Search

Objective Methods Results Significance Focal cortical dysplasia (FCD) is a common cause of drug‐resistant focal epilepsy but can be challenging to detect visually on magnetic resonance imaging. Three artificial intelligence models for automated FCD detection are publicly available (MAP18, deepFCD, MELD) but have only been compared on single‐center data. Our first objective is to compare them on independent multicenter test data. Additionally, we train and compare three new models and make them publicly available.We retrospectively collected FCD cases from four epilepsy centers. We chose three novel models that take two‐dimensional (2D) slices (2D‐nnUNet), 2.5D slices (FastSurferCNN), and large 3D patches (3D‐nnUNet) as inputs and trained them on a subset of Bonn data. As core evaluation metrics, we used voxel‐level Dice similarity coefficient (DSC), cluster‐level F1 score, subject‐level detection rate, and specificity.We collected 329 subjects, 244 diagnosed with FCD (27.7 ± 14.4 years old, 54% male) and 85 healthy controls (7.1 ± 2.4 years old, 51% female). We used 118 subjects for model training and kept the remaining subjects as an independent test set. 3D‐nnUNet achieved the highest F1 score of .58, the highest DSC of .36 (95% confidence interval [CI] = .30–.41), a detection rate of 55%, and a specificity of 86%. deepFCD showed the highest detection rate (82%) but had the lowest specificity (0%) and cluster‐level precision (.03, 95% CI = .03–.04, F1 score = .07). MELD showed the least performance variation across centers, with detection rates between 46% and 54%.This study shows the variance in performance for FCD detection models in a multicenter dataset. The two models with 3D input data showed the highest sensitivity. The 2D models performed worse than all other models, suggesting that FCD detection requires 3D data. The greatly improved precision of 3D‐nnUNet may make it a sensible choice to aid FCD detection. [ABSTRACT FROM AUTHOR]

Background and Aim: Computer‐aided detection (CADe) systems can efficiently detect polyps during colonoscopy. However, false‐positive (FP) activation is a major limitation of CADe. We aimed to compare the rate and causes of FP using CADe before and after an update designed to reduce FP. Methods: We analyzed CADe‐assisted colonoscopy videos recorded between July 2022 and October 2022. The number and causes of FPs and excessive time spent by the endoscopist on FP (ET) were compared pre‐ and post‐update using 1:1 propensity score matching. Results: During the study period, 191 colonoscopy videos (94 and 97 in the pre‐ and post‐update groups, respectively) were recorded. Propensity score matching resulted in 146 videos (73 in each group). The mean number of FPs and median ET per colonoscopy were significantly lower in the post‐update group than those in the pre‐update group (4.2 ± 3.7 vs 18.1 ± 11.1; P < 0.001 and 0 vs 16 s; P < 0.001, respectively). Mucosal tags, bubbles, and folds had the strongest association with decreased FP post‐update (pre‐update vs post‐update: 4.3 ± 3.6 vs 0.4 ± 0.8, 0.32 ± 0.70 vs 0.04 ± 0.20, and 8.6 ± 6.7 vs 1.6 ± 1.7, respectively). There was no significant decrease in the true positive rate (post‐update vs pre‐update: 95.0% vs 99.2%; P = 0.09) or the adenoma detection rate (post‐update vs pre‐update: 52.1% vs 49.3%; P = 0.87). Conclusions: The updated CADe can reduce FP without impairing polyp detection. A reduction in FP may help relieve the burden on endoscopists. [ABSTRACT FROM AUTHOR]

Objectives: A computer‐aided detection (CAD) system was developed to support the detection of colorectal lesions by deep learning using video images of lesions and normal mucosa recorded during colonoscopy. The study's purpose was to evaluate the stand‐alone performance of this device under blinded conditions. Methods: This multicenter prospective observational study was conducted at four Japanese institutions. We used 326 videos of colonoscopies recorded with patient consent at institutions in which the Ethics Committees approved the study. The sensitivity of successful detection of the CAD system was calculated using the target lesions, which were detected by adjudicators from two facilities for each lesion appearance frame; inconsistencies were settled by consensus. Successful detection was defined as display of the detection flag on the lesion for more than 0.5 s within 3 s of appearance. Results: Of the 556 target lesions from 185 cases, detection success sensitivity was 97.5% (95% confidence interval [CI] 95.8–98.5%). The "successful detection sensitivity per colonoscopy" was 93% (95% CI 88.3–95.8%). For the frame‐based sensitivity, specificity, positive predictive value, and negative predictive value were 86.6% (95% CI 84.8–88.4%), 84.7% (95% CI 83.8–85.6%), 34.9% (95% CI 32.3–37.4%), and 98.2% (95% CI 97.8–98.5%), respectively. Trial registration: University Hospital Medical Information Network (UMIN000044622). [ABSTRACT FROM AUTHOR]

Precise and unambiguous segmentation of pulmonary nodules from the CT images is imperative for a CAD framework implementation delineated for the prognosis of lung cancer. Lung nodule segmentation is an appealing research discipline for accurate dismemberment of lung cancer but the irregularity in shades, contours, and compositions, and the affinity between the tumors and the neighboring regions makes it an arduous task. This paper proffers a series atrous convolution enhanced U‐Net which uses a series of concatenated dilated convolution blocks after every stage in the encoder and decoder path. Our approach helps in obtaining the quintessential components from the feature maps, in addition to the absolute convergence of the model. It is largely assessed on the publicly accessible LIDC‐IDRI dataset. The average Dice Similarity Coefficient (DSC) obtained is 81.10% with an Intersection over Union (IoU/ Jaccard Index) of 72.24%. Exploratory outcomes prove that our architecture achieves ameliorate performance. [ABSTRACT FROM AUTHOR]

Background: Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated. Purpose: To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences. Study Type: Retrospective. Population: A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female). Field Strength/Sequence: T1‐weighted imaging and dynamic contrast‐enhanced MRI (DCE‐MRI) with gradient echo sequences, T2‐weighted imaging (T2WI) with spin‐echo sequences, diffusion‐weighted imaging with single‐shot echo‐planar sequence and at 1.5‐T. Assessment: A convolutional neural network and long short‐term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI‐RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE‐MRI and non‐DCE sequences, respectively. Statistical Tests: Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P‐value <0.05 was considered statistically significant. Results: With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE‐MRI, the DL‐based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE‐MRI/T2WI alone, respectively. Data Conclusion: The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent‐free combination is comparable to DCE‐MRI alone and the radiologists' reading in AUC and sensitivity. Evidence Level: 3. Technical Efficacy: Stage 2. [ABSTRACT FROM AUTHOR]

Objectives: The usefulness of computer‐aided detection systems (CADe) for colonoscopy has been increasingly reported. In many countries, however, data on the cost‐effectiveness of their use are lacking; consequently, CADe for colonoscopy has not been covered by health insurance. We aimed to evaluate the cost‐effectiveness of colonoscopy using CADe in Japan. Methods: We conducted a simulation model analysis using Japanese data to examine the cost‐effectiveness of colonoscopy with and without CADe for a population aged 40–74 years who received colorectal cancer (CRC) screening with a fecal immunochemical test (FIT). The rates of receiving FIT screening and colonoscopy following a positive FIT were set as 40% and 70%, respectively. The sensitivities of FIT for advanced adenomas and CRC Dukes' A–D were 26.5% and 52.8–78.3%, respectively. CADe colonoscopy was judged to be cost‐effective when its incremental cost‐effectiveness ratio (ICER) was below JPY 5,000,000 per quality‐adjusted life‐years (QALYs) gained. Results: Compared to conventional colonoscopy, CADe colonoscopy showed a higher QALY (20.4098 vs. 20.4088) and lower CRC incidence (2373 vs. 2415 per 100,000) and mortality (561 vs. 569 per 100,000). When the CADe cost was set at JPY 1000–6000, the ICER per QALY gained for CADe colonoscopy was lower than JPY 5,000,000 (JPY 796,328–4,971,274). The CADe cost threshold at which the ICER for CADe colonoscopy exceeded JPY 5,000,000 was JPY 6040. Conclusions: Computer‐aided detection systems for colonoscopy has the potential to be cost‐effective when the CADe cost is up to JPY 6000. These results suggest that the insurance reimbursement of CADe for colonoscopy is reasonable. [ABSTRACT FROM AUTHOR]

Background: Demand for prostate MRI is increasing, but scan times remain long even in abbreviated biparametric MRIs (bpMRI). Deep learning can be leveraged to accelerate T2‐weighted imaging (T2WI). Purpose: To compare conventional bpMRIs (CL‐bpMRI) with bpMRIs including a deep learning‐accelerated T2WI (DL‐bpMRI) in diagnosing prostate cancer. Study Type: Retrospective. Population: Eighty consecutive men, mean age 66 years (47–84) with suspected prostate cancer or prostate cancer on active surveillance who had a prostate MRI from December 28, 2020 to April 28, 2021 were included. Follow‐up included prostate biopsy or stability of prostate‐specific antigen (PSA) for 1 year. Field Strength and Sequences: A 3 T MRI. Conventional axial and coronal T2 turbo spin echo (CL‐T2), 3‐fold deep learning‐accelerated axial and coronal T2‐weighted sequence (DL‐T2), diffusion weighted imaging (DWI) with b = 50 sec/mm2, 1000 sec/mm2, calculated b = 1500 sec/mm2. Assessment: CL‐bpMRI and DL‐bpMRI including the same conventional diffusion‐weighted imaging (DWI) were presented to three radiologists (blinded to acquisition method) and to a deep learning computer‐assisted detection algorithm (DL‐CAD). The readers evaluated image quality using a 4‐point Likert scale (1 = nondiagnostic, 4 = excellent) and graded lesions using Prostate Imaging Reporting and Data System (PI‐RADS) v2.1. DL‐CAD identified and assigned lesions of PI‐RADS 3 or greater. Statistical Tests: Quality metrics were compared using Wilcoxon signed rank test, and area under the receiver operating characteristic curve (AUC) were compared using Delong's test. Significance: P = 0.05. Results: Eighty men were included (age: 66 ± 9 years; 17/80 clinically significant prostate cancer). Overall image quality results by the three readers (CL‐T2, DL‐T2) are reader 1: 3.72 ± 0.53, 3.89 ± 0.39 (P = 0.99); reader 2: 3.33 ± 0.82, 3.31 ± 0.74 (P = 0.49); reader 3: 3.67 ± 0.63, 3.51 ± 0.62. In the patient‐based analysis, the reader results of AUC are (CL‐bpMRI, DL‐bpMRI): reader 1: 0.77, 0.78 (P = 0.98), reader 2: 0.65, 0.66 (P = 0.99), reader 3: 0.57, 0.60 (P = 0.52). Diagnostic statistics from DL‐CAD (CL‐bpMRI, DL‐bpMRI) are sensitivity (0.71, 0.71, P = 1.00), specificity (0.59, 0.44, P = 0.05), positive predictive value (0.23, 0.24, P = 0.25), negative predictive value (0.88, 0.88, P = 0.48). Conclusion: Deep learning‐accelerated T2‐weighted imaging may potentially be used to decrease acquisition time for bpMRI. Evidence Level: 3. Technical Efficacy: Stage 2. [ABSTRACT FROM AUTHOR]

