You are here

Article Text

Article menu
Download PDFPDF
Poster and E-Posters
03. Endometrial cancer
280 Radiomics based prediction of pathological and molecular features of endometrial cancer managed at an Irish tertiary referral centre
  1. Claudia Condon1,
  2. Helena Bartels2,3,
  3. Tony Geoghegan4,
  4. Ann Treacy5 and
  5. Donal Brennan1,3,6
  1. 1Department of Gynaecological Oncology, Mater Misericordiae University Hospital, Dublin, Ireland
  2. 2National Maternity Hospital, Dublin, Ireland
  3. 3UCD School of Medicine, Dublin, Ireland
  4. 4Department of Radiology, Mater Misericordiae University Hospital, Dublin, Ireland
  5. 5Department of Histopathology, Mater Misericordiae University Hospital, Dublin, Ireland
  6. 6University College Dublin Gynaecological Oncology Group (UCD-GOG), Mater Misericordiae University Hospital and St Vincent’s University Hospital, Dublin, Ireland

Abstract

Introduction/Background Endometrial cancer (EC) is the most common gynaecological malignancy in the developed world. Prognostic indicators for EC have recently been revised to include molecular features. Radiomics is the field of extracting quantitative image biomarkers from medical imaging. Radiomics has shown potential to provide imaging biomarkers to predict molecular features.

Methodology We performed retrospective analysis on a population treated for EC at a tertiary referral centre. T2-weighted MRI were manually segmented for the endometrial tumour. Feature extraction was performed using PyRadiomics, followed by feature filtering using correlation and Near-Zero Variance filtering. Multivariate logistic regression was performed to develop a model using the 10 most predictive radiomic features. Prediction performance was assessed using Area Under the Curve (AUC) of the receiver operating characteristic curve (ROC) and accuracy.

Results 71 patients were included. There were 55 (77%) cases of endometrioid cancer and 16 (23%) cases of non-endometrioid. The mean age was 64.5 years (SD 12.7 years) and the mean Body Mass Index was 34.8 kg/m2 (SD 10.7 kg/m2).The multivariate logistic regression model produced an AUC of 0.85 for lympho-vascular space invasion (LVSI), 0.7 for non-endometrioid histology, 0.62 for tumour grade, 0.64 for (Mismatch Repair (MMR) instability and 0.3 for p53 mutation. ROC curves and confusion matrixes of the logistic regression analysis are demonstrated in Figure 1.

Conclusion We developed a radiomics model that has equivocal performance to more complex models in predicting non-endometrioid histology and LVSI. Model performance for MMR instability and p53 mutation may be improved by a larger population. This study adds to the potential use of radiomics in EC. Further study is needed to standardise radiomic processing in EC and identify the most appropriate imaging sequences and predictive models to assess molecular features.

Disclosures No conflict of interest to disclose.

Abstract 280 Figure 1
Abstract 280 Figure 1

a. ROC curve for logistic regression model predicting non-endometriaid histology. b. Confusion matrix for testing model for non-endometrioid histology. c. ROC curve for logistic regression model predicting high grade pathology. d. Confusion matrix for testing model for high grade pathology. e. ROC curve for logistic regression model predicting LVSL f. Confusion matrix for testing model for LVSI. g. ROC curve for logistic regressian model predicting MMR instability.h. Confusion matrix for testing model for MMR instability. i. ROC curve for logistic regression model predicting p53 mutation. j. Confusion matrix for testing model for p63 mutation

https://doi.org/10.1136/ijgc-2024-ESGO.320

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.