Support vector machines for oral lesion classification

A. Chodorowski1, T. Gustavsson1, U. Mattsson2
1Cbalmem University of Technology, Gothenburg, Sweden
2Central Hospital, Karlstad, Sweden

Tóm tắt

We investigate support vector machines (SVM) in the context of oral lesion classification using digital color images as input. Two common lesions of similar visual appearance to the human observer were evaluated: oral leukoplakia, which is a potentially pre-cancerous lesion, and oral lichenoid reactions (with subclasses of atrophic, plaqueformed and reticular reactions), which are usually harmless lesions. In total, 89% (212 out of 238, 5-fold CV) were correctly classified in a two-class problem (precancerous vs. non-pre-cancerous) and 78% (61 out of 78, hold-out) into four classes (complete classification). The proposed method can be used as a decision support tool in CADx systems for oral lesion classification and detection of potentially pre-cancerous lesions.

Từ khóa

#Support vector machines #Support vector machine classification #Lesions #Color #Humans #Atrophy #Biomedical imaging #Hospitals #Risk management #Medical services

Tài liệu tham khảo

cortes, 1995, Prediction of generalization ability in learning machines 10.1007/BF00994018 10.1007/978-1-4757-2440-0 schölkopf, 1999, Kernel-Dependent Support Vector Error Bounds, Ninth International conference on Artificial Neural Networks, 575 weston, 2000, Feature selection for SVMs, Advances in neural information processing systems, 13 veropoulos, 1999, Controlling the sensitivity of Support Vector Machines, IJCAI, 55 a, 2000, Pattern Recognition Methods for Oral Lesion Classification using Digital Color Images chapelle, 2000, Model Selection for Support Vector Machines, Advances in neural information processing systems, 12