Photo Credit: Tippapatt
Findings underscore the proposed strategy’s potential for advancing diagnostic and prognostic lung most cancers remedy planning and decision-making programs.
Combining probably the most related options from machine studying considerably improves the potential for lung most cancers detection, in accordance with knowledge just lately printed in Heliyon. According to Liangyu Li and colleagues, machine studying presents important potential for lung most cancers detection and allows early prognosis, doubtlessly enhancing affected person outcomes. However, function extraction stays a vital problem in lung most cancers detection. The research mixed the Gray-level co-occurrence matrix (GLCM) with Haralick options and autoencoder methods, which the research group analyzed utilizing supervised machine studying strategies. Support Vector Machine (SVM) Radial Base Function (RBF) and SVM Gaussian demonstrated flawless efficiency, with SVM polynomial reaching 99.89% accuracy utilizing GLCM with autoencoder, Haralick, and autoencoder options. SVM Gaussian achieved 99.56% accuracy, and SVM RBF achieved 99.35% accuracy utilizing GLCM with Haralick options. The researchers recommend that these findings underscore the proposed strategy’s potential for advancing diagnostic and prognostic lung most cancers remedy planning and decision-making programs.
https://www.physiciansweekly.com/hybrid-features-machine-learning-optimize-lung-cancer-detection/