Computer-aided diagnosis of lung carcinoma using deep learning - a pilot study

TL;DR

This pilot study evaluates various deep learning models for lung cancer diagnosis using biopsy slides, demonstrating their potential to assist pathologists by providing rapid and accurate detection comparable to experienced human observers.

Contribution

The study compares multiple deep learning models for lung cancer diagnosis on biopsy slides, identifying their effectiveness and potential to improve diagnostic speed and accuracy.

Findings

Deep learning models achieved AUCs between 0.8810 and 0.9119.

Models can potentially speed up diagnosis without compromising accuracy.

Deep learning analysis may assist pathologists in lung cancer detection.

Abstract

Aim: Early detection and correct diagnosis of lung cancer are the most important steps in improving patient outcome. This study aims to assess which deep learning models perform best in lung cancer diagnosis. Methods: Non-small cell lung carcinoma and small cell lung carcinoma biopsy specimens were consecutively obtained and stained. The specimen slides were diagnosed by two experienced pathologists (over 20 years). Several deep learning models were trained to discriminate cancer and non-cancer biopsies. Result: Deep learning models give reasonable AUC from 0.8810 to 0.9119. Conclusion: The deep learning analysis could help to speed up the detection process for the whole-slide image (WSI) and keep the comparable detection rate with human observer.