Related Experiment Video
Updated: Jan 15, 2026
13:35
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
Published on: March 21, 2021
11.6K
AI-Based 3D-Segmentation Quantifies Sarcopenia in Multiple Myeloma Patients.
Thuy-Duong Do1,2, Tobias Nonnenmacher1, Marieke Burghardt3,4
1Clinic of Diagnostic and Interventional Radiology (DIR), Heidelberg University Hospital, 69120 Heidelberg, Germany.
Diagnostics (Basel, Switzerland)
|October 16, 2025
Summary
Multiple myeloma patients undergoing treatment experience significant muscle loss, particularly in the iliopsoas and gluteal muscles. This sarcopenia is linked to changes in Body-Mass Index (BMI) and can be accurately tracked using AI-driven imaging analysis.
Area of Science:
- Oncology
- Radiology
- Sarcopenia Research
Background:
- Sarcopenia, characterized by muscle mass and strength loss, leads to functional decline and increased fall risk.
- Multiple myeloma (MM) treatment can impact skeletal muscle, necessitating detailed monitoring.
- Understanding these muscle changes is crucial for managing patient outcomes.
Purpose of the Study:
- To investigate skeletal muscle changes in multiple myeloma patients during treatment.
- To evaluate the effectiveness of AI-based 3D segmentation for assessing muscle volume and intramuscular adipose tissue.
- To correlate muscle changes with Body-Mass Index (BMI) variations.
Main Methods:
- Retrospective analysis of 51 MM patients using whole-body low-dose CT scans before and after treatment.
- Automated 3D segmentation using AI (TotalSegmentator and BOA tool) to quantify muscle volume (MV) and intramuscular adipose tissue (IMAT).
- Evaluation of specific muscle groups including autochthonous back, iliopsoas, and gluteal muscles.
Main Results:
- Muscle volume (MV) loss and intramuscular adipose tissue (IMAT) increase significantly correlated with BMI changes (r=0.7, p<0.0001).
- Patients with decreased BMI lost MV, while those with increased BMI showed increased IMAT.
- MV loss was most pronounced in the iliopsoas (-9.8%) and gluteus maximus (-9.1%) muscles.
Conclusions:
- AI-based 3D segmentation offers a reliable and efficient method for detailed sarcopenia assessment in MM patients.
- Detectable loss of MV and increase in IMAT are associated with BMI fluctuations during MM treatment.
- Muscle loss patterns suggest differential impact based on fiber type, with fast-twitch fibers being more affected, informing targeted exercise interventions.
