Fig. 2.

Flowchart of the development and comparison of the deep learning models and the integrated models with PI-RADS assessment. Abbreviation: T2WI, T2-weighted image; ADC, apparent diffusion coefficient; DWI, diffusion-weighted image; PCa, prostate cancer; csPCa, clinically significant prostate cancer; ROI, region of interest; PI-RADS, Prostate Imaging and Reporting and Data System; DL-BM, deep learning models for the classification between benign and malignant lesions; DL-CS, deep learning models for the classification between clinically significant and non-clinically significant PCa; DL-CS-Res, the deep learning model based on ResNet3D network for the classification between clinically significant and non-clinically significant PCa; PIDL-CS, integrated model combining DL-CS-Res and PI-RADS assessment; AUC, area under receiver operating characteristic curve