Senthurun Mylvaganam BSc (Hons) MBBS MA FFST FRCS
Consultant Oncoplastic, Reconstructive and Cosmetic Breast Surgeon
Artificial Intelligence (AI) is rapidly becoming one of the most talked-about developments in healthcare. While headlines often focus on futuristic possibilities, AI is already beginning to influence how breast cancer is detected, diagnosed, and treated.
For patients, the idea of computers becoming involved in medical decision-making can feel both exciting and concerning. However, the reality is that AI is unlikely to replace breast specialists, radiologists, pathologists, or surgeons. Instead, it is expected to become a powerful tool that supports clinicians, helping them make faster, more accurate, and more personalised decisions.
The future of breast cancer care may be one where technology and human expertise work together to improve outcomes and patient experience.
What Is Artificial Intelligence?
Artificial Intelligence refers to computer systems that can analyse large amounts of data, identify patterns, and make predictions based on that information.
In breast cancer care, AI systems can be trained using millions of mammograms, MRI scans, pathology slides, genetic profiles, and clinical outcomes. By learning from these datasets, AI can identify subtle patterns that may not always be visible to the human eye.
The goal is not to replace doctors but to provide an additional layer of analysis that may improve accuracy and efficiency.
Earlier Detection of Breast Cancer
One of the most promising areas for AI is breast screening.
Studies have shown that AI-assisted mammography may improve cancer detection rates while reducing the workload for radiologists. AI systems are increasingly capable of identifying suspicious abnormalities and highlighting areas that require closer review.
Future screening programmes may use AI to:
- Highlight suspicious areas on mammograms
- Reduce false-positive findings
- Prioritise higher-risk cases for urgent review
- Improve consistency between radiologists
- Increase screening capacity within healthcare systems
As breast imaging demand continues to rise, AI could help reduce delays and support earlier diagnosis.
More Personalised Screening
Currently, many women are offered screening based primarily on age.
In the future, AI may allow screening to become far more personalised.
Advanced algorithms are being developed that combine imaging findings, breast density, family history, genetics, and lifestyle factors to estimate an individual’s future breast cancer risk.
This could lead to:
- More frequent screening for higher-risk women
- Less intensive screening for lower-risk women
- Earlier MRI surveillance in selected patients
- Improved identification of women who may benefit from preventative strategies
Rather than a “one-size-fits-all” approach, screening may become tailored to each woman’s risk profile.
Improving Breast Cancer Diagnosis
Diagnosing breast cancer involves much more than reading a mammogram.
Pathologists examine tissue samples under a microscope, assessing tumour type, grade, receptor status, and other important characteristics that influence treatment.
AI is increasingly being used in digital pathology to analyse whole-slide images. Research suggests that AI can assist in detecting invasive cancers, identifying microscopic abnormalities, and improving consistency between observers.
In the future, AI may help:
- Improve diagnostic accuracy
- Reduce reporting variability
- Identify subtle tumour features
- Accelerate pathology turnaround times
- Support more precise tumour classification
This could help ensure patients receive the most appropriate treatment recommendations as quickly as possible.
Predicting Which Treatments Will Work Best
Perhaps one of the most exciting future applications of AI is precision medicine.
Breast cancer is not a single disease. Two patients with apparently similar cancers may respond very differently to the same treatment.
AI systems are being developed to analyse:
- Imaging data
- Tumour biology
- Genetic information
- Histopathology findings
- Previous treatment outcomes
By combining these factors, AI may be able to predict which patients are most likely to benefit from specific treatments.
Potential future benefits include:
- Better selection of chemotherapy candidates
- More personalised endocrine therapy decisions
- Improved immunotherapy prediction
- Reduced overtreatment
- Better treatment outcomes
The ultimate goal is to match the right treatment to the right patient at the right time.
AI and Breast Surgery
AI may also influence surgical planning.
Advanced imaging analysis could help surgeons better understand tumour size, shape, and extent before surgery. Future systems may generate highly detailed three-dimensional maps of a cancer and predict the most effective surgical approach.
Potential applications include:
- Improved breast-conserving surgery planning
- Better prediction of cosmetic outcomes
- More accurate assessment of tumour margins
- Enhanced reconstruction planning
- Reduced re-operation rates
For patients considering breast reconstruction, AI may eventually help predict recovery, complication risk, and likely aesthetic outcomes based on large datasets from previous patients.
Predicting Side Effects and Recovery
Not all treatment decisions are based solely on curing cancer. Quality of life is equally important.
Researchers are developing AI models capable of predicting treatment-related complications and side effects. Future tools may help identify patients at higher risk of lymphoedema, wound complications, treatment toxicity, or prolonged recovery.
This may allow:
- More personalised rehabilitation programmes
- Earlier intervention for complications
- Better informed consent discussions
- Improved survivorship planning
This represents an important shift from reactive care to proactive care.
Will AI Replace Breast Specialists?
The simple answer is no.
Breast cancer care involves far more than pattern recognition and data analysis. Patients need empathy, communication, clinical judgement, and shared decision-making.
AI cannot sit with a patient who has just received a cancer diagnosis. It cannot understand individual fears, family circumstances, personal priorities, or emotional needs.
Instead, AI is likely to become another tool used by clinicians—similar to MRI scanners, pathology testing, or genetic analysis.
The most effective future model will combine:
- Advanced technology
- Evidence-based medicine
- Specialist expertise
- Human compassion
The relationship between patient and clinician will remain central to breast cancer care.
Challenges and Limitations
Despite its promise, AI is not without challenges.
Several important questions remain:
- How accurate are AI systems across different populations?
- Can algorithms be trusted in complex clinical situations?
- Who is responsible if AI makes an error?
- How should patient data be protected?
- How can bias within datasets be reduced?
Healthcare systems must ensure that AI is introduced safely, transparently, and with appropriate clinical oversight.
The Future of Breast Cancer Care
Artificial Intelligence has the potential to transform every stage of the breast cancer journey—from risk prediction and screening through diagnosis, treatment selection, surgery, and long-term follow-up.
While many of these developments remain in evolution, the direction of travel is clear: more personalised, more precise, and more data-driven care.
Importantly, technology should never replace the human side of medicine. The future of breast cancer treatment is unlikely to be doctors versus AI. Instead, it will be doctors working alongside AI to deliver safer, smarter, and more individualised care.
For patients, that future offers the possibility of earlier diagnosis, more tailored treatment, fewer unnecessary interventions, and ultimately better outcomes.
References
- McKinney SM et al. International evaluation of an AI system for breast cancer screening. Nature. 2020;577:89–94.
- Rodriguez-Ruiz A et al. Detection of breast cancer with mammography: effect of artificial intelligence support. Radiology. 2019;290(2):305–314.
- Yala A et al. A deep learning mammography-based model for improved breast cancer risk prediction. Radiology. 2019;292(1):60–66.
- Bahl M. Artificial intelligence for risk assessment and screening in breast imaging. Radiologic Clinics of North America. 2021;59(1):1–11.
- Ehteshami Bejnordi B et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318(22):2199–2210.
- Lotter W et al. Robust breast cancer detection in mammography and digital pathology using deep learning. Nature Medicine. 2021.
- Topol EJ. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Basic Books; 2019.
- World Health Organization. Ethics and Governance of Artificial Intelligence for Health. Available at: https://www.who.int/publications/i/item/9789240029200
- Royal College of Radiologists. Artificial Intelligence Framework for Clinical Radiology. Available at: https://www.rcr.ac.uk
- NHS England. Artificial Intelligence in Healthcare. Available at: https://www.england.nhs.uk/aac/what-we-do/how-can-the-aac-help-me/artificial-intelligence/
