SUMMARY
The research of Imon Banerjee, Ph.D., pertains to computer science, particularly artificial intelligence (AI) and data mining. Her studies show implicit bias in the AI model toward race across multiple imaging modalities. Dr. Banerjee's goal is to decrease AI-driven healthcare disparities. She reduces this tendency by using model unlearning and adversarial debiasing. These techniques decrease inaccurate, harmful and outdated information learned by the AI models.
She collaborates with institutions and centers that serve minority groups, such as Emory University in Atlanta and the Mountain Park Health Center in Arizona, to train and evaluate the AI models with diverse datasets.
In addition to AI disparity, Dr. Banerjee's research is focused on developing novel techniques for fusion of multisource medical data. Data such as images, tabular content and clinic notes from hospital systems are used to build AI models to benefit diagnosis and treatment. Dr. Banerjee collaborates with faculties from oncology, cardiology, pathology, neurology and radiology to develop multimodal AI solutions to support clinical diagnosis and prognosis.
She collaborates with multiple faculties at Arizona State University via the Mayo Clinic and Arizona State University Alliance for Health Care. Dr. Banerjee has more than 120 peer-reviewed publications in scientific journals and presents at conferences. Her h-index, which shows how many times other authors have cited her publications, is 26. Dr. Banerjee is a primary supervisor of three postdocs, six Ph.D. students and four M.S. students. She is currently leading four National Institutes of Health-funded projects as multiple principal investigator and two Mayo Clinic-funded projects.
Focus areas
- Multimodal fusion of imaging and nonimaging data for clinical diagnosis and prognosis.
- Natural language processing to support data curation for state and national cancer registry.
- "Fair" AI model development using computational debiasing.
Significance to patient care
The computational development toward the AI effort provides opportunities to reduce human bias and error in providing a second opinion for the healthcare team. This significantly improves the efficiency of patient care and allows the healthcare team to focus more on the individuals.
Professional highlights
- Member, Radiology Informatics Committee, Radiological Society of North America, 2023-present.
- Alternate chair, Special Emphasis Panel, National Cancer Institute, 2022,2023.
- Course director, Advanced Imaging AI Course, Radiological Society of North America, 2023.
- Member, Clinical Informatics and Digital Health Study Section, National Institutes of Health, 2023.
- Member, Imaging Guided Interventions and Surgery Study Section, National Institutes of Health, 2023.
- Member, Informatics Technology for Cancer Research Study Section, National Institutes of Health, 2023.
- Associate editor, Nature Scientific Report, 2022.
- Member, Graduate Admissions Committee, Computer Science Program, Arizona State University, 2022.
- Section editor, The Public Library of Science, Digital Health, 2021.