Machine learning enhanced optical spectroscopy for breast cancer diagnosis: A review
Clinical Snapshot
PICO Framework
| P — Population | Women with breast cancer or suspected breast lesions undergoing optical spectroscopy-based diagnostic evaluation |
| I — Intervention | Machine learning and deep learning enhanced optical spectroscopy (Raman, fluorescence, DOS, photoacoustic) |
| C — Comparator | Conventional optical spectroscopy methods or traditional breast cancer diagnostic approaches |
| O — Outcomes | Diagnostic accuracy, sensitivity, specificity for breast cancer detection and subtype classification |
Bottom Line
This narrative review explores the promising integration of machine learning with optical spectroscopy for breast cancer diagnosis, reporting diagnostic accuracies up to 94% for cancer subtype classification. While the technology shows potential for non-invasive, rapid diagnosis using spectral biomarkers like hemoglobin and collagen, significant barriers remain for clinical translation. The review lacks systematic methodology and formal quality assessment of included studies, limiting confidence in the synthesised evidence. Key challenges include data variability, model interpretability, and standardisation requirements. For Australian clinicians, this technology remains investigational and would require substantial validation, regulatory approval, and cost-effectiveness demonstration before clinical adoption. Current evidence suggests potential but insufficient maturity for immediate practice change, with further research needed in explainable AI, multimodal approaches, and diverse population validation.
Key Findings
P Value: Not applicable for narrative review
Effect Size: Up to 94% diagnostic accuracy for subtype classification
Primary Outcome: Diagnostic accuracy for breast cancer detection and subtype classification
Nnt Or Sensitivity: Sensitivity and specificity values not systematically reported across studies
Confidence Interval: Not reported
Clinical Application
Currently limited by technical complexity, cost, and lack of standardised protocols for clinical implementation Would require TGA approval for diagnostic devices; potential integration with BreastScreen Australia programs pending validation studies; cost-effectiveness analysis needed for PBS consideration Women undergoing breast cancer screening or diagnostic evaluation, particularly those requiring non-invasive assessment
Abstract
This literature review examines the transformative role of machine learning (ML) and deep learning (DL) in enhancing optical spectroscopy for breast cancer diagnosis. By synthesizing advancements from peer-reviewed studies (2015-2025), we evaluate how ML/DL integration improves the detection of malignancy-associated biochemical changes, enabling noninvasive, rapid, and accurate differentiation between healthy and cancerous tissues. This review highlights key spectroscopic modalities, such as Raman, fluorescence, diffusive optical spectroscopy (DOS), and photoacoustic spectroscopy (PAS), and their integration with AI-driven models, such as convolutional neural networks (CNNs), support vector machines (SVMs), and logistic regression. These techniques achieve diagnostic accuracies of up to 94% in subtype classification (e.g., luminal A, HER2-positive) by analyzing spectral biomarkers such as hemoglobin, lipids, and collagen. Challenges such as data variability, model interpretability, and clinical integration barriers are critically assessed. These findings underscore the potential of ML/DL-enhanced spectroscopy to standardize diagnostics, reduce unnecessary biopsies, and personalize treatment monitoring. Future directions emphasize the need for explainable AI (XAI), multimodal data fusion, and large-scale, diverse datasets to bridge translational gaps. By addressing technical, ethical, and regulatory hurdles, this integration promises to advance early detection, improve clinical outcomes, and reshape precision oncology.
References
- 1.Nakul, M., Rao, S. D., Karnati, M., Aziz, F., Bhaskar, D. P., Dehury, B., & Mazumder, N. (2026). Machine learning enhanced optical spectroscopy for breast cancer diagnosis: A review. Lasers in Medical Science. https://doi.org/10.1016/j.pdpdt.2022.103215
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
3 Aug 2026
European journal of radiology
A CT-based deep learning model to differentiate between benign and malignant adrenal lesions
3 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service