 for more experienced radiologists (Reader 1 AUC: Session 1—0.649 and Session 2—0.938, p = 0.017; Reader 2 AUC: Session 1—0.781 and Session 2—0.921, p = 0.157); whereas no improvement was observed for the less experienced reader (AUC: Session 1—0.541 and Session 2—0.607, p = 0.699). Conclusion: The inclusion of ultra-high b-value DWI sequence improved the ability of classification of renal lesions in patients with HLRCC for experienced radiologists. Consideration should be given toward incorporation of DWI with b-2000 s/mm2 into existing renal MRI protocols. [ABSTRACT FROM AUTHOR]

Men of African ancestry have a disproportionately higher incidence of prostate cancer and likelihood of mortality when compared to men of European ancestry. The underlying reasons for this are unknown and may be due to an interplay of genomic and environmental factors. In this patient population, higher incidence can potentially be counteracted by earlier screening and more intense surveillance. Recent American Urological Association guidelines now support screening men of African ancestry beginning at age 40-45 years with a grade B recommendation. Multiparametric MRI (mpMRI) has proven to be very useful in detecting clinically significant prostate cancer, but access to this resource is often limited among communities of color. In this clinical trial, we will assess the influence of mpMRI and MRI/US fusion-guided biopsy on detection rates of clinically significant prostate cancer in men of African ancestry and compare these results with self-referred patients who are predominantly of European origin. This clinical trial (NCT05872503) is a prospective, single-arm observational study. Up to 345 biopsy-naïve patients age >35 years with PSA ≥3ng/mL, positive rectal exam, or strong family history of prostate cancer who self-identify as having African ancestry will be recruited. Study patients will be referred by local hospitals that provide care mainly to communities of color, and patients will undergo mpMRI at the National Cancer Institute. Patients with identified PI-RADS ≥3 lesions will undergo MRI/US fusion-guided biopsy within six months of the initial mpMRI and will receive standard-of-care treatment and follow-up for five years with annual phone or virtual visits. Patients without PI-RADS ≥3 lesions will not receive biopsy and will be followed for five years via serum PSA and mpMRI. Cancer detection rates at the patient-level between men of African ancestry and previously accrued patients of European ancestry will be compared using Fisher's exact test of independence. Results: Conclusions: [ABSTRACT FROM AUTHOR]

Purpose: Upfront knowledge of tumor growth rates of clear cell renal cell carcinoma in von Hippel-Lindau syndrome (VHL) patients can allow for a more personalized approach to either surveillance imaging frequency or surgical planning. In this study, we implement a machine learning algorithm utilizing radiomic features of renal tumors identified on baseline magnetic resonance imaging (MRI) in VHL patients to predict the volumetric growth rate category of these tumors. Materials and Methods: A total of 73 VHL patients with 173 pathologically confirmed Clear Cell Renal Cell Carcinoma (ccRCCs) underwent MRI at least at two different time points between 2015 and 2021. Each tumor was manually segmented in excretory phase contrast T1 weighed MRI and co-registered on pre-contrast, corticomedullary and nephrographic phases. Radiomic features and volumetric data from each tumor were extracted using the PyRadiomics library in Python (4544 total features). Tumor doubling time (DT) was calculated and patients were divided into two groups: DT < = 1 year and DT > 1 year. Random forest classifier (RFC) was used to predict the DT category. To measure prediction performance, the cohort was randomly divided into 100 training and test sets (80% and 20%). Model performance was evaluated using area under curve of receiver operating characteristic curve (AUC-ROC), as well as accuracy, F1, precision and recall, reported as percentages with 95% confidence intervals (CIs). Results: The average age of patients was 47.2 ± 10.3 years. Mean interval between MRIs for each patient was 1.3 years. Tumors included in this study were categorized into 155 Grade 2; 16 Grade 3; and 2 Grade 4. Mean accuracy of RFC model was 79.0% [67.4–90.6] and mean AUC-ROC of 0.795 [0.608–0.988]. The accuracy for predicting DT classes was not different among the MRI sequences (P-value = 0.56). Conclusion: Here we demonstrate the utility of machine learning in accurately predicting the renal tumor growth rate category of VHL patients based on radiomic features extracted from different T1-weighted pre- and post-contrast MRI sequences. [ABSTRACT FROM AUTHOR]

Introduction: Multiple scoring systems have been proposed for prostate MRI reporting. We sought to review the clinical impact of the new Prostate Imaging Reporting and Data System v2 (PI-RADS) and compare those results to our proposed Simplified Qualitative System (SQS) score with respect to detection of prostate cancers and clinically significant prostate cancers. Methods: All patients who underwent multiparametric prostate MRI (mpMRI) had their images interpreted using PI-RADS v1 and SQS score. PI-RADS v2 was calculated from prospectively collected data points. Patients with positive mpMRIs were then referred by their urologists for enrollment in an IRB-approved prospective phase III trial of mpMRI-Ultrasound (MR/TRUS) fusion biopsy of suspicious lesions. Standard 12-core biopsy was performed at the same setting. Clinical data were collected prospectively. Results: 1060 patients were imaged using mpMRI at our institution during the study period. 341 participants were then referred to the trial. 312 participants underwent MR/TRUS fusion biopsy of 452 lesions and were included in the analysis. 202 participants had biopsy-proven cancer (64.7%) and 206 (45.6%) lesions were positive for cancer. Distribution of cancer detected at each score produced a Gaussian distribution for SQS while PI-RADS demonstrates a negatively skewed curve with 82.1% of cases being scored as a 4 or 5. Patient-level data demonstrated AUC of 0.702 (95% CI 0.65 to 0.73) for PI-RADS and 0.762 (95% CI 0.72 to 0.81) for SQS (p< 0.0001) with respect to the detection of prostate cancer. The analysis for clinically significant prostate cancer at a per lesion level resulted in an AUC of 0.725 (95% CI 0.69 to 0.76) and 0.829 (95% CI 0.79 to 0.87) for the PI-RADS and SQS score, respectively (p< 0.0001). Conclusions: mpMRI is a useful tool in the workup of patients at risk for prostate cancer, and serves as a platform to guide further evaluation with MR/TRUS fusion biopsy. SQS score provided a more normal distribution of scores and yielded a higher AUC than PI-RADS v2. However until our findings are validated, we recommend reporting of detailed sequence-specific findings. This will allow for prospectively collected data to be utilized in determining the impact of ongoing changes to these scoring systems as our understanding of mpMRI interpretation evolves. [ABSTRACT FROM AUTHOR]

Objective: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher’s exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.A total of 773 consecutive patients (median age 61 [IQR 56–67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67–76%] vs. 63% [95% CI 56–69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62–80%] vs. 75% [95% CI 63–85%]), positive predictive value (44% [95% CI 39–49%] vs. 38% [95% CI 32–43%]), or negative predictive value (89% [95% CI 86–92%] vs. 89% [95% CI 85–93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54–5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63–4.24; P = 0.24).Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.Materials and methods: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher’s exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.A total of 773 consecutive patients (median age 61 [IQR 56–67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67–76%] vs. 63% [95% CI 56–69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62–80%] vs. 75% [95% CI 63–85%]), positive predictive value (44% [95% CI 39–49%] vs. 38% [95% CI 32–43%]), or negative predictive value (89% [95% CI 86–92%] vs. 89% [95% CI 85–93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54–5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63–4.24; P = 0.24).Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.Results: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher’s exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.A total of 773 consecutive patients (median age 61 [IQR 56–67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67–76%] vs. 63% [95% CI 56–69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62–80%] vs. 75% [95% CI 63–85%]), positive predictive value (44% [95% CI 39–49%] vs. 38% [95% CI 32–43%]), or negative predictive value (89% [95% CI 86–92%] vs. 89% [95% CI 85–93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54–5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63–4.24; P = 0.24).Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.Conclusion: To assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.This retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher’s exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.A total of 773 consecutive patients (median age 61 [IQR 56–67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67–76%] vs. 63% [95% CI 56–69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62–80%] vs. 75% [95% CI 63–85%]), positive predictive value (44% [95% CI 39–49%] vs. 38% [95% CI 32–43%]), or negative predictive value (89% [95% CI 86–92%] vs. 89% [95% CI 85–93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54–5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63–4.24; P = 0.24).Our study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology. [ABSTRACT FROM AUTHOR]

The role of multiparametric MRI (mpMRI) in the detection of prostate cancer is well-established. Based on the limited role of dynamic contrast enhancement (DCE) in PI-RADS v2.1, the risk of potential side effects, and the increased cost and time, there has been an increase in studies advocating for the omission of DCE from MRI assessments. Per PI-RADS v2.1, DCE is indicated in the assessment of PI-RADS 3 lesions in the peripheral zone, with its most pronounced effect when T2WI and DWI are of insufficient quality. The aim of this study was to evaluate the methodology and reporting in the literature from the past 5 years regarding the use of DCE in prostate MRI, especially with respect to the indications for DCE as stated in PI-RADS v2.1, and to describe the different approaches used across the studies. We searched for studies investigating the use of bpMRI and/or mpMRI in the detection of clinically significant prostate cancer between January 2017 and April 2022 in the PubMed, Web of Science, and Google Scholar databases. Through the search process, a total of 269 studies were gathered and 41 remained after abstract and full-text screening. The following information was extracted from the eligible studies: general clinical and technical characteristics of the studies, the number of PI-RADS 3 lesions, different definitions of clinically significant prostate cancer (csPCa), biopsy thresholds, reference standard methods, and number and experience of readers. Forty-one studies were included in the study. Only 51% (21/41) of studies reported the prevalence of csPCa in their equivocal lesion (PI-RADS category 3 lesions) subgroups. Of the included studies, none (0/41) performed a stratified sub-analysis of the DCE benefit versus MRI quality and 46% (19/41) made explicit statements about removing MRI scans based on a range of factors including motion, noise, and image artifacts. Furthermore, the number of studies investigating the role of DCE using readers with varying experience was relatively low. This review demonstrates that a high proportion of the studies investigating whether bpMRI can replace mpMRI did not transparently report information inherent to their study design concerning the key indications of DCE, such as the number of clinically insignificant/significant PI-RADS 3 lesions, nor did they provide any sub-analyses to test image quality, with some removing bad quality MRI scans altogether, or reader-experience-dependency indications for DCE. For the studies that reported on most of the DCE indications, their conclusions about the utility of DCE were heavily definition-dependent (with varying definitions of csPCa and of the PI-RADS category biopsy significance threshold). Reporting the information inherent to the study design and related to the specific indications for DCE as stated in PI-RADS v2.1 is needed to determine whether DCE is helpful or not. With most of the recent literature being retrospective and not including the data related to DCE indications in particular, the ongoing dispute between bpMRI and mpMRI is likely to linger. [ABSTRACT FROM AUTHOR]

IMPORTANCE Targeted magnetic resonance (MR)/ultrasound fusion prostate biopsy has been shown to detect prostate cancer. The implications of targeted biopsy alone vs standard extended-sextant biopsy or the 2 modalities combined are not well understood. OBJECTIVE To assess targeted vs standard biopsy and the 2 approaches combined for the diagnosis of intermediate- to high-risk prostate cancer. DESIGN, SETTING, AND PARTICIPANTS Prospective cohort study of 1003 men undergoing both targeted and standard biopsy concurrently from 2007 through 2014 at the National Cancer Institute in the United States. Patients were referred for elevated level of prostate-specific antigen (PSA) or abnormal digital rectal examination results, often with prior negative biopsy results. Risk categorization was compared among targeted and standard biopsy and, when available, whole-gland pathology after prostatectomy as the “gold standard.” INTERVENTIONS Patients underwent multiparametric prostate magnetic resonance imaging to identify regions of prostate cancer suspicion followed by targeted MR/ultrasound fusion biopsy and concurrent standard biopsy. MAIN OUTCOMES AND MEASURES The primary objective was to compare targeted and standard biopsy approaches for detection of high-risk prostate cancer (Gleason score ≥4 + 3); secondary end points focused on detection of low-risk prostate cancer (Gleason score 3 + 3 or low-volume 3 + 4) and the biopsy ability to predict whole-gland pathology at prostatectomy. RESULTS Targeted MR/ultrasound fusion biopsy diagnosed 461 prostate cancer cases, and standard biopsy diagnosed 469 cases. There was exact agreement between targeted and standard biopsy in 690 men (69%) undergoing biopsy. Targeted biopsy diagnosed 30% more high-risk cancers vs standard biopsy (173 vs 122 cases, P < .001) and 17% fewer low-risk cancers (213 vs 258 cases, P < .001). When standard biopsy cores were combined with the targeted approach, an additional 103 cases (22%) of mostly low-risk prostate cancer were diagnosed (83% low risk, 12% intermediate risk, and 5% high risk). The predictive ability of targeted biopsy for differentiating low-risk from intermediate- and high-risk disease in 170 men with whole-gland pathology after prostatectomy was greater than that of standard biopsy or the 2 approaches combined (area under the curve, 0.73, 0.59, and 0.67, respectively; P < .05 for all comparisons). CONCLUSIONS AND RELEVANCE Among men undergoing biopsy for suspected prostate cancer, targeted MR/ultrasound fusion biopsy, compared with standard extended-sextant ultrasound-guided biopsy, was associated with increased detection of high-risk prostate cancer and decreased detection of low-risk prostate cancer. Future studies will be needed to assess the ultimate clinical implications of targeted biopsy. TRIAL REGISTRATION clinicaltrials.gov Identifier: NCT00102544 [ABSTRACT FROM AUTHOR]

Prostate MRI is currently the best diagnostic imaging method for detecting PCa. Magnetic resonance imaging ( MRI)/ultrasonography ( US) fusion allows the sensitivity and specificity of MRI to be combined with the real-time capabilities of transrectal ultrasonography ( TRUS). Multiple approaches and techniques exist for MRI/ US fusion and include direct 'in bore' MRI biopsies, cognitive fusion, and MRI/ US fusion via software-based image coregistration platforms. [ABSTRACT FROM AUTHOR]

BACKGROUND The Prostate Cancer Prevention Trial risk calculator for high-grade (PCPTHG) prostate cancer (CaP) was developed to improve the detection of clinically significant CaP. In this study, the authors compared the performance of the PCPTHG against multiparametric magnetic resonance imaging (MP-MRI) in predicting men at risk of CaP. METHODS Men with an abnormal prostate-specific antigen (PSA) level or digital rectal examination (DRE) and a suspicious lesion on a 3-Tesla MP-MRI were enrolled prospectively. Three radiologists reviewed and graded all lesions on a 5-point Likert scale. Biopsy of suspicious lesion(s) was performed using a proprietary MRI/transrectal ultrasound fusion-guided prostate biopsy system, after which 12-core biopsy was performed. A genitourinary pathologist reviewed all pathology slides. The performance of PCPTHG was compared with that of MP-MRI in predicting clinically significant CaP. RESULTS Of 175 men who were eligible for analysis, 64.6% (113 of 175 men) were diagnosed with CaP, including 93 of 113 men (82.3%) who had clinically significant disease. Age, abnormal DRE, PSA, PSA density, prostate size, extraprostatic extension on MRI, apparent diffusion coefficient value, and MRI lesion size were identified as significant predictors of high-grade CaP (all P < .05). The area under the receiver operating characteristic curve of PCPTHG for predicting high-grade CaP was 0.676 (95% confidence interval [CI], 0.592-0.751). By using a risk cutoff of ≥15% for biopsy as, proposed previously for high-grade CaP, sensitivity was 96.4%, specificity was 7.6%, and the false-positive rate was 51.1%. In contrast, the area under the receiver operating characteristic curve of MP-MRI for high-grade CaP was 0.769 (95% CI, 0.703-0.834), and it was 0.812 (95% CI, 0.754-0.869) for clinically significant CaP. CONCLUSIONS MP-MRI outperforms PCPTHG in predicting clinically significant CaP, and its application may help select patients who will benefit from CaP diagnosis and treatment. Cancer 2014;120:2876-2882. © 2014 American Cancer Society. [ABSTRACT FROM AUTHOR]

Purpose: To present fully automated DL-based prostate cancer detection system for prostate MRI. Methods: MRI scans from two institutions, were used for algorithm training, validation, testing. MRI-visible lesions were contoured by an experienced radiologist. All lesions were biopsied using MRI-TRUS-guidance. Lesions masks, histopathological results were used as ground truth labels to train UNet, AH-Net architectures for prostate cancer lesion detection, segmentation. Algorithm was trained to detect any prostate cancer ≥ ISUP1. Detection sensitivity, positive predictive values, mean number of false positive lesions per patient were used as performance metrics. Results: 525 patients were included for training, validation, testing of the algorithm. Dataset was split into training (n = 368, 70%), validation (n = 79, 15%), test (n = 78, 15%) cohorts. Dice coefficients in training, validation sets were 0.403, 0.307, respectively, for AHNet model compared to 0.372, 0.287, respectively, for UNet model. In validation set, detection sensitivity was 70.9%, PPV was 35.5%, mean number of false positive lesions/patient was 1.41 (range 0–6) for UNet model compared to 74.4% detection sensitivity, 47.8% PPV, mean number of false positive lesions/patient was 0.87 (range 0–5) for AHNet model. In test set, detection sensitivity for UNet was 72.8% compared to 63.0% for AHNet, mean number of false positive lesions/patient was 1.90 (range 0–7), 1.40 (range 0–6) in UNet, AHNet models, respectively. Conclusion: We developed a DL-based AI approach which predicts prostate cancer lesions at biparametric MRI with reasonable performance metrics. While false positive lesion calls remain as a challenge of AI-assisted detection algorithms, this system can be utilized as an adjunct tool by radiologists. [ABSTRACT FROM AUTHOR]

Multiparametric magnetic resonance imaging (mpMRI) has led to improved diagnosis and risk stratification of prostate cancer. The Prostate Imaging Reporting and Data System (PI-RADS) is a widely-adopted standardized interpretation scheme for prostate mpMRI. Lesions are scored 1-5 based on suspicion for clinically significant prostate (csPCa), defined as Grade Group ≥ 2, with increasing positive predictive value indicated by higher score. Multiple studies have demonstrated the positive predictive value of a PI-RADS 5 lesion for csPCa to cluster around 70-80%. Since nearly 80% of those with PI-RADS 5 lesions harbor clinically significant disease on biopsy, many receive upfront therapy. There is limited understanding of what happens to remaining patients with PI-RADS 5 lesions in whom biopsies reveal less aggressive disease. The purpose of this study is to evaluate the clinical course of those with PI-RADS 5 lesions with Grade Group 1 disease who were placed on Active Surveillance (AS). This analysis was limited to AS patients with GG1 prostate cancer on targeted biopsy of a solitary PI-RADS 5 index lesion performed from 2007 to 2022. Each scan was read by a high-volume genitourinary radiologist (BT or PC). These patients underwent systematic and targeted biopsy by physicians experienced with MRI-fusion biopsies (PP, BW, SG). Repeat biopsies were performed based on clinicopathologic concern for progression (rising PSA, MRI changes) or local AS protocols. For MRIs preceding PI-RADS scoring, an internal Likert suspicion scoring system that has been validated in the literature was used and converted into PI-RADS scores. Beginning in 2015, internal mpMRI readings were reported using PI-RADS v2.0 and in 2019 transitioned to PI-RADS v2.1. Biopsy specimens were reviewed by dedicated genitourinary pathologists. Descriptive statistics were performed. Univariate analyses, including independent samples t-test, chi-squared analysis, and Fisher's exact test, were performed to evaluate for factors associated with disease upgrading. 21 patients met inclusion criteria. The mean PSA was 7.9 ng/ml (range 2.4-14.5) (Table 1). At median follow up of 4.3 years, 15/21 (71%) patients progressed to GG≥2 disease, 5 of whom (24% of initial cohort) progressed to GG≥3 (Figure 1). Median time to progression to GG≥2 and GG≥3 was 3.3 years and 4.4 years, respectively. Of the 6 who did not progress, 1 underwent prostatectomy (upgraded to GG2 on final pathology) and 5 were maintained on AS. Of the 16 who progressed to GG≥2, 6/21 (29%) were continued on AS. 5 of these patients remained on AS (median follow-up 3.3 years after progression) and one underwent prostatectomy. Overall, 11 (52%) received definitive therapy. On univariate analysis, only mean maximum cancer core length was associated with progression to radical therapy (4.8 vs 8.0 mm, p=0.048). Patients with PI-RADS 5 lesions and GG1 PCa on AS demonstrate a rate of upgrading to GG≥2 of >70% and nearly a quarter were upgraded to GG≥3. Nearly 50% of patients progressed to radical treatment at 4 years. This represents a high rate of upgrading in a short period of time relative to larger AS series, which place pathologic upgrading at 25-50%. Further studies, including longer-term follow-up, will be necessary. Genomic classification of these initially indolent lesions may provide clarity regarding the best management. The question of how our findings should affect practice is important. With half of patients suitable for AS at follow-up, it is reasonable to continue AS as the preferred management. However, there is a higher risk of requiring intervention and these patients should be counseled and monitored accordingly. While focal therapy is not guideline-endorsed for GG1 disease, this may be a population that could benefit. [ABSTRACT FROM AUTHOR]

