Exploring Automated Contouring Across Institutional Boundaries: A Deep Learning Approach with Mouse Micro-CT Datasets

TL;DR

This study demonstrates that Swin UNETR, a deep learning model using hierarchical transformers, outperforms existing methods in mouse organ segmentation across different micro-CT datasets, showing high accuracy and robustness.

Contribution

The paper introduces Swin UNETR for mouse organ segmentation, showing it surpasses nnU-Net and AIMOS, especially in varied imaging conditions, highlighting its generalizability.

Findings

Swin UNETR achieves higher dice scores than nnU-Net and AIMOS.

The model maintains robustness across different imaging noise levels.

Swin UNETR performs well on external datasets with different imaging parameters.

Abstract

Image-guided mouse irradiation is essential to understand interventions involving radiation prior to human studies. Our objective is to employ Swin UNEt Transformers (Swin UNETR) to segment native micro-CT and contrast-enhanced micro-CT scans and benchmark the results against 3D no-new-Net (nnU-Net). Swin UNETR reformulates mouse organ segmentation as a sequence-to-sequence prediction task, using a hierarchical Swin Transformer encoder to extract features at 5 resolution levels, and connects to a Fully Convolutional Neural Network (FCNN)-based decoder via skip connections. The models were trained and evaluated on open datasets, with data separation based on individual mice. Further evaluation on an external mouse dataset acquired on a different micro-CT with lower kVp and higher imaging noise was also employed to assess model robustness and generalizability. Results indicate that Swin UNETR consistently outperforms nnU-Net and AIMOS in terms of average dice similarity coefficient (DSC) and Hausdorff distance (HD95p), except in two mice of intestine contouring. This superior performance is especially evident in the external dataset, confirming the model's robustness to variations in imaging conditions, including noise and quality, thereby positioning Swin UNETR as a highly generalizable and efficient tool for automated contouring in pre-clinical workflows.