Designing a portable and accessible diffuse reflectance spectroscopy system for real-time detection of cervical intraepithelial neoplasia

• Published in: Journal of innovative optical health science Vol. 18; no. 4
• Main Authors: Scarbrough, Allison, Moses, Diana, Lu, Tongtong, Yu, Bing
• Format: Journal Article
• Language: English
• Published: Singapore World Scientific Publishing Company 01.07.2025; World Scientific Publishing Co. Pte., Ltd; World Scientific Publishing
• Subjects: Accessibility; Artificial intelligence; Cancer; Cancer screening; Cervical cancer; Diffuse reflectance spectroscopy; global health; Intestine; Medical screening; Optical properties; Optics; Organs; Portability; Raspberry Pi; Real time; Reflectance; Research Article; Small intestine; Spectra; Spectroscopy; Spectrum analysis; Tissues; global health; Raspberry Pi; cancer screening; Cervical cancer; artificial intelligence
• ISSN: 1793-5458; 1793-7205
• DOI: 10.1142/S1793545825440018

Significance: Over 80% of cervical cancer cases occur in lower-to-middle income countries (LMIC’s). This is partly because current screening techniques lack affordability, accessibility, and/or reliability for use in LMIC’s. Aim: To develop an optical technique for cervical cancer screening that is affordable, accessible, and reliable for use in LMIC’s. Approach: We developed a portable diffuse reflectance spectroscopy (DRS) system, which costs < $ 2 5 0 0 USD to manufacture, and employs a Raspberry Pi to extract the absorption ( μ a ) and reduced scattering ( μ s ′ ) coefficients of biological tissue. The system was subject to travel and intentional rough handling. It was further used to capture 320 DRS spectra taken from 64 tissue-mimicking phantoms. Two users collected phantom data, one “expert”, and one “novice” in biomedical optics. The system was also used to collect 335 spectra from colon, small intestine, and rectal tissue of a fresh ex vivo porcine specimen. A previously described artificial intelligence model was used to extract optical properties, and a GradientBoostingClassifier identified the organ of origin for ex vivo spectra. Results: System alignment was robust to intentional rough handling and travel. Phantom μ a and μ s ′ were predicted with average root-mean square error of < 1 0 % , regardless of user. Regarding ex vivo data, the system predicted the organ of origin with 80–90% accuracy. Statistical differences between predicted μ a were observed in all three organs ( p < 0 . 0 0 1 –0.03), and between μ s ′ in two organs ( p < 0 . 0 0 1 –0.07). Conclusions: The DRS system has the potential to be affordable, reliable, and accessible for cervical screening in LMIC’s.