Artificial Intelligence in Ovarian Cancer Histopathology: A Systematic Review

Purpose - To characterise and assess the quality of published research evaluating artificial intelligence (AI) methods for ovarian cancer diagnosis or prognosis using histopathology data. Methods - A search of 5 sources was conducted up to 01/12/2022. The inclusion criteria required that research evaluated AI on histopathology images for diagnostic or prognostic inferences in ovarian cancer, including tubo-ovarian and peritoneal tumours. Reviews and non-English language articles were excluded. The risk of bias was assessed for every included model using PROBAST. Results - A total of 1434 research articles were identified, of which 36 were eligible for inclusion. These studies reported 62 models of interest, including 35 classifiers, 14 survival prediction models, 7 segmentation models, and 6 regression models. Models were developed using 1-1375 slides from 1-664 ovarian cancer patients. A wide array of outcomes were predicted, including overall survival (9/62), histological subtypes (7/62), stain quantity (6/62) and malignancy (5/62). Older studies used traditional machine learning (ML) models with hand-crafted features, while newer studies typically employed deep learning (DL) to automatically learn features and predict the outcome(s) of interest. All models were found to be at high or unclear risk of bias overall. Research was frequently limited by insufficient reporting, small sample sizes, and insufficient validation. Conclusion - Limited research has been conducted and none of the associated models have been demonstrated to be ready for real-world implementation. Recommendations are provided addressing underlying biases and flaws in study design, which should help inform higher-quality reproducible future research. Key aspects include more transparent and comprehensive reporting, and improved performance evaluation using cross-validation and external validations.