A 3D-2D Hybrid U-Net Convolutional Neural Network Approach to Prostate Organ Segmentation of Multiparametric MR

OBJECTIVE. Prostate cancer is the most commonly diagnosed cancer in men in the United States with more than 200,000 new cases in 2018. Multiparametric MRI (mpMRl) is increasingly used for prostate cancer evaluation. Prostate organ segmentation is an essential step of surgical planning for prostate fusion biopsies. Deep learning convolutional neural networks (CNNs) are the predominant method of machine learning for medical image recognition. In this study, we describe a deep learning approach, a subset of artificial intelligence, for automatic localization and segmentation of prostates from mpMRI. MATERIALS AND METHODS. This retrospective study included patients who underwent prostate MRI and ultrasound-MRI fusion transrectal biopsy between September 2014 and December 2016. Axial T2-weighted images were manually segmented by two abdominal radiologists, which served as ground truth. These manually segmented images were used for training on a customized hybrid 3D-2D U-Net CNN architecture in a fivefold cross-validation paradigm for neural network training and validation. The Dice score, a measure of overlap between manually segmented and automatically derived segmentations, and Pearson linear correlation coefficient of prostate volume were used for statistical evaluation. RESULTS. The CNN was trained on 299 MRI examinations (total number of MR images = 7774) of 287 patients. The customized hybrid 3D-2D U-Net had a mean Dice score of 0.898 (range, 0.890-0.908) and a Pearson correlation coefficient for prostate volume of 0.974. CONCLUSION. A deep learning CNN can automatically segment the prostate organ from clinical MR images. Further studies should examine developing pattern recognition for lesion localization and quantification.

Automated summary

In this study, a deep learning approach using convolutional neural networks was used for automatic segmentation of prostate organs from mpMRI, achieving high accuracy in segmentation and correlation with prostate volume. Further research is needed to explore pattern recognition for lesion localization and quantification.