The advent of multiparametric magnetic resonance imaging (mpMRI) has helped to localize clinically significant prostate cancer (csPCA). Focal Therapy (FT) has emerged in the mpMRI era, which can treat MRI-visible lesions while avoiding side effects of whole-gland treatment. However, FT remains an investigational treatment option for PCa patients with intermediate-risk disease. Little is known about how many patients on active surveillance (AS) with Gleason grade group (GG) 2 disease retain eligibility for FT over time, or risk factors for loss of eligibility. The objective of this study is to evaluate initial and long-term FT eligibility (FTE) of patients with GG2 disease. A prospectively maintained cohort was retrospectively queried for patients initiated on AS between 2007;and 2020 with GG2 PCa. Patients with biopsy-concordant GG2, unilateral, MRI-visible PIRADS 2-5 lesions amenable to hemiablation were considered FT candidates. Those with PSA>20 ng/mL, >4 MRI lesions, bilateral (BL) MRI-visible/biopsy-concordant lesions, or contralateral GG≥2 PCa or MRI-invisible lesions were excluded. Patients were considered to progress if they developed BL GG≥2 disease or unilateral GG≥3 PCa. Patients without GG progression maintained FTE and those with GG progression maintained FTE if they had unilateral biopsy-concordant/MRI-visible GG≤3, no contralateral GG≥2 disease, and PSA<20 ng/mL. Univariate and multivariate analyses were conducted to compare patients who maintained and lost FTE. 252 PCa patients were identified as eligible for FT with an average follow-up of 3.4 years, 83 of whom (33%) had GG2 disease and were FT candidates. 29/83 (35%) lost FT eligibility, 19/83 (23%) with progression to high-risk disease, 6/83 (7.2%) due to development of BL GG≥2 disease, and 4/83 (4.8%) with development of MRI-invisible csPCA. Baseline characteristics are shown in Table 1. Univariate analysis demonstrated that those who lost FTE had smaller prostates than those who maintained it (44.9 mL vs. 56.2mL, respectively, p=0.018). PSA density was similar between the groups. No significant differences were noted in initial imaging and pathologic parameters. No factors significantly associated with loss of FTE were identified on logistic regression (Table 2). 33% of the patients on AS had GG2 disease and were initially eligible for FT. 65% of patients with GG2 disease were still eligible for FT after a median follow up of 3.4 years; over one third of these patients lose FTE. This data regarding the loss of a FT therapeutic window could prove useful in counseling GG2 patients considering AS, FT, or radical treatment. [ABSTRACT FROM AUTHOR]

The introduction of multiparametric magnetic resonance imaging (mpMRI) has significantly improved the early detection of clinically significant prostate cancer. The use of mpMRI has enabled more precise disease characterization, enabling improved risk stratification and candidate selection for active surveillance (AS). However, little is known about the clinical outcomes associated with small mpMRI lesions, which may be associated with low tumor burden and a potentially less aggressive course. This study aims to define the rates of prostate cancer progression and radical therapy for patients on AS with small index lesions and to explore the relationship between index lesion growth rates and cancer progression. A prospectively maintained database of patients on active surveillance at the National Cancer Institute was queried for patients with mpMRI index lesions ≤7mm in greatest diameter who had ≥2 mpMRIs and MRI-Ultrasound fusion biopsy sessions. Patients were identified with mpMRI lesions confirmed on MRI/Ultrasound fusion biopsy to have no worse than Gleason grade group (GG) 1 prostatic adenocarcinoma. Index lesions were defined as the MRI lesions with the highest PI-RADS score, with size used as a tiebreaker. For MRIs preceding PI-RADS scoring, an internal Likert suspicion scoring system that has been validated in the literature was used and converted into PI-RADS scores. MR review was conducted by a high-volume dedicated genitourinary radiologist.;Time to GG progression was calculated to be the difference between initial mpMRI and mpMRI at the time of cancer progression. Between 2007-2022, patients on AS with small index lesions measuring ≤7 mm (n=88) were identified. 26.53% of patients whose index lesions which grew between 0 and 1 mm/year (13/49) progressed to GG2 disease, with an average time to progression of 5.28 years. Of these patients, 12.24% (6/49) progressed to radical therapy, on average 6.16 years after initiating AS (Table 1). Eight years after initial mpMRI, 28.41% of patients in the full cohort (25/88) progressed to radical therapy (Figure 1). Overall, only 5.68% (5/88) of patients developed GG3 disease within 2 years of follow-up, and 2.27% (2/88) progressed to radical therapy. Our findings have important implications for timing of follow-up for patients on AS with small index lesions. The low rate of clinical progression to GG2 disease and radical therapy indicates a less aggressive clinical course than prior published AS series in the pre-MRI era. The presence of small index lesions;may therefore be considered as a favorable marker for determining eligibility and risk of progression for patients considering AS and may guide the timing of repeat imaging to personalize surveillance strategies. [ABSTRACT FROM AUTHOR]

Segmentation of the prostate in magnetic resonance image has become more in need for its assistance to diagnosis and surgical planning of prostate carcinoma. Due to the natural variability of anatomical structures, statistical shape model has been widely applied in medical image segmentation. Robust and distinctive local features are critical for statistical shape model to achieve accurate segmentation results. The scale invariant feature transformation (SIFT) has been employed to capture the information of the local patch surrounding the boundary. However, when SIFT feature being used for segmentation, the scale and variance are not specified with the location of the point of interest. To deal with it, the discriminant analysis in machine learning is introduced to measure the distinctiveness of the learned SIFT features for each landmark directly and to make the scale and variance adaptive to the locations. As the gray values and gradients vary significantly over the boundary of the prostate, separate appearance descriptors are built for each landmark and then optimized. After that, a two stage coarse-to-fine segmentation approach is carried out by incorporating the local shape variations. Finally, the experiments on prostate segmentation from MR image are conducted to verify the efficiency of the proposed algorithms. [ABSTRACT FROM PUBLISHER]

A method for the design and rapid manufacture of a patient specific tissue slicing device based on in vivo images in order to facilitate the process of correlating the images with histopathology is presented. The method is applied to radical prostatectomy specimens where the customized mold is designed using magnetic resonance (MR) images of each patient obtained prior to surgery. In this case, the mold holds the prostate in place while a knife with a single blade or multiple blades is inserted in slots which are positioned to obtain tissue blocks corresponding to the slices in the MR images. The resulting histological specimens demonstrate good anatomical correlation with the MR images. [ABSTRACT FROM AUTHOR]

The Coronavirus disease 2019 (COVID-19) pandemic has significantly affected health care systems throughout the world. A Qualtrics survey was targeted for radiologists around the world to study its effect on the operations of prostate MRI studies and biopsies. Descriptive statistics were reported. A total of 60 complete responses from five continents were included in the analysis. 70% of the responses were from academic institutions. Among all participants, the median (range) number of prostate MRI was 20 (0, 135) per week before the COVID-19 pandemic versus 10 (0, 30) during the lockdown period; the median (range) number of prostate biopsies was 4.5 (0, 60) per week before the COVID-19 versus 0 (0, 12) during the lockdown period. Among the 30% who used bowel preparation for their patients prior to MRI routinely, 11% stopped the bowel preparation due to the pandemic. 47% reported that their radiology departments faced staff disruptions, while 68% reported changes in clinic schedules in other clinical departments, particularly urology, genitourinary medical oncology, and radiation oncology. Finally, COVID-19 pandemic was found to disrupt not only the clinical prostate MRI operations but also impacted prostate MRI/biopsy research in up to 50% of institutions. The impact of this collateral damage in delaying diagnosis and treatment of prostate cancer is yet to be explored. [ABSTRACT FROM AUTHOR]

To investigate the diagnostic performance of a deep convolutional neural network for differentiation of clear cell renal cell carcinoma (ccRCC) from renal oncocytoma. In this retrospective study, 74 patients (49 male, mean age 59.3) with 243 renal masses (203 ccRCC and 40 oncocytoma) that had undergone MR imaging 6 months prior to pathologic confirmation of the lesions were included. Segmentation using seed placement and bounding box selection was used to extract the lesion patches from T2-WI, and T1-WI pre-contrast, post-contrast arterial and venous phases. Then, a deep convolutional neural network (AlexNet) was fine-tuned to distinguish the ccRCC from oncocytoma. Five-fold cross validation was used to evaluate the AI algorithm performance. A subset of 80 lesions (40 ccRCC, 40 oncocytoma) were randomly selected to be classified by two radiologists and their performance was compared to the AI algorithm. Intra-class correlation coefficient was calculated using the Shrout-Fleiss method. Overall accuracy of the AI system was 91% for differentiation of ccRCC from oncocytoma with an area under the curve of 0.9. For the observer study on 80 randomly selected lesions, there was moderate agreement between the two radiologists and AI algorithm. In the comparison sub-dataset, classification accuracies were 81%, 78%, and 70% for AI, radiologist 1, and radiologist 2, respectively. The developed AI system in this study showed high diagnostic performance in differentiation of ccRCC versus oncocytoma on multi-phasic MRIs. • A robust radiologic method to accurately differentiate ccRCC and oncocytoma is not available. • The AI system in the present study showed high diagnostic performance in differentiation of ccRCC and oncocytoma on MRI. • There was moderate agreement between the two radiologists and AI algorithm for the subset observer study. [ABSTRACT FROM AUTHOR]

