Unsupervised Anomaly Detection on Implicit Shape representations for Sarcopenia Detection

TL;DR

This paper presents an unsupervised method using implicit neural representations to detect sarcopenia by modeling normal muscle shapes and identifying anomalies through reconstruction errors, demonstrating effective discrimination on a dataset of segmented muscle volumes.

Contribution

It introduces a novel unsupervised approach leveraging implicit neural representations for muscle shape analysis and sarcopenia detection, without requiring manual annotations.

Findings

Effective discrimination between sarcopenic and normal muscles

Successful unsupervised separation of muscle health states

Utilization of reconstruction error for anomaly detection

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.