Automated segmentation of pretreatment computed tomography for evaluating intersite radiomic heterogeneity…

AI / informaticsEuropean journal of obstetrics, gynecology, and reproductive biology· Jul 2026

Automated segmentation of pretreatment computed tomography for evaluating intersite radiomic heterogeneity between platinum-resistant and platinum-sensitive ovarian cancer cohorts: a proof of concept study.

Albert Jacob, K T Harichandrakumar, V C Sunitha … P Veena

Medical Imaging AIAI / informaticsPrognosis

Computed tomography model modestly distinguished platinum-resistant from platinum-sensitive high-grade serous ovarian cancer

Automated segmentation of pretreatment computed tomography for evaluating intersite radiomic heterogeneity between platinum-resistant and platinum-sensitive ovarian cancer cohorts: a proof of concept study.

Albert Jacob … P Veena

European journal of obstetrics, gynecology, and reproductive biology · Jul 2026

Purpose

To evaluate the feasibility of utilizing automated segmentation of pretreatment contrast-enhanced computed tomography (contrast-enhanced computed tomography) images to characterize and evaluate intersite radiomic heterogeneity between platinum-resistant and platinum-sensitive cohorts in high-grade serous ovarian cancer.

Methods

Pretreatment CECTs of 114 High Grade Serous Ovarian Cancer patients diagnosed from January 2016 till January 2023 were formatted with the dcm2niix tool.

n = 114 High Grade Serous Ovarian

Results

model separated the two groups only modestly, better than a coin flip but far from reliable

AUC 0.67 (95% CI 0.59 to 0.74)

null 0

0.59

0.74

CI excludes the null - significant

More results

Surface area-volume ratios of omental disease, pelvic disease and supradiaphragmatic lymph nodes were found to differ significantly between the groups.

Nine models satisfied the selection criteria.

The best model used Catboost and surface area-volume ratio of omental disease and pelvic disease.

“

Conclusion

Automated segmentation of pretreatment contrast-enhanced computed tomography images in high-grade serous ovarian cancer is feasible with ovseg and enables the automated extraction of multi-site imaging features that reflect distinct structural variations between treatment-response cohorts, demonstrating modest capabilities for retrospective cohort classification.

Automated segmentation of pretreatment computed tomography for evaluating intersite radiomic heterogeneity between platinum-resistant and platinum-sensitive ovarian cancer cohorts: a proof of concept study.

Automated segmentation of pretreatment computed tomography for evaluating intersite radiomic heterogeneity between platinum-resistant and platinum-sensitive ovarian cancer cohorts: a proof of concept study.

Related papers