About 2.3 million women were diagnosed with breast cancer in 2020, resulting in 685,000 deaths globally. Breast cancer screening with mammography is considered effective in reducing breast cancer related mortality. However, due to the scarcity of experienced radiologists, almost 25% of detectable cancers are being missed. This can be overcome by using tools of artificial intelligence in breast cancer diagnosis and treatment.
Artificial intelligence (AI) is the use of mathematical algorithms that mimic human cognitive abilities and can help address difficult healthcare challenges including complex biological abnormalities such as cancer. All AI systems work by processing large volumes of specific, well-labelled “training data”, and analysing this data for patterns. It later uses these patterns to make predictions about future states of any system- even biological systems such as the human body.
Future of Breast Cancer Management
The future of both diagnosis and treatment of breast cancer will rely heavily on the medical guidance provided by AI systems. An enormous amount of radiology, genetics, and microbiology related data can be systematically collected and managed for personalized treatment with assistance of AI systems.
Connecting biology with AI can help oncologist to develop precise and proficient personalised treatments for patients with breast cancer. The implementation of AI systems in breast cancer management can improve diagnostic accuracy of breast cancer, accelerate the discovery of new drugs and improve conservation of breast tissue in robotic surgery.
Artificial Intelligence in Diagnosis of Breast Cancer
Without the use of radiology, especially in breast cancer, the healthcare system would be incomplete. However, the large number of women screened and the heavy work load can result in some cases of breast cancer being missed. It is important to minimize misses and interpretation errors of visible lesions at digital mammography, which contribute to delayed detection of cancers. AI-based systems extract all the visible and non-visible image features to generate more precise results that have high sensitivity rate in comparison to other conventional technologies.
Studies have shown that radiologists had improved diagnostic performance for detection of breast cancer at mammography when using an AI computer system for support. Moreover, this was done with no additional reading time, independent of the type of cancer lesion or quality of diagnostic image.
Role Of Artificial Intelligence In Precision Oncology
Recent advances in clinical oncology have involved AI-based novel molecular strategies. This includes in-depth analysis and characterisation of cancer genomic data that has led to rapidly evolving strategies in the field of precision oncology.
Precision oncology is the precise targeting and characterization of individual tumour cells and marker proteins. This can help in early cancer detection by identification of novel biomarkers and target sites, precise diagnosis, and identification of selective target sites. Moreover, this highly precise data can be used to design drugs that target specific cancer cells based upon their genetic variability and accelerate drug discovery.
Artificial Intelligence In Surgery
Through surveillance imaging, and real time video input AI, can support surgeons in decision making during surgery. Previously, high risk breast tissues would be surgically removed only to be revealed as benign after analysis of the biopsied specimens following the surgery. AI assistance can reduce the need for radical surgery by over 30%. Machine models can accurately predict high-risk cancer lesions via image-guided needle biopsies and can limit unnecessary surgical excisions.
Further, AI can help support the surgeon in making suitable clinical decisions through predictions based data analysis of the patient’s age, gender, and other biological parameters. This can improve accuracy of morbidity predictions and help personalise care strategies to each patient’s specific needs.
For many years to come, surgery, chemotherapy, and radiotherapy will remain the mainstay of cancer therapy. Concurrently, there is an increasing interest in improving clinical strategies through AI assistance in diagnosis and therapy of breast cancer and other cancers.
Using AI in the practice of medicine as whole can help avoid emotional problems, cultural and moral beliefs, and fatigue that typically plague the field of medicine.
It can help optimise decision-making and assist in continued up-gradation of the tools available to assist medical physicians in the diagnosis and in exploration of carcinogenesis in real time.
References
Iqbal, M.J., Javed, Z., Sadia, H. et al. Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future. Cancer Cell Int 21, 270 (2021). https://cancerci.biomedcentral.com/articles/10.1186/s12935-021-01981-1. Accessed on 01-09-2021.
Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, Wang Y, Dong Q, Shen H, Wang Y. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243. https://pubmed.ncbi.nlm.nih.gov/29507784/. Accessed on 01-09-2021.
Li Deng and Dong Yu (2014), “Deep Learning: Methods and Applications”, Foundations and Trends® in Signal Processing: Vol. 7: No. 3–4, pp 197-387. https://nowpublishers.com/article/Details/SIG-039
Dlamini Z, Francies FZ, Hull R, Marima R. Artificial intelligence (AI) and big data in cancer and precision oncology. Comput Struct Biotechnol J. 2020 Aug 28;18:2300-2311. https://pubmed.ncbi.nlm.nih.gov/32994889/. Accessed on 01-09-2021.
Artificial Intelligence – Opportunities in Cancer Research. National Cancer Institute, USA. https://www.cancer.gov/research/areas/diagnosis/artificial-intelligence. Accessed on 01-09-2021.
Nehmat Houssami, Christoph I. Lee, Diana S.M. Buist, Dacheng Tao.Artificial intelligence for breast cancer screening: Opportunity or hype? The Breast, Volume 36, 2017, Pages 31-33. ISSN 0960-9776,https://www.sciencedirect.com/science/article/abs/pii/S0960977617305751. Accessed on 01-09-2021.
MammoScreen AI Tool Improves Diagnostic Performance of Radiologists in Detecting Breast Cancer. Cancer Network. https://www.cancernetwork.com/view/mammoscreen-ai-tool-improves-diagnostic-performance-of-radiologists-in-detecting-breast-cancer. Accessed on 01-09-2021.
McKinney, S.M., Sieniek, M., Godbole, V. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89–94 (2020). https://www.nature.com/articles/s41586-019-1799-6. Accessed on 01-09-2021.
Hickman, S.E., Baxter, G.C. & Gilbert, F.J. Adoption of artificial intelligence in breast imaging: evaluation, ethical constraints and limitations. Br J Cancer 125, 15–22 (2021). https://www.nature.com/articles/s41416-021-01333-w. Accessed on 01-09-2021.
Know the cancer – Breast cancer treatment
Previous : Menopause, Hormone therapy and Breast cancer