M. Abbas

Building AI systems
that advance cancer care.

Research Fellow in Computational Pathology & AI at Mayo Clinic, developing deep learning methods for gigapixel-scale pathology image analysis and multi-modal cancer diagnostics & prognostics.

PhD from LaTIM, INSERM UMR1101 (Université de Bretagne Occidentale), focused on AI-driven therapeutic monitoring of colorectal cancer liver metastases — from organ and lesion segmentation to treatment response assessment. Collaboration with the French Federation of Digestive Oncology (FFCD).

2025 —

Research Fellow — Computational Pathology & AI

Mayo Clinic, Rochester, MN

2022 — 2025

PhD — Medical Image Analysis

LaTIM, INSERM UMR1101 · Université de Bretagne Occidentale

2022

R&D Intern — AI for Medical Imaging

Dassault Systèmes

2021

Research Intern — Digital Pathology & AI

LIRMM (CNRS), Montpellier

2019 — 2022

MEng — Electrical & Electronics Engineering

ENSEA · Exchange at NTNU, Norway

Focus areas

Computational Pathology

AI for gigapixel whole-slide image analysis. Multi-modal integration with clinical, molecular, and imaging data for precision oncology.

Tumor Segmentation

Instance-aware deep learning for detection and segmentation of colorectal cancer liver metastases in CT. Transfer learning across clinical datasets.

Surgical Planning AI

Automated liver resection planning — predicting future liver remnant from anatomical and pathological segmentation masks.

Cross-Domain Transfer

Cross-dimensional knowledge transfer and multi-modal fusion for robust model deployment across institutions and imaging protocols.

Clinical Trials

FFCD

PRODIGE 9 & 20

AI imaging criteria for treatment response. Organ atrophy as predictive factor.

T2004

Liver Metastases Monitoring

Automatic liver and lesion segmentation for metastatic colorectal cancer patients.

T2301

BEVATROPHY

Multi-organ segmentation models for body composition in clinical trials.

Selected work

All publications on Google Scholar