ENDO_STAGE Magnetic Resonance Imaging: Classification to Screen Endometriosis
Bibliographic record
Abstract
Introduction: Transvaginal sonography is the first-line imaging technique to diagnose endometriosis, but magnetic resonance imaging is more accurate in staging the extent of lesions, especially for deep pelvic endometriosis. The revised American Society for Reproductive Medicine and Enzian classifications are commonly used to stage the extent of endometriosis. However, a review underlined their weaknesses in terms of complexity, lack of clinical reproducibility and low correlation with surgical complications and fertility outcomes. Thus, to this day, in clinical practice, there is a lack of consensual, standardized or common nomenclature to stage the extent of endometriosis, posing a worldwide challenge. Objectives: The aims of our study were to: (i) develop a new classification (entitled Endo-Stage MRI) based on patterns of endometriosis as observed with magnetic resonance imaging; (ii) compare results with those of the rASRM classification; (iii) estimate the Endo-Stage MRI accuracy to predict the rate of surgical complications; and (iv) propose an Endo-Stage MRI system of triage (low, intermediate, high) that correlates with the risk of surgical complications. The goal is to improve the effectiveness of care pathways and allow for the planning of a multidisciplinary approach when necessary. Patients and methods: A single-center observational study using available clinical and imaging data. According to anatomical locations and the extent of endometriotic lesions, a standardized classification comprising six stages of severity (0–5) was designed. Results: A total of 751 patients with pelvic endometriosis underwent surgery from January 2013 to December 2018 in a tertiary care university hospital. Their Endo-Stage MRI classification was correlated with: (i) the rate of overall complications (grade I–IV Clavien-Dindo classification, (ii) the rate of major complications (grades III–IV) and (iii) the rate of voiding dysfunction requiring self-catheterization lasting more than one month. According to the Endo-Stage MRI classification, stages 0, 1, 2, 3, 4 and 5 were observed in 26 (3%), 156 (21%), 40 (5%), 22 (3%), 290 (39%) and 217 (29%) patients, respectively. Using the proposed Endo-Stage MRI system as triage, low (stages 0–2), intermediate (stages 3–4) and high-risk (stage 5), complications were observed in 29 (13%), 109 (34.9%) and 103 (47.4%) patients, respectively. In multivariate analysis, the Endo-Stage MRI system of triage was strongly predictive of surgical complications and achieved higher accuracy than the revised American Society for Reproductive Medicine classification (AUC: 0.78 (95% CI, 0.76–0.80) vs. 0.61 (95% CI, 0.58–0.64)). Conclusion: Our study proposes a new imaging classification of endometriosis coined Endo-Stage MRI classification. The results suggest that when applied to a clinical situation, it may improve care pathways by providing crucial information for identifying intermediate and/or high-risk stages of endometriosis with increased rates of surgical complications. To make this classification applicable, a multicentric validation study is necessary to assess the relevancy and clinical value of the current anatomical MRI classification.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".