Search

This study aims to develop and evaluate radiomics-based machine learning (ML) models for predicting meningioma grades using multiparametric magnetic resonance imaging (MRI). The study utilized the BraTS-MEN dataset's training split, including 698 patients (524 with grade 1 and 174 with grade 2-3 meningiomas). We extracted 4872 radiomic features from T1, T1 with contrast, T2, and FLAIR MRI sequences using PyRadiomics. LASSO regression reduced features to 176. The data was split into training (60%), validation (20%), and test (20%) sets. Five ML algorithms (TabPFN, XGBoost, LightGBM, CatBoost, and Random Forest) were employed to build models differentiating low-grade (grade 1) from high-grade (grade 2-3) meningiomas. Hyperparameter tuning was performed using Optuna, optimizing model-specific parameters and feature selection. The CatBoost model demonstrated the best performance, achieving an area under the receiver operating characteristic curve (AUROC) of 0.838 [95% confidence interval (CI): 0.689-0.935], precision of 0.492 (95% CI: 0.371-0.623), recall of 0.838 (95% CI: 0.689-0.935), F1 score of 0.620 (95% CI: 0.495-0.722), accuracy of 0.729 (95% CI: 0.650-0.800), an area under the precision-recall curve (AUPRC) of 0.620 (95% CI: 0.433-0.753), and Brier score of 0.156 (95% CI: 0.122-0.200). Other models showed comparable performance, with mean AUROCs ranging from 0.752 to 0.784. The radiomics-based ML approach presented in this study showcases the potential for non-invasive and pre-operative grading of meningiomas using multiparametric MRI. Further validation on larger and independent datasets is necessary to establish the robustness and generalizability of these findings., (© 2024. The Author(s).)

Kidney diseases pose a global healthcare burden, with millions requiring renal replacement therapy. Ischemia/reperfusion injury (IRI) is a common pathology of acute kidney injury, causing hypoxia and subsequent inflammation-induced kidney damage. Accurate detection of acute kidney injury due to IRI is crucial for timely intervention. We used longitudinal, multi-parametric magnetic resonance imaging (MRI) employing arterial spin labelling (ASL), diffusion weighted imaging (DWI), and dynamic contrast enhanced (DCE)-MRI to assess IRI induced changes in both the injured and healthy contralateral kidney, in a unilateral IRI mouse model (n = 9). Multi-parametric MRI demonstrated significant differences in kidney volume (p = 0.001), blood flow (p = 0.002), filtration coefficient (p = 0.038), glomerular filtration rate (p = 0.005) and apparent diffusion coefficient (p = 0.048) between the injured kidney and contralateral kidney on day 1 post-IRI surgery. Identification of the injured kidney using principal component analysis including most of the imaging parameters demonstrated an area under the curve (AUC) of 0.97. These results point to the utility of multi-parametric MRI in early detection of IRI-induced kidney damage suggesting that the combination of various MRI parameters may be suitable for monitoring the extent of injury in this model., (© 2024. The Author(s).)

In addition to focal lesions, diffusely abnormal white matter (DAWM) is seen on brain MRI of multiple sclerosis (MS) patients and may represent early or distinct disease processes. The role of MRI-observed DAWM is understudied due to a lack of automated assessment methods. Supervised deep learning (DL) methods are highly capable in this domain, but require large sets of labeled data. To overcome this challenge, a DL-based network (DAWM-Net) was trained using semi-supervised learning on a limited set of labeled data for segmentation of DAWM, focal lesions, and normal-appearing brain tissues on multiparametric MRI. DAWM-Net segmentation performance was compared to a previous intensity thresholding-based method on an independent test set from expert consensus (N = 25). Segmentation overlap by Dice Similarity Coefficient (DSC) and Spearman correlation of DAWM volumes were assessed. DAWM-Net showed DSC > 0.93 for normal-appearing brain tissues and DSC > 0.81 for focal lesions. For DAWM-Net, the DAWM DSC was 0.49 ± 0.12 with a moderate volume correlation (ρ = 0.52, p < 0.01). The previous method showed lower DAWM DSC of 0.26 ± 0.08 and lacked a significant volume correlation (ρ = 0.23, p = 0.27). These results demonstrate the feasibility of DL-based DAWM auto-segmentation with semi-supervised learning. This tool may facilitate future investigation of the role of DAWM in MS., (© 2024. The Author(s).)

Triple-negative breast cancer (TNBC) is often treated with neoadjuvant systemic therapy (NAST). We investigated if radiomic models based on multiparametric Magnetic Resonance Imaging (MRI) obtained early during NAST predict pathologic complete response (pCR). We included 163 patients with stage I-III TNBC with multiparametric MRI at baseline and after 2 (C2) and 4 cycles of NAST. Seventy-eight patients (48%) had pCR, and 85 (52%) had non-pCR. Thirty-six multivariate models combining radiomic features from dynamic contrast-enhanced MRI and diffusion-weighted imaging had an area under the receiver operating characteristics curve (AUC) > 0.7. The top-performing model combined 35 radiomic features of relative difference between C2 and baseline; had an AUC = 0.905 in the training and AUC = 0.802 in the testing set. There was high inter-reader agreement and very similar AUC values of the pCR prediction models for the 2 readers. Our data supports multiparametric MRI-based radiomic models for early prediction of NAST response in TNBC., (© 2024. The Author(s).)

Prostate cancer is one of the most common and fatal diseases among men, and its early diagnosis can have a significant impact on the treatment process and prevent mortality. Since it does not have apparent clinical symptoms in the early stages, it is difficult to diagnose. In addition, the disagreement of experts in the analysis of magnetic resonance images is also a significant challenge. In recent years, various research has shown that deep learning, especially convolutional neural networks, has appeared successfully in machine vision (especially in medical image analysis). In this research, a deep learning approach was used on multi-parameter magnetic resonance images, and the synergistic effect of clinical and pathological data on the accuracy of the model was investigated. The data were collected from Trita Hospital in Tehran, which included 343 patients (data augmentation and learning transfer methods were used during the process). In the designed model, four different types of images are analyzed with four separate ResNet50 deep convolutional networks, and their extracted features are transferred to a fully connected neural network and combined with clinical and pathological features. In the model without clinical and pathological data, the maximum accuracy reached 88%, but by adding these data, the accuracy increased to 96%, which shows the significant impact of clinical and pathological data on the accuracy of diagnosis., (© 2024. The Author(s).)

Prediction of glioma is crucial to provide a precise treatment plan to optimize the prognosis of children with glioma. However, studies on the grading of pediatric gliomas using radiomics are limited. Meanwhile, existing methods are mainly based on only radiomics features, ignoring intuitive information about tumor morphology on traditional imaging features. This study aims to utilize multiparametric magnetic resonance imaging (MRI) to identify high-grade and low-grade gliomas in children and establish a classification model based on radiomics features and clinical features. A total of 85 children with gliomas underwent tumor resection, and part of the tumor tissue was examined pathologically. Patients were categorized into high-grade and low-grade groups according to World Health Organization guidelines. Preoperative multiparametric MRI data, including contrast-enhanced T1-weighted imaging, T2-weighted imaging, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted images, and apparent diffusion coefficient sequences, were obtained and labeled by two radiologists. The images were preprocessed, and radiomics features were extracted for each MRI sequence. Feature selection methods were used to select radiomics features, and statistically significant clinical features were identified using t-tests. The selected radiomics features and conventional MRI features were used to train the AutoGluon models. The improved model, based on radiomics features and conventional MRI features, achieved a balanced classification accuracy of 66.59%. The cross-validated areas under the receiver operating characteristic curve for the classifier of AutoGluon frame were 0.8071 on the test dataset. The results indicate that the performance of AutoGluon models can be improved by incorporating conventional MRI features, highlighting the importance of the experience of radiologists in accurately grading pediatric gliomas. This method can help predict the grade of pediatric glioma before pathological examination and assist in determining the appropriate treatment plan, including radiotherapy, chemotherapy, drugs, and gene surgery., (© 2024. The Author(s).)

Background: Biochemical recurrence (BCR) following primary interventional treatment occurs in approximately one-third of patients with prostate cancer (PCa). Next-generation imaging (NGI) can identify local and metastatic recurrence with greater sensitivity than conventional imaging, potentially allowing for more effective interventions. This narrative review examines the current clinical evidence on the utility of NGI for patients with BCR., Methods: A search of PubMed was conducted to identify relevant publications on NGI applied to BCR. Given other relevant recent reviews on the topic, this review focused on papers published between January 2018 to May 2023., Results: NGI technologies, including positron emission tomography (PET) radiotracers and multiparametric magnetic resonance imaging, have demonstrated increased sensitivity and selectivity for diagnosing BCR at prostate-specific antigen (PSA) concentrations <2.0 ng/ml. Detection rates range between 46% and 50%, with decreasing PSA levels for choline (1-3 ng/ml), fluciclovine (0.5-1 ng/ml), and prostate-specific membrane antigen (0.2-0.49 ng/ml) PET radiotracers. Expert working groups and European and US medical societies recommend NGI for patients with BCR., Conclusions: Available data support the improved detection performance and selectivity of NGI modalities versus conventional imaging techniques; however, limited clinical evidence exists demonstrating the application of NGI to treatment decision-making and its impact on patient outcomes. The emergence of NGI and displacement of conventional imaging may require a reexamination of the current definitions of BCR, altering our understanding of early recurrence. Redefining the BCR disease state by formalizing the role of NGI in patient management decisions will facilitate greater alignment across research efforts and better reflect the published literature., (© 2023. The Author(s).)

This study aimed to differentiate isocitrate dehydrogenase (IDH) mutation status with the voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and to discover biological underpinnings of the clusters. A total of 69 patients with treatment-naïve diffuse glioma were scanned with pH-sensitive amine chemical exchange saturation transfer MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach was used for feature extraction from acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH status. The highest performance to predict IDH mutation status was found for 10-class clustering, with a mean area under the curve, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. Targeted biopsies revealed that the tissues with labels 7-10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. In conclusion, A machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors., (© 2022. The Author(s).)

Stereotactic radiosurgery planning for cerebral arteriovenous malformations (AVM) is complicated by the variability in appearance of an AVM nidus across different imaging modalities. We developed a deep learning approach to automatically segment cerebrovascular-anatomical maps from multiple high-resolution magnetic resonance imaging/angiography (MRI/MRA) sequences in AVM patients, with the goal of facilitating target delineation. Twenty-three AVM patients who were evaluated for radiosurgery and underwent multi-parametric MRI/MRA were included. A hybrid semi-automated and manual approach was used to label MRI/MRAs with arteries, veins, brain parenchyma, cerebral spinal fluid (CSF), and embolized vessels. Next, these labels were used to train a convolutional neural network to perform this task. Imaging from 17 patients (6362 image slices) was used for training, and 6 patients (1224 slices) for validation. Performance was evaluated by Dice Similarity Coefficient (DSC). Classification performance was good for arteries, veins, brain parenchyma, and CSF, with DSCs of 0.86, 0.91, 0.98, and 0.91, respectively in the validation image set. Performance was lower for embolized vessels, with a DSC of 0.75. This demonstrates the proof of principle that accurate, high-resolution cerebrovascular-anatomical maps can be generated from multiparametric MRI/MRA. Clinical validation of their utility in radiosurgery planning is warranted., (© 2022. The Author(s).)

Magnetic resonance imaging (MRI) is playing an increasingly important role in evaluating chronic kidney disease (CKD). It has the potential to be used not only for evaluation of physiological and pathological states, but also for prediction of disease course. Although different MRI sequences have been employed in renal disease, there are few studies that have compared the different sequences. We compared several multiparametric MRI sequences, and compared their results with the estimated glomerular filtration rate. Principal component analysis showed a similarity between T1 values and tissue perfusion (arterial spin labelling), and between fractional anisotropy (diffusion tensor imaging) and apparent diffusion coefficient values (diffusion-weighted imaging). In multiple regression analysis, only T2* values, derived from the blood oxygenation level-dependent (BOLD) MRI sequence, were associated with estimated glomerular filtration rate slope after adjusting for degree of proteinuria, a classic prognostic factor for CKD. In receiver operating characteristic curve analysis, T2* values were a good predictor of rapid deterioration, regardless of the degree of proteinuria. This suggests further study of the use of BOLD-derived T2* values in the workup of CKD, especially to predict the disease course., (© 2021. The Author(s).)

