Abstract
Cervical cancer remains one of the leading causes of cancer-related morbidity among women worldwide, and its early detection depends heavily on the accuracy of cytological and colposcopic interpretation, a task traditionally limited by inter-observer variability and low specificity. Over the past several years, deep learning has been increasingly integrated into cervical screening pipelines, extending far beyond simple cell classification toward whole-slide image analysis and multimodal fusion of colposcopy, cytology and HPV status [1,2]. A scoping review covering studies published between 2009 and 2022 identified thirty-two eligible works applying machine learning and deep learning to cervical cancer screening, with convolutional neural networks, ResNet and support vector machine architectures achieving diagnostic accuracies exceeding 97% on curated datasets [1].
References
This work is licensed under a Creative Commons Attribution 4.0 International License.