Deep Learning Improves Speed and Accuracy of Prostate Gland Segmentations on Magnetic Resonance Imaging for Targeted Biopsy

• Published in: The Journal of urology Vol. 206; no. 3; pp. 604 - 612
• Main Authors: Soerensen, Simon John Christoph, Fan, Richard E., Seetharaman, Arun, Chen, Leo, Shao, Wei, Bhattacharya, Indrani, Kim, Yong-hun, Sood, Rewa, Borre, Michael, Chung, Benjamin I., To'o, Katherine J., Rusu, Mirabela, Sonn, Geoffrey A.
• Format: Journal Article
• Language: English
• Published: Philadelphia, PA Wolters Kluwer 01.09.2021
• Subjects: Adult Urology; Datasets as Topic; Deep Learning; Feasibility Studies; Humans; Image Processing, Computer-Assisted - methods; Image-Guided Biopsy - methods; Magnetic Resonance Imaging, Interventional; Male; Multimodal Imaging - methods; Multiparametric Magnetic Resonance Imaging; Proof of Concept Study; Prospective Studies; Prostate - diagnostic imaging; Prostate - pathology; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - pathology; Reproducibility of Results; Retrospective Studies; Software; Time Factors; Ultrasonography, Interventional - methods; deep learning; magnetic resonance imaging; ultrasonography; imaging-guided biopsy
• ISSN: 0022-5347; 1527-3792; 1527-3792
• DOI: 10.1097/JU.0000000000001783

Purpose:Targeted biopsy improves prostate cancer diagnosis. Accurate prostate segmentation on magnetic resonance imaging (MRI) is critical for accurate biopsy. Manual gland segmentation is tedious and time-consuming. We sought to develop a deep learning model to rapidly and accurately segment the prostate on MRI and to implement it as part of routine magnetic resonance-ultrasound fusion biopsy in the clinic.Materials and Methods:A total of 905 subjects underwent multiparametric MRI at 29 institutions, followed by magnetic resonance-ultrasound fusion biopsy at 1 institution. A urologic oncology expert segmented the prostate on axial T2-weighted MRI scans. We trained a deep learning model, ProGNet, on 805 cases. We retrospectively tested ProGNet on 100 independent internal and 56 external cases. We prospectively implemented ProGNet as part of the fusion biopsy procedure for 11 patients. We compared ProGNet performance to 2 deep learning networks (U-Net and holistically-nested edge detector) and radiology technicians. The Dice similarity coefficient (DSC) was used to measure overlap with expert segmentations. DSCs were compared using paired t-tests.Results:ProGNet (DSC=0.92) outperformed U-Net (DSC=0.85, p <0.0001), holistically-nested edge detector (DSC=0.80, p <0.0001), and radiology technicians (DSC=0.89, p <0.0001) in the retrospective internal test set. In the prospective cohort, ProGNet (DSC=0.93) outperformed radiology technicians (DSC=0.90, p <0.0001). ProGNet took just 35 seconds per case (vs 10 minutes for radiology technicians) to yield a clinically utilizable segmentation file.Conclusions:This is the first study to employ a deep learning model for prostate gland segmentation for targeted biopsy in routine urological clinical practice, while reporting results and releasing the code online. Prospective and retrospective evaluations revealed increased speed and accuracy.