Truace
Subscribe

machine-learning-derived myosteatosis as predictor of recurrence in stage II-III colon cancer

Source article: Association between body composition and recurrence in stage II-III colon cancer: a retrospective cohort study

Colorectal Cancer (CRC) is a common cause of cancer death and prognostic factors are used to determine management. Patients with advanced disease often become cachectic, losing skeletal muscle mass and density, as well as subcutaneous fat. CT can be used to assess body composition by measuring skeletal muscle area, density and subcutaneous and visceral fat. We hypothesise that evidence of sarcopenia or myosteatosis at diagnosis is associated with an increased risk of cancer recurrence. Patients discussed at the…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-0920· cite & verify
Association between body composition and recurrence in stage II-III colon cancer: a retrospective cohort study
Known effects of low-level radiation exposure : health implications of the TMI accident : proceedings of a conference, April 1979 by Shrivastava, P. K. (Prakash K.) National Cancer Institute (U.S.). Public domain
Trace impact readingContested
P 67The P score combines the specificity and measured human impact of the grounded problem claim with the strength of this Trace’s cited sources.

Both sides are scored from claims and sources, not community votes.

G 70The G score combines the specificity and measured human impact of the grounded gain claim with the strength of this Trace’s cited sources.

In brief

Researchers applied a machine learning model called Mosamatic to routine CT staging scans from 615 patients with stage II-III colon cancer treated between 2015-2021 at one center to quantify skeletal muscle area, density, and fat. They found myosteatosis was more common in those who later recurred and was linked to worse recurrence-free survival at 1 and 5 years.

If validated, automated CT body composition could add a readily available prognostic marker to colon cancer management, helping stratify recurrence risk beyond traditional tumor factors. Uncertainty remains because the data are retrospective, single-institution, and rely on pre-defined literature cutoffs for myosteatosis and sarcopenia.

Main points

  1. 615 patients with stage II-III colon cancer who underwent surgery between 2015-2021 at a single institution were studied; 120 developed recurrence.
  2. Skeletal muscle radiation attenuation was lower in recurrence group (34.3 HU vs 32.2 HU, p = 0.012) while Skeletal Muscle Index did not differ significantly.
  3. 71.7% of patients who developed recurrence had myosteatosis versus 54.9% in no recurrence group (p=0.001), with no significant RFS difference for sarcopenia alone (p=0.17).

The gain

Using a machine learning model to measure CT body composition at L3 identified myosteatosis as an independent predictor of recurrence in stage II-III colon cancer.

The problem

Patients with stage II-III colon cancer whose CT body composition showed myosteatosis via machine learning analysis had significantly lower 5-year recurrence-free survival.

The rundown

The study collated patients discussed at a colorectal cancer multidisciplinary team meeting from 2015-2021, including only stage II-III colon cancer after surgery and excluding rectal cancer and neoadjuvant therapy cases.

Body composition was derived from initial CT staging scans at L3 using Mosamatic, applying literature definitions for sarcopenia and myosteatosis, with recurrence-free survival as primary outcome and multivariate analysis showing HR=1.62 for myosteatosis.

Sources

  1. Peer-reviewedClinical Nutrition ESPEN2026-08-26

The debate