A Novel Texture Analysis Method Based on Reverse Biorthogonal Wavelet and Co-Occurrence Matrix Applied for Classification of Hepatocellular Carcinoma and Hepatic Hemangioma
| Autor: | Jia-Jun Qiu, Min Wang, Yue Wu, Bei Hui, Lin Ji, Jia Chen |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0301 basic medicine
Hepatic Hemangioma Materials science business.industry Health Informatics Pattern recognition medicine.disease Texture (geology) 030218 nuclear medicine & medical imaging 03 medical and health sciences Co-occurrence matrix 030104 developmental biology 0302 clinical medicine Hepatocellular carcinoma medicine Radiology Nuclear Medicine and imaging Artificial intelligence business Biorthogonal wavelet Analysis method |
| Zdroj: | Journal of Medical Imaging and Health Informatics. 8:1835-1843 |
| ISSN: | 2156-7018 |
| Popis: | Purpose: To explore the feasibility of classifying hepatocellular carcinoma (HCC) and hepatic hemangioma (HEM) using texture features of non-enhanced computed tomography (CT) images, especially to investigate the effectiveness of a novel texture analysis method based on the combination of wavelet and co-occurrence matrix. Methods: 269 patients were retrospectively analyzed, including 129 HCCs and 140 HEMs. We cropped tumor regions of interest (ROIs) on non-enhanced CT images, and then used four texture analysis methods to extract quantitative data of the ROIs: gray-level histogram (GLH), gray-level co-occurrence matrix (GLCM), reverse biorthogonal wavelet transform (RBWT), and reverse biorthogonal wavelet co-occurrence matrix (RBCM). The RBCM was a novel method proposed in this study that combined wavelet transform and co-occurrence matrix. It discretized wavelet coefficient matrices based on the statistical characteristics of the training set. Thus, four sets of texture features were obtained. We then conducted classification studies using support vector machine on each set of texture features. 10-fold cross training and testing were used in the classifications, and their results were evaluated and compared. In addition, we tested the significant differences in the texture features of the RBCM method and explored the possible relationships between textures and lesion types. Results: The RBCM method achieved the best classification performance: its average accuracy was 82.14%; its average AUC (area under the receiver operating characteristic curve) was 0.8423. In addition, using the methods of GLH, GLCM, and RBWT, their average accuracies were 75.81%, 78.79%, and 78.8%, respectively. Conclusions: It indicates that the developed texture analysis methods are rewarding for computer-aided diagnosis of HCC and HEM based on non-enhanced CT images. Furthermore, the distinguishing ability of the proposed RBCM method is more pronounced. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|