Technology Category
Data Mining & Knowledge Management: Anomaly/Outlier DetectionKnowledge Representation and Reasoning: Diagnosis and Abductive ReasoningComputer Vision: 3D Computer Vision
Unsupervised Anomaly Detection on Implicit Shape representations for Sarcopenia Detection
🤖 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
Application Category
📝 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
Research questions and friction points this paper is trying to address.
Detects sarcopenia via muscle shape analysis.
Uses implicit neural representations for anomaly detection.
Separates normal and abnormal muscles unsupervised.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Implicit neural representation modeling
Unsupervised anomaly detection method
Conditional INR auto-decoding strategy
🔎 Similar Papers
2024-05-29arXiv.orgCitations: 0
