Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Dynamic tumor tracking for locally advanced pancreatic cancer: precision in motion.

Translational cancer research·2026
Same author

Implementing Timely Germline Genetic Testing for Patients With Pancreatic Cancer Using a Genetics Copilot for Point-of-Care Education and Health Assessment.

JCO precision oncology·2026
Same author

Differences in overall survival for invasive epithelial ovarian cancer by race and ethnicity: results from the Ovarian Cancer Association Consortium.

British journal of cancer·2026
Same author

Ovarian cancer tumor immune profiles associated with intrauterine device and oral contraceptive use.

British journal of cancer·2026
Same author

Aerobic Exercise Activates S1PR1 Signaling in Tumor Endothelial Cells to Promote Vascular Function in Pancreatic Cancer.

Cancer research·2026
Same author

Pancreatic Cancer Early Detection Biomarkers for High-Risk Individuals: Insights From the PRECEDE Consortium.

International journal of cancer·2026

Related Experiment Video

Updated: Mar 29, 2026

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography
07:33

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

989

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

Sabeen Ahmed1,2, Nathan Parker3, Margaret Park4,5

  • 1Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL 33612, USA.

Cells
|March 27, 2026
PubMed
Summary

A new AI tool, SMAART-AI, accurately assesses skeletal muscle area (SMA) and index (SMI) from CT scans for cancer cachexia. This automated method improves survival prediction and aids in early detection, enhancing cancer patient care.

Keywords:
artificial intelligencecancer cachexiamachine learningradiographic biomarkerreliabilityrobustnessuncertainty

More Related Videos

The Colon-26 Carcinoma Tumor-bearing Mouse as a Model for the Study of Cancer Cachexia
08:55

The Colon-26 Carcinoma Tumor-bearing Mouse as a Model for the Study of Cancer Cachexia

Published on: November 30, 2016

17.4K
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
13:35

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

12.1K

Related Experiment Videos

Last Updated: Mar 29, 2026

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography
07:33

Non-invasive Skeletal Muscle Quantification in Small Animals Using Micro-computed Tomography

Published on: November 8, 2024

989
The Colon-26 Carcinoma Tumor-bearing Mouse as a Model for the Study of Cancer Cachexia
08:55

The Colon-26 Carcinoma Tumor-bearing Mouse as a Model for the Study of Cancer Cachexia

Published on: November 30, 2016

17.4K
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
13:35

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

12.1K

Area of Science:

  • Oncology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Cancer cachexia leads to skeletal muscle mass loss, impacting survival and quality of life.
  • Assessing skeletal muscle area (SMA) and index (SMI) via CT is crucial for cachexia prognostication.
  • Manual CT annotation is time-consuming, and automated tools lack consistent reliability.

Purpose of the Study:

  • To develop and validate SMAART-AI, a fully automated pipeline for reliable skeletal muscle assessment from oncology CT scans.
  • To quantify prediction uncertainty for trustworthy AI deployment in clinical settings.
  • To evaluate the integration of SMA/SMI with clinical data for improved survival prediction and cachexia detection.

Main Methods:

  • Developed SMAART-AI for automated L3 vertebral level localization and skeletal muscle segmentation.
  • Quantified prediction uncertainty to identify unreliable outputs.
  • Benchmarked performance against expert annotations and existing tools across multiple cancer cohorts (gastroesophageal, pancreatic, colorectal, ovarian).

Main Results:

  • SMAART-AI achieved high accuracy (Dice score 97.80% ± 0.93% in gastroesophageal cancer) and low deviation from expert annotations (median 2.48% SMA deviation).
  • Uncertainty scores effectively flagged high-error predictions.
  • Integrating SMA/SMI improved survival prediction (concordance index +2.19% to +9.82%) and supported cachexia detection (70.00% accuracy, F1 80.00%).

Conclusions:

  • SMAART-AI offers a reliable, automated, and uncertainty-aware framework for skeletal muscle assessment using CT scans.
  • The tool enhances oncologic prognostication and aids in early cachexia detection.
  • SMAART-AI is clinically translatable for scalable application in cancer patient management.