Limited-site adaptation reveals representation-specific MRI transportability for lymphovascular invasion in endometrial cancer
- 1McGill University
Abstract
ObjectivesTo determine how clinically anchored MRI representations behave from supportive internal testing through locked institutional transfer and limited target-site adaptation for prediction of substantial lymphovascular space invasion (LVSI) in endometrial cancer.
Materials and MethodsThis retrospective two-center study included 206 women undergoing preoperative 3-T MRI between March 2016 and March 2023. Hospital A provided training (n = 117) and supportive internal testing (n = 13); Hospital B provided strict external testing (n = 76; 12 positive). Age and CA125 formed the clinical baseline and were included in every imaging model. In 200 repeated stratified two-fold Hospital B splits, each patient was evaluated outside the adaptation half. Models remained locked; adaptation changed only the threshold or applied no-empirical-Bayes (no-EB) ComBat before threshold selection.
ResultsDenseNet121, U-NEXtractor, and fusion U-NEXtractor achieved internal AUC 1.000 but strict external AUCs of 0.685, 0.671, and 0.669, respectively. At development-locked thresholds, sensitivities were 0.167, 0.583, and 0.417. Threshold adaptation increased median sensitivity to 0.833 for all three, with specificities of 0.625, 0.500, and 0.500. No-EB ComBat changed median AUC by -0.007, -0.007, and -0.014, respectively, versus strict transfer. U-NEXtractor prediction ranking was most stable (median Spearman {rho}, 0.999), whereas fusion did not improve transportability. Empirical-Bayes ComBat lacked complete repeated-split coverage.
ConclusionStrong internal performance did not establish transportability. Limited target-site threshold adaptation recovered operating sensitivity without improving discrimination; feature harmonization produced no consistent AUC gain and affected representations differently.
Related
- Association of HER2, p53, and lymphovascular space invasion with lymph node metastasis in endometrial cancer: a retrospective cohort study
- Is the Benefit of High-Potency Progestins for Endometrial Hyperplasia Specific to Diminished Ovarian Reserve? [Letter]
- Reclassifying No Specific Molecular Profile Endometrial Cancer: A Narrative Review of Molecular Heterogeneity, Prognostic Refinement, and Clinical Management
- The Characteristics of Tumor Microenvironment by the Single Cell Profile in Endometrial Cancer of no Specific Molecular Profile (NSMP) Subtype.
- 396 Slit2–Robo1/2 signaling orchestrates a lymphovascular–myeloid axis that limits T cell priming and drives immunotherapy resistance
BibTeX
@misc{giovanni2026limitedsite,
title = {{Limited-site adaptation reveals representation-specific MRI transportability for lymphovascular invasion in endometrial cancer}},
author = {D. A. Di Giovanni and A. Takada and T. Horikoshi and T. Tsuboyama and H. Yokota and R. Zakarian and Y. Matsumoto and M. Vallieres and C. Reinhold},
howpublished = {medRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.14.26358100},
url = {https://www.medrxiv.org/content/10.64898/2026.07.14.26358100v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Limited-site adaptation reveals representation-specific MRI transportability for lymphovascular invasion in endometrial cancer
AU - D. A. Di Giovanni
AU - A. Takada
AU - T. Horikoshi
AU - T. Tsuboyama
AU - H. Yokota
AU - R. Zakarian
AU - Y. Matsumoto
AU - M. Vallieres
AU - C. Reinhold
PY - 2026
DA - 2026/07/14
PB - medRxiv
DO - 10.64898/2026.07.14.26358100
UR - https://www.medrxiv.org/content/10.64898/2026.07.14.26358100v2
AB - ObjectivesTo determine how clinically anchored MRI representations behave from supportive internal testing through locked institutional transfer and limited target-site adaptation for prediction of substantial lymphovascular space invasion (LVSI) in endometrial cancer. Materials and MethodsThis retrospective two-center study included 206 women undergoing preoperative 3-T MRI between March 2016 and March 2023. Hospital A provided training (n = 117) and supportive internal testing (n = 13); Hospital B provided strict external testing (n = 76; 12 positive). Age and CA125 formed the clinical baseline and were included in every imaging model. In 200 repeated stratified two-fold Hospital B splits, each patient was evaluated outside the adaptation half. Models remained locked; adaptation changed only the threshold or applied no-empirical-Bayes (no-EB) ComBat before threshold selection. ResultsDenseNet121, U-NEXtractor, and fusion U-NEXtractor achieved internal AUC 1.000 but strict external AUCs of 0.685, 0.671, and 0.669, respectively. At development-locked thresholds, sensitivities were 0.167, 0.583, and 0.417. Threshold adaptation increased median sensitivity to 0.833 for all three, with specificities of 0.625, 0.500, and 0.500. No-EB ComBat changed median AUC by -0.007, -0.007, and -0.014, respectively, versus strict transfer. U-NEXtractor prediction ranking was most stable (median Spearman {rho}, 0.999), whereas fusion did not improve transportability. Empirical-Bayes ComBat lacked complete repeated-split coverage. ConclusionStrong internal performance did not establish transportability. Limited target-site threshold adaptation recovered operating sensitivity without improving discrimination; feature harmonization produced no consistent AUC gain and affected representations differently.
ER -