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.

Prostate cancer is the second leading cause of cancer death among men in the United States. The diagnosis of prostate MRI often relies on accurate prostate zonal segmentation. However, state-of-the-art automatic segmentation methods often fail to produce well-contained volumetric segmentation of the prostate zones since certain slices of prostate MRI, such as base and apex slices, are harder to segment than other slices. This difficulty can be overcome by leveraging important multi-scale image-based information from adjacent slices, but current methods do not fully learn and exploit such cross-slice information. In this paper, we propose a novel cross-slice attention mechanism, which we use in a Transformer module to systematically learn cross-slice information at multiple scales. The module can be utilized in any existing deep-learning-based segmentation framework with skip connections. Experiments show that our cross-slice attention is able to capture cross-slice information significant for prostate zonal segmentation in order to improve the performance of current state-of-the-art methods. Cross-slice attention improves segmentation accuracy in the peripheral zones, such that segmentation results are consistent across all the prostate slices (apex, mid-gland, and base). The code for the proposed model is available at https://bit.ly/CAT-Net .

Automatic segmentation of prostatic zones on multi-parametric MRI (mpMRI) can improve the diagnostic workflow of prostate cancer. We designed a spatial attentive Bayesian deep learning network for the automatic segmentation of the peripheral zone (PZ) and transition zone (TZ) of the prostate with uncertainty estimation. The proposed method was evaluated by using internal and external independent testing datasets, and overall uncertainties of the proposed model were calculated at different prostate locations (apex, middle, and base). The study cohort included 351 MRI scans, of which 304 scans were retrieved from a de-identified publicly available datasets (PROSTATEX) and 47 scans were extracted from a large U.S. tertiary referral center (external testing dataset; ETD)). All the PZ and TZ contours were drawn by research fellows under the supervision of expert genitourinary radiologists. Within the PROSTATEX dataset, 259 and 45 patients (internal testing dataset; ITD) were used to develop and validate the model. Then, the model was tested independently using the ETD only. The segmentation performance was evaluated using the Dice Similarity Coefficient (DSC). For PZ and TZ segmentation, the proposed method achieved mean DSCs of 0.80±0.05 and 0.89± 0.04 on ITD, as well as 0.79±0.06 and 0.87±0.07 on ETD. For both PZ and TZ, there was no significant difference between ITD and ETD for the proposed method. This DL-based method enabled the accuracy of the PZ and TZ segmentation, which outperformed the state-of-art methods (DeeplabV3+, Attention U-Net, R2U-Net, USE-Net and U-Net). We observed that segmentation uncertainty peaked at the junction between PZ, TZ and AFS. Also, the overall uncertainties were highly consistent with the actual model performance between PZ and TZ at three clinically relevant locations of the prostate.

Our study supports the safety and effectiveness of 3-T in-bore MR-guided prostate biopsy; Prostate Imaging Reporting and Data System version 2 enabled risk stratification in patients with positive ... PurposeTo determine the diagnostic yield of in-bore 3-T magnetic resonance (MR) imaging–guided prostate biopsy and stratify performance according to Prostate Imaging Reporting and Data System (PI-R...

Diffusion-relaxation correlation spectrum imaging (DR CSI) parameters correlate with histopathologic microscopic prostate tissue compartments—epithelium, stroma, and lumen—in men with prostate cancer. Background Microstructural MRI has the potential to improve diagnosis and characterization of prostate cancer (PCa), but validation with histopathology is lacking. Purpose To validate ex vivo diffu...

Purpose: To quantifyvariation across the breasts and to evaluate the accuracy of precontrast T₁estimation with and withoutvariation in breast MRI patients at 3 Tesla (T).Materials and Methods: and variable flip angle (VFA) T₁mapping were included in our dynamic contrast‐enhanced (DCE) breast imaging protocol to study a total of 25 patients on a 3.0T GE MR 750 system. We computed precontrast T₁relaxation in fat, which we assumed to be consistent across a cohort of breast imaging subjects, with and without compensation forvariation. The mean and standard deviation ofand T₁values were calculated for statistical data analysis.Results: Our measurements showed a consistentfield difference between the left and right breasts. The left breast has an average 15.4% higher flip angle than the prescribed flip angle, and the right breast has an average 17.6% lower flip angle than the prescribed flip angle. This average 33% flip angle difference, which can be vendor and model specific, creates a 52% T₁estimation bias in fat between breasts using the VFA T₁mapping technique. The T₁variation is reduced to 7% by includingcorrection.Conclusion: We have shown that severevariation over the breasts can cause a substantial error in T₁estimation between the breasts, in VFA T₁maps at 3T, but that compensating for these variations can considerably improve accuracy of T₁measurements, which can directly benefit quantitative breast DCE‐MRI at 3T. J. Magn. Reson. Imaging 2013;38:454–459.