Multi-domain data are widely leveraged in vision applications taking advantage of complementary information from different modalities, e.g., brain tumor segmentation from multi-parametric magnetic resonance imaging (MRI). However, due to possible data corruption and different imaging protocols, the availability of images for each domain could vary amongst multiple data sources in practice, which makes it challenging to build a universal model with a varied set of input data. To tackle this problem, we propose a general approach to complete the random missing domain(s) data in real applications. Specifically, we develop a novel multi-domain image completion method that utilizes a generative adversarial network (GAN) with a representational disentanglement scheme to extract shared content encoding and separate style encoding across multiple domains. We further illustrate that the learned representation in multi-domain image completion could be leveraged for high-level tasks, e.g., segmentation, by introducing a unified framework consisting of image completion and segmentation with a shared content encoder. The experiments demonstrate consistent performance improvement on three datasets for brain tumor segmentation, prostate segmentation, and facial expression image completion respectively. [ABSTRACT FROM AUTHOR]

Introduction: Prostate cancer has traditionally been diagnosed by an elevation in PSA or abnormal exam leading to a systematic transrectal ultrasound (TRUS)-guided biopsy. This diagnostic pathway underdiagnoses clinically significant disease while over diagnosing clinically insignificant disease. In this review, we aim to provide an overview of the recent literature regarding the role of multiparametric MRI (mpMRI) in the management of prostate cancer. Materials and Methods: A thorough literature review was performed using PubMed to identify articles discussing use of mpMRI of the prostate in management of prostate cancer. Conclusion: The incorporation of mpMRI of the prostate addresses the shortcomings of the prostate biopsy while providing several other advantages. mpMRI allows some men to avoid an immediate biopsy and permits visualization of areas likely to harbor clinically significant cancer prior to biopsy to facilitate use of MR-targeted prostate biopsies. This allows for reduction in diagnosis of clinically insignificant disease as well as improved detection and better characterization of higher risk cancers, as well as the improved selection of patients for active surveillance. In addition, mpMRI can be used for selection and monitoring of patients for active surveillance and treatment planning during surgery and focal therapy. [ABSTRACT FROM AUTHOR]

To evaluate CycleGAN's ability to enhance T2-weighted image (T2WI) quality. A CycleGAN algorithm was used to enhance T2WI quality. 96 patients (192 scans) were identified from patients who underwent multiple axial T2WI due to poor quality on the first attempt (RAD1) and improved quality on re-acquisition (RAD2). CycleGAN algorithm gave DL classifier scores (0–1) for quality quantification and produced enhanced versions of QI1 and QI2 from RAD1 and RAD2, respectively. A subset (n = 20 patients) was selected for a blinded, multi-reader study, where four radiologists rated T2WI on a scale of 1–4 for quality. The multi-reader study presented readers with 60 image pairs (RAD1 vs RAD2, RAD1 vs QI1, and RAD2 vs QI2), allowing for selecting sequence preferences and quantifying the quality changes. The DL classifier correctly discerned 71.9 % of quality classes, with 90.6 % (96/106) as poor quality and 48.8 % (42/86) as diagnostic in original sequences (RAD1, RAD2). CycleGAN images (QI1, QI2) demonstrated quantitative improvements, with consistently higher DL classifier scores than original scans (p < 0.001). In the multi-reader analysis, CycleGAN demonstrated no qualitative improvements, with diminished overall quality and motion in QI2 in most patients compared to RAD2, with noise levels remaining similar (8/20). No readers preferred QI2 to RAD2 for diagnosis. Despite quantitative enhancements with CycleGAN, there was no qualitative boost in T2WI diagnostic quality, noise, or motion. Expert radiologists didn't favor CycleGAN images over standard scans, highlighting the divide between quantitative and qualitative metrics. [ABSTRACT FROM AUTHOR]

• Detection of local recurrence in patients with prior radiotherapy is challenging. • A bpMRI-based AI model detected most locally radiorecurrent cancers. • The AI model performance was comparably better in patients with larger glands. • The AI detection rates were higher in external beam radiation therapy group. To evaluate a biparametric MRI (bpMRI)-based artificial intelligence (AI) model for the detection of local prostate cancer (PCa) recurrence in patients with radiotherapy history. This study included post-radiotherapy patients undergoing multiparametric MRI and subsequent MRI/US fusion-guided and/or systematic biopsy. Histopathology results were used as ground truth. The recurrent cancer detection sensitivity of a bpMRI-based AI model, which was developed on a large dataset to primarily identify lesions in treatment-naïve patients, was compared to a prospective radiologist assessment using the Wald test. Subanalysis was conducted on patients stratified by the treatment modality (external beam radiation treatment [EBRT] and brachytherapy) and the prostate volume quartiles. Of the 62 patients included (median age = 70 years; median PSA = 3.51 ng/ml; median prostate volume = 27.55 ml), 56 recurrent PCa foci were identified within 46 patients. The AI model detected 40 lesions in 35 patients. The AI model performance was lower than the prospective radiology interpretation (Rad) on a patient-(AI: 76.1% vs. Rad: 91.3%, p = 0.02) and lesion-level (AI: 71.4% vs. Rad: 87.5%, p = 0.01). The mean number of false positives per patient was 0.35 (range: 0–2). The AI model performance was higher in EBRT group both on patient-level (EBRT: 81.5% [22/27] vs. brachytherapy: 68.4% [13/19]) and lesion-level (EBRT: 79.4% [27/34] vs. brachytherapy: 59.1% [13/22]). In patients with gland volumes >34 ml (n = 25), detection sensitivities were 100% (11/11) and 94.1% (16/17) on patient- and lesion-level, respectively. The reported bpMRI-based AI model detected the majority of locally recurrent prostate cancer after radiotherapy. Further testing including external validation of this model is warranted prior to clinical implementation. [ABSTRACT FROM AUTHOR]

