Information

Related Research Units

Translational Research Program Research
Fetal Neonatal Neuroimaging and Developmental Science Center Research
General Pediatrics Research
Genetics and Genomics Research
Newborn Medicine Research
Radiology Research

Research Overview

Dr. Mohammad Hussain is an AI and medical imaging researcher whose work focuses on developing advanced machine learning and deep learning methods to improve disease characterization, prognosis, and individualized outcome prediction. His research integrates multimodal neuroimaging, clinical, and genomic data to better understand brain development and neurocognitive outcomes, particularly in children and adults with congenital heart disease (CHD). Over the course of his career, he has developed innovative AI approaches for medical image analysis, including segmentation-free organ volume estimation, cancer grading and staging, radiogenomic prediction, active learning for medical imaging, and neurocognitive outcome modeling.

At Boston Children’s Hospital and Harvard Medical School, Dr. Hussain leads research aimed at predicting long-term neurodevelopmental and cognitive outcomes using multimodal data collected across the lifespan. His current work combines structural and functional brain MRI, clinical information, and genomic features to develop explainable and clinically meaningful AI models that support precision medicine. A central goal of his research program is to bridge artificial intelligence, neuroimaging, and translational medicine to enable earlier identification of individuals at risk for adverse neurodevelopmental outcomes and to facilitate personalized interventions that improve lifelong health and cognitive trajectories.

Research Background

Dr. Mohammad Hussain is an Instructor in Pediatrics at Boston Children’s Hospital and Harvard Medical School. He received his Ph.D. and M.Sc. degrees in Biomedical Engineering from the University of British Columbia, Canada, following B.Sc. and M.Sc. degrees in Electrical and Electronic Engineering from Bangladesh University of Engineering and Technology (BUET). He completed postdoctoral training at Simon Fraser University and Boston Children’s Hospital, specializing in artificial intelligence, machine learning, and medical image analysis.

Dr. Hussain’s research spans artificial intelligence, neuroimaging, medical image computing, and precision medicine. He has authored more than 25 peer-reviewed publications, with the majority as first author. He has served as Principal Investigator on multiple competitively funded projects, including fellowships from the American Heart Association and NHLBI-supported programs. His contributions include the development of AI methods for cancer characterization, organ analysis, active learning, and neurocognitive outcome prediction. His work has been recognized through international awards, including honors from the Medical Image Computing and Computer Assisted Intervention (MICCAI) community and Boston Children’s Hospital. In addition to his research activities, Dr. Hussain serves as a reviewer and editor for numerous leading journals in artificial intelligence, medical imaging, and biomedical engineering, contributing to the advancement of the field through both scholarship and scientific service.

Publications

  1. Machine learning to infer neurocognitive testing scores among adolescents and young adults with congenital heart disease. Commun Med (Lond). 2026 Feb 06; 6(1). View Abstract
  2. Transcatheter Left Ventricular Restoration in Ischemic Heart Failure and Dilated Cardiomyopathy. Catheter Cardiovasc Interv. 2026 Mar; 107(4):898-908. View Abstract
  3. Inferring neurocognition using artificial intelligence on brain MRIs. Front Neuroimaging. 2024; 3:1455436. View Abstract
  4. Deep learning of structural MRI predicts fluid, crystallized, and general intelligence. Sci Rep. 2024 11 14; 14(1):27935. View Abstract
  5. RCT: Relational Connectivity Transformer for Enhanced Prediction of Absolute and Residual Intelligence. International Workshop on PRedictive Intelligence In MEdicine. 2024; 35-47. View Abstract
  6. Patient's airway monitoring during cardiopulmonary resuscitation using deep networks. Med Eng Phys. 2024 07; 129:104179. View Abstract
  7. LAIU-Net: A Learning-to-Augment-incorporated Robust U-Net for Depressed Humans’ Tongue Segmentation. Displays. 2023; 102371. View Abstract
  8. Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT. Comput Med Imaging Graph. 2022 12; 102:102127. View Abstract
  9. Learning-to-augment incorporated noise-robust deep CNN for detection of COVID-19 in noisy X-ray images. J Comput Sci. 2022 Sep; 63:101763. View Abstract
  10. Effects of electrically conductive nano-biomaterials on regulating cardiomyocyte behavior for cardiac repair and regeneration. Acta Biomater. 2022 02; 139:141-156. View Abstract
  11. Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of COVID-19 in X-ray images. Comput Biol Med. 2021 09; 136:104704. View Abstract
  12. Cascaded Regression Neural Nets for Kidney Localization and Segmentation-free Volume Estimation. IEEE Trans Med Imaging. 2021 06; 40(6):1555-1567. View Abstract
  13. Learnable image histograms-based deep radiomics for renal cell carcinoma grading and staging. Comput Med Imaging Graph. 2021 06; 90:101924. View Abstract
  14. Light-controlled growth factors release on tetrapodal ZnO-incorporated 3D-printed hydrogels for developing smart wound scaffold. Adv Funct Mater. 2021 May 26; 31(22). View Abstract

Contact Mohammad Arafat Hussain

Print Profile