Background: There is uncertainty on how multiparametric MRI (mpMRI) and MRI-targeted biopsy (MRI-TB) can be best used to manage low-risk prostate cancer patients on Active Surveillance (AS). We performed a scoping review to evaluate the benefits and harm associated with four different biopsy scenarios in which mpMRI can be implemented in AS., Methods: Medline, Embase and Cochrane Library databases (1 January 2013-18 September 2020) were searched. Included studies were on men with low-risk prostate cancer enrolled in AS, who had mpMRI ± MRI-TB and standard prostate biopsy (systematic transrectal ultrasound or transperineal saturation biopsy), at confirmatory or follow-up biopsy. Primary outcomes were the number of Gleason score upgrades and biopsies avoided., Results: Eight confirmatory biopsy studies and three follow-up biopsy studies were included. Compared to the benchmark of using standard biopsy (SB) for all men, the addition of MRI-TB increased the detection of Gleason score upgrades at both confirmatory (6/8 studies) and follow-up biopsy (3/3 studies), with increments of 1.7-11.8 upgrades per 100 men. 6/7 studies suggested that the use of a positive mpMRI to triage men for MRI-TB or SB alone would detect fewer Gleason score upgrades than benchmark at confirmatory biopsy, but the combination of MRI-TB and SB would detect more upgrades than the benchmark. For follow-up biopsy, the evidence on mpMRI triage biopsy scenarios was inconclusive due to the small number of included studies., Conclusions: The addition of MRI-TB to benchmark (SB for all men) maximises the detection of Gleason score upgrades at confirmatory and follow-up biopsy. When the use of mpMRI to triage men for a biopsy is desired, the combination of MRI-TB and SB should be considered for men with positive mpMRI at confirmatory biopsy. The evidence on mpMRI triage scenarios was inconclusive in the follow-up biopsy setting., (© 2021. The Author(s), under exclusive licence to Springer Nature Limited part of Springer Nature.)

Introduction: Multiparametric magnetic resonance imaging (mpMRI), the use of three multiple imaging sequences, typically T2-weighted, diffusion weighted (DWI) and dynamic contrast enhanced (DCE) images, has a high sensitivity and specificity for detecting significant cancer. Current guidance now recommends its use prior to biopsy. However, the impact of DCE is currently under debate regarding test accuracy. Biparametric MRI (bpMRI), using only T2 and DWI has been proposed as a viable alternative. We conducted a contemporary systematic review and meta-analysis to further examine the diagnostic performance of bpMRI in the diagnosis of any and clinically significant prostate cancer., Methods: A systematic review of the literature from 01/01/2017 to 06/07/2019 was performed by two independent reviewers using predefined search criteria. The index test was biparametric MRI and the reference standard whole-mount prostatectomy or prostate biopsy. Quality of included studies was assessed by the QUADAS-2 tool. Statistical analysis included pooled diagnostic performance (sensitivity; specificity; AUC), meta-regression of possible covariates and head-to-head comparisons of bpMRI and mpMRI where both were performed in the same study., Results: Forty-four articles were included in the analysis. The pooled sensitivity for any cancer detection was 0.84 (95% CI, 0.80-0.88), specificity 0.75 (95% CI, 0.68-0.81) for bpMRI. The summary ROC curve yielded a high AUC value (AUC = 0.86). The pooled sensitivity for clinically significant prostate cancer was 0.87 (95% CI, 0.78-0.93), specificity 0.72 (95% CI, 0.56-0.84) and the AUC value was 0.87. Meta-regression analysis revealed no difference in the pooled diagnostic estimates between bpMRI and mpMRI., Conclusions: This meta-analysis on contemporary studies shows that bpMRI offers comparable test accuracies to mpMRI in detecting prostate cancer. These data are broadly supportive of the bpMRI approach but heterogeneity does not allow definitive recommendations to be made. There is a need for prospective multicentre studies of bpMRI in biopsy naïve men., (© 2020. Crown.)

Amyloid plaques are a hallmark of Alzheimer's disease (AD) that develop in its earliest stages. Thus, non-invasive detection of these plaques would be invaluable for diagnosis and the development and monitoring of treatments, but this remains a challenge due to their small size. Here, we investigated the utility of manganese-enhanced MRI (MEMRI) for visualizing plaques in transgenic rodent models of AD across two species: 5xFAD mice and TgF344-AD rats. Animals were given subcutaneous injections of MnCl 2 and imaged in vivo using a 9.4 T Bruker scanner. MnCl 2 improved signal-to-noise ratio but was not necessary to detect plaques in high-resolution images. Plaques were visible in all transgenic animals and no wild-types, and quantitative susceptibility mapping showed that they were more paramagnetic than the surrounding tissue. This, combined with beta-amyloid and iron staining, indicate that plaque MR visibility in both animal models was driven by plaque size and iron load. Longitudinal relaxation rate mapping revealed increased manganese uptake in brain regions of high plaque burden in transgenic animals compared to their wild-type littermates. This was limited to the rhinencephalon in the TgF344-AD rats, while it was most significantly increased in the cortex of the 5xFAD mice. Alizarin Red staining suggests that manganese bound to plaques in 5xFAD mice but not in TgF344-AD rats. Multi-parametric MEMRI is a simple, viable method for detecting amyloid plaques in rodent models of AD. Manganese-induced signal enhancement can enable higher-resolution imaging, which is key to visualizing these small amyloid deposits. We also present the first in vivo evidence of manganese as a potential targeted contrast agent for imaging plaques in the 5xFAD model of AD.

