A Deep Learning based Pipeline for Efficient Oral Cancer Screening on Whole Slide Images

TL;DR

This paper introduces a fully automated deep learning pipeline for oral cancer detection on whole slide images, combining nucleus detection, focus selection, and CNN classification to improve accuracy and efficiency in large-scale screening.

Contribution

The novel focus selection step enables fast, human-level accuracy focus decisions, enhancing the pipeline's overall performance for oral cancer screening.

Findings

Improved accuracy over previous methods

Efficient processing suitable for large-scale screening

Open-source code available for reproducibility

Abstract

Oral cancer incidence is rapidly increasing worldwide. The most important determinant factor in cancer survival is early diagnosis. To facilitate large scale screening, we propose a fully automated pipeline for oral cancer detection on whole slide cytology images. The pipeline consists of fully convolutional regression-based nucleus detection, followed by per-cell focus selection, and CNN based classification. Our novel focus selection step provides fast per-cell focus decisions at human-level accuracy. We demonstrate that the pipeline provides efficient cancer classification of whole slide cytology images, improving over previous results both in terms of accuracy and feasibility. The complete source code is available at https://github.com/MIDA-group/OralScreen.