Benign/Cancer Diagnostics Based on X-Ray Diffraction: Comparison of Data Analytics Approaches
<b>Background/Objectives</b>: With the number of detected breast cancer cases growing every year, there is a need to augment histopathological analysis with fast preliminary screening. We examine the feasibility of using X-ray diffraction measurements for this purpose. <b>Methods:</b> In this work, we obtained more than 6000 diffraction patterns from 211 patients and examined both standard and custom-developed methods, including Fourier coefficient analysis, for their interpretation. Various preprocessing steps and machine learning classifiers were compared to determine the optimal combination. <b>Results:</b> We demonstrated that benign and cancerous clusters are well separated, with specificity and sensitivity exceeding 0.9. For wide-angle scattering, the two-dimensional Fourier method is superior, while for small angles, the conventional analysis based on azimuthal integration of the images provides similar metrics. <b>Conclusions</b>: X-ray diffraction of biopsy tissues, supported by machine learning approaches to data analytics, can be an essential tool for pathological services. The method is rapid and inexpensive, providing excellent metrics for benign/cancer classification.
Authors
- Lev Mourokh (ORCID: https://orcid.org/0000-0003-4918-7251)
- Alexander Alekseev (ORCID: https://orcid.org/0000-0002-2800-6047)
- Viacheslav Shcherbakov (ORCID: https://orcid.org/0000-0003-3628-1804)
- Charlene Greenwood (ORCID: https://orcid.org/0000-0003-1332-3864)
- Peter A. Lazarev (ORCID: https://orcid.org/0009-0000-8799-3209)
- Sergey A. Denisov (ORCID: https://orcid.org/0000-0001-7881-1979)
- Keith D. Rogers (ORCID: https://orcid.org/0000-0003-0423-8940)
- J. Louise Jones (ORCID: https://orcid.org/0000-0003-3880-3274)
- Benjamin Blinchevsky
- Lois Adams
- Sasha Murokh
- Viacheslav Kubytskyi
- Oleksii Avdieiev
- Ashkan Ajeer (ORCID: https://orcid.org/0000-0002-5942-8613)
Institutions
- Queens College, CUNY (US)
- Centre National de la Recherche Scientifique (FR)
- Queen Mary University of London (GB)
- Université Paris-Saclay (FR)
- Karaganda Buketov University (KZ)
- Laboratoire de Chimie Physique (FR)
- Institut de Chimie (FR)
- Laboratoire de Physique des 2 Infinis Irène Joliot-Curie (FR)
- Keele University (GB)
- Cranfield University (GB)
Publication Details
- Journal
- Cancers
- Published
- 2025-05-14
- DOI
- https://doi.org/10.3390/cancers17101662
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Queen Mary University of London
- National Institute for Health and Care Research
- St George's University Hospitals NHS Foundation Trust
- Barts Health NHS Trust