DeepGI: An Automated Approach for Gastrointestinal Tract Segmentation in MRI Scans
Ye Zhang, Yulu Gong, Dongji Cui, Xinrui Li, Xinyu Shen
TL;DR
The paper tackles the challenge of time-consuming and variable manual GI tract segmentation in MRI for radiotherapy planning. It proposes a tri-path deep learning framework that combines Inception-V4 for initial classification, UNet++ with a VGG19 encoder for 2.5D segmentation, and Edge U-Net for grayscale edge-enhanced segmentation, with ensemble averaging to fuse outputs. Innovative data preprocessing includes 2.5D stacking and grayscale processing to improve robustness and generalization. Experimental results show Edge U-Net excels on grayscale data while 2.5D UNet++ with VGG19 performs best on 2.5D data, underscoring the approach’s versatility and potential clinical impact.
Abstract
Gastrointestinal (GI) tract cancers pose a global health challenge, demanding precise radiotherapy planning for optimal treatment outcomes. This paper introduces a cutting-edge approach to automate the segmentation of GI tract regions in magnetic resonance imaging (MRI) scans. Leveraging advanced deep learning architectures, the proposed model integrates Inception-V4 for initial classification, UNet++ with a VGG19 encoder for 2.5D data, and Edge UNet for grayscale data segmentation. Meticulous data preprocessing, including innovative 2.5D processing, is employed to enhance adaptability, robustness, and accuracy. This work addresses the manual and time-consuming segmentation process in current radiotherapy planning, presenting a unified model that captures intricate anatomical details. The integration of diverse architectures, each specializing in unique aspects of the segmentation task, signifies a novel and comprehensive solution. This model emerges as an efficient and accurate tool for clinicians, marking a significant advancement in the field of GI tract image segmentation for radiotherapy planning.