A single-cell transcriptomic analysis of endometriosis, endometriomas, eutopic endometrial samples and uninvolved ovary tissues highlights cell populations characteristic of these tissue types. Transcriptional and cellular heterogeneity across tissues suggests novel therapeutic targets and biomarkers for this disease.

Clinical oncology tumor board decision support system made by the Decider project.

Two or three subtypes of high grade serous ovarian cancer subtypes fit data from different populations better than four

Comprehensively and confidently navigating Endometriosis and Adenomyosis and their comorbidities. #MaintainerMonth

🧠Deep Learning-based✔️ Ovarian Cancer🙅🏻‍♀️ Subtypes Identification using Multi-Omics Data✅

Analysis of treatment naive and neo-adjuvant chemotherapy treated high-grade serous ovarian cancer samples

Tumor subclonality of expression-based cancer subtypes

[EMBC 2022] Multi-agent Feature Selection for Integrative Multi-omics Analysis

Implements four major subtype classifiers for high-grade serous (HGS) ovarian cancer.

MSDS Thesis - Pan-Collagen Survival Analysis of CNV in Ovarian Cancer

Quantitatively evaluate tumor stroma reaction within ovarian cancers, and establish assocaitaions to prognosis, molecular signatures.

Solution (Top 6) for 3D segmentation of ovarian cancer with peritoneal carcinosis using CT scans.

Proteomics and IHC data analysis for LGSC and SBT tumour microenvironment study.

Research implementation on supporting medical diagnosis under incomplete data.

An AI-based decision support system for ovarian cancer diagnosis, based on our research leveraging ML and Explainable AI. The system predicts cancer risk and explains decisions to aid healthcare professionals.

A full-stack ML-powered web application for early risk prediction of Ovarian Cancer, PCOS, and Hepatitis B, enabling data-driven clinical decision support.

Medical Image Classification: Benign vs. Malignant Ovarian Cysts Using Transfer Learning in CNNs

Machine Learning model for predicting ovarian tumor malignancy (benign vs malignant) using clinical biomarkers. Achieves 94% accuracy with Random Forest.