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of ${n}$ stacked transformations are applied to each image during network training. The underlying assumption is that the “expected” domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented “big” data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with ${n}={9}$ transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than “shallower” stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment. [ABSTRACT FROM AUTHOR]

Objectives: To determine the rate of Gleason Grade Group (GGG) upgrading in African‐American (AA) men with a prior diagnosis of low‐grade prostate cancer (GGG 1 or GGG 2) on 12‐core systematic biopsy (SB) after multiparametric magnetic resonance imaging (mpMRI) and fusion biopsy (FB); and whether AA men who continued active surveillance (AS) after mpMRI and FB fared differently than a predominantly Caucasian (non‐AA) population. Patients and methods: A database of men who had undergone mpMRI and FB was queried to determine rates of upgrading by FB amongst men deemed to be AS candidates based on SB prior to referral. After FB, Kaplan–Meier curves were generated for AA men and non‐AA men who then elected AS. The time to GGG upgrading and time continuing AS were compared using the log‐rank test. Results: AA men referred with GGG 1 disease on previous SB were upgraded to GGG ≥3 by FB more often than non‐AA men, 22.2% vs 12.7% (P = 0.01). A total of 32 AA men and 258 non‐AA men then continued AS, with a median (interquartile range) follow‐up of 39.19 (24.24–56.41) months. The median time to progression was 59.7 and 60.5 months, respectively (P = 0.26). The median time continuing AS was 61.9 months and not reached, respectively (P = 0.80). Conclusions: AA men were more likely to be upgraded from GGG 1 on SB to GGG ≥3 on initial FB; however, AA and non‐AA men on AS subsequently progressed at similar rates following mpMRI and FB. A greater tendency for SB to underestimate tumour grade in AA men may explain prior studies that have shown AA men to be at higher risk of progression during AS. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) has become integral to diagnosing and managing patients with suspected or confirmed prostate cancer. However, the benefits of utilizing MRI can be hindered by quality issues during imaging acquisition, interpretation, and reporting. As the utilization of prostate MRI continues to increase in clinical practice, the variability in MRI quality and how it can negatively impact patient care have become apparent. The American College of Radiology (ACR) has recognized this challenge and developed several initiatives to address the issue of inconsistent MRI quality and ensure that imaging centers deliver high-quality patient care. These initiatives include the Prostate Imaging Reporting and Data System (PI-RADS), developed in collaboration with an international panel of experts and members of the European Society of Urogenital Radiology (ESUR), the Prostate MR Image Quality Improvement Collaborative, which is part of the ACR Learning Network, the ACR Prostate Cancer MRI Center Designation, and the ACR Appropriateness Criteria. In this article, we will discuss the importance of these initiatives in establishing quality assurance and quality control programs for prostate MRI and how they can improve patient outcomes. [ABSTRACT FROM AUTHOR]

Abstract Context The Prostate Imaging-Reporting and Data System (PI-RADS) v2 analysis system for multiparametric magnetic resonance imaging (mpMRI) detection of prostate cancer (PCa) is based on PI-RADS v1, accumulated scientific evidence, and expert consensus opinion. Objective To summarize the accuracy, strengths and weaknesses of PI-RADS v2, discuss pathway implications of its use and outline opportunities for improvements and future developments. Evidence acquisition For this consensus expert opinion from the PI-RADS steering committee, clinical studies, systematic reviews, and professional guidelines for mpMRI PCa detection were evaluated. We focused on the performance characteristics of PI-RADS v2, comparing data to systems based on clinicoradiologic Likert scales and non–PI-RADS v2 imaging only. Evidence selections were based on high-quality, prospective, histologically verified data, with minimal patient selection and verifications biases. Evidence synthesis It has been shown that the test performance of PI-RADS v2 in research and clinical practice retains higher accuracy over systematic transrectal ultrasound (TRUS) biopsies for PCa diagnosis. PI-RADS v2 fails to detect all cancers but does detect the majority of tumors capable of causing patient harm, which should not be missed. Test performance depends on the definition and prevalence of clinically significant disease. Good performance can be attained in practice when the quality of the diagnostic process can be assured, together with joint working of robustly trained radiologists and urologists, conducting biopsy procedures within multidisciplinary teams. Conclusions It has been shown that the test performance of PI-RADS v2 in research and clinical practice is improved, retaining higher accuracy over systematic TRUS biopsies for PCa diagnosis. Patient summary Multiparametric magnetic resonance imaging (MRI) and MRI-directed biopsies using the Prostate Imaging-Reporting and Data System improves the detection of prostate cancers likely to cause harm, and at the same time decreases the detection of disease that does not lead to harms if left untreated. The keys to success are high-quality imaging, reporting, and biopsies by radiologists and urologists working together in multidisciplinary teams. Take Home Message Multiparametric magnetic resonance imaging (MRI) and MRI-directed biopsies using the Prostate Imaging-Reporting and Data System improves the detection of prostate cancers likely to cause harm, and at the same time decreases the detection of disease that does not lead to harm if left untreated. The keys to success are high-quality imaging, reporting, and biopsies by radiologists and urologists working together in multidisciplinary teams. [ABSTRACT FROM AUTHOR]