Answers are grounded in this paper and cite their sources.
Classification models using machine learning achieved 99% identification accuracy in chondrosarcoma diagnosis, suggesting LIBS synergy may enhance clinical assessment.
Chondrosarcoma (CS) is a kind of chondrogenic tumor, and it is the second most common malignant bone tumor. At present, histopathological examination combined with imaging examination is generally used for the diagnosis of CS. In recent years, laser-induced breakdown spectroscopy (LIBS) has made great progress in tumor detection and has become a promising tool for cancer diagnosis. In this work, the method of LIBS combined with machine learning is used to detect CS, including the identification of healthy cartilage tissue and CS tissue, and the grading of low-grade CS(LG-CS)and high-grade CS (HG-CS). Firstly, the LIBS spectra of healthy, LG-CS and HG-CS tissues were collected and the spectral data were preprocessed. Then, the characteristic spectral lines of some elements and molecular bands in the three kinds of tissues were analyzed. Finally, support vector machine (SVM), convolutional neural network (CNN) and the combination of random forest and CNN (RF-CNN) were used to establish classification models respectively. The results show that the performance of RF-CNN classifier is the best, and the identification accuracy and grading accuracy can reach 99% and 96%, respectively. The above results prove that LIBS combined with machine learning is an effective method to diagnose CS, and it is expected to assist in clinical diagnosis in the future.
No takes yet. Share an insight, caveat, or question.
Xu et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: