Computer-Aided Diagnosis in Hysteroscopic Imaging
| Autor: | Neofytou, Marios S., Tanos, Vasilios, Constantinou, Ioannis P., Kyriacou, Efthyvoulos C., Pattichis, Marios S., Pattichis, Constantinos S. |
|---|---|
| Přispěvatelé: | Pattichis, Constantinos S. [0000-0003-1271-8151], Pattichis, Marios S. [0000-0002-1574-1827], Kyriacou, Efthyvoulos C. [0000-0002-4589-519X] |
| Rok vydání: | 2015 |
| Předmět: |
Computer science
Computer-aided hysteroscopy Diseases CAD HSL and HSV User-Computer Interface Probabilistic neural network Endometrial cancer Health Information Management Image texture middle aged Computer vision Texture features receiver operating characteristic Classification (of information) Classification rates Textures Middle Aged Classification Computer Science Applications Computer aided diagnosis female Female Neural networks Biotechnology Feature extraction computer interface Hysteroscopy Computer-aided diagnostic (CAD) Probabilistic neural networks Image Interpretation Computer-Assisted Humans human procedures Electrical and Electronic Engineering Gray level differences Support vector machines uterus business.industry Uterus Endoscopy computer assisted diagnosis Pattern recognition Endometrial Neoplasms Support vector machine Support vector machine (SVMs) ROC Curve Computer-aided diagnosis Computer aided diagnostics RGB color model pathology Artificial intelligence business |
| Zdroj: | IEEE Journal of Biomedical and Health Informatics IEEE J.Biomedical Health Informat. |
| ISSN: | 2168-2208 2168-2194 |
| DOI: | 10.1109/jbhi.2014.2332760 |
| Popis: | The paper presents the development of a computeraided diagