Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unet

TL;DR

This paper introduces an explainable 3D U-Net model for segmenting gastrointestinal organs in radiotherapy, aiming to improve accuracy, interpretability, and efficiency in treatment planning.

Contribution

It presents a novel deep learning pipeline that integrates explainability into 3D U-Net for gastrointestinal segmentation in radiotherapy.

Findings

Enhanced interpretability of segmentation results

Reduced manual outlining time for clinicians

Potential for improved treatment accuracy

Abstract

In treating gastrointestinal cancer using radiotherapy, the role of the radiation oncologist is to administer high doses of radiation, through x-ray beams, toward the tumor while avoiding the stomach and intestines. With the advent of precise radiation treatment technology such as the MR-Linac, oncologists can visualize the daily positions of the tumors and intestines, which may vary day to day. Before delivering radiation, radio oncologists must manually outline the position of the gastrointestinal organs in order to determine position and direction of the x-ray beam. This is a time consuming and labor intensive process that may substantially prolong a patient's treatment. A deep learning (DL) method can automate and expedite the process. However, many deep neural networks approaches currently in use are black-boxes which lack interpretability which render them untrustworthy and impractical in a healthcare setting. To address this, an emergent field of AI known as Explainable AI (XAI) may be incorporated to improve the transparency and viability of a model. This paper proposes a deep learning pipeline that incorporates XAI to address the challenges of organ segmentation.