Disclaimer statement: The information and resources contained within this document are for educational purposes only. Please make sure to discuss any resources with the Here for the Girls Team. This information should not be used for self-diagnosis or treatment. This information should not be used in lieu of care from a licensed physician or mental health practitioner. Although the content of the resources has been reviewed by the Here for the Girls Team, you should use caution whenever accessing or referring to information from outside sources, including the Internet.
How AI is Being Integrated into Breast Cancer Services
The University of North Carolina at Chapel Hill School of Medicine (2023) is taking steps to include artificial intelligence (AI) in detecting cancerous tissue. AI in medicine has developed slowly over the years due to limitations, public opinion, and insufficient funding. However, in 1976 Rutgers University developed an AI prototype that “was the development of a consultation program for glaucoma using the CASNET model.” (Kaul et al., 2020). The CASNET model was used for patient management, such as having a knowledge base of diseases and providing the physician with recommendations. In 2017, the U.S. Food and Drug Administration created a Deep Learning (DL) system named CardioAI that “was able to analyze cardiac magnetic resonance images in a matter of seconds, providing information such as cardiac ejection fraction.” (Kaul et al., 2020). The primary purpose was to support physicians in diagnosing patients at a much faster rate. The University of North Carolina at Chapel Hill School of Medicine is utilizing similar measures when assessing tumors for cancerous cells that have been removed surgically. During surgery when a tumor is removed, the tumor is “photographed using a mammography machine and reviewed by the team to make sure the area of abnormality was removed.” (2023) The process of assessing the tumor can take up to a week which delays results and patients obtaining the information more quickly. However, the AI model was created in hopes of making the results instantaneous. The AI model has been taught from previous photographs of tumors to predict the margins and compare those results to those that a surgeon has identified. It was reported, that “researchers compared that data to the typical accuracy of human interpretation and discovered that the AI model performed as well as humans, if not better.” (2023) Additionally, the AI model can help provide support in reporting margins for women who have denser breasts. The new model is still in the early phases of being educated on tumor photographs and detecting margins, but researchers share hopes it will be helpful in the future. Researchers emphasize that the new AI technology can act as a support resource for medical facilities that are limited to medical personnel (2023).
If you would like to read more about the AI model research, you can click here. If you have any questions, please reach out to support@hereforthegirls.org
References:
Kaul, V., Enslin, S. and Gross, S. A. (2020). History of artificial intelligence in medicine. Gastrointestinal Endoscopy, 92(4), 807-812. doi: https://doi.org/10.1016/j.gie.2020.06.040.
University of North Carolina at Chapel Hill School Medicine. (2023, September 25). Researchers develop ai model to improve tumor removal accuracy during breast cancer surgery. Medical Xpress. Retrieved from: https://medicalxpress.com/news/2023-09-ai-tumor-accuracy-breast-cancer.html