Abstract 7662: Convolutional neural network algorithms and hematoxylin-and-eosin-stained images predict clinical outcomes in high-grade serous ovarian cancer patients with advanced age and stage

Ovarian cancer is the deadliest among gynecologic cancers. It is partly due to the mild symptoms in early stages and relatively high diagnostic age (about 63-year-old median age). These factors contribute to the short chemotherapy response time and survival time with about 18- and 36-months median progression-free survival and overall survival duration, respectively. The advancements of convolutional neural network (CNN) machine learning algorithms provide opportunities for the development of cost- and time-effective models which is urgently needed for ovarian cancer patients, especially for those with elevated risk. A CNN model was trained with hematoxylin and eosin (H&E) stained tumor whole slide images (WSIs) from ovarian cancer patients with advanced stages. 773 WSIs of 335 patients from TCGA-OV dataset were separated randomly for training and testing cohort. The model was then applied on testing cohort with advanced stage and age patients for H&E survival score. The c-index of the predicted risk on overall survival (OS) and progression-free survival (PFS) were 0.66 and 0.63, respectively. The log-rank p-values of patients between low and high risk were 0.00137 and 0.00138, respectively. The model was then further evaluated with an external dataset. The c-index of the predicted risk were 0.64 and 0.72 for OS and PFS, respectively. And the log-rank test between patients with low and high risk achieved p-values 0.017 and 0.0047 for OS and PFS, respectively. In conclusion, a novel prognostic CNN model was developed for ovarian cancer patients with advanced age and stage for better disease management.

Citation Format: Chun Wai Ng, Kwong-kwok Wong, Berrett Lawson, Sammy Ferri-Borgogno, Samuel Mok. Convolutional neural network algorithms and hematoxylin-and-eosin-stained images predict clinical outcomes in high-grade serous ovarian cancer patients with advanced age and stage [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7662.