Cancer diagnosis based on laser-induced breakdown spectroscopy with bagging-voting fusion model

Abstract

Advances in cancer diagnostics play a pivotal role in increasing early detection of cancer. Integrating laser-induced breakdown spectroscopy (LIBS) with machine learning algorithms has attracted wide interest in cancer diagnosis. However, using a single model`s efficacy is limited by algorithm principles, making it challenging to meet the comprehensive needs of cancer diagnosis. Here, we demonstrate a bagging-voting fusion (BVF) algorithm for the detection and identification of multiple types of cancer. In the BVF model of this paper, support vector machine (SVM), artificial neural network (ANN), k-nearest neighbors (KNN), quadratic discriminant analysis (QDA), and random forest (RF) models, which have relatively small homogeneity to obtain more comprehensive decision boundaries, are fused at both the training and decision levels. LIBS spectral data was collected from four types of serum samples, including liver cancer, lung cancer, esophageal cancer, and healthy control. LIBS detection was conducted on the samples, which were directly dropped onto ordered microarray silicon substrates and dried. The results showed that the BVF model achieved an accuracy of 92.53 % and a recall of 92.92 % across the four types of serum, outperforming the best single machine-learning model (SVM: accuracy 75.86 %, recall 77.50 %). Moreover, the BVF model with manual line selection feature extraction required only 140 s for a single detection and identification. In conclusion, the aforementioned results demonstrated that LIBS with BVF has excellent performance in detecting a multitude of cancers, and is expected to provide a new method for efficient and accurate cancer diagnosis.