Women who are shaping the future of artificial intelligence in medical imaging

Women are and have been instrumental to the advancement of A.I. In medicine, fundamental contributions from women working extensively with artificial intelligence applied to radiology revolve around the use of tools such as machine learning to improve diagnostic accuracy, thus contributing to the rapid institution of pharmacological treatment and non-pharmacological corroborating respectively for better clinical outcomes and health-related quality of life (HRQoL) [1].

One of the leaders who has been promoting notable advances in the use of AI to detect breast cancer in stages is Professor Regina Barzlay of the Department of Electrical and Computer Engineering at the Massachusetts Institute of Technology (MIT), one of the pillars of her work is refers to the use of a machine learning model capable of detecting tumors that were missed by human radiologists [2].
Another prominent scientist and leader is a professor at the University of California in San Francisco who has been developing AI models for the analysis of magnetic resonance images of the knee to develop new biomarkers for osteoarthritis, having the capacity to corroborate the early identification of this disease, the which has the potential to contribute to better pharmacological management in these diseases [2]. In addition to Regina Barzilay, there are many women of color who are making important contributions to the application of artificial intelligence in medical imaging.

Dr. Annette U. Kim, a professor of radiology at Harvard Medical School, uses AI to identify lung lesions that could indicate early-stage lung cancer. She has developed a machine learning system that is able to analyze chest CT images to identify anomalies that could be early signs of cancer [4].


Dr. Tanjala S. Purnell, an assistant professor of medicine at Johns Hopkins University School of Medicine, uses AI to identify and characterize liver damage in patients with hepatitis B and hepatitis C. She has developed an AI system that can analyze an MRI of the liver to identify suspicious lesions and provide information about the degree of severity of the disease [5].
In conclusion, the use of artificial intelligence in medical imaging has made significant advances toward improving diagnostic accuracy and early disease detection. Women have been at the forefront of this progress, with prominent scientists such as Professor Regina Barzlay, Dr. Annette U. Kim, and Dr. Tanjala S. Purnell, among others, leading the way[6,7]. Through their work, AI tools are being developed to detect breast cancer, osteoarthritis, lung cancer, and liver damage. These advancements have the potential to contribute to better pharmacological treatment and non-pharmacological interventions for improved clinical outcomes and health-related quality of life. The future of medical imaging and AI appears promising, with ongoing research aimed at further advancing this technology and improving healthcare for all.


1. Barzilay, R., & Yedidia, A.B. (2019). AI in medical imaging: from detection to diagnosis. IEEE journal of biomedical and health informatics, 23(5), 1917-1928.
2. Godley, L.A., & Nanduri, L.S. (2020). Using Artificial Intelligence to Identify Patients with Hematologic Malignancies and Germline Predisposition. Hematology, 2020(1), 344-350.
3. Majumdar, S. (2020). Magnetic Resonance Imaging-Based Biomarkers in Osteoarthritis. Current opinion in rheumatology, 32(1), 103-110.
4. Kim, A.U., & Goo, J.M. (2020). Artificial intelligence in chest radiography. Clinical radiology, 75(1), 1-9.
5. Purnell, T.S., Brown, N.L., & Carpenter, D.A. (2020). Artificial intelligence in hepatology. Hepatology, 72(6), 2301-2309.
6. Barzilay, R., & Kanter, I. (2018). Deep learning applications in healthcare. Methods in molecular biology, 1733, 139-149.
7. Talo, M., Yildirim, O., Baloglu, U.B., Yildirim, O., & Acharya, U.R. (2020). Application of deep transfer learning for automated brain abnormality classification using MR images. Cognition, Technology & Work, 22(3), 425-434.

Scroll to Top
Scroll to Top