Author:
Qin Zhuanping,Sun Wenhao,Guo Tinghang,Lu Guangda
Abstract
AbstractAiming at the problems of the complex background of colorectal cancer tissue cell images and the difficulty of detection caused by the low differentiation of cancer cell regions, a deep learning method is used to detect the cancer cell regions. By integrating the skip feedback connection structure into U-Net and combining it with the Swin Transformer for feature extraction, we improve the multi-level feature extraction capabilities of the model. This algorithm enables end-to-end recognition of colorectal adenocarcinoma tissue images and achieves an accuracy of 95.8% on the NCT-CRC-HE-100K dataset, demonstrating its potential to significantly support colorectal cancer detection and treatment.
Funder
Tianjin Municipal Education Commission Scientific Research Program Project
Tianjin Science and Technology Plan Project of the Open Bidding for Selecting the Best Candidates
Publisher
Springer Science and Business Media LLC
Reference26 articles.
1. Mármol I, Sánchez-de-Diego C, Pradilla Dieste A, et al. Colorectal carcinoma: a general overview and future perspectives in colorectal cancer. Int J Mol Sci. 2017;18(1):197.
2. Xiusen Q, Wentai G, Wuteng C, et al. Advances in study of colorectal mucinous adenocarcinoma. Chin J Bases Clin Gen Surg. 2020;27(7):906–11.
3. Pei Xiaoyue Hu, Ling BL, et al. Clinicopathological and immunohistochemical features in different histological types of colorectal carcinoma. J Clin Pathol Res. 2020;40(8):1941–8.
4. Liu R, et al. AIMIC: deep learning for microscopic image classification. Comput Methods Programs Biomed. 2022;226: 107162.
5. Jiabao Z, Zhiyong X. Gland and colonoscopy segmentation method combining self-attention and convolutional neural network. Laser Optoelectron Progr. 2023;60(02):291–9.