Prostate cancer

Pharmacokinetics

Area under curve

Effective diffusion coefficient

Mann–Whitney U test

Computer science

Receiver operating characteristic

Radiology

Pattern recognition (psychology)

Data set

Internal medicine

Wilcoxon signed-rank test

Artificial intelligence

Confidence interval

Medicine

Nuclear medicine

Convolutional neural network

Cancer

Magnetic resonance imaging

Machine learning

Journal of Magnetic Resonance Imaging

Background Deep learning is the most promising methodology for automatic computer‐aided diagnosis of prostate cancer (PCa) with multiparametric MRI (mp‐MRI). Purpose To develop an automatic approach based on deep convolutional neural network (DCNN) to classify PCa and noncancerous tissues (NC) with mp‐MRI. Study Type Retrospective. Subjects In all, 195 patients with localized PCa were collected from a PROSTATEx database. In total, 159/17/19 patients with 444/48/55 observations (215/23/23 PCas and 229/25/32 NCs) were randomly selected for training/validation/testing, respectively. Sequence T 2 ‐weighted, diffusion‐weighted, and apparent diffusion coefficient images. Assessment A radiologist manually labeled the regions of interest of PCas and NCs and estimated the Prostate Imaging Reporting and Data System (PI‐RADS) scores for each region. Inspired by VGG‐Net, we designed a patch‐based DCNN model to distinguish between PCa and NCs based on a combination of mp‐MRI data. Additionally, an enhanced prediction method was used to improve the prediction accuracy. The performance of DCNN prediction was tested using a receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Moreover, the predicted result was compared with the PI‐RADS score to evaluate its clinical value using decision curve analysis. Statistical Test Two‐sided Wilcoxon signed‐rank test with statistical significance set at 0.05. Results The DCNN produced excellent diagnostic performance in distinguishing between PCa and NC for testing datasets with an AUC of 0.944 (95% confidence interval: 0.876–0.994), sensitivity of 87.0%, specificity of 90.6%, PPV of 87.0%, and NPV of 90.6%. The decision curve analysis revealed that the joint model of PI‐RADS and DCNN provided additional net benefits compared with the DCNN model and the PI‐RADS scheme. Data Conclusion The proposed DCNN‐based model with enhanced prediction yielded high performance in statistical analysis, suggesting that DCNN could be used in computer‐aided diagnosis (CAD) for PCa classification. Level of Evidence: 3 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;48:1570–1577

Computer‐aided diagnosis of prostate cancer using a deep convolutional neural network from multiparametric MRI