Unsupervised Anomaly Detection on Implicit Shape representations for Sarcopenia Detection

2025-02-13

AI Summary

This work addresses the challenge of unsupervised early screening for sarcopenia. We propose an anomaly detection method based on implicit neural representations (INRs) of 3D muscle shape—departing from conventional volumetric measurements. Our approach introduces a two-stage unsupervised framework: (1) a conditional INR models a continuous latent space encoding muscle geometry; (2) a self-decoding strategy learns disentangled latent representations that inherently separate normal from pathological morphologies, enabling label-free sarcopenia identification. Evaluated on 103 clinically segmented whole-body CT/MRI volumes, our method demonstrates significantly enhanced sensitivity to muscle shape degeneration and achieves higher detection accuracy than standard volumetric biomarkers. It establishes a novel paradigm for unsupervised, shape-aware intelligent diagnosis of sarcopenia.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: 3D Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Sarcopenia is an age-related progressive loss of muscle mass and strength that significantly impacts daily life. A commonly studied criterion for characterizing the muscle mass has been the combination of 3D imaging and manual segmentations. In this paper, we instead study the muscles' shape. We rely on an implicit neural representation (INR) to model normal muscle shapes. We then introduce an unsupervised anomaly detection method to identify sarcopenic muscles based on the reconstruction error of the implicit model. Relying on a conditional INR with an auto-decoding strategy, we also learn a latent representation of the muscles that clearly separates normal from abnormal muscles in an unsupervised fashion. Experimental results on a dataset of 103 segmented volumes indicate that our double anomaly detection strategy effectively discriminates sarcopenic and non-sarcopenic muscles.

Problem

• Detects sarcopenia via muscle shape analysis.
• Uses implicit neural representations for anomaly detection.
• Separates normal and abnormal muscles unsupervised.

Innovation

• Implicit neural representation modeling
• Unsupervised anomaly detection method
• Conditional INR auto-decoding strategy