Multi-parametric MRI (mp-MRI) is considered the best non-invasive imaging modality for diagnosing prostate cancer (PCa). However, mp-MRI for PCa diagnosis is currently limited by the qualitative or semi-quantitative interpretation criteria, leading to inter-reader variability and a suboptimal ability to assess lesion aggressiveness. Convolutional neural networks (CNNs) are a powerful method to automatically learn the discriminative features for various tasks, including cancer detection. We propose a novel multi-class CNN, FocalNet, to jointly detect PCa lesions and predict their aggressiveness using Gleason score (GS). FocalNet characterizes lesion aggressiveness and fully utilizes distinctive knowledge from mp-MRI. We collected a prostate mp-MRI dataset from 417 patients who underwent 3T mp-MRI exams prior to robotic-assisted laparoscopic prostatectomy (RALP). FocalNet is trained and evaluated in this large study cohort with 5-fold cross-validation. In the free-response receiver operating characteristics (FROC) analysis for lesion detection, FocalNet achieved 89.7% and 87.9% sensitivity for index lesions and clinically significant lesions at 1 false positive per patient, respectively. For GS classification, evaluated by the receiver operating characteristics (ROC) analysis, FocalNet received the area under the curve (AUC) of 0.81 and 0.79 for the classifications of clinically significant PCa (GS≥3+4) and PCa with GS≥4+3, respectively. With the comparison to the prospective performance of radiologists using the current diagnostic guideline, FocalNet demonstrated comparable detection sensitivity for index lesions and clinically significant lesions, only 3.4% and 1.5% lower than highly experienced radiologists without statistical significance.

No abstract

GENITOURINARY IMAGINGM ultiparametric MRI is an important tool in the diagnosis of prostate cancer (PCa) (1,2). However, multiparametric MRI still misses PCa in up to 45% of men and faces challenges in distinguishing clinically significant PCa from indolent PCa (2,3). Thus, histopathologic examination of PCa remains the reference standard. A Gleason score based on the microscopic appearance of PCa is assigned to indicate its aggressiveness (4).Diffusion-weighted MRI is a critical component of multiparametric MRI and is sensitive to tissue microstructure changes in PCa (5). However, current clinical analysis using a monoexponential signal model to calculate apparent diffu-Materials and Methods: Men with PCa who underwent 3-T MRI and robotic-assisted radical prostatectomy between June 2018 and January 2019 were prospectively studied. After prostatectomy, the fresh whole prostate specimens were imaged in patient-specific threedimensionally printed molds by using 3-T MRI with DR-CSI and were then sliced to create coregistered WMHP slides. The DR-CSI spectral signal component fractions (f A , f B , f C ) were compared with epithelial, stromal, and luminal area fractions (f epithelium , f stroma , f lumen ) quantified in PCa and benign tissue regions. A linear mixed-effects model assessed the correlations between (f A , f B , f C ) and (f epithelium , f stroma , f lumen ), and the strength of correlations was evaluated by using Spearman correlation coefficients. Differences between PCa and benign tissues in terms of DR-CSI signal components and microscopic tissue compartments were assessed using two-sided t tests.Results: Prostate specimens from nine men (mean age, 65 years 6 7 [standard deviation]) were evaluated; 20 regions from 17 PCas, along with 20 benign tissue regions of interest, were analyzed. Three DR-CSI spectral signal components (spectral peaks) were consistently identified. The f A , f B , and f C were correlated with f epithelium , f stroma , and f lumen (all P , .001), with Spearman correlation coefficients of 0.74 (95% confidence interval [CI]: 0.62, 0.83), 0.80 (95% CI: 0.66, 0.89), and 0.67 (95% CI: 0.51, 0.81), respectively. PCa exhibited differences compared with benign tissues in terms of increased f A (PCa vs benign, 0.37 6 0.05 vs 0.27 6 0.06; P , .001), decreased f C (PCa vs benign, 0.18 6 0.06 vs 0.31 6 0.13; P = .01), increased f epithelium (PCa vs benign, 0.44 6 0.13 vs 0.26 6 0.16; P , .001), and decreased f lumen (PCa vs benign, 0.14 6 0.08 vs 0.27 6 0.18; P = .004). Conclusion:Diffusion-relaxation correlation spectrum imaging signal components correlate with microscopic tissue compartments in the prostate and differ between cancer and benign tissue.

Our main objective is to develop a novel deep learning-based algorithm for automatic segmentation of prostate zone and to evaluate the proposed algorithm on an additional independent testing data in comparison with inter-reader consistency between two experts. With IRB approval and HIPAA compliance, we designed a novel convolutional neural network (CNN) for automatic segmentation of the prostatic transition zone (TZ) and peripheral zone (PZ) on T2-weighted (T2w) MRI. The total study cohort included 359 patients from two sources; 313 from a deidentified publicly available dataset (SPIE-AAPM-NCI PROSTATEX challenge) and 46 from a large U.S. tertiary referral center with 3T MRI (external testing dataset (ETD)). The TZ and PZ contours were manually annotated by research fellows, supervised by genitourinary (GU) radiologists. The model was developed using 250 patients and tested internally using the remaining 63 patients from the PROSTATEX (internal testing dataset (ITD)) and tested again (n=46) externally using the ETD. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation performance. DSCs for PZ and TZ were 0.74±0.08 and 0.86±0.07 in the ITD respectively. In the ETD, DSCs for PZ and TZ were 0.74±0.07 and 0.79±0.12, respectively. The inter-reader consistency (Expert 2 vs. Expert 1) were 0.71±0.13 (PZ) and 0.75±0.14 (TZ). This novel DL algorithm enabled automatic segmentation of PZ and TZ with high accuracy on both ITD and ETD without a performance difference for PZ and less than 10% TZ difference. In the ETD, the proposed method can be comparable to experts in the segmentation of prostate zones.

No abstract