Assessing the Robustness of Deep Learning-Assisted Pathological Image Analysis Under Practical Variables of Imaging System

With the advancement of deep learning, computer-assisted clinical diagnosis, such as liquid-based cervical cytology, has attracted more attention. However, the fragile robustness of deep learning models has a non-negligible impact on their classification accuracy and reliability. To be more specific, various scanner parameters will be used depending on the pathologist’s preferences during the clinical diagnosis process (e.g., field source brightness, contrast, saturation, etc.), and this variation will lead to the unstable performance of the model. In this paper, we construct an evaluation pathway to assess the stability and consistency of deep learning models under various customized scanner parameters. Specifically, a multi-scanned dataset consists of 4200 whole slide images (WSIs) is generated by scanning 200 stained slices using various scanner parameters. Moreover, we conducted a large number of experiments to investigate the robustness of numerous models, including convolution-based and transformer-based models concerning various scanner parameter settings. Furthermore, we introduce several indicators to analyze the prediction accuracy, consistency and robustness of the model on the constructed dataset. The experimental results indicate that the deep learning models are sensitive to luminance-related scanner parameters. In addition, transformer-based models have better robustness than traditional convolutional neural networks. Our code has been made available¹.

1. INTRODUCTION

Cervical cancer is still one of the worst health threats to women worldwide, reported in Global Cancer Statistics 2020 [1]. Clinical pathology screening with liquid-based cytology (LBC, thinprep) is a positive recommendation for the early detection of cervical precancerous lesions and effectively prevents the progression of invasive cancer [2]. However, inefficient and labor-intensive conventional analysis under microscopy cannot meet the growing demand for regular screening. In recent years, the advancement of digital pathology technology has led to significant progress in clinical processing through the digitalization of whole slide images. With the evolution of deep neural networks (DNNs) such as convolutional neural networks (CNN) and vision transformers [3], [4], [5], artificial intelligence (AI)-assisted diagnosis can significantly strengthen the working efficiency and diagnostic quality of pathologists.