Deep Learning for Histopathological Classification and Prognostication of Gynaecologic Smooth Muscle Tumours
Trial Snapshot
- Phase
- Not Applicable
- Status
- Recruiting
- Sponsor
- Institut Bergonié
- Enrollment
- 392
- Locations
- 1
- Primary Endpoint
- Develop deep learning models that can accurately subclassify gynaecologic smooth muscle tumours
Study Overview
Brief Summary
Smooth muscle tumors of the uterus that do not fit the diagnostic criteria of benignity (such as leiomyomas) or malignancy (such as leiomyosarcomas) are called STUMP (smooth muscle tumor of uncertain malignant potential). A potential solution to this problem could be the application of predictive models using artificial intelligence (AI) to aid in the histopathological classification and prognosis of gynecological smooth muscle tumors. Deep learning using convolutional neural networks represents a specific class of machine learning, in which predictive models are trained by considering small groups of pixels in digital images and iteratively identifying salient features. In this study, we aim to develop deep learning models capable of accurately subclassifying and predicting the prognosis of gynecological smooth muscle tumors, based on histopathological features of hematoxylin and eosin (H&E) slides. The aim is to develop a diagnostic and prognostic algorithm to help pathologists better classify and diagnose uterine smooth muscle tumors and predict their clinical course.
Study Design
- Study Type
- Observational
- Observational Model
- Cohort
- Time Perspective
- Retrospective
Eligibility Criteria
- Sex
- Female
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Patients with a diagnosis of uterine smooth muscle tumors (leiomyomas, smooth muscle tumors of uncertain malignancy and leiomyosarcomas), registered in the RRePS database and/or treated at Institut Bergonié or one of the participating centers.
- •Histopathological material available (kerosene blocks and/or slides).
- •The follow-up (outcome) is required for each LMS/ STUMP.
Exclusion Criteria
- Not provided
Outcomes
Primary Outcomes
Develop deep learning models that can accurately subclassify gynaecologic smooth muscle tumours
Time Frame: throughout the conduct of the study - an expected average of 6 months after data collection
This project aims to improve the diagnosis and prognosis of gynecologic smooth muscle tumors, including leiomyomas (LM), leiomyosarcomas (LMS), and smooth muscle tumors of uncertain malignant potential (STUMP). In detail, a workflow comprising 2 stages will be developed to automatically classify GSMT subtypes from whole-slide images and to predict progression-free survival for patients in the LMS and STUMP groups, thereby providing clinicians with a more effective tool to improve workflow quality.
Secondary Outcomes
- Develop a prognostic tool for STUMP(6 months after receiving the data.)