3D Transport-based Morphometry (3D-TBM) for medical image analysis

TL;DR

3D-TBM introduces a transport-based framework for analyzing 3D medical images, enabling effective classification and interpretability by embedding images into a transport domain and providing tools for visualization and analysis.

Contribution

This paper presents 3D-TBM, a comprehensive tool that implements transport-based morphometry for 3D medical images, including data processing, embedding, analysis, and visualization functionalities.

Findings

Facilitates interpretation of clinical features in original image space

Provides a practical toolkit with tutorials and source code

Enables effective classification and analysis of 3D medical images

Abstract

Transport-Based Morphometry (TBM) has emerged as a new framework for 3D medical image analysis. By embedding images into a transport domain via invertible transformations, TBM facilitates effective classification, regression, and other tasks using transport-domain features. Crucially, the inverse mapping enables the projection of analytic results back into the original image space, allowing researchers to directly interpret clinical features associated with model outputs in a spatially meaningful way. To facilitate broader adoption of TBM in clinical imaging research, we present 3D-TBM, a tool designed for morphological analysis of 3D medical images. The framework includes data preprocessing, computation of optimal transport embeddings, and analytical methods such as visualization of main transport directions, together with techniques for discerning discriminating directions and related analysis methods. We also provide comprehensive documentation and practical tutorials to support researchers interested in applying 3D-TBM in their own medical imaging studies. The source code is publicly available through PyTransKit.