Reliable Radiologic Skeletal Muscle Area Assessment—A Biomarker for Cancer Cachexia Diagnosis

TL;DR

A new AI tool called SMAART-AI reliably measures muscle mass from CT scans, helping diagnose cancer cachexia and improve patient outcomes.

Contribution

SMAART-AI introduces an uncertainty-aware pipeline for automated muscle quantification, enabling reliable and scalable assessment of cancer cachexia.

Findings

SMAART-AI achieved a Dice score of 97.80% ± 0.93% in gastroesophageal cancer and a median SMA deviation of 2.48% from expert annotations.

Integrating SMA/SMI with clinical features improved survival prediction by up to +9.82% in pancreatic cancer and supported cachexia detection with 70% accuracy.

Abstract

What are the main findings?
SMAART-AI is an uncertainty-aware CT muscle analysis pipeline that combines robust segmentation with ensemble uncertainty and triage, supporting reliable automated muscle quantification across heterogeneous cancer cohorts.SMAART-AI enables multimodal integration of imaging-derived muscle metrics (SMA/SMI) with clinical features, improving downstream modeling for prognostic tasks (survival) and clinical endpoints (e.g., cachexia/recurrence prediction).

SMAART-AI is an uncertainty-aware CT muscle analysis pipeline that combines robust segmentation with ensemble uncertainty and triage, supporting reliable automated muscle quantification across heterogeneous cancer cohorts.

SMAART-AI enables multimodal integration of imaging-derived muscle metrics (SMA/SMI) with clinical features, improving downstream modeling for prognostic tasks (survival) and clinical endpoints (e.g., cachexia/recurrence prediction).

What are the implications of the main findings?
Uncertainty-based filtering creates a transparent deployment pathway by flagging higher-risk (noisy/out-of-distribution) cases for expert review while allowing scalable automated processing for routine cases.CT-derived muscle biomarkers can be operationalized at scale for cachexia assessment across cancers, strengthening prognostic stratification when combined with clinical data and supporting reproducible, longitudinal monitoring.

Uncertainty-based filtering creates a transparent deployment pathway by flagging higher-risk (noisy/out-of-distribution) cases for expert review while allowing scalable automated processing for routine cases.

CT-derived muscle biomarkers can be operationalized at scale for cachexia assessment across cancers, strengthening prognostic stratification when combined with clinical data and supporting reproducible, longitudinal monitoring.

Loss of skeletal muscle mass in cancer cachexia is associated with poorer survival, reduced treatment tolerance, and diminished quality of life. Routine oncology computed tomography (CT) can yield skeletal muscle area (SMA) and skeletal muscle index (SMI) for early cachexia assessment and prognostication, but manual annotation is labor intensive and existing automated tools often show inconsistent reliability. We developed SMAART-AI (Skeletal Muscle Assessment—Automated and Reliable Tool based on AI), a fully automated pipeline that localizes the third lumbar (L3) vertebral level, segments skeletal muscle, and quantifies prediction uncertainty to flag potentially unreliable outputs. Performance and reliability were evaluated across gastroesophageal, pancreatic, colorectal, and ovarian cancer cohorts, benchmarking against expert annotations and existing tools. SMAART-AI achieved a Dice score of 97.80% ± 0.93% in gastroesophageal cancer and a median SMA deviation of 2.48% from expert annotations across pancreatic, colorectal, and ovarian cohorts. Uncertainty scores correlated strongly with prediction error, enabling identification of high-error cases to support trustworthy deployment. Integrating the SMA/SMI with clinical features and body mass index (BMI) improved survival prediction (concordance index was +2.19% for colorectal, +9.82% for pancreatic, and +2.58% for ovarian cancer) and supported cachexia detection (70.00% accuracy; F1 80.00%). Overall, SMAART-AI provides an uncertainty-aware, clinically translatable framework for scalable CT-based muscle assessment and improved oncologic prognostication.

Figures