1201P - Novel deep learning model and validation of whole slide images in lung cancer diagnosis

Background

Lung cancer is the leading cause of cancer-related deaths worldwide and the second cause of death in Poland. Two of the crucial factors contributing to these fatalities are delayed diagnosis and suboptimal prognosis. The rapid advancement of deep learning (DL) approaches provides a significant opportunity for medical imaging techniques to play a crucial role in the early diagnosis of lung tumors and the following stages of treatment. This study presents a DL-based model for efficient lung cancer detection using Whole Slide Images WSIs and validated by Polish active pathologists in order to support them on a daily basis.

Methods

Our methodology combines convolutional neural networks (CNNs) and separable CNNs with residual blocks, thereby improving classification performance. Our model improves accuracy (96% to 98%) and robustness in distinguishing between cancerous and non-cancerous lung cell images in less than 10 seconds.

Results

The model's overall performance surpassed that of active pathologists, with an accuracy of 100% vs. 79%. There was a significant linear correlation between pathologists' accuracy and years of experience (r Pearson = 0.71, 95% CI 0.14 to 0.93, p = 0.022).

Conclusions

We conclude that this model enhances the accuracy of cancer detection and the model outperformed results reported by active pathologists, suggesting that an AI algorithm assisted by pathologists can enhance diagnostic skills and reduce the lead time in the diagnosis process.

Clinical trial identification

Editorial acknowledgement

Legal entity responsible for the study

The authors.

Funding

Poznan University of Medical Sciences.

Disclosure

All authors have declared no conflicts of interest.