Classification of Epithelial Ovarian Carcinoma Whole-Slide Pathology Images Using Deep Transfer Learning
This work addresses the challenge of accurate and consistent histotype classification in ovarian cancer diagnosis, which is critical for patient treatment but currently hindered by variability in pathologist assessments.
The researchers tackled the problem of classifying epithelial ovarian carcinoma whole-slide images, which currently suffers from poor inter-observer agreement among pathologists, and achieved a mean accuracy of 87.54% and Cohen's kappa of 0.8106 using a deep transfer learning algorithm.
Ovarian cancer is the most lethal cancer of the female reproductive organs. There are $5$ major histological subtypes of epithelial ovarian cancer, each with distinct morphological, genetic, and clinical features. Currently, these histotypes are determined by a pathologist's microscopic examination of tumor whole-slide images (WSI). This process has been hampered by poor inter-observer agreement (Cohen's kappa $0.54$-$0.67$). We utilized a \textit{two}-stage deep transfer learning algorithm based on convolutional neural networks (CNN) and progressive resizing for automatic classification of epithelial ovarian carcinoma WSIs. The proposed algorithm achieved a mean accuracy of $87.54\%$ and Cohen's kappa of $0.8106$ in the slide-level classification of $305$ WSIs; performing better than a standard CNN and pathologists without gynecology-specific training.