Md Mehedi Hassan is a Ph.D. researcher in STEM (Computer and Information Science) at the University of South Australia, engaged in a fully funded research project focused on the diagnosis of liver diseases using abdominal CT imaging and deep learning. His research integrates computer science, data science, and clinical knowledge to develop advanced artificial intelligence frameworks for medical image analysis, based on real-world industry datasets.
He holds both a Master of Science and a Bachelor of Science in Computer Science and Engineering, and has published in leading journals such as Engineering Applications of Artificial Intelligence, Scientific Reports (Nature), IEEE Access and others. He serves as a peer reviewer for several... Read more
About me
Md Mehedi Hassan is a Ph.D. researcher in STEM (Computer and Information Science) at the University of South Australia, engaged in a fully funded research project focused on the diagnosis of liver diseases using abdominal CT imaging and deep learning. His research integrates computer science, data science, and clinical knowledge to develop advanced artificial intelligence frameworks for medical image analysis, based on real-world industry datasets.
He holds both a Master of Science and a Bachelor of Science in Computer Science and Engineering, and has published in leading journals such as Engineering Applications of Artificial Intelligence, Scientific Reports (Nature), IEEE Access and others. He serves as a peer reviewer for several high-impact Q1 journals and has edited five academic books in the domains of federated learning, brain network analysis, graph neural networks (GNNs), and digital health, published by Springer, CRC Press, and River Press (IEEE).
In addition to his academic work, Mehedi Hassan served as Chief Executive Officer of The Virtual BD from 2018 to 2025 and Chief Advisor at TownDevs, both IT companies focused on innovative software solutions and digital transformation.
About me
I am a Ph.D. candidate at the University of South Australia, developing HU-aware 3D-CNNs for real-time liver disease classification using abdominal CT scans. My research integrates liver segmentation, HU-based voxel encoding, residual learning, and radiomic features, with multimodal fusion of CT data and radiology reports to improve disease staging. The models are designed for clinical interpretability using Grad-CAM, SHAP, and HU attribution, and are validated on real-time, industry-acquired data from radiology partners in Adelaide.
Research
Hassan, Md Mehedi, Anindya Nag, Riya Biswas, Md Shahin Ali, Sadika Zaman, Anupam Kumar Bairagi, and Chetna Kaushal. "Explainable artificial intelligence for natural language processing: A survey." Data & Knowledge Engineering 160 (2025): 102470.
Hassan, Md Mehedi, Sadika Zaman, Md Mushfiqur Rahman, Anupam Kumar Bairagi, Walid El-Shafai, Rajkumar Singh Rathore, and Deepak Gupta. "Efficient prediction of coronary artery disease using machine learning algorithms with feature selection techniques." Computers and Electrical Engineering 115 (2024): 109130.
Haque, Rezuana, Md Mehedi Hassan, Anupam Kumar Bairagi, and Sheikh Mohammed Shariful Islam. "NeuroNet19: an explainable deep neural network model for the classification of brain tumors using magnetic resonance imaging data." Scientific reports 14, no. 1 (2024): 1524.
Islam, Md Tanvir, Safkat Shahrier Swapnil, Md Masum Billal, Asif Karim, Niusha Shafiabady, and Md Mehedi Hassan. "Resource constraint crop damage classification using depth channel shuffling." Engineering Applications of Artificial Intelligence 144 (2025): 110117.
Kaur, Amandeep, Chetna Kaushal, Md Mehedi Hassan, and Si Thu Aung, eds. "Federated Deep Learning for Healthcare: A Practical Guide with Challenges and Opportunities." (2024). [Book]
Hassan, Md Mehedi, Rezuana Haque, Sheikh Mohammed Shariful Islam, Hossam Meshref, Roobaea Alroobaea, Mehedi Masud, and Anupam Kumar Bairagi. "NeuroWave-Net: Enhancing epileptic seizure detection from EEG brain signals via advanced convolutional and long short-term memory networks." AIMS Bioengineering 11, no. 1 (2024).
Research
I am a Ph.D. candidate at the University of South Australia, developing HU-aware 3D-CNNs for real-time liver disease classification using abdominal CT scans. My research integrates liver segmentation, HU-based voxel encoding, residual learning, and radiomic features, with multimodal fusion of CT data and radiology reports to improve disease staging. The models are designed for clinical interpretability using Grad-CAM, SHAP, and HU attribution, and are validated on real-time, industry-acquired data from radiology partners in Adelaide.
Teaching & student supervision