Deep Shape Analysis on Abdominal Organs for Diabetes Prediction

TL;DR

This paper introduces a deep neural network that analyzes abdominal organ shapes directly from raw point clouds to predict diabetes, outperforming traditional shape descriptors.

Contribution

It presents a novel end-to-end deep learning approach for abdominal shape analysis that eliminates the need for shape alignment or handcrafted features.

Findings

The network effectively distinguishes healthy and diabetic individuals based on abdominal shapes.

The learned shape representations outperform traditional descriptors like BrainPrint.

The method simplifies shape analysis by operating directly on raw point clouds.

Abstract

Morphological analysis of organs based on images is a key task in medical imaging computing. Several approaches have been proposed for the quantitative assessment of morphological changes, and they have been widely used for the analysis of the effects of aging, disease and other factors in organ morphology. In this work, we propose a deep neural network for predicting diabetes on abdominal shapes. The network directly operates on raw point clouds without requiring mesh processing or shape alignment. Instead of relying on hand-crafted shape descriptors, an optimal representation is learned in the end-to-end training stage of the network. For comparison, we extend the state-of-the-art shape descriptor BrainPrint to the AbdomenPrint. Our results demonstrate that the network learns shape representations that better separates healthy and diabetic individuals than traditional representations.