Point-of-care digital cytology with artificial intelligence for cervical cancer screening at a peripheral clinic in Kenya

Cervical cancer is highly preventable but remains a common and deadly cancer in areas without screening programmes. Pap smear analysis is the most commonly used screening method but is labour-intensive, subjective and requires access to medical experts. We developed a diagnostic system in which microscopy samples are digitized at the point-of-care (POC) and analysed by a cloud-based deep-learning system (DLS) and evaluated the system for the detection of cervical cell atypia in Pap smears at a peripheral clinic in Kenya. A total of 740 conventional Pap smears were collected, digitized with a portable slide scanner and uploaded over mobile networks to a cloud server for training and validation of the system. In total, 16,133 manually-annotated image regions where used for training of the DLS. The DLS achieved a high average sensitivity (97.85%; 95% confidence interval (CI) 83.95—99.75%) and area under the curve (AUCs) (0.95) for the detection of cervical-cellular atypia, compared to the pathologist assessment of digital and physical slides. Specificity was higher for high-grade atypia (95.9%; 95% CI 94.9—97.6%) than for low-grade atypia (84.2%; 95% CI 79.9—87.9%). Negative predictive values were high (99.3-100%), and no samples classified as high grade by manual sample analysis had false-negative assessments by the DLS. The study shows that advanced digital microscopy diagnostics supported by machine learning algorithms is implementable in rural, resource-constrained areas, and can achieve a diagnostic accuracy close to the level of highly trained experts. Summary box What is already known? • Cervical cancer can be prevented with Pap smear screening, but manual sample analysis is labor-intensive, subjective and not widely-available in regions with the highest disease prevalence • Novel digital methods, such as image-based artificial intelligence (AI), show promise for facilitated analysis of microscopy samples • Digital methods are typically limited to high-end laboratories, due to the requirements for advanced equipment and supportive digital infrastructure What are the new findings? • A point-of-care diagnostic system where samples are digitized with a portable slide scanner and analyzed using a cloud-based AI model can be implemented in rural settings and utilized to automatically interpret Pap smears and identify potentially precancerous samples with similar accuracy as a pathologist specialized in reading Pap smears. What do the new findings imply? • The results demonstrate how advanced digital methods, such as AI-based digital microscopy, can be implemented in rural, resource-limited areas, and used for analysis of microscopy samples, such as Pap smears. • This technology shows promise as a novel method for digital microscopy diagnostics, which can be implemented in rural settings, and could be of particular value in areas lacking cytotechnicians and pathologists.