Tissue Artifact Segmentation and Severity Assessment for Automatic Analysis using WSI

• Published in: IEEE access 2023-01, Vol.11, p.1-1
• Main Authors: Hossain, Md Shakhawat, Shahriar, Galib Muhammad, Syeed, M M Mahbubul, Uddin, Mohammad Faisal, Hasan, Mahady, Hossain, Md Sakir, Bari, Rubina
• Format: Article
• Language: English
• Subjects: Air bubbles; artifact detection; Artificial intelligence; Artificial neural networks; automated image analysis; Automation; Biological tissues; Biomedical imaging; Computer vision; Convolutional neural networks; Diagnosis; Digital imaging; digital pathology; Evaluation; Image analysis; Image color analysis; Image segmentation; Microscopy; Pathology; quality evaluation; Tissue artifact; whole slide image
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3250556

Traditionally, pathological analysis and diagnosis are performed by manually eyeballing glass-slide specimen under a microscope by an expert. Whole slide image (WSI) is the digital specimen produced from the glass-slide. WSI enabled specimen to be observed on a computer-screen and led to computational pathology where computer-vision and artificial intelligence are utilized for automated analysis and diagnosis. With the current computational advancement, entire WSI can be analyzed autonomously without human supervision. However, the analysis could fail or lead to wrong diagnosis if the WSI is affected by tissue artifacts such as tissue fold or air bubble depending on the severity. Existing artifact detection methods rely on experts for severity assessment to eliminate artifact-affected regions from analysis. This process is time-consuming, exhausting and undermines the goal of automated analysis or removal of artifacts without evaluating their severity, which could result in the loss of diagnostically important data. Therefore, it is necessary to detect artifacts and then assess their severity automatically. In this paper, we propose a system that incorporates severity evaluation with the artifact detection utilizing convolutional neural networks (CNN). The proposed system uses DoubleUNet to segment artifacts and an ensemble network of six fine-tuned CNN models to determine severity. This method outperformed current state-of-the-art in accuracy by 9% for artifact segmentation and achieved a strong correlation of 97% with pathologist's evaluation for severity assessment. The robustness of the system was demonstrated using our proposed heterogeneous dataset and practical usability was ensured by integrating it with an automated analysis system.