Background: Pulmonary embolism (PE) is a common but fatal clinical condition and the gold standard of diagnosis is computed tomography pulmonary angiography (CTPA). Prompt diagnosis and rapid treatment can dramatically reduce mortality in patients. However, the diagnosis of PE is often delayed and missed. Methods: In this study, we identified a deep learning model Scaled‐YOLOv4 that enables end‐to‐end automated detection of PE to help solve these problems. A total of 307 CTPA data (Tianjin 142 cases, Linyi 133 cases, and FUMPE 32 cases) were included in this study. The Tianjin dataset was divided 10 times in the ratio of training set: validation set: test set = 7:2:1 for model tuning, and both the Linyi and FUMPE datasets were used as independent external test sets to evaluate the generalization of the model. Results: Scaled‐YOLOv4 was able to process one patient in average 3.55 s [95% CI: 3.51–3.59 s]. It also achieved an average precision (AP) of 83.04 [95% CI: 79.36–86.72] for PE detection on the Tianjin test set, and 75.86 [95% CI: 75.48–76.24] and 72.74 [95% CI: 72.10–73.38] on Linyi and FUMPE, respectively. Conclusions: This deep learning algorithm helps detect PE in real time, providing radiologists with aided diagnostic evidence without increasing their workload, and can effectively reduce the probability of delayed patient diagnosis. [ABSTRACT FROM AUTHOR]

Background: Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows. Purpose: To develop a clinically feasible end‐to‐end CMBs detection network with a single‐stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE‐Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes. Study Type: Retrospective. Subjects: Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2). Field Strength/Sequence: A 3 T field strength and 3D GRE sequence scan for SWI reconstructions. Assessment: The sensitivity, FPavg (false‐positive per subject), and precision measures were computed and analyzed with statistical analysis. Statistical Tests: A paired t‐test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant. Results: The proposed TPE‐Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FPavg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FPavg of 0.55. The precision was significantly higher than the other models. Data Conclusion: The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic. Evidence Level: 1 Technical Efficacy: Stage 2 [ABSTRACT FROM AUTHOR]

Background: Whereas Artificial Intelligence (AI) based tools have recently been introduced in the field of gastroenterology, application in inflammatory bowel disease (IBD) is in its infancies. We established AI‐based algorithms to distinguish IBD from infectious and ischemic colitis using endoscopic images and clinical data. Methods: First, we trained and tested a Convolutional Neural Network (CNN) using 1796 real‐world images from 494 patients, presenting with three diseases (IBD [n = 212], ischemic colitis [n = 157], and infectious colitis [n = 125]). Moreover, we evaluated a Gradient Boosted Decision Trees (GBDT) algorithm using five clinical parameters as well as a hybrid approach (CNN + GBDT). Patients and images were randomly split into two completely independent datasets. The proposed approaches were benchmarked against each other and three expert endoscopists on the test set. Results: For the image‐based CNN, the GBDT algorithm and the hybrid approach global accuracies were.709,.792, and.766, respectively. Positive predictive values were.602,.702, and.657. Global areas under the receiver operating characteristics (ROC) and precision recall (PR) curves were.727/.585,.888/.823, and.838/.733, respectively. Global accuracy did not differ between CNN and endoscopists (.721), but the clinical parameter‐based GBDT algorithm outperformed CNN and expert image classification. Conclusions: Decision support systems exclusively based on endoscopic image analysis for the differential diagnosis of colitis, representing a complex clinical challenge, seem not yet to be ready for primetime and more diverse image datasets may be necessary to improve performance in future development. The clinical value of the proposed clinical parameters algorithm should be evaluated in prospective cohorts. [ABSTRACT FROM AUTHOR]

Gastrointestinal endoscopy is a subjective procedure that frequently requires tissue samples for diagnosis. Contact optical biopsy (OB) techniques have the aim of providing direct diagnosis of endoscopic areas without excising tissue samples but lack the wide‐area coverage required for locating and resecting lesions. This article presents a large‐area robotically deployed OB imaging platform for endoscopic detection of colorectal cancer as an add‐on for conventional endoscopes. In vitro, in silicon colon phantoms, the platform achieves an optical resolution of 0.5 line pairs per millimeter, while resolving simulated cancer lesions down to 0.75 mm diameter across large‐area images (55‐103 cm2). Large‐area OB images were generated in an ex vivo porcine colon. The platform allows centimeter‐sized large‐area OB imaging in vitro and ex vivo with submillimeter resolution, including automatic data segmentation of simulated cancer areas. The ability for robotic actuation and spectrum collection is also shown for ex vivo animal colon. If successful, this technology could widen access to user‐independent high‐quality endoscopy and early detection of gastrointestinal cancers. [ABSTRACT FROM AUTHOR]

Background and Aim: Multiple computer‐aided techniques utilizing artificial intelligence (AI) have been created to improve the detection of polyps during colonoscopy and thereby reduce the incidence of colorectal cancer. While adenoma detection rates (ADR) and polyp detection rates (PDR) are important colonoscopy quality indicators, adenoma miss rates (AMR) may better quantify missed lesions, which can ultimately lead to interval colorectal cancer. The purpose of this systematic review and meta‐analysis was to determine the efficacy of computer‐aided colonoscopy (CAC) with respect to AMR, ADR, and PDR in randomized controlled trials. Methods: A comprehensive, systematic literature search was performed across multiple databases in September of 2022 to identify randomized, controlled trials that compared CAC with traditional colonoscopy. Primary outcomes were AMR, ADR, and PDR. Results: Fourteen studies totaling 10 928 patients were included in the final analysis. There was a 65% reduction in the adenoma miss rate with CAC (OR, 0.35; 95% CI, 0.25–0.49, P < 0.001, I2 = 50%). There was a 78% reduction in the sessile serrated lesion miss rate with CAC (OR, 0.22; 95% CI, 0.08–0.65, P < 0.01, I2 = 0%). There was a 52% increase in ADR in the CAC group compared with the control group (OR, 1.52; 95% CI, 1.39–1.67, P = 0.04, I2 = 47%). There was 93% increase in the number of adenomas > 10 mm detected per colonoscopy with CAC (OR 1.93; 95% CI, 1.18–3.16, P < 0.01, I2 = 0%). Conclusions: The results of the present study demonstrate the promise of CAC in improving AMR, ADR, PDR across a spectrum of size and morphological lesion characteristics. [ABSTRACT FROM AUTHOR]

Background: Due to the complex nature of digital breast tomosynthesis (DBT) in imaging techniques, reading times are longer than 2D mammograms. A robust computer‐aided diagnosis system in DBT could help radiologists reduce their workload and reading times. Purpose: The purpose of this study was to develop algorithms for detecting biopsy‐proven breast lesions on DBT using multi‐depth level convolutional models and leveraging non‐biopsied samples. As biopsied positive samples in a lesion dataset are limited, we hypothesized that false positive (FP) findings by detection algorithms from non‐biopsied benign lesions could improve detection algorithms by using them as data augmentation. Approach: We first extracted 2D slices from DBT volumes with biopsy‐proven breast lesions (cancer and benign), with non‐biopsied benign lesions (actionable), and for controls. Then, to provide lesion continuity along the z‐direction, we combined a lesion slice with its immediate adjacent slices to synthesize 2.5‐dimensional (2.5D) images of the lesion by assigning them into R, G, and B color channels. We used 224 biopsy‐proven lesions from 39 cancer and 62 benign patients from a DBTex challenge dataset of 1000 scans. We included the 2.5D images of immediate neighboring slices from the lesion's center to increase the number of training samples. For lesion detection, we used the YOLOv5 algorithm as our base network. We trained a baseline algorithm (medium‐depth level) using biopsied samples to detect actionable FPs in non‐biopsied images. Afterward, we fine‐tuned the baseline model on the augmented image set (actionable FPs added). For lesion inferencing, we processed the DBT volume slice‐by‐slice to estimate bounding boxes in each slice, and then combined them by connecting bounding boxes along the depth via volumetric morphological closing. We trained an additional model (large) with deeper‐depth levels by repeating the above process. Finally, we developed an ensemble algorithm by combining the medium and large detection models. We used the free‐response operating characteristic curve to evaluate our algorithms. We reported mean sensitivity per FPs per DBT volume only for biopsied views and sensitivity at 2‐false positives per image (2FPI) for all views. However, due to the limited accessibility to the truth of the challenge validation and test datasets, we used sensitivity at 2FPI for statistical evaluation. Results: For the DBTex independent validation set, the medium baseline model achieved a mean sensitivity of 0.627 FPs per DBT volume, and a sensitivity of 0.640 at 2FPI. After adding actionable FP lesions, the model had an improved 2FPI of 0.769 over the baseline (p‐value = 0.013). Our ensemble algorithm with multi‐depth levels (medium + large) achieved a mean sensitivity of 0.815 FPs per DBT volume and an improved sensitivity at 2FPI of 0.80 over the baseline (p‐value < 0.001) on the validation set. Finally, our ensemble model achieved a mean sensitivity of 0.786 FPs per DBT volume and a sensitivity of 0.743 at 2FPI on the DBTex independent test set. Conclusions: Our results show that actionable FP findings hold useful information for lesion detection algorithms, and our ensemble detection model with multi‐depth levels improves lesion detection performance. [ABSTRACT FROM AUTHOR]

Aim: Colorectal cancer is the second commonest cause of cancer death worldwide. Colonoscopy plays a key role in the control of colorectal cancer and, in that regard, maximizing detection (and removal) of pre‐cancerous adenomas at colonoscopy is imperative. GI Genius™ (Medtronic Ltd) is a computer‐aided detection system that integrates with existing endoscopy systems and improves adenoma detection during colonoscopy. COLO‐DETECT aims to assess the clinical and cost effectiveness of GI Genius™ in UK routine colonoscopy practice. Methods and analysis: Participants will be recruited from patients attending for colonoscopy at National Health Service sites in England, for clinical symptoms, surveillance or within the national Bowel Cancer Screening Programme. Randomization will involve a 1:1 allocation ratio (GI Genius™‐assisted colonoscopy:standard colonoscopy) and will be stratified by age category (<60 years, 60–<74 years, ≥74 years), sex, hospital site and indication for colonoscopy. Demographic data, procedural data, histology and post‐procedure patient experience and quality of life will be recorded. COLO‐DETECT is designed and powered to detect clinically meaningful differences in mean adenomas per procedure and adenoma detection rate between GI Genius™‐assisted colonoscopy and standard colonoscopy groups. The study will close when 1828 participants have had a complete colonoscopy. An economic evaluation will be conducted from the perspective of the National Health Service. A patient and public representative is contributing to all stages of the trial. Registered at ClinicalTrials.gov (NCT04723758) and ISRCTN (10451355). What will this trial add to the literature?: COLO‐DETECT will be the first multi‐centre randomized controlled trial evaluating GI Genius™ in real world colonoscopy practice and will, uniquely, evaluate both clinical and cost effectiveness. [ABSTRACT FROM AUTHOR]

Background: In 2020, breast cancer becomes the most leading diagnosed cancer all over the world. The burden is increasing in the prevention and treatment of breast cancer. Accurately detecting breast lesions in screening images is important for early detection of cancer. Architectural distortion (AD) is one of the breast lesions that need to be detected. Purpose: To develop a deep‐learning‐based computer‐aided detection (CADe) model for AD in digital breast tomosynthesis (DBT). This model uses the superior–inferior directional context of DBT and anatomic prior knowledge to reduce false positive (FP). It can identify some negative samples that cannot be distinguished by deep learning features. Methods: The proposed CADe model consists of three steps. In the first step, a deep learning detection network detects two‐dimensional (2D) candidates of ADs in DBT slices with the inputs preprocessed by Gabor filters and convergence measure. In the second step, three‐dimensional (3D) candidates are obtained by stacking 2D candidates along superior–inferior direction. In the last step, FP reduction for 3D candidates is implemented based on superior–inferior directional context and anatomic prior knowledge of breast. DBT data from 99 cases with AD were used as the training set to train the CADe model, and data from 208 cases were used as an independent test set (including 108 cases with AD and 100 cases without AD as the control group). The free‐response receiver operating characteristic and mean true positive fraction (MTPF) in the range of 0.05–2.0 FPs per volume are used to evaluate the model. Results: Compared with the baseline model based on convergence measure, our proposed method demonstrates significant improvement (MTPF: 0.2826 ± 0.0321 vs. 0.6640 ± 0.0399). Results of an ablation study show that our proposed context‐ and anatomy‐based FP reduction methods improve the detection performance. The number of FPs per DBT volume reduces from 2.47 to 1.66 at 80% sensitivity after employing these two schemes. Conclusions: The deep learning model demonstrates practical value for AD detection. The results indicate that introducing superior–inferior directional context and anatomic prior knowledge into model can indeed reduce FPs and improve the performance of CADe model. [ABSTRACT FROM AUTHOR]

Purpose: Accurate detection of transition zone (TZ) prostate cancer (PCa) on magnetic resonance imaging (MRI) remains challenging using clinical subjective assessment due to overlap between PCa and benign prostatic hyperplasia (BPH). The objective of this paper is to describe a deep‐learning‐based framework for fully automated detection of PCa in the TZ using T2‐weighted (T2W) and apparent diffusion coefficient (ADC) map MR images. Method: This was a single‐center IRB‐approved cross‐sectional study of men undergoing 3T MRI on two systems. The dataset consisted of 196 patients (103 with and 93 without clinically significant [Grade Group 2 or higher] TZ PCa) to train and test our proposed methodology, with an additional 168 patients with peripheral zone PCa used only for training. We proposed an ensemble of classifiers in which multiple U‐Net‐based models are designed for prediction of TZ PCa location on ADC map MR images, with initial automated segmentation of the prostate to guide detection. We compared accuracy of ADC alone to T2W and combined ADC+T2W MRI for input images, and investigated improvements using ensembles over their constituent models with different methods of diversity in individual models by hyperparameter configuration, loss function and model architecture. Results: Our developed algorithm reported sensitivity and precision of 0.829 and 0.617 in 56 test cases containing 31 instances of TZ PCa and in 25 patients without clinically significant TZ tumors. Patient‐wise classification accuracy had an area under receiver operator characteristic curve (AUROC) of 0.974. Single U‐Net models using ADC alone (sensitivity 0.829, precision 0.534) outperformed assessment using T2W (sensitivity 0.086, precision 0.081) and assessment using combined ADC+T2W (sensitivity 0.687, precision 0.489). While the ensemble of U‐Nets with varying hyperparameters demonstrated the highest performance, all ensembles improved PCa detection compared to individual models, with sensitivities and precisions close to the collective best of constituent models. Conclusion: We describe a deep‐learning‐based method for fully automated TZ PCa detection using ADC map MR images that outperformed assessment by T2W and ADC+T2W. [ABSTRACT FROM AUTHOR]

Purpose: We propose a deep learning‐based computer‐aided detection (CADe) method to detect breast lesions in ultrafast DCE‐MRI sequences. This method uses both the 3D spatial information and temporal information obtained from the early‐phase of the dynamic acquisition. Methods: The proposed CADe method, based on a modified 3D RetinaNet model, operates on ultrafast T1 weighted sequences, which are preprocessed for motion compensation, temporal normalization, and are cropped before passing into the model. The model is optimized to enable the detection of relatively small breast lesions in a screening setting, focusing on detection of lesions that are harder to differentiate from confounding structures inside the breast. Results: The method was developed based on a dataset consisting of 489 ultrafast MRI studies obtained from 462 patients containing a total of 572 lesions (365 malignant, 207 benign) and achieved a detection rate, sensitivity, and detection rate of benign lesions of 0.90 (0.876–0.934), 0.95 (0.934–0.980), and 0.81 (0.751–0.871) at four false positives per normal breast with 10‐fold cross‐testing, respectively. Conclusions: The deep learning architecture used for the proposed CADe application can efficiently detect benign and malignant lesions on ultrafast DCE‐MRI. Furthermore, utilizing the less visible hard‐to‐detect lesions in training improves the learning process and, subsequently, detection of malignant breast lesions. [ABSTRACT FROM AUTHOR]

A computer‐aided detection (CADe) scheme, relying on a large number of high‐quality images with annotations, could help radiologists effectively detect lung nodules. However, such medical data are generally difficult to obtain. To address this issue, this paper proposes a novel method based on a conditional generative adversarial network (CGAN) to generate new samples for data augmentation (DA). This method employs a 3D CGAN based on a squeeze‐and‐excitation mechanism and residual learning to synthesize realistic and diverse lung nodules in chest computed tomography (CT) images to improve the performance of the CADe system. To evaluate the proposed method, this paper uses synthetic samples for DA to train the lung nodule detection network. The results indicate that these synthetic samples, which cover a part of the data distribution unfilled by the original data, can boost the overall performance of the nodule detection network at fixed false positive (FP) rates. [ABSTRACT FROM AUTHOR]

Purpose: Percutaneous transforaminal endoscopic discectomy (PTED) is one of the most common minimally invasive surgery methods used in clinic in recent years. In this study, we developed a computer‐aided detection system (CADS) based on convolutional neural network (CNN) to automatically recognize nerve and dura mater images under PTED surgery. Methods: We collected surgical videos from 65 patients with lumbar disc herniation who underwent PTED; we then converted the videos into images, and randomly divided some images into a training dataset, a validation dataset, test dataset. The training dataset and validation dataset were composed of 10 454 images containing nerve and dura mater from 50 randomly selected patients; test dataset contained 12 000 images from the remaining 15 patients. Results: The results showed that sensitivity, specificity, and accuracy reached 90.90%, 93.68%, and 92.29%, respectively. CADS could recognize the nerve and dura mater with no significant difference (P > 0.05) between each patient in test dataset. In comparison with clinicians of different levels, the performance of CADS was lower than that of a spinal endoscopist, but significantly higher than that of general surgeons. With the assistance of CADS, the performance of the general surgeons approached that of the spinal endoscopist. Conclusions: CNN can recognize well nerve and dura mater images in PTED surgery, and can help general surgeons to improve their ability to recognize tissues during the operation. [ABSTRACT FROM AUTHOR]

