Related Experiment Video
Updated: Jul 31, 2025
10:58
Quantitation of Intra-peritoneal Ovarian Cancer Metastasis
Published on: July 18, 2016
11.0K
Associating Peritoneal Metastasis With T2-Weighted MRI Images in Epithelial Ovarian Cancer Using Deep Learning and
Mingxiang Wei1, Yu Zhang2, Cong Ding3
1Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Gusu School, Nanjing Medical University, Suzhou, Jiangsu, China.
Journal of Magnetic Resonance Imaging : JMRI
|May 3, 2023
Summary
Deep learning and radiomics on T2W MRI can help detect peritoneal metastasis in epithelial ovarian cancer. These AI tools improved radiologist sensitivity, aiding clinical decisions for EOC patients.
Area of Science:
- Radiology
- Oncology
- Artificial Intelligence
Background:
- Preoperative diagnosis of peritoneal metastasis (PM) in epithelial ovarian cancer (EOC) is challenging.
- Accurate diagnosis impacts clinical decision-making for EOC patients.
Purpose of the Study:
- To evaluate T2-weighted (T2W) MRI-based deep learning (DL) and radiomics for PM detection in EOC.
- To compare the performance of DL, radiomics, and clinical models, including an ensemble model.
Main Methods:
- Retrospective study with 479 EOC patients across five centers.
- Developed DL, radiomics, and clinical models using T2W MRI data.
- An ensemble model combined these approaches; performance was assessed with ROC analysis.
Main Results:
- The ensemble model demonstrated superior performance (AUCs) compared to individual DL and clinical models in validation sets.
- Model assistance significantly improved radiologist sensitivity, particularly for less experienced readers.
- One resident also showed improved specificity with model assistance.
Conclusions:
- T2W MRI-based DL and radiomics show promise for preoperative PM prediction in EOC.
- These AI-driven methods can assist clinicians in decision-making for EOC management.
