Fully Automated Organ Segmentation in Male Pelvic CT Images

Abstract

Accurate segmentation of prostate and surrounding organs at risk is important for prostate cancer radiotherapy treatment planning. We present a fully automated workflow for male pelvic CT image segmentation using deep learning. The architecture consists of a 2D localization network followed by a 3D segmentation network for volumetric segmentation of prostate, bladder, rectum, and femoral heads. We used a multi-channel 2D U-Net followed by a 3D U-Net with encoding arm modified with aggregated residual networks, known as ResNeXt. The models were trained and tested on a pelvic CT image dataset comprising 136 patients. Test results show that 3D U-Net based segmentation achieves mean (SD) Dice coefficient values of 90 (2.0)% ,96 (3.0)%, 95 (1.3)%, 95 (1.5)%, and 84 (3.7)% for prostate, left femoral head, right femoral head, bladder, and rectum, respectively, using the proposed fully automated segmentation method.

arXiv comment21 pages; 11 figures; 4 tables

References in corpus (1)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Cited by in corpus (10)

• Intelligent Inverse Treatment Planning via Deep Reinforcement Learning, a Proof-of-Principle Study in High Dose-rate Brachytherapy for Cervical Cancer
• 3D RoI-aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation
• A machine learning approach to using Quality-of-Life patient scores in guiding prostate radiation therapy dosing
• ARPM-net: A novel CNN-based adversarial method with Markov Random Field enhancement for prostate and organs at risk segmentation in pelvic CT images
• AUNet: Attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms
• A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy
• Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Net
• Generalizability of deep learning based fluence map prediction as an inverse planning approach
• Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
• DeepWL: Robust EPID based Winston-Lutz Analysis using Deep Learning and Synthetic Image Generation