Multi-scale radiomics in pelvic MRI for endometriosis subtyping: highlighting data heterogeneity constraints

preprint OA: green CC0
⚙ AI-generated summary by gemini-2.5-flash-lite, 2026-08-01 ⓘ

This study developed and evaluated a multi-scale radiomics pipeline for endometriosis subtyping from pelvic MRIs, finding preliminary subtype signals but highlighting data heterogeneity and small cohort size as significant constraints.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

⚙ AI-generated deep summary by qwen3.7-flash, 2026-09-09 · read from full text ⓘ

This study evaluates a radiomics-based pipeline for subtyping endometriosis using pelvic MRI data from the UT-EndoMRI dataset. Researchers extracted features from segmented uterine and ovarian regions to train supervised classifiers that distinguish patients with endometriomas from those without, achieving an AUC of 0.80 with Wavelet-derived features and Gradient Boosting. However, the model exhibited low specificity due to false positives, and ComBat harmonization failed to consistently improve performance in this small, multi-site cohort. Unsupervised clustering revealed reproducible but poorly separated patient partitions that remained associated with acquisition variables, highlighting the fragility of such models in heterogeneous datasets. This paper is centrally about endometriosis — specifically focusing on the challenges of data heterogeneity in MRI radiomics for subtyping deep infiltrating lesions and endometriomas.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

Analyzing female pelvic MRIs is challenging, especially for evaluating endometriosis, where visual features are influenced by several factors, including anatomical complexity, technical variability, and inter-reader variability. Here, we evaluate a radiomics-based pipeline for patient-level endometriosis subtyping using the publicly available UT-EndoMRI dataset. We extract radiomics features from manually segmented uterine and ovarian regions and compare several multi-scale feature representations and feature-selection strategies. We train supervised classifiers to distinguish patients with at least one endometrioma from those without, and perform an unsupervised perturbation analysis to assess whether radiomics profiles reveal reproducible patient subgroups. The best supervised performance is achieved using raw Wavelet-derived features and a Gradient Boosting classifier, yielding an AUC of 0.80. However, this model produces several false positives, resulting in low specificity. ComBat harmonization does not consistently improve performance, suggesting that post hoc harmonization is insufficient in a small, multi-site cohort in which acquisition groups contained very few patients. Using an unsupervised clustering analysis, we identify reproducible but poorly separated partitions that remain associated with acquisition variables. Overall, these results suggest that pelvic MRI radiomics contain a preliminary signal for endometriosis subtyping, while highlighting the fragility of radiomics-based subtyping in small, multi-site datasets.
Full text 3,035 characters · extracted from oa-html · click to expand
Electrical Engineering and Systems Science > Image and Video Processing [Submitted on 29 Jul 2026] Title:Multi-scale radiomics in pelvic MRI for endometriosis subtyping: highlighting data heterogeneity constraints View PDFAbstract:Analyzing female pelvic MRIs is challenging, especially for evaluating endometriosis, where visual features are influenced by several factors, including anatomical complexity, technical variability, and inter-reader variability. Here, we evaluate a radiomics-based pipeline for patient-level endometriosis subtyping using the publicly available UT-EndoMRI dataset. We extract radiomics features from manually segmented uterine and ovarian regions and compare several multi-scale feature representations and feature-selection strategies. We train supervised classifiers to distinguish patients with at least one endometrioma from those without, and perform an unsupervised perturbation analysis to assess whether radiomics profiles reveal reproducible patient subgroups. The best supervised performance is achieved using raw Wavelet-derived features and a Gradient Boosting classifier, yielding an AUC of 0.80. However, this model produces several false positives, resulting in low specificity. ComBat harmonization does not consistently improve performance, suggesting that post hoc harmonization is insufficient in a small, multi-site cohort in which acquisition groups contained very few patients. Using an unsupervised clustering analysis, we identify reproducible but poorly separated partitions that remain associated with acquisition variables. Overall, these results suggest that pelvic MRI radiomics contain a preliminary signal for endometriosis subtyping, while highlighting the fragility of radiomics-based subtyping in small, multi-site datasets. Submission history From: Elodie Germani [view email] [via CCSD proxy][v1] Wed, 29 Jul 2026 09:39:38 UTC (1,432 KB) References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer (What is the Explorer?) Connected Papers (What is Connected Papers?) Litmaps (What is Litmaps?) scite Smart Citations (What are Smart Citations?) Code, Data and Media Associated with this Article alphaXiv (What is alphaXiv?) CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub (What is DagsHub?) Gotit.pub (What is GotitPub?) Hugging Face (What is Huggingface?) ScienceCast (What is ScienceCast?) Demos Recommenders and Search Tools Influence Flower (What are Influence Flowers?) CORE Recommender (What is CORE?) arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

⚙ Ask this paper AI returns verbatim quotes from the full text · source: oa-html ⓘ

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

openalex
last seen: 2026-09-24T06:01:16.130947+00:00
License: CC0 · commercial use OK