Research on the evaluation of rectal function after LAR based on CEEMDAN‐Fast‐ICA algorithm

• Published in: IET science, measurement & technology Vol. 17; no. 4; pp. 167 - 182
• Main Authors: Zan, Peng, Zhao, Yutong, Zhong, Hua, Yu, Yang, Wang, Yuanbo, Shao, Yijia, Li, Chunyong
• Format: Journal Article
• Language: English
• Published: Wiley 01.06.2023
• Subjects: CEEMDAN; FAST‐ICA; multi‐sensor information fusion; PSO‐SVM; rectal function assessment
• ISSN: 1751-8822; 1751-8830
• DOI: 10.1049/smt2.12140

Rectal cancer is one of the most common lower gastrointestinal diseases worldwide. Currently, the common treatment is low anterior resection (LAR) of the rectum, which preserves the anus of the patient. However, it is easy to cause low anterior resection syndrome after surgery, which has a significant negative impact on the life of patients, and there is no unified evaluation standard for postoperative rectal function. To solve this problem, a multi‐sensor fusion rectal information acquisition system is designed in this paper, and a rectal signal processing method is proposed to theoretically evaluate the rectal function of postoperative patients. The method uses the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the one‐dimensional rectal signal to solve the underdetermined ICA problem, uses the Fast independent component analysis (Fast‐ICA) to separate the pure rectal signal, uses the wavelet packet to extract features, and uses the particle swarm optimization optimizes support vector machine (PSO‐SVM) to classify and evaluate postoperative function. According to the experimental results, the rectal signal preprocessing effect is good, the evaluation prediction rate is 99.5565%, and the algorithm classification results are accurate, which provides a certain preliminary theoretical basis and reference value for the evaluation of rectal function after LAR. In this work, aiming at the problems in the diagnosis of rectal function after low anterior resection of rectal cancer, our team designed a multi‐sensor fusion rectal information acquisition system. Based on this system, a rectal signal processing method based on CEEMDAN fast ICA is proposed. The method uses CEEMDAN to decompose the one‐dimensional rectal signal to solve the underdetermined ICA problem, uses the Fast‐ICA algorithm to separate the pure rectal signal, uses the wavelet packet to extract features, and uses the PSO‐SVM pattern recognition to achieve postoperative functional evaluation. According to the experimental results, the accuracy of rectal function evaluation based on this system was 99.5565%. This method can obtain the dynamic characteristics of rectum and realize the prediction and diagnosis of rectal function after operation. It is helpful for the recovery of rectal function in patients undergoing low anterior resection for rectal cancer. This study laid a foundation for the diagnosis of rectal dynamics after LAR surgery.