Computer-aided colorectal cancer diagnosis: AI-driven image segmentation and classification

Abstract

Colorectal cancer is an enormous health concern since it is among the most lethal types of malignancy. The manual examination has its limitations, including subjectivity and data overload. To overcome these challenges, computer-aided diagnostic systems focusing on image segmentation and abnormality classification have been developed. This study presents a two-stage approach for the automatic detection of five types of colorectal abnormalities in addition to a control group: polyp, low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia, serrated adenoma, adenocarcinoma. In the first stage, UNet3+ was used for image segmentation to locate the anomalies, while in the second stage, the Cross-Attention Multi-Scale Vision Transformer deep learning model was used to predict the type of anomaly after highlighting the anomaly on the raw images. In anomaly segmentation, UNet3+ achieved values of 0.9872, 0.9422, 0.9832, and 0.9560 for Dice Coefficient, Jaccard Index, Sensitivity, Specificity respectively. In anomaly detection, the Cross-Attention Multi-Scale Vision Transformer model attained a classification performance of 0.9340, 0.9037, 0.9446, 0.8723, 0.9102, 0.9849 for accuracy, F1 score, precision, recall, Matthews correlation coefficient, and specificity, respectively. The proposed approach proves its capacity to alleviate the overwhelm of pathologists and enhance the accuracy of colorectal cancer diagnosis by achieving high performance in both the identification of anomalies and the segmentation of regions.

Keywords: Anomaly classification; Colorectal cancer; Computer-aided diagnosis; Deep learning; Histopathology; Image segmentation.

Figure 1. An overview of the proposed strategy.

Figure source credit: MIaMIA Group (2022).

Figure 2. Sample of raw images, masks and proposed method outputs.

Figure source credit: MIaMIA Group (2022).

Figure 3. The UNet3+ network structure.

Figure 4. The network structure of the CrossVIT.

Figure source credit: MIaMIA Group (2022).

Figure 5. The visualization of each class.

(A) Control group, (B) polyp, (C) high-grade intraepithelial neoplasia, (D) low-grade intraepithelial neoplasia, (E) adenocarcinoma and (F) serrated adenoma. Figure source credit: MIaMIA Group (2022).