We investigated whether a convolutional neural network (CNN) can enhance the usability of computer‐aided detection (CAD) of chest radiographs for various pulmonary abnormal lesions. The numbers of normal and abnormal patients were 6055 and 3463, respectively. Two radiologists delineated regions of interest for lesions and labeled the disease types as ground truths. The datasets were split into training, tuning, and testing as 7:1: 2. Total test sets were randomly selected in 1214 normal and 690 abnormal. A 5‐fold, cross‐validation was performed on our datasets. For the classification of normal and abnormal, we developed a CNN based on DenseNet169; for abnormal detection, The You Only Look Once (YOLO) v2 with DenseNet was used. Detection and classification of normal and five classes of diseases (nodule[s], consolidation, interstitial opacity, pleural effusion, and pneumothorax) on chest radiographs were analyzed. Our CNN model classified chest radiographs as normal or abnormal with an accuracy of 97.8%. For the results of the abnormal, F1 score, was 75.2 ± 2.28% for nodules, 55.0 ± 4.3% for consolidation, 78.2 ± 7.85% for interstitial opacity, 81.6 ± 2.07% for pleural effusion, and 70.0 ± 7.97% for pneumothorax, respectively. In addition, we conducted the experiments between our method and RetinaNet with only nodules. The results of our method and RetinaNet at cutoff‐0.5 in the free response operating characteristic curve were 83.45% and 80.55%, respectively. Our algorithm demonstrated viable detection and disease classification capacity and could be used for CAD of lung diseases on chest radiographs. [ABSTRACT FROM AUTHOR]

Purpose: Early detection of lung cancer is of importance since it can increase patients' chances of survival. To detect nodules accurately during screening, radiologists would commonly take the axial, coronal, and sagittal planes into account, rather than solely the axial plane in clinical evaluation. Inspired by clinical work, the paper aims to develop an accurate deep learning framework for nodule detection by a combination of multiple planes. Methods: The nodule detection system is designed in two stages, multiplanar nodule candidate detection, multiscale false positive (FP) reduction. At the first stage, a deeply supervised encoder–decoder network is trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are merged. To further refine results, a three‐dimensional multiscale dense convolutional neural network that extracts multiscale contextual information is applied to remove non‐nodules. In the public LIDC‐IDRI dataset, 888 computed tomography scans with 1186 nodules accepted by at least three of four radiologists are selected to train and evaluate our proposed system via a tenfold cross‐validation scheme. The free‐response receiver operating characteristic curve is used for performance assessment. Results: The proposed system achieves a sensitivity of 94.2% with 1.0 FP/scan and a sensitivity of 96.0% with 2.0 FPs/scan. Although it is difficult to detect small nodules (i.e., <6 mm), our designed CAD system reaches a sensitivity of 93.4% (95.0%) of these small nodules at an overall FP rate of 1.0 (2.0) FPs/scan. At the nodule candidate detection stage, results show that the system with a multiplanar method is capable to detect more nodules compared to using a single plane. Conclusion: Our approach achieves good performance not only for small nodules but also for large lesions on this dataset. This demonstrates the effectiveness of our developed CAD system for lung nodule detection. [ABSTRACT FROM AUTHOR]

Background and Study Aims: Small polyps are occasionally missed during colonoscopy. This study was conducted to validate the diagnostic performance of a polyp‐detection algorithm to alert endoscopists to unrecognized lesions. Methods: A computer‐aided detection (CADe) algorithm was developed based on convolutional neural networks using training data from 1991 still colonoscopy images from 283 subjects with adenomatous polyps. The CADe algorithm was evaluated on a validation dataset including 50 short videos with 1–2 polyps (3.5 ± 1.5 mm, range 2–8 mm) and 50 videos without polyps. Two expert colonoscopists and two physicians in training separately read the same videos, blinded to the presence of polyps. The CADe algorithm was also evaluated using eight full videos with polyps and seven full videos without a polyp. Results: The per‐video sensitivity of CADe for polyp detection was 88% and the per‐frame false‐positive rate was 2.8%, with a confidence level of ≥30%. The per‐video sensitivity of both experts was 88%, and the sensitivities of the two physicians in training were 84% and 76%. For each reader, the frames with missed polyps appearing on short videos were significantly less than the frames with detected polyps, but no trends were observed regarding polyp size, morphology or color. For full video readings, per‐polyp sensitivity was 100% with a per‐frame false‐positive rate of 1.7%, and per‐frame specificity of 98.3%. Conclusions: The sensitivity of CADe to detect small polyps was almost equivalent to experts and superior to physicians in training. A clinical trial using CADe is warranted. [ABSTRACT FROM AUTHOR]

Objectives: The role of image analysis in 3‐dimensional (3D) automated breast ultrasound (ABUS) images is increasingly important because of its widespread use as a screening tool in whole‐breast examinations. However, reviewing a large number of images acquired from ABUS is time‐consuming and sometimes error prone. The aim of this study, therefore, was to develop an efficient computer‐aided detection (CADe) algorithm to assist the review process. Methods: The proposed CADe algorithm consisted of 4 major steps. First, initial tumor candidates were formed by extracting and merging hypoechoic square cells on 2‐dimensional (2D) transverse images. Second, a feature‐based classifier was then constructed using 2D features to filter out nontumor candidates. Third, the remaining 2D candidates were merged longitudinally into 3D masses. Finally, a 3D feature‐based classifier was used to further filter out nontumor masses to obtain the final detected masses. The proposed method was validated with 176 passes of breast images acquired by an Acuson S2000 automated breast volume scanner (Siemens Medical Solutions USA, Inc., Malvern, PA), including 44 normal passes and 132 abnormal passes containing 162 proven lesions (79 benign and 83 malignant). Results: The proposed CADe system could achieve overall sensitivity of 100% and 90% with 6.71 and 5.14 false‐positives (FPs) per pass, respectively. Our results also showed that the average number of FPs per normal pass (7.16) was more than the number of FPs per abnormal pass (6.56) at 100% sensitivity. Conclusions: The proposed CADe system has a great potential for becoming a good companion tool with ABUS imaging by ensuring high sensitivity with a relatively small number of FPs. [ABSTRACT FROM AUTHOR]

Purpose: Breast cancer is the most common cancer and the leading cause of cancer‐related deaths for women all over the world. Recently, automated breast ultrasound (ABUS) has become a new and promising screening modality for whole breast examination. However, reviewing volumetric ABUS is time‐consuming and lesions could be missed during the examination. Therefore, computer‐aided cancer detection in ABUS volume is extremely expected to help clinician for the breast cancer screening. Methods: We develop a novel end‐to‐end 3D convolutional network for automated cancer detection in ABUS volume, in order to accelerate reviewing and meanwhile to provide high detection sensitivity with low false positives (FPs). Specifically, an efficient 3D Inception Unet‐style architecture with fusion deep supervision mechanism is proposed to attain decent detection performance. In addition, a novel asymmetric loss is designed to help the network balancing false positive and false negative regions, thus improving detection sensitivity for small cancerous lesions. Results: The efficacy of our network was extensively validated on a dataset including 196 patients with 661 cancer regions. Our network obtained a detection sensitivity of 95.1% with 3.0 FPs per ABUS volume. Furthermore, the average inference time of the network was 0.1 second per volume, which largely shortens the conventional reviewing time. Conclusions: The proposed network provides efficient and accurate cancer detection scheme using ABUS volume, and may assist clinicians for more efficient breast cancer screening. [ABSTRACT FROM AUTHOR]

Manual detection of small uncalcified pulmonary nodules (diameter <4 mm) in thoracic computed tomography (CT) scans is a tedious and error‐prone task. Automatic detection of disperse micronodules is, thus, highly desirable for improved characterization of the fatal and incurable occupational pulmonary diseases. Here, we present a novel computer‐assisted detection (CAD) scheme specifically dedicated to detect micronodules. The proposed scheme consists of a candidate‐screening module and a false positive (FP) reduction module. The candidate‐screening module is initiated by a lung segmentation algorithm and is followed by a combination of 2D/3D features‐based thresholding parameters to identify plausible micronodules. The FP reduction module employs a 3D convolutional neural network (CNN) to classify each identified candidate. It automatically encodes the discriminative representations by exploiting the volumetric information of each candidate. A set of 872 micro‐nodules in 598 CT scans marked by at least two radiologists are extracted from the Lung Image Database Consortium and Image Database Resource Initiative to test our CAD scheme. The CAD scheme achieves a detection sensitivity of 86.7% (756/872) with only 8 FPs/scan and an AUC of 0.98. Our proposed CAD scheme efficiently identifies micronodules in thoracic scans with only a small number of FPs. Our experimental results provide evidence that the automatically generated features by the 3D CNN are highly discriminant, thus making it a well‐suited FP reduction module of a CAD scheme. [ABSTRACT FROM AUTHOR]

The problem of computer‐aided detection of architectural distortion (AD) in a digitised mammogram has been attempted in this manuscript. In examining a mammogram, the decision regarding a particular region of interest (RoI) is dependent on the appearance of the surrounding regions. However, in existing methods to detect AD the inference about an RoI is dependent on the appearance of this RoI alone. In addition, multiple radiologists infer the same mammogram in coming to a final decision about the mammogram. Contrary to popular ensemble classifiers like Adaboost and Random Forest, the authors propose an ensemble based method (imitating multiple radiologists by classifiers) for detecting AD such that the decision on a test RoI is dependent on the decisions of the surrounding RoIs in the proposed ensemble classifier. The proposed context‐based ensemble classifier has been validated on two mammographic databases. The proposal shows promising results in both the databases. [ABSTRACT FROM AUTHOR]

