Endometrial hyperplasia is a condition defined by abnormal proliferation of glands in the lining of the uterus. Endometrial hyperplasia without atypia is unlikely to progress whereas endometrial atypical hyperplasia has a high-risk of progression to cancer. Current classification schemes have poor reproducibility, which limits their prognostic capability.
In this work package we aim to develop an automated and objective machine-learning based tool for prognostic assessment of endometrial hyperplasia, to reduce risk of over- and under-treatment of patients.
Aim 1: Develop an automated tool for measurement of prognostic features
The figure above shows the APP workflow for risk classification of endometrial hyperplasia. A) Detection of endometrial tissue B) Labelling of endometrial structures including epithelial glands (green), lumen (yellow) and surrounding stroma (blue) C) Heatmap to identify the most dense region of glands D) Labelling of gland nuclei.
Aim 2: Develop a model for risk classification of endometrial hyperplasia lesions

Aim 3: Validate and test the tool and model on a large patient cohort
Aim 4: Implement the tool and model into the diagnostic workflow