Background: Prostate multiparametric magnetic resonance imaging (mpMRI) has become a popular initial investigation of an elevated PSA and is being incorporated into active surveillance protocols. Decisions on prostate cancer investigation and management based solely on a normal mpMRI remains controversial. Histopathological findings of a totally embedded normal mpMRI lobe are rarely described., Methods: A retrospective review of the histological findings of negative preoperative mpMRI lobes in men treated by robot assisted laparoscopic radical prostatectomy (RALP). Inclusion criteria included a preoperative low risk mpMRI for both lobes (Prostate Imaging-Reporting and Data System (PIRADS) ≤ 2) or one negative lobe (with a PIRADS 3-5 in the opposite lobe)., Results: A single normal mpMRI lobe was identified in 1018 men (PIRADS 3-5 group). Both lobes were normal in 179 men (PIRADS ≤ 2 group). Prostate cancer was identified in 47.6% (485/1018) of the normal mpMRI lobe opposite a PIRADS 3-5 lesion, including 13.2% (134/1018) with >0.5 cc of International Society of Urologic Pathologists (ISUP) grade 2, or a higher grade cancer. ISUP grade 4-5 was only identified in 2% (20/1018). Compared to RALP histology of the PIRADS 3-5 mpMRI tumour, a pathological ISUP upgrade in the normal mpMRI lobe was identified in 58/1018 men (5.7%). In the PIRADS ≤ 2 group extraprostatic extension occurred in 19% (34/179) and seminal vesicle invasion (pT3b) in 3.9% (7/179). There was no difference in margin status between the PIRADS 3-5 and ≤2 groups (p = 0.247)., Conclusions: mpMRI underestimates tumour grade and volume compared to totally embedded histopathological analysis of RALP specimens, although ISUP grade 4-5 cancer is uncommon. Our analysis provides useful insight into the multifocality of prostate cancers, and highlights the utility of systematic biopsy, in addition to targeted biopsies. These results have ramifications for clinical decisions on prostate cancer management based solely on the mpMRI appearance, including active surveillance.

High-grade gliomas are an aggressive and invasive malignancy which are susceptible to treatment resistance due to heterogeneity in intratumoral properties such as cell proliferation and density and perfusion. Non-invasive imaging approaches can measure these properties, which can then be used to calibrate patient-specific mathematical models of tumor growth and response. We employed multiparametric magnetic resonance imaging (MRI) to identify tumor extent (via contrast-enhanced T 1 -weighted, and T 2 -FLAIR) and capture intratumoral heterogeneity in cell density (via diffusion-weighted imaging) to calibrate a family of mathematical models of chemoradiation response in nine patients with unresected or partially resected disease. The calibrated model parameters were used to forecast spatially-mapped individual tumor response at future imaging visits. We then employed the Akaike information criteria to select the most parsimonious member from the family, a novel two-species model describing the enhancing and non-enhancing components of the tumor. Using this model, we achieved low error in predictions of the enhancing volume (median: - 2.5%, interquartile range: 10.0%) and a strong correlation in total cell count (Kendall correlation coefficient 0.79) at 3-months post-treatment. These preliminary results demonstrate the plausibility of using multiparametric MRI data to inform spatially-informative, biologically-based predictive models of tumor response in the setting of clinical high-grade gliomas.

With the rapid growth and increasing use of brain MRI, there is an interest in automated image classification to aid human interpretation and improve workflow. We aimed to train a deep convolutional neural network and assess its performance in identifying abnormal brain MRIs and critical intracranial findings including acute infarction, acute hemorrhage and mass effect. A total of 13,215 clinical brain MRI studies were categorized to training (74%), validation (9%), internal testing (8%) and external testing (8%) datasets. Up to eight contrasts were included from each brain MRI and each image volume was reformatted to common resolution to accommodate for differences between scanners. Following reviewing the radiology reports, three neuroradiologists assigned each study to abnormal vs normal, and identified three critical findings including acute infarction, acute hemorrhage, and mass effect. A deep convolutional neural network was constructed by a combination of localization feature extraction (LFE) modules and global classifiers to identify the presence of 4 variables in brain MRIs including abnormal, acute infarction, acute hemorrhage and mass effect. Training, validation and testing sets were randomly defined on a patient basis. Training was performed on 9845 studies using balanced sampling to address class imbalance. Receiver operating characteristic (ROC) analysis was performed. The ROC analysis of our models for 1050 studies within our internal test data showed AUC/sensitivity/specificity of 0.91/83%/86% for normal versus abnormal brain MRI, 0.95/92%/88% for acute infarction, 0.90/89%/81% for acute hemorrhage, and 0.93/93%/85% for mass effect. For 1072 studies within our external test data, it showed AUC/sensitivity/specificity of 0.88/80%/80% for normal versus abnormal brain MRI, 0.97/90%/97% for acute infarction, 0.83/72%/88% for acute hemorrhage, and 0.87/79%/81% for mass effect. Our proposed deep convolutional network can accurately identify abnormal and critical intracranial findings on individual brain MRIs, while addressing the fact that some MR contrasts might not be available in individual studies.

Background: Transrectal (TR) and transperineal (TP) approaches for prostate biopsy have different morbidity profiles. Our institution transitioned to a preference for multiparametric MRI-based triage and TP biopsy since 2014. The aim of this study was to compare clinical, microbiological and health economic outcomes between TR and TP prostate biopsy., Methods: A consecutive cohort study considered prostate biopsies over an 11 year period. Hospital presentations across the region within 30 days of biopsy were analysed for details and subsequent outcomes according to biopsy approach. Cost for each encounter (routine and unplanned) were analysed and generalised linear models applied, as well as cost implications for inclusion of mpMRI-based triage and TP biopsy preference., Results: In total, 2048 prostate biopsies were performed. Similar re-presentation rates per occurred for each biopsy approach (90 patients, TR 4.8%, TP 3.8%, p = 0.29), with 23 patients presenting more than once (119 total presentations). Presentations after TR biopsy were more likely to be of infectious aetiology (TR 2.92%, TP 0.26% de novo, p < 0.001) and result in hospital admission (TR 43/49, 93.4%; TP 14/24, 58.3%; p = 0.007) for similar rates of urinary retention (TR 2.76% vs TP 3.63%, p = 1). The mean overall cost (biopsy and re-presentations) was higher for the TP group (p < 0.001), adjusted for year and age, but reduced over time and was similar for patients who re-presented (p = 0.98). Incorporation of mpMRI (with subsequently avoided biopsies), TP biopsy and re-presentations resulted in AU$783.27 saving per biopsy., Conclusions: TR biopsy resulted in more infectious complications and hospital admissions than TP biopsy for similar rates of re-presentation and urinary retention. TP biopsy costs reduced over time and use in conjunction with mpMRI provides an overall cost saving. Routine TP biopsy is safe and feasible, with further cost savings expected with other approaches (local anaesthetic) under investigation.

Background: To evaluate the additive role of Ga-68 PSMA PET as a primary staging tool in patients bearing prostate cancer in single PIRADS 4 or 5 index lesions., Methods: Eighty-one biopsy-naive patients with preoperative mpMRI and Ga-68 PSMA PET who underwent radical prostatectomy (RP) were evaluated retrospectively. Forty-nine patients had PIRADS 4 and 32 had PIRADS 5 index lesions. The localization, grade, and volumetric properties of dominant (DT) and non-dominant tumors (NDT) in RP were compared to the index lesions of mpMRI and Ga-68 PSMA PET., Results: The median age and PSA level were 62 (IQR; 59-69) years and 7 (IQR; 2-8) ng/ml, respectively. Ga-68 PSMA PET detected DTs in 100% of the patients including 13 patients in whom mpMR failed. In 45 patients an NDT was reported in RP. Ga-68 PSMA PET accurately detected NDT in 24 of 45 (53.3%) patients. Six patients (12.2%) in PIRADS 4 and 8 (25%) in PIRADS 5 group showed upgrading. In PIRADS 4, Ga-68 PSMA PET localized DT in all patients with upgraded tumors whereas mpMRI missed exact location in 2 of 6 (33.3%). In PIRADS 5 both mpMRI and Ga-68 PSMA PET accurately located all DTs. Overall detection rates of extracapsular extension (ECE) and seminal vesicle invasion (SVI) by mpMRI were 51.1% and 53.8%, respectively. Ga-68 PSMA PET detected ECE and SVI in 27.9% and 30.7%, respectively. When mpMRI and Ga-68 PSMA PET were used in combination detection rates of ECE and SVI increased to 65.1 and 61.5%. Ga-68 PSMA PET-detected six of ten patients with positive lymph nodes whereas mpMRI could not identify any., Conclusions: Ga-68 PSMA PET has a better diagnostic accuracy in detecting DT, NDT, upgrading, adverse pathology in patients with PIRADS 4 index lesions. However, mpMRI better predicted ECE and SVI than Ga-68 PSMA PET.

Despite the key-role of the Prostate Imaging and Reporting and Data System (PI-RADS) in the diagnosis and characterization of prostate cancer (PCa), this system remains to be affected by several limitations, primarily associated with the interpretation of equivocal PI-RADS 3 lesions and with the debated role of Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI), which is only used to upgrade peripheral PI-RADS category 3 lesions to PI-RADS category 4 if enhancement is focal. We aimed at investigating the usefulness of radiomics for detection of PCa lesions (Gleason Score ≥ 6) in PI-RADS 3 lesions and in peripheral PI-RADS 3 upgraded to PI-RADS 4 lesions (upPI-RADS 4). Multiparametric MRI (mpMRI) data of patients who underwent prostatic mpMRI between April 2013 and September 2018 were retrospectively evaluated. Biopsy results were used as gold standard. PI-RADS 3 and PI-RADS 4 lesions were re-scored according to the PI-RADS v2.1 before and after DCE-MRI evaluation. Radiomic features were extracted from T2-weighted MRI (T2), Apparent diffusion Coefficient (ADC) map and DCE-MRI subtracted images using PyRadiomics. Feature selection was performed using Wilcoxon-ranksum test and Minimum Redundancy Maximum Relevance (mRMR). Predictive models were constructed for PCa detection in PI-RADS 3 and upPI-RADS 4 lesions using at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. 41 PI-RADS 3 and 32 upPI-RADS 4 lesions were analyzed. Among 293 radiomic features, the top selected features derived from T2 and ADC. For PI-RADS 3 stratification, second order model showed higher performances (Area Under the Receiver Operating Characteristic Curve-AUC- = 80%), while for upPI-RADS 4 stratification, first order model showed higher performances respect to superior order models (AUC = 89%). Our results support the significant role of T2 and ADC radiomic features for PCa detection in lesions scored as PI-RADS 3 and upPI-RADS 4. Radiomics models showed high diagnostic efficacy in classify PI-RADS 3 and upPI-RADS 4 lesions, outperforming PI-RADS v2.1 performance.

Background: Black men have significantly higher incidence and are up to three times more likely to die of prostate cancer (PCa) than White men. Multiparametric magnetic resonance imaging-ultrasound fusion biopsy (FBx) has emerged as a promising modality for the detection of PCa. The goal of our study is to identify differences in utilization of FBx between Black and White men presenting with suspicion of PCa., Methods: We performed a retrospective review of Black and White men who presented with suspicion of PCa and required biopsy from January 2014 to December 2018. Multivariate logistic regression analysis was done to study the influence of race on the utilization of FBx., Results: Six hundred nineteen (Black: 182, White: 437) men were included in the study. Forty-one out of 182 (22.5%) Black men underwent FBx compared with 225/437 (51.5%) of White men (P < 0.001). After adjusting for age, race, prostate-specific antigen level, digital rectal exam, family history of PCa and health insurance provider, Black race was found to be a significant negative predictor of obtaining FBx (OR:0.32, 95% CI: 0.21-0.51, P < 0.001). Black race stayed an independent negative predictor (OR: 0.36, 95% CI: 0.20-0.64, P < 0.001) in the cohort of patients who were biopsy naïve; however, although reduced, there was no significant difference in the cohort with a prior negative biopsy (OR: 0.51, 95% CI: 0.19-1.36, P = 0.179)., Conclusions: Although FBx is a superior modality for early detection of PCa, we found that Black men were less likely to undergo FBx when presenting with PCa suspicion. Further investigation is needed to evaluate if this difference is patient preference or if there are underlying socioeconomic, cultural or provider biases influencing this disparity.

Differentiating pseudoprogression from true tumor progression has become a significant challenge in follow-up of diffuse infiltrating gliomas, particularly high grade, which leads to a potential treatment delay for patients with early glioma recurrence. In this study, we proposed to use a multiparametric MRI data as a sequence input for the convolutional neural network with the recurrent neural network based deep learning structure to discriminate between pseudoprogression and true tumor progression. In this study, 43 biopsy-proven patient data identified as diffuse infiltrating glioma patients whose disease progressed/recurred were used. The dataset consists of five original MRI sequences; pre-contrast T1-weighted, post-contrast T1-weighted, T2-weighted, FLAIR, and ADC images as well as two engineered sequences; T1post-T1pre and T2-FLAIR. Next, we used three CNN-LSTM models with a different set of sequences as input sequences to pass through CNN-LSTM layers. We performed threefold cross-validation in the training dataset and generated the boxplot, accuracy, and ROC curve, AUC from each trained model with the test dataset to evaluate models. The mean accuracy for VGG16 models ranged from 0.44 to 0.60 and the mean AUC ranged from 0.47 to 0.59. For CNN-LSTM model, the mean accuracy ranged from 0.62 to 0.75 and the mean AUC ranged from 0.64 to 0.81. The performance of the proposed CNN-LSTM with multiparametric sequence data was found to outperform the popular convolutional CNN with a single MRI sequence. In conclusion, incorporating all available MRI sequences into a sequence input for a CNN-LSTM model improved diagnostic performance for discriminating between pseudoprogression and true tumor progression.

Non-alcoholic steatohepatitis (NASH) is major health burden lacking effective pharmacological therapies. Clinical trials enrol patients with histologically-defined NAFLD (non-alcoholic fatty liver disease) activity score (NAS) ≥ 4 and Kleiner-Brunt fibrosis stage (F) ≥ 2; however, screen failure rates are often high following biopsy. This study evaluated a non-invasive MRI biomarker, iron-corrected T1 mapping (cT1), as a diagnostic pre-screening biomarker for NASH. In a retrospective analysis of 86 biopsy confirmed NAFLD patients we explored the potential of blood and imaging biomarkers, both in isolation and in combination, to discriminate those who have NAS ≥ 4 and F ≥ 2 from those without. Stepwise logistic regression was performed to select the optimal combination of biomarkers, diagnostic accuracy was determined using area under the receiver operator curve and model validated confirmed with and fivefold cross-validation. Results showed that levels of cT1, AST, GGT and fasting glucose were all good predictors of NAS ≥ 4 and F ≥ 2, and the model identified the combination of cT1-AST-fasting glucose (cTAG) as far superior to any individual biomarker (AUC 0.90 [0.84-0.97]). This highlights the potential utility of the composite cTAG score for screening patients prior to biopsy to identify those suitable for NASH clinical trial enrolment.

The aim of this prospective single-institution clinical trial (NCT02002455) was to evaluate the potential of advanced post-processing methods for 18 F-Fluciclovine PET and multisequence multiparametric MRI in the prediction of prostate cancer (PCa) aggressiveness, defined by Gleason Grade Group (GGG). 21 patients with PCa underwent PET/CT, PET/MRI and MRI before prostatectomy. DWI was post-processed using kurtosis (ADC k , K), mono- (ADC m ), and biexponential functions (f, D p , D f ) while Logan plots were used to calculate volume of distribution (V T ). In total, 16 unique PET (V T , SUV) and MRI derived quantitative parameters were evaluated. Univariate and multivariate analysis were carried out to estimate the potential of the quantitative parameters and their combinations to predict GGG 1 vs >1, using logistic regression with a nested leave-pair out cross validation (LPOCV) scheme and recursive feature elimination technique applied for feature selection. The second order rotating frame imaging (RAFF), monoexponential and kurtosis derived parameters had LPOCV AUC in the range of 0.72 to 0.92 while the corresponding value for V T was 0.85. T he best performance for GGG prediction was achieved by K parameter of kurtosis function followed by quantitative parameters based on DWI, RAFF and 18 F-FACBC PET. No major improvement was achieved using parameter combinations with or without feature selection. Addition of 18 F-FACBC PET derived parameters (V T , SUV) to DWI and RAFF derived parameters did not improve LPOCV AUC.

Background: Prostate cancer focal therapy aims to minimize the side-effects of whole gland treatments, such as radical prostatectomy and radiotherapy without compromising oncological efficacy. However, concerns exist regarding the multifocal nature of prostate cancer and the lack of long-term oncological data for this form of treatment. In recent years, the routine adoption of multi-parametric magnetic resonance imaging (mpMRI) of the prostate has improved our ability to select candidates for focal therapy and to accurately deliver this form of prostate cancer treatment., Methods: We performed a review of the literature to provide a summary of the oncological and functional outcomes of men receiving primary prostate focal therapy. Furthermore, we discuss the impact of the routine implementation of mpMRI as part of the initial prostate cancer diagnostic pathway on the selection of candidates and delivery of focal therapy. Finally, we summarize knowledge gaps in the field and highlight active clinical trials in this arena., Results: Primary focal therapy involves the application of one of a number of energies that ablate tissue, such as cryotherapy and high intensity focused ultrasound (HIFU). Success is principally dependent on highly accurate patient selection and disease localization underpinned in large part by the routine integration of pre-biopsy mpMRI. Prospective medium-term follow-up data for primary HIFU and cryotherapy for men with intermediate-risk disease have shown acceptable cancer control with low risk of side effects and complications. Additional research is needed to clearly define an appropriate follow-up approach and to guide the management of in- and out-of-field recurrences. Multiple comparative trials with randomization against standard care are currently underway in men with intermediate- and high-risk prostate cancer., Conclusion: The widespread adoption of prostate mpMRI has led to improved disease localization, enabling the performance of focal therapy as a viable treatment strategy for men with low volume intermediate-risk prostate cancer.

Background: Lymph node invasion (LNI) is a strong adverse prognostic factor in prostate cancer (PCa). The purpose of this study was to evaluate the role of Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) scores for estimating the risk of LN metastasis. The study also aimed to investigate the additional value of PI-RADSv2 scores when used in combination with clinical nomograms for the prediction of LNI in patients with PCa., Methods: We retrospectively identified 308 patients who underwent multiparametric magnetic resonance imaging (mpMRI) and RP with pelvic lymph node dissection (PLND). Clinicopathological parameters and PI-RADSv2 scores were assessed. Univariate and multivariate logistic analyses were performed. The area under the receiver operating characteristic curves (AUCs) and decision curve analysis (DCA) were generated for assessing the incremental value of PI-RADSv2 scores combined with the Briganti and Memorial Sloan Kettering Cancer Center (MSKCC) nomograms., Results: Overall, 20 (6.5%) patients had LNI. At univariate analysis, all clinicopathological characteristics and PI-RADSv2 scores were significantly associated to LNI (p < 0.04). However, multivariate analysis revealed that only PI-RADSv2 scores and percentage of positive cores were independently significant (p ≤ 0.006). The PI-RADSv2 score was the most accurate predictor (AUC, 80.2%). The threshold of PI-RADSv2 score was 5, which provided high sensitivity (18/20, 90.0%) and negative predictive value (203/205, 99.0%). When PI-RADSv2 scores were combined with Briganti and MSKCC nomograms, the AUC value increased from 75.1 to 86.3% and from 79.2 to 87.9%, respectively (p ≤ 0.001). The DCA also demonstrated that the two nomograms plus PI-RADSv2 scores improved clinical risk prediction of LNI., Conclusions: The patients with a PI-RADSv2 score <5 were associated with a very low risk of LNI in PCa. Preoperative PI-RADSv2 scores could help improve the accuracy of clinical nomograms for predicting pelvic LN metastasis at radical prostatectomy.

Background: To understand the value of multiparametric magnetic resonance imaging (mpMRI) and targeted biopsies at recruitment on active surveillance (AS) outcomes., Materials and Methods: This retrospective single-center study enrolled two cohorts of 206 and 310 patients in AS. The latter group was submitted to mpMRI and targeted biopsies at recruitment. Kaplan-meier curves quantified progression-free survival (PFS) and Bioptic-PFS (B-PFS: no upgrading or >3 positive cores) in the two cohorts. Cox-regression analyses tested independent predictors of PFS and B-PFS. In patients submitted to radical prostatectomy (RP) after AS, significant cancer (csPCa) was defined as: GS ≥ 4 + 3 and/or pT ≥ 3a and/or pN+ . Logistic-regression analyses predicted csPCa at RP., Results and Limitations: Median time follow-up and median time of persistence in AS were 46 (24-70) and 36 (23-58) months, respectively. Patients submitted to mpMRI at AS begin, showed greater PFS at 1- (98% vs. 91%), 3- (80% vs. 57%), and 5-years (70% vs. 35%) follow-up, respectively (all p < 0.01). At Cox-regression analysis only confirmatory mpMRI± targeted biopsy (HR: 0.3; 95% CI 0.2-0.5; p < 0.01) at AS begin was an independent predictor of PFS. Globally, 50 (16%) vs. 128 (62%) and 26 (8.5%) vs. 64 (31%) [all p < 0.01] men in the two groups experienced any-cause and bioptic AS discontinuation, respectively. Patients submitted to confirmatory mpMRI experienced greater 1-(98% vs. 93%), 3-(90% vs. 75%), and 5-years (83% vs. 56%) B-PFS, respectively (all p < 0.01). At Cox-regression analysis, mpMRI±-targeted biopsy at AS begin was associated with B-PFS (HR: 0.3; 95% CI 0.2-0.6; p < 0.01). No differences were recorded in csPCa rates between the two groups (22% vs. 28%; p = 0.47). Limitations of the study are the single-center retrospective nature and the absence of long-term follow-up., Conclusions: Confirmatory mpMRI±-targeted biopsies are associated with higher PFS and B-PFS during AS. However, a non-negligible percentage of patients experience csPCa after switching to active treatment.

Background: Prostate cancer risk prediction models and multiparametric magnetic resonance imaging (mpMRI) are used for individualised pre-biopsy risk assessment. However, biparametric MRI (bpMRI) has emerged as a simpler, more rapid MRI approach (fewer scan sequences, no intravenous contrast-media) to reduce costs and facilitate a more widespread clinical implementation. It is unknown how bpMRI and risk models perform conjointly. Therefore, the objective was to develop a predictive model for significant prostate cancer (sPCa) in biopsy-naive men based on bpMRI findings and clinical parameters., Methods: Eight hundred and seventy-six biopsy-naive men with clinical suspicion of prostate cancer (prostate-specific antigen, <50 ng/mL; tumour stage, volume , and PSA density ) were created to detect sPCa (any biopsy-core with Gleason grade-group, ≥2) and compared by analysing the areas under the curves and decision curves., Results: Overall, sPCa was detected in 350/876 men (40%) with median (inter-quartile range) age and PSA level of 65 years (60-70) and 7.3 ng/mL (5.5-10.6), respectively. The model defined by bpMRI scores, age, tumour stage, and PSA density had the highest discriminatory power (area under the curve, 0.89), showed good calibration on internal bootstrap validation, and resulted in the greatest net benefit on decision curve analysis. Applying a biopsy risk threshold of 20% meant that 42% of men could avoid a biopsy, 50% fewer insignificant cancers were diagnosed, and only 7% of significant cancers (grade-group, ≥2) were missed., Conclusions: A predictive model based on bpMRI scores and clinical parameters significantly improved risk stratification for sPCa in biopsy-naïve men and could be used for clinical decision-making and counselling men prior to prostate biopsies.

Glioblastoma (GBM) is a heterogeneous and lethal brain cancer. These tumors are followed using magnetic resonance imaging (MRI), which is unable to precisely identify tumor cell invasion, impairing effective surgery and radiation planning. We present a novel hybrid model, based on multiparametric intensities, which combines machine learning (ML) with a mechanistic model of tumor growth to provide spatially resolved tumor cell density predictions. The ML component is an imaging data-driven graph-based semi-supervised learning model and we use the Proliferation-Invasion (PI) mechanistic tumor growth model. We thus refer to the hybrid model as the ML-PI model. The hybrid model was trained using 82 image-localized biopsies from 18 primary GBM patients with pre-operative MRI using a leave-one-patient-out cross validation framework. A Relief algorithm was developed to quantify relative contributions from the data sources. The ML-PI model statistically significantly outperformed (p < 0.001) both individual models, ML and PI, achieving a mean absolute predicted error (MAPE) of 0.106 ± 0.125 versus 0.199 ± 0.186 (ML) and 0.227 ± 0.215 (PI), respectively. Associated Pearson correlation coefficients for ML-PI, ML, and PI were 0.838, 0.518, and 0.437, respectively. The Relief algorithm showed the PI model had the greatest contribution to the result, emphasizing the importance of the hybrid model in achieving the high accuracy.

In this study we assessed the repeatability of radiomics features on small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI). The premise of radiomics is that quantitative image-based features can serve as biomarkers for detecting and characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, and different bin widths for image discretization. Although we found many radiomics features and preprocessing combinations with high repeatability (Intraclass Correlation Coefficient > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters. Neither image normalization, using a variety of approaches, nor the use of pre-filtering options resulted in consistent improvements in repeatability. We urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend the use of open source implementations.

Background: The use of multiparametric magnetic resonance imaging (mpMRI) in the setting of patients under active surveillance (AS) is promising. In this systematic-review we aimed to analyse the role of mpMRI in patients under AS., Methods: A comprehensive literature research for English-language original and review articles, recently published, was carried out using Medline, Scopus and Web of sciences databases until 30 October 2017. The following MeSH terms were used: 'active surveillance', 'prostate cancer', 'multiparametric magnetic resonance imaging'. A diagnostic meta-analysis was performed for 3.0 T mpMRI in predicting disease re-classification., Results: In total, 226 studies were selected after research and after removal of duplicates. After analysis on inclusion criteria, 43 studies were identified as eligible for this systematic review with a total of 6,605 patients. The timing of MRI during follow-up of AS differed from all studies like criteria for inclusion in the AS protocol. Overall, there was a low risk of bias across all studies. The diagnostic meta-analysis for 1.5 tesla showed a sensitivity of 0.60, negative predictive value (NPV) of 0.75 and a hierarchical summary receiving operating curve (HSROC) of 0.74 while for 3.0 tesla mpMRI a sensitivity of 0.81, a NPV of 0.78 and a HSROC of 0.83., Conclusions: Overall, the available evidence suggests that both 1.5 or 3.0 Tesla mpMRI are a valid tool to monitor progression during AS follow-up, showing good accuracy capabilities in detecting PCa re-classification. However, the modality to better define what means 'disease progression' on mpMRI must be further evaluated.

Background: Multiparametric magnetic resonance imaging (MP-MRI) and MRI/ultrasound (US) fusion-guided biopsy are becoming more widely used techniques for prostate cancer (PCa) diagnosis and management. However, their widespread adoption and use, where available, are limited by cost and added time. These limitations could be minimized if a biparametric MRI (BP-MRI) focusing on T2-weighted and diffusion-weighted imaging is performed. Herein we report the cancer detection rate of BP-MRI compared with full MP-MRI., Methods: Biopsy-naive and prior negative biopsy patients with clinical suspicion for PCa underwent MP-MRI with an imaging protocol incorporating narrow field-of-view T2-weighted, diffusion-weighted, and DCE pelvic MRI. Then patients underwent MRI/US fusion-guided biopsy of target lesions between November 2013 and October 2017. The pathology results were compared to the positivity of the DCE sequence compared to the BP-MRI findings alone., Results: There were 648 targeted lesions biopsied in 344 patients. We defined biparametric screen filter positivity as both T2-weighted and diffusion-weighted imaging positivity for the same lesion. The majority of target lesions (552/648, 85%) were screen filter positive. For those that were screen filter negative, a minority (14/96, 15%) had DCE-positive findings. Of these, 2/3 (67%) cancer-positive cases were seen on T2-weighted imaging. For those 82 that were screen filter negative and DCE negative, the DCE phase would not have added imaging suspicion. Only 3/82 (3.7%) were cancer positive; 2 with low risk, grade group 1 cancer and 1 with intraductal carcinoma, all identified on targeted T2-weighted MRI positivity., Conclusions: BP-MRI for the evaluation of PCa and for guiding MRI/US fusion-targeted biopsy has the advantages of reducing cost, time, and contrast exposure of MP-MRI by eliminating the DCE phase. These benefits are realized without forfeiting valuable diagnostic information, as shown by similar cancer detection rates of BP-MRI and MP-MRI in this study, particularly for clinically significant cases of PCa.

Multiparametric magnetic resonance imaging (mpMRI) has become increasingly important for the clinical assessment of prostate cancer (PCa), but its interpretation is generally variable due to its relatively subjective nature. Radiomics and classification methods have shown potential for improving the accuracy and objectivity of mpMRI-based PCa assessment. However, these studies are limited to a small number of classification methods, evaluation using the AUC score only, and a non-rigorous assessment of all possible combinations of radiomics and classification methods. This paper presents a systematic and rigorous framework comprised of classification, cross-validation and statistical analyses that was developed to identify the best performing classifier for PCa risk stratification based on mpMRI-derived radiomic features derived from a sizeable cohort. This classifier performed well in an independent validation set, including performing better than PI-RADS v2 in some aspects, indicating the value of objectively interpreting mpMRI images using radiomics and classification methods for PCa risk assessment.