HKUST Launches Large AI Model 'MOME' for Testing in Over Ten Hospitals, Revolutionizing Breast Cancer Diagnosis

A research team led by Prof. Hao CHEN, Assistant Professor of the Department of Computer Science and Engineering, Department of Chemical and Biological Engineering, and Division of Life Science at HKUST, has developed a large AI model named Mixture of Modality Experts (MOME) for non-invasive breast cancer diagnosis. 
 
Trained on China's largest multiparametric MRI dataset, MOME achieves expert-level accuracy in classifying tumor malignancy, comparable to experienced radiologists. It is currently undergoing clinical validation in over ten hospitals. MOME effectively integrates diverse imaging modalities, supports molecular subtyping, and predicts treatment responses, potentially reducing unnecessary biopsies and enhancing treatment predictions. Prof. Chen highlighted MOME's adaptability and interpretability, emphasizing its potential to transform medical imaging and improve patient outcomes. 
 
The study, titled "A Large Model for Non-Invasive and Personalized Management of Breast Cancer from Multiparametric MRI", was jointly conducted by HKUST’s Smart Lab, Harvard University, Shenzhen People’s Hospital, PLA General Hospital, and Yunnan Cancer Center. It was recently published in Nature Communications.
 
For more information, please refer to: HKUST Launches Large AI Model “MOME” for Testing in Over Ten Hospitals | HKUST School of Engineering