Breast cancer becomes a significant public health problem in the world. During the early detection of breast cancer, it is a very challenging task to classify accurately the benign–malignant patterns in digital mammograms. This study proposes a new fully automated computer‐aided diagnosis (CAD) system for breast cancer diagnosis with high‐accuracy and low‐computational requirements. The expectation–maximisation algorithm is investigated to extract automatically the region of interests (ROIs) within mammograms. The standard shape, statistical, and textural features of ROIs are extracted and combined with multi‐resolution and multi‐orientation features derived from a new feature extraction technique based on wavelet‐based contourlet transform. A hybrid feature selection approach based on combining the support vector machine recursive feature elimination with correlation bias reduction algorithm is proposed. Also, the authors investigate a new similarity‐based learning algorithm, called Q, for benign–malignant classification. The proposed CAD system is applied to real clinical mammograms, and the experimental results demonstrate the superior performance of the proposed CAD system over other existing CAD systems in terms of accuracy 98.16%, sensitivity 98.63%, specificity 97.80%, and computational time 2.2 s. This reveals the effectiveness of the proposed CAD system in improving the accuracy of breast cancer diagnosis in real‐time systems. [ABSTRACT FROM AUTHOR]

Purpose: Assessment of optic disc pallor in fundus photographs may be frequently misinterpreted due to the subjective nature of interpretation. We developed a fully automatic computer‐aided detection (CAD) system for optic disc pallor using colour fundus photographs and evaluated the accuracy of the system. Methods: A newly proposed CAD system was developed for automated segmentation and image analysis of optic disc pallor, and a logistic regression model was developed for risk analysis. A total of 230 photographs with variable degree of optic disc pallor, and 123 normal optic discs confirmed by optical coherence tomography were tested for validation of the software. Sensitivity and specificity of the CAD system in automatic detection of optic disc pallor using colour fundus photographs were evaluated. The results of manual detection of optic disc pallor on fundus photographs by two independent ophthalmologists were compared with the efficacy of the CAD system. Results: The fully automated CAD system achieved a sensitivity of 95.3% and a specificity of 96.7% for detecting optic disc pallor in colour fundus images. The overall accuracy of the CAD system was 96.1%, which was superior to the results of manual detection by individual examiners. Conclusions: We developed an automated CAD system that successfully detected optic disc pallor in fundus photographs. The proposed algorithm can assist the clinical judgement of ophthalmologists for detecting optic disc pallor in fundus photographs. [ABSTRACT FROM AUTHOR]

Objectives: To develop a U‐Net–based deep learning approach (U‐DL) for bladder segmentation in computed tomography urography (CTU) as a part of a computer‐assisted bladder cancer detection and treatment response assessment pipeline. Materials and methods: A dataset of 173 cases including 81 cases in the training/validation set (42 masses, 21 with wall thickening, 18 normal bladders), and 92 cases in the test set (43 masses, 36 with wall thickening, 13 normal bladders) were used with Institutional Review Board approval. An experienced radiologist provided three‐dimensional (3D) hand outlines for all cases as the reference standard. We previously developed a bladder segmentation method that used a deep learning convolution neural network and level sets (DCNN‐LS) within a user‐input bounding box. However, some cases with poor image quality or with advanced bladder cancer spreading into the neighboring organs caused inaccurate segmentation. We have newly developed an automated U‐DL method to estimate a likelihood map of the bladder in CTU. The U‐DL did not require a user‐input box and the level sets for postprocessing. To identify the best model for this task, we compared the following models: (a) two‐dimensional (2D) U‐DL and 3D U‐DL using 2D CT slices and 3D CT volumes, respectively, as input, (b) U‐DLs using CT images of different resolutions as input, and (c) U‐DLs with and without automated cropping of the bladder as an image preprocessing step. The segmentation accuracy relative to the reference standard was quantified by six measures: average volume intersection ratio (AVI), average percent volume error (AVE), average absolute volume error (AAVE), average minimum distance (AMD), average Hausdorff distance (AHD), and the average Jaccard index (AJI). As a baseline, the results from our previous DCNN‐LS method were used. Results: In the test set, the best 2D U‐DL model achieved AVI, AVE, AAVE, AMD, AHD, and AJI values of 93.4 ± 9.5%, −4.2 ± 14.2%, 9.2 ± 11.5%, 2.7 ± 2.5 mm, 9.7 ± 7.6 mm, 85.0 ± 11.3%, respectively, while the corresponding measures by the best 3D U‐DL were 90.6 ± 11.9%, −2.3 ± 21.7%, 11.5 ± 18.5%, 3.1 ± 3.2 mm, 11.4 ± 10.0 mm, and 82.6 ± 14.2%, respectively. For comparison, the corresponding values obtained with the baseline method were 81.9 ± 12.1%, 10.2 ± 16.2%, 14.0 ± 13.0%, 3.6 ± 2.0 mm, 12.8 ± 6.1 mm, and 76.2 ± 11.8%, respectively, for the same test set. The improvement for all measures between the best U‐DL and the DCNN‐LS were statistically significant (P < 0.001). Conclusion: Compared to a previous DCNN‐LS method, which depended on a user‐input bounding box, the U‐DL provided more accurate bladder segmentation and was more automated than the previous approach. [ABSTRACT FROM AUTHOR]

Abstract: Breast tumours are the leading cause of cancer death among female adults. Early diagnosis, discovery and treatment are currently the optimal approach to reducing mortality rates and increasing the length of cancer patients' lives. Presently, mammography is the most effective screening method for early breast tumour detection. This paper proposes a decomposition and recompilation approach for the analysis of mammograms. The decomposition stage is based on multiband generation processes (MBGP), which are used to expand the dimensionality of a mammogram. Recompilation uses principal‐component analysis (PCA) to generate different views of the mammogram based on the orthonormal basis vectors. Using Otsu's thresholding method, the abnormal parts of mammographic images can be easily detected. In experiments, the average Jaccard values determined using the Bayes, Markov, Windows, and proposed method were 0.253, 0.228, 0.201, and 0.441, respectively, for images from the mini–MIAS; averages were 0.132, 0.186, 0.158, and 0.261 for images from the Digital Database for Screening Mammography. Thus, the proposed method outperformed the other methods. The main contributions of the current paper are as follows: A novel methodology consisting of multiband generation processes and principal‐component analysis for analyzing abnormities in mammograms is proposed. Two practical data sets were used to develop and evaluate the proposed approach. [ABSTRACT FROM AUTHOR]

Purpose: To evaluate the usefulness of magnetic resonance imaging (MRI) computer-aided detection and diagnosis (CAD) for the detection of tumor-infiltrating lymphocytes (TILs) in triple-negative breast cancer (TNBC) patients. TNBC is a heterogeneous malignancy with a varying prognosis. Recently, the importance of TILs in TNBC has been determined.Materials and Methods: We retrospectively enrolled 60 lesions of TNBC. Either at 1.5T or 3T MRI, including T1 , T2 -weighted, and dynamic contrast-enhanced, images were obtained. The CAD results for all lesions were obtained, and we analyzed quantitative kinetic features including the initial peak enhancement and enhancement profiles. We divided the tumors into two groups: those with a TIL level of less than 50%, and those with a TIL level of 50% or more. Kinetic parameters were compared using Student's t-tests and chi-square tests.Results: There were 48 low-TIL lesions and 12 high-TIL lesions. The portion of persistent enhancement of tumors was negatively associated with the TIL levels (P = 0.003). The persistent minus washout value of the low-TIL group was higher than that of the high-TIL group (P = 0.008). The odds ratios were 0.944 (P = 0.012) for the persistent portion and 0.971 (P = 0.008) for the persistent minus washout value.Conclusion: The prediction model using kinetic enhancement parameters, particularly persistent proportion and plateau minus washout value, could be helpful for identifying TIL levels in TNBC and may be used as an imaging biomarker to guide the treatment plan.Level Of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:760-766. [ABSTRACT FROM AUTHOR]

Purpose: To identify breast MR imaging biomarkers to predict histologic grade and receptor status of ductal carcinoma in situ (DCIS).Materials and Methods: Informed consent was waived in this Health Insurance Portability and Accountability Act-compliant Institutional Review Board-approved study. Case inclusion was conducted from 7332 consecutive breast MR studies from January 1, 2009, to December 31, 2012. Excluding studies with benign diagnoses, studies without visible abnormal enhancement, and pathology containing invasive disease yielded 55 MR-imaged pathology-proven DCIS seen on 54 studies. Twenty-eight studies (52%) were performed at 1.5 Tesla (T); 26 (48%) at 3T. Regions-of-interest representing DCIS were segmented for precontrast, first and fourth postcontrast, and subtracted first and fourth postcontrast images on the open-source three-dimensional (3D) Slicer software. Fifty-seven metrics of each DCIS were obtained, including distribution statistics, shape, morphology, Renyi dimensions, geometrical measure, and texture, using the 3D Slicer HeterogeneityCAD module. Statistical correlation of heterogeneity metrics with DCIS grade and receptor status was performed using univariate Mann-Whitney test.Results: Twenty-four of the 55 DCIS (44%) were high nuclear grade (HNG); 44 (80%) were estrogen receptor (ER) positive. Human epidermal growth factor receptor-2 (HER2) was amplified in 10/55 (18%), nonamplified in 34/55 (62%), unknown/equivocal in 8/55 (15%). Surface area-to-volume ratio showed significant difference (P < 0.05) between HNG and non-HNG DCIS. No metric differentiated ER status (0.113 < p ≤ 1.000). Seventeen metrics showed significant differences between HER2-positive and HER2-negative DCIS (0.016 < P < 0.050).Conclusion: Quantitative heterogeneity analysis of DCIS suggests the presence of MR imaging biomarkers in classifying DCIS grade and HER2 status. Validation with larger samples and prospective studies is needed to translate these results into clinical applications.Level Of Evidence: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2017;46:1748-1759. [ABSTRACT FROM AUTHOR]

