| Abstrakt: |
Squamous cell carcinoma (SCC) is one of the most common as well as deadliest kinds of laryngeal cancer. The precise and early identification of laryngeal cancer plays a pivotal role in reducing mortality and maintaining laryngeal structure and vocal fold function. But small variations in the laryngeal tissues may go undetected by the human eye, which leads to misdiagnosis. In this study, we devise an early laryngeal cancer classification framework using the hybridization of deep and handcrafted features. The deep features of the DenseNet 201 using transfer learning and handcrafted features using Local Binary Pattern (LBP) and First-order statistics (STAT)s are extracted from the endoscopic narrowband images of the larynx and fused together which resulted in more representative features. From these hybridized features, the optimal features are selected by the Recursive Feature Elimination with Random Forest (RFE- RF) method. Firstly, the selected hybrid features are classified with three effective Machine Learning classifiers like Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbor (k-NN), and the results are compared with a stacking-based ensemble learning classification method using (SVM), (RF) and (k-NN) in order to distinguish early-stage SCC tissues, healthy tissues and precancerous tissues. The combination of hybrid features, effective feature selection, and an Ensemble classifier produced a median categorization recall of 99.5% on a standard dataset, which surpasses the state of the art (recall = 98%). [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink