Automated grading and staging of ovarian cancer using deep learning on the transmission optical microscopy bright-field images of thin biopsy tissue samples

TL;DR

This paper introduces a deep learning method using transfer learning and hyperparameter optimization to automatically grade and stage ovarian cancer from histopathological images, achieving high accuracy and aiding diagnosis.

Contribution

The study presents a novel automated framework for ovarian cancer staging using deep learning with transfer learning, data augmentation, and genetic algorithm-based hyperparameter tuning.

Findings

Achieved 97.62% accuracy on independent test set.

Demonstrated effectiveness of transfer learning and hyperparameter optimization.

Provided a scalable solution for digital histopathology analysis.

Abstract

Ovarian cancer remains a challenging malignancy to diagnose and manage, with prognosis heavily dependent on the stage at detection. Accurate grading and staging, primarily based on histopathological examination of biopsy tissue samples, are crucial for treatment planning and predicting outcomes. However, this manual process is time-consuming and subject to inter-observer variability among pathologists. The increasing volume of digital histopathology slides necessitates the development of robust, automated methods to assist in this critical diagnostic step for ovarian cancer. (Methods) This study presents a deep learning framework for the automated prediction of ovarian cancer stage (classified into five categories: 0, I, II, III, IV) using routine histopathological images. We employed a transfer learning approach, fine-tuning a ResNet-101 convolutional neural network pre-trained on ImageNet. The training process incorporated comprehensive data augmentation, weighted random sampling, and class weighting to address dataset characteristics. Hyperparameter optimization for learning rate, dropout rate, and weight decay was performed using a genetic algorithm to enhance model performance and generalization. (Results) Evaluated on an independent test set of ovarian thin tissue brightfield images, the developed model achieved a high overall classification accuracy of 97.62%.