preprint · medRxiv
Cervical cancer presents a heavy disease burden in regions such as Tanzania, where a shortage of pathologists makes timely and accurate diagnosis difficult. Automated analysis of Pap smear slides offers a potential solution to enhance diagnostic workflow and precision. This research evaluated several deep learning convolutional neural network models trained on normal and cancerous cell images from the Centre for Recognition and Inspection of Cells dataset. Models were assessed using accuracy, sensitivity, and specificity. EfficientNetB7 achieved the highest performance, registering an accuracy of 0.95, sensitivity of 0.84, and specificity of 0.97. Conversely, InceptionNet-V3 yielded the lowest results. Distinguishing between certain borderline cell categories, specifically ASC-US and LSIL, remained challenging because of subtle cellular differences. Incorporating whole smear analysis or extra context is suggested to enhance future classification accuracy.
In areas facing severe shortages of trained pathologists, automated screening tools can relieve healthcare bottlenecks. Identifying cervical pre-cancer earlier and more accurately allows healthcare providers to deliver timely interventions, potentially lowering mortality rates from a treatable condition.
This research could support diagnostic software developers creating clinical decision-support tools for cytopathology laboratories and screening clinics. The work remains at an early, laboratory-tested stage using an existing image dataset. Significant development is still required, particularly in refining classification between borderline cell classes and integrating whole smear analysis, before it is ready for operational clinical deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract The global burden of cervical cancer, with a notable prevalence in regions like Tanzania, highlights the critical need for timely and accurate diagnosis. The scarcity of pathologists in such areas underscores the importance of developing automated tools for the cytopathological analysis of cervical cancer images to improve diagnostic efficiency and accuracy. This study investigated the performance of advanced artificial intelligence (AI) algorithms for screening cervical cancer using Pap smear cytological slides from the Centre for Recognition and Inspection of Cells CRIC dataset. Deep learning models were trained on images of both cervical cancer and normal cervix cells, with the evaluation of model performance focusing on specificity, sensitivity, and accuracy. Among the evaluated convolutional neural network (CNN) architectures—EfficientNetB7, MobileNet, ResNet50, ResNet152, and InceptionNet-V3—EfficientNetB7 emerged as the top performer, demonstrating impressive accuracy, sensitivity and specificity metrics (accuracy: 0.95, sensitivity: 0.84, specificity: 0.97). In contrast, InceptionNet-V3 showed the lowest performance across similar metrics (accuracy: 0.78, sensitivity: 0.35, specificity: 0.87). The study also highlighted the challenges in distinguishing between specific cell classes, particularly between ASC-US and LSIL, due to the subtle nuances of cytomorphological criteria. The findings suggest that while AI can significantly aid in cervical cancer screening, the complexity of cell image classification demands further exploration, possibly incorporating whole smear analysis or additional contextual information to improve accuracy. Despite the observed classification challenges, such as between ASC-US and LSIL classes, the potential for AI in supporting clinical decision-making in cervical cancer management is evident.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1101/2025.03.09.25323636
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