Purpose Symmetry is an important feature of human anatomy and the absence of symmetry in medical images can indicate the presence of pathology. Quantification of image symmetry can then be used to improve the automatic analysis of medical images. Methods A method is presented that computes both local and global symmetry in 2D medical images. A symmetry axis is determined to define for each position p in the image a mirrored position [ABSTRACT FROM AUTHOR]

Purpose Computer-aided detection (CADe) systems for mammography screening still mark many false positives. This can cause radiologists to lose confidence in CADe, especially when many false positives are obviously not suspicious to them. In this study, we focus on obvious false positives generated by microcalcification detection algorithms. Methods We aim at reducing the number of obvious false-positive findings by adding an additional step in the detection method. In this step, a multiclass machine learning method is implemented in which dedicated classifiers learn to recognize the patterns of obvious false-positive subtypes that occur most frequently. The method is compared to a conventional two-class approach, where all false-positive subtypes are grouped together in one class, and to the baseline CADe system without the new false-positive removal step. The methods are evaluated on an independent dataset containing 1,542 screening examinations of which 80 examinations contain malignant microcalcifications. Results Analysis showed that the multiclass approach yielded a significantly higher sensitivity compared to the other two methods ( P < 0.0002). At one obvious false positive per 100 images, the baseline CADe system detected 61% of the malignant examinations, while the systems with the two-class and multiclass false-positive reduction step detected 73% and 83%, respectively. Conclusions Our study showed that by adding the proposed method to a CADe system, the number of obvious false positives can decrease significantly ( P < 0.0002). [ABSTRACT FROM AUTHOR]

Purpose: Develop a computer-aided detection (CAD) system for masses in digital breast tomosynthesis (DBT) volume using a deep convolutional neural network (DCNN) with transfer learning from mammograms. Methods: A data set containing 2282 digitized film and digital mammograms and 324 DBT volumes were collected with IRB approval. The mass of interest on the images was marked by an experienced breast radiologist as reference standard. The data set was partitioned into a training set (2282 mammograms with 2461 masses and 230 DBT views with 228 masses) and an independent test set (94 DBT views with 89 masses). For DCNN training, the region of interest (ROI) containing the mass (true positive) was extracted from each image. False positive (FP) ROIs were identified at prescreening by their previously developed CAD systems. After data augmentation, a total of 45 072 mammographic ROIs and 37 450 DBT ROIs were obtained. Data normalization and reduction of non-uniformity in the ROIs across heterogeneous data was achieved using a background correction method applied to each ROI. A DCNN with four convolutional layers and three fully connected (FC) layers was first trained on the mammography data. Jittering and dropout techniques were used to reduce overfitting. After training with the mammographic ROIs, all weights in the first three convolutional layers were frozen, and only the last convolution layer and the FC layers were randomly initialized again and trained using the DBT training ROIs. The authors compared the performances of two CAD systems for mass detection in DBT: one used the DCNN-based approach and the other used their previously developed feature-based approach for FP reduction. The prescreening stage was identical in both systems, passing the same set of mass candidates to the FP reduction stage. For the feature-based CAD system, 3D clustering and active contour method was used for segmentation; morphological, gray level, and texture features were extracted and merged with a linear discriminant classifier to score the detected masses. For the DCNN-based CAD system, ROIs from five consecutive slices centered at each candidate were passed through the trained DCNN and a mass likelihood score was generated. The performances of the CAD systems were evaluated using free-response ROC curves and the performance difference was analyzed using a non-parametric method. Results: Before transfer learning, the DCNN trained only on mammograms with an AUC of 0.99 classified DBT masses with an AUC of 0.81 in the DBT training set. After transfer learning with DBT, the AUC improved to 0.90. For breast-based CAD detection in the test set, the sensitivity for the feature-based and the DCNN-based CAD systems was 83% and 91%, respectively, at 1 FP/DBT volume. The difference between the performances for the two systems was statistically significant (p-value < 0.05). Conclusions: The image patterns learned from the mammograms were transferred to the mass detection on DBT slices through the DCNN. This study demonstrated that large data sets collected from mammography are useful for developing new CAD systems for DBT, alleviating the problem and effort of collecting entirely new large data sets for the new modality. [ABSTRACT FROM AUTHOR]

Purpose: To develop and evaluate a method for an automatic detection of brain metastases in MR images.Materials and Methods: Nineteen patients were scanned using a 1.5 Tesla MR scanner. Two radiologists and a radiation oncologist marked the location of the brain metastases. The training group consisted of eight patients harboring 20 metastases. First, three-dimensional (3D) tumor-appearance templates were cross-correlated with MR brain images to evaluate their similarity, and a correlation threshold was established for metastasis candidates. Afterward, a method to reduce false positive rate (FPR) was applied: each detected object was segmented and its degree of anisotropy (DA) was obtained, removing the elongated structures with a DA above the optimal value from the receiver operating characteristic curve. Finally, the method was statistically validated in two groups: 11 patients with 42 brain metastases and 11 patients without metastases.Results: The method led to a sensitivity of 80% and an FPR per slice of 0.023 and 2.75 per patient in the training group. In the first validation group, a sensitivity of 88.10% and an FPR per slice of 0.05 corresponding to 6.91 false positives per patient were obtained. DA implementation decreased 3.5 times FPR compared with templates alone. It improved the radiologist's performance in metastases less than 10 mm from 89-93% to 100%. In the second validation group the FPR was 0.04 per slice and 5.18 per patient.Conclusion: This method demonstrates that 3D template matching applying DA technique has high sensitivity and low FPR for detecting brain metastases in MR images. J. Magn. Reson. Imaging 2016;44:642-652. [ABSTRACT FROM AUTHOR]

Purpose: Automated detection of solitary pulmonary nodules using positron emission tomography (PET) and computed tomography (CT) images shows good sensitivity; however, it is difficult to detect nodules in contact with normal organs, and additional efforts are needed so that the number of false positives (FPs) can be further reduced. In this paper, the authors propose an improved FP-reduction method for the detection of pulmonary nodules in PET/CT images by means of convolutional neural networks (CNNs). Methods: The overall scheme detects pulmonary nodules using both CT and PET images. In the CT images, a massive region is first detected using an active contour filter, which is a type of contrast enhancement filter that has a deformable kernel shape. Subsequently, high-uptake regions detected by the PET images are merged with the regions detected by the CT images. FP candidates are eliminated using an ensemble method; it consists of two feature extractions, one by shape/metabolic feature analysis and the other by a CNN, followed by a two-step classifier, one step being rule based and the other being based on support vector machines. Results: The authors evaluated the detection performance using 104 PET/CT images collected by a cancer-screening program. The sensitivity in detecting candidates at an initial stage was 97.2%, with 72.8 FPs/case. After performing the proposed FP-reduction method, the sensitivity of detection was 90.1%, with 4.9 FPs/case; the proposed method eliminated approximately half the FPs existing in the previous study. Conclusions: An improved FP-reduction scheme using CNN technique has been developed for the detection of pulmonary nodules in PET/CT images. The authors' ensemble FP-reduction method eliminated 93% of the FPs; their proposed method using CNN technique eliminates approximately half the FPs existing in the previous study. These results indicate that their method may be useful in the computer-aided detection of pulmonary nodules using PET/CT images. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to investigate the potential to improve lung cancer recurrence risk prediction performance for stage I NSCLS patients by integrating oversampling, feature selection, and score fusion techniques and develop an optimal prediction model. Methods: A dataset involving 94 early stage lung cancer patients was retrospectively assembled, which includes CT images, nine clinical and biological (CB) markers, and outcome of 3-yr disease-free survival (DFS) after surgery. Among the 94 patients, 74 remained DFS and 20 had cancer recurrence. Applying a computer-aided detection scheme, tumors were segmented from the CT images and 35 quantitative image (QI) features were initially computed. Two normalized Gaussian radial basis function network (RBFN) based classifiers were built based on QI features and CB markers separately. To improve prediction performance, the authors applied a synthetic minority oversampling technique (SMOTE) and a BestFirst based feature selection method to optimize the classifiers and also tested fusion methods to combine QI and CB based prediction results. Results: Using a leave-one-case-out cross-validation (K-fold cross-validation) method, the computed areas under a receiver operating characteristic curve (AUCs) were 0.716±0.071 and 0.642±0.061, when using the QI and CB based classifiers, respectively. By fusion of the scores generated by the two classifiers, AUC significantly increased to 0.859±0.052 (p < 0.05) with an overall prediction accuracy of 89.4%. Conclusions: This study demonstrated the feasibility of improving prediction performance by integrating SMOTE, feature selection, and score fusion techniques. Combining QI features and CB markers and performing SMOTE prior to feature selection in classifier training enabled RBFN based classifier to yield improved prediction accuracy. [ABSTRACT FROM AUTHOR]

Purpose: The authors are developing a computerized system for bladder segmentation in CT urography (CTU) as a critical component for computer-aided detection of bladder cancer. Methods: A deep-learning convolutional neural network (DL-CNN) was trained to distinguish between the inside and the outside of the bladder using 160?000 regions of interest (ROI) from CTU images. The trained DL-CNN was used to estimate the likelihood of an ROI being inside the bladder for ROIs centered at each voxel in a CTU case, resulting in a likelihood map. Thresholding and hole-filling were applied to the map to generate the initial contour for the bladder, which was then refined by 3D and 2D level sets. The segmentation performance was evaluated using 173 cases: 81 cases in the training set (42 lesions, 21 wall thickenings, and 18 normal bladders) and 92 cases in the test set (43 lesions, 36 wall thickenings, and 13 normal bladders). The computerized segmentation accuracy using the DL likelihood map was compared to that using a likelihood map generated by Haar features and a random forest classifier, and that using our previous conjoint level set analysis and segmentation system (CLASS) without using a likelihood map. All methods were evaluated relative to the 3D hand-segmented reference contours. Results: With DL-CNN-based likelihood map and level sets, the average volume intersection ratio, average percent volume error, average absolute volume error, average minimum distance, and the Jaccard index for the test set were 81.9% ± 12.1%, 10.2% ± 16.2%, 14.0% ± 13.0%, 3.6 ± 2.0 mm, and 76.2% ± 11.8%, respectively. With the Haar-feature-based likelihood map and level sets, the corresponding values were 74.3% ± 12.7%, 13.0% ± 22.3%, 20.5% ± 15.7%, 5.7 ± 2.6 mm, and 66.7% ± 12.6%, respectively. With our previous CLASS with local contour refinement (LCR) method, the corresponding values were 78.0% ± 14.7%, 16.5% ± 16.8%, 18.2% ± 15.0%, 3.8 ± 2.3 mm, and 73.9% ± 13.5%, respectively. Conclusions: The authors demonstrated that the DL-CNN can overcome the strong boundary between two regions that have large difference in gray levels and provides a seamless mask to guide level set segmentation, which has been a problem for many gradient-based segmentation methods. Compared to our previous CLASS with LCR method, which required two user inputs to initialize the segmentation, DL-CNN with level sets achieved better segmentation performance while using a single user input. Compared to the Haar-feature-based likelihood map, the DL-CNN-based likelihood map could guide the level sets to achieve better segmentation. The results demonstrate the feasibility of our new approach of using DL-CNN in combination with level sets for segmentation of the bladder. [ABSTRACT FROM AUTHOR]

Purpose: In the past decades, computer-aided detection(CADe)systems have been developed to aid screening radiologists in the detection of malignant microcalcifications. These systems are useful to avoid perceptual oversights and can increase the radiologists' detection rate. However, due to the high number of false positives marked by these CADesystems, they are not yet suitable as an independent reader. Breast arterial calcifications (BACs) are one of the most frequent false positives marked by CADesystems. In this study, a method is proposed for the elimination of BACs as positive findings. Removal of these false positives will increase the performance of the CADesystem in finding malignant microcalcifications. Methods: A multistage method is proposed for the removal of BAC findings. The first stage consists of a microcalcification candidate selection, segmentation and grouping of the microcalcifications, and classification to remove obvious false positives. In the second stage, a case-based selection is applied where cases are selected which contain BACs. In the final stage, BACs are removed from the selected cases. The BACs removal stage consists of a GentleBoost classifier trained on microcalcification features describing their shape, topology, and texture. Additionally, novel features are introduced to discriminate BACs from other positive findings. Results: The CADesystem was evaluated with and without BACs removal. Here, both systems were applied on a validation set containing 1088 cases of which 95 cases contained malignant microcalcifications. After bootstrapping, free-response receiver operating characteristics and receiver operating characteristics analyses were carried out. Performance between the two systems was compared at 0.98 and 0.95 specificity. At a specificity of 0.98, the sensitivity increased from 37% to 52% and the sensitivity increased from 62% up to 76% at a specificity of 0.95. Partial areas under the curve in the specificity range of 0.8-1.0 were significantly different between the system without BACs removal and the system with BACs removal, 0.129 ± 0.009 versus 0.144 ± 0.008 (p<0.05), respectively. Additionally, the sensitivity at one false positive per 50 cases and one false positive per 25 cases increased as well, 37% versus 51% (p<0.05) and 58% versus 67% (p<0.05) sensitivity, respectively. Additionally, the CADesystem with BACs removal reduces the number of false positives per case by 29% on average. The same sensitivity at one false positive per 50 cases in the CADesystem without BACs removal can be achieved at one false positive per 80 cases in the CADesystem with BACs removal. Conclusions: By using dedicated algorithms to detect and remove breast arterial calcifications, the performance of CADesystems can be improved, in particular, at false positive rates representative for operating points used in screening. [ABSTRACT FROM AUTHOR]

Purpose: The authors are developing a computer-aided detection system for bladder cancer on CT urography (CTU). In this study, the authors focused on developing a system for detecting masses fully or partially within the contrast-enhanced (C) region of the bladder. Methods: With IRB approval, a data set of 70 patients with biopsy-proven bladder lesions fully or partially immersed within the contrast-enhanced region (C region) of the bladder was collected for this study: 35 patients for the training set (39 malignant, 7 benign lesions) and 35 patients for the test set (49 malignant, 4 benign lesions). The bladder in the CTU images was automatically segmented using the authors' conjoint level set analysis and segmentation system, which they developed specifically to segment the bladder. A closed contour of the C region of the bladder was generated by maximum intensity projection using the property that the dependently layering contrast material in the bladder will be filled consistently to the same level along all CTU slices due to gravity. Potential lesion candidates within the C region contour were found using the authors' Straightened Periphery ANalysis (SPAN) method. SPAN transforms a bladder wall to a straightened thickness profile, marks suspicious pixels on the profile, and clusters them into regions of interest to identify potential lesion candidates. The candidate regions were automatically segmented using the authors' autoinitialized cascaded level set segmentation method. Twenty-three morphological features were automatically extracted from the segmented lesions. The training set was used to determine the best subset of these features using simplex optimization with the leave-one-out case method. A linear discriminant classifier was designed for the classification of bladder lesions and false positives. The detection performance was evaluated on the independent test set by free-response receiver operating characteristic analysis. Results: At the prescreening step, the authors' system achieved 84.4% sensitivity with an average of 4.3 false positives per case (FPs/case) for the training set, and 84.9% sensitivity with 5.4 FPs/case for the test set. After linear discriminant analysis (LDA) classification with the selected features, the FP rate improved to 2.5 FPs/case for the training set, and 4.3 FPs/case for the test set without missing additional true lesions. By varying the threshold for the LDA scores, at 2.5 FPs/case, the sensitivities were 84.4% and 81.1% for the training and test sets, respectively. At 1.7 FPs/case, the sensitivities decreased to 77.8% and 75.5%, respectively. Conclusions: The results demonstrate the feasibility of the authors' method for detection of bladder lesions fully or partially immersed in the contrast-enhanced region of CTU. [ABSTRACT FROM AUTHOR]

Purpose: To develop a computer-aided detection (CAD) scheme for mass detection on digitized mammograms that achieves a high sensitivity while maintaining a low false positive (FP) rate using morphological enhancement and simple linear iterative clustering (SLIC) method. Methods: The authors developed a multiple stage method for breast mass detection. The proposed CAD scheme consists of five major components: (1) preprocessing based on morphological enhancement, which enhances mass-like patterns while removing unrelated background clutters, (2) segmentation of mass candidates based on the SLIC method, which groups mass and background tissue into different regions, (3) prescreening of suspicious regions using rule-based classification that eliminates regions unlikely to represent masses, (4) potential lesion contour refinement based on distance regularized level set evolution, and (5) FP reduction based on feature extraction and an ensemble of undersampled support vector machines. Two datasets were built to design and evaluate the system: a mass dataset containing 187 cases (386 mammograms) and a nonmass dataset containing 88 mammograms. All cases were acquired from the digital database for screening mammography (DDSM). Approximately two thirds of the available masses were used for training the system, and the remaining masses and nonmass dataset were used for testing. Results: Testing of the proposed CAD system on the mass dataset yielded a mass-based sensitivity of 98.55%, 97.10%, 92.75% at 0.84, 0.63, 0.55 FP mark/image, respectively. Tested on the nonmass dataset, the scheme showed a FP rate of 0.55, 0.34, 0.30 mark/image. Conclusions: The results indicate that the system is promising in improving the performance of current CAD systems by reducing FP rate while achieving relatively high sensitivity. [ABSTRACT FROM AUTHOR]

Purpose: Automated 3D breast ultrasound (ABUS) has gained interest in breast imaging. Especially for screening women with dense breasts, ABUS appears to be beneficial. However, since the amount of data generated is large, the risk of oversight errors is substantial. Computer aided detection (CADe) may be used as a second reader to prevent oversight errors. When CADe is used in this fashion, it is essential that small cancers are detected, while the number of false positive findings should remain acceptable. In this work, the authors improve their previously developed CADe system in the initial candidate detection stage. Methods: The authors use a large number of 2D Haar-like features to differentiate lesion structures from false positives. Using a cascade of GentleBoost classifiers that combines these features, a likelihood score, highly specific for small cancers, can be efficiently computed. The likelihood scores are added to the previously developed voxel features to improve detection. Results: The method was tested in a dataset of 414 ABUS volumes with 211 cancers. Cancers had a mean size of 14.72 mm. Free-response receiver operating characteristic analysis was performed to evaluate the performance of the algorithm with and without using the aforementioned Haar-like feature likelihood scores. After the initial detection stage, the number of missed cancer was reduced by 18.8% after adding Haar-like feature likelihood scores. Conclusions: The proposed technique significantly improves our previously developed CADe system in the initial candidate detection stage. [ABSTRACT FROM AUTHOR]

Purpose: Renal calculi are common extracolonic incidental findings on computed tomographic colonography (CTC). This work aims to develop a fully automated computer-aided diagnosis system to accurately detect renal calculi on CTC images. Methods: The authors developed a total variation (TV) flow method to reduce image noise within the kidneys while maintaining the characteristic appearance of renal calculi. Maximally stable extremal region (MSER) features were then calculated to robustly identify calculi candidates. Finally, the authors computed texture and shape features that were imported to support vector machines for calculus classification. The method was validated on a dataset of 192 patients and compared to a baseline approach that detects calculi by thresholding. The authors also compared their method with the detection approaches using anisotropic diffusion and nonsmoothing. Results: At a false positive rate of 8 per patient, the sensitivities of the new method and the baseline thresholding approach were 69% and 35% (p < 1e - 3) on all calculi from 1 to 433 mm³ in the testing dataset. The sensitivities of the detection methods using anisotropic diffusion and nonsmoothing were 36% and 0%, respectively. The sensitivity of the new method increased to 90% if only larger and more clinically relevant calculi were considered. Conclusions: Experimental results demonstrated that TV-flow and MSER features are efficient means to robustly and accurately detect renal calculi on low-dose, high noise CTC images. Thus, the proposed method can potentially improve diagnosis. [ABSTRACT FROM AUTHOR]

Purpose: The authors are developing a computer-aided detection system to assist radiologists in analysis of coronary artery disease in coronary CT angiograms (cCTA). This study evaluated the accuracy of the authors' coronary artery segmentation and tracking method which are the essential steps to define the search space for the detection of atherosclerotic plaques. Methods: The heart region in cCTA is segmented and the vascular structures are enhanced using the authors' multiscale coronary artery response (MSCAR) method that performed 3D multiscale filtering and analysis of the eigenvalues of Hessian matrices. Starting from seed points at the origins of the left and right coronary arteries, a 3D rolling balloon region growing (RBG) method that adapts to the local vessel size segmented and tracked each of the coronary arteries and identifies the branches along the tracked vessels. The branches are queued and subsequently tracked until the queue is exhausted. With Institutional Review Board approval, 62 cCTA were collected retrospectively from the authors' patient files. Three experienced cardiothoracic radiologists manually tracked and marked center points of the coronary arteries as reference standard following the 17-segment model that includes clinically significant coronary arteries. Two radiologists visually examined the computer-segmented vessels and marked the mistakenly tracked veins and noisy structures as false positives (FPs). For the 62 cases, the radiologists marked a total of 10191 center points on 865 visible coronary artery segments. Results: The computer-segmented vessels overlapped with 83.6% (8520/10191) of the center points. Relative to the 865 radiologist-marked segments, the sensitivity reached 91.9% (795/865) if a true positive is defined as a computer-segmented vessel that overlapped with at least 10% of the reference center points marked on the segment. When the overlap threshold is increased to 50% and 100%, the sensitivities were 86.2% and 53.4%, respectively. For the 62 test cases, a total of 55 FPs were identified by radiologist in 23 of the cases. Conclusions: The authors' MSCAR-RBG method achieved high sensitivity for coronary artery segmentation and tracking. Studies are underway to further improve the accuracy for the arterial segments affected by motion artifacts, severe calcified and noncalcified soft plaques, and to reduce the false tracking of the veins and other noisy structures. Methods are also being developed to detect coronary artery disease along the tracked vessels. [ABSTRACT FROM AUTHOR]

Purpose: The buildup of noncalcified plaques (NCPs) that are vulnerable to rupture in coronary arteries is a risk for myocardial infarction. Interpretation of coronary CT angiography (cCTA) to search for NCP is a challenging task for radiologists due to the low CT number of NCP, the large number of coronary arteries, and multiple phase CT acquisition. The authors conducted a preliminary study to develop machine learning method for automated detection of NCPs in cCTA. Methods: With IRB approval, a data set of 83 ECG-gated contrast enhanced cCTA scans with 120 NCPs was collected retrospectively from patient files. A multiscale coronary artery response and rolling balloon region growing (MSCAR-RBG) method was applied to each cCTA volume to extract the coronary arterial trees. Each extracted vessel was reformatted to a straightened volume composed of cCTA slices perpendicular to the vessel centerline. A topological soft-gradient (TSG) detection method was developed to prescreen for NCP candidates by analyzing the 2D topological features of the radial gradient field surface along the vessel wall. The NCP candidates were then characterized by a luminal analysis that used 3D geometric features to quantify the shape information and gray-level features to evaluate the density of the NCP candidates. With machine learning techniques, useful features were identified and combined into an NCP score to differentiate true NCPs from false positives (FPs). To evaluate the effectiveness of the image analysis methods, the authors performed tenfold cross-validation with the available data set. Receiver operating characteristic (ROC) analysis was used to assess the classification performance of individual features and the NCP score. The overall detection performance was estimated by free response ROC (FROC) analysis. Results: With our TSG prescreening method, a prescreening sensitivity of 92.5% (111/120) was achieved with a total of 1181 FPs (14.2 FPs/scan). On average, six features were selected during the tenfold cross-validation training. The average area under the ROC curve (AUC) value for training was 0.87 ± 0.01 and the AUC value for validation was 0.85 ± 0.01. Using the NCP score, FROC analysis of the validation set showed that the FP rates were reduced to 3.16, 1.90, and 1.39 FPs/scan at sensitivities of 90%, 80%, and 70%, respectively. Conclusions: The topological soft-gradient prescreening method in combination with the luminal analysis for FP reduction was effective for detection of NCPs in cCTA, including NCPs causing positive or negative vessel remodeling. The accuracy of vessel segmentation, tracking, and centerline identification has a strong impact on NCP detection. Studies are underway to further improve these techniques and reduce the FPs of the CADe system. [ABSTRACT FROM AUTHOR]

Purpose To present results of a pilot study to develop software that identifies regions suspicious for prostate transition zone (TZ) tumor, free of user input. Materials and Methods Eight patients with TZ tumors were used to develop the model by training a Naïve Bayes classifier to detect tumors based on selection of most accurate predictors among various signal and textural features on T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) maps. Features tested as inputs were: average signal, signal standard deviation, energy, contrast, correlation, homogeneity and entropy (all defined on T2WI); and average ADC. A forward selection scheme was used on the remaining 20% of training set supervoxels to identify important inputs. The trained model was tested on a different set of ten patients, half with TZ tumors. Results In training cases, the software tiled the TZ with 4 × 4-voxel 'supervoxels,' 80% of which were used to train the classifier. Each of 100 iterations selected T2WI energy and average ADC, which therefore were deemed the optimal model input. The two-feature model was applied blindly to the separate set of test patients, again without operator input of suspicious foci. The software correctly predicted presence or absence of TZ tumor in all test patients. Furthermore, locations of predicted tumors corresponded spatially with locations of biopsies that had confirmed their presence. Conclusion Preliminary findings suggest that this tool has potential to accurately predict TZ tumor presence and location, without operator input. J. Magn. Reson. Imaging 2014;40:301-305 © 2013 Wiley Periodicals, Inc. [ABSTRACT FROM AUTHOR]

Purpose: A computer-aided detection (CADe) system based on quantitative tissue clustering algorithm was proposed to identify potential tumors in automated breast ultrasound (ABUS) images. Methods: Our three-dimensional (3D) ABUS images database included 148 biopsy-verified lesions (size 0.4-7.9 cm; mean 1.76 cm). An ABUS volume was comprised of 229-282 slices of twodimensional (2D) images. For tumor detection, the fast 3D mean shift method was used to remove the speckle noise and the segment tissues with similar properties. The hypoechogenic regions, i.e., the tumor candidates, were extracted using fuzzy c-means clustering. Seven features related to echogenicity and morphology were quantified and used to predict the likelihood of identifying a tumor and filtering out the false-positive (FP) regions. Results: The sensitivity of the proposed CADe system achieved 89.19% (132/148) with 2.00 FPs per volume. For the volumes without lesion, the FP rate was 1.27. The sensitivity was 92.50% (74/80) for malignant tumors and 85.29% (58/68) for benign tumors. Conclusions: The proposed CADe system provides an automatic and quantitative procedure for tumor detection in ABUS images. Further studies are needed to reduce the FP rate of the CADe algorithm. [ABSTRACT FROM AUTHOR]

Purpose: Develop a computer-aided detection (CADe) system for clustered microcalcifications in digital breast tomosynthesis (DBT) volume enhanced with multiscale bilateral filtering (MSBF) regularization. Methods: With Institutional Review Board approval and written informed consent, two-view DBT of 154 breasts, of which 116 had biopsy-proven microcalcification (MC) clusters and 38 were free of MCs, was imaged with a General Electric GEN2 prototype DBT system. The DBT volumes were reconstructed with MSBF-regularized simultaneous algebraic reconstruction technique (SART) that was designed to enhance MCs and reduce background noise while preserving the quality of other tissue structures. The contrast-to-noise ratio (CNR) of MCs was further improved with enhancement-modulated calcification response (EMCR) preprocessing, which combined multiscale Hessian response to enhance MCs by shape and bandpass filtering to remove the low-frequency structured background. MC candidates were then located in the EMCR volume using iterative thresholding and segmented by adaptive region growing. Two sets of potential MC objects, cluster centroid objects and MC seed objects, were generated and the CNR of each object was calculated. The number of candidates in each set was controlled based on the breast volume. Dynamic clustering around the centroid objects grouped the MC candidates to form clusters. Adaptive criteria were designed to reduce false positive (FP) clusters based on the size, CNR values and the number of MCs in the cluster, cluster shape, and cluster based maximum intensity projection. Free-response receiver operating characteristic (FROC) and jackknife alternative FROC (JAFROC) analyses were used to assess the performance and compare with that of a previous study. Results: Unpaired two-tailed t-test showed a significant increase ( p < 0.0001) in the ratio of CNRs for MCs with and without MSBF regularization compared to similar ratios for FPs. For view-based detection, a sensitivity of 85% was achieved at an FP rate of 2.16 per DBT volume. For case-based detection, a sensitivity of 85% was achieved at an FP rate of 0.85 per DBT volume. JAFROC analysis showed a significant improvement in the performance of the current CADe system compared to that of our previous system ( p = 0.003). Conclusions: MBSF regularized SART reconstruction enhances MCs. The enhancement in the signals, in combination with properly designed adaptive threshold criteria, effective MC feature analysis, and false positive reduction techniques, leads to a significant improvement in the detection of clustered MCs in DBT. [ABSTRACT FROM AUTHOR]