Pathological Insights: Enhanced Vision Transformers for the Early Detection of Colorectal Cancer

Abstract

Simple Summary Accounting for 10% of the new cases in 2020, colorectal cancer (CRC) is one of the most prevalent cancers worldwide. Unfortunately, CRC is frequently identified at a later stage, despite the fact that early detection greatly increases survival rates. Diagnostic endoscopy is the gold standard; however, identifying abnormalities at an early stage is challenging. In particular, convolutional neural networks (CNNs) are being used by researchers to improve detection through deep learning. But prior approaches were primarily concerned with polyp detection. This work provided a novel method for polyp segmentation and endoscopic pathological finding categorization using vision transformers and spatial transformers for the early identification of colorectal cancer (CRC). These approaches perform noticeably better than the current CNN-based algorithms. This work opens up exciting possibilities for improving on early CRC detection beyond just identifying polyps.Abstract Endoscopic pathological findings of the gastrointestinal tract are crucial for the early diagnosis of colorectal cancer (CRC). Previous deep learning works, aimed at improving CRC detection performance and reducing subjective analysis errors, are limited to polyp segmentation. Pathological findings were not considered and only convolutional neural networks (CNNs), which are not able to handle global image feature information, were utilized. This work introduces a novel vision transformer (ViT)-based approach for early CRC detection. The core components of the proposed approach are ViTCol, a boosted vision transformer for classifying endoscopic pathological findings, and PUTS, a vision transformer-based model for polyp segmentation. Results demonstrate the superiority of this vision transformer-based CRC detection method over existing CNN and vision transformer models. ViTCol exhibited an outstanding performance in classifying pathological findings, with an area under the receiver operating curve (AUC) value of 0.9999 +/- 0.001 on the Kvasir dataset. PUTS provided outstanding results in segmenting polyp images, with mean intersection over union (mIoU) of 0.8673 and 0.9092 on the Kvasir-SEG and CVC-Clinic datasets, respectively. This work underscores the value of spatial transformers in localizing input images, which can seamlessly integrate into the main vision transformer network, enhancing the automated identification of critical image features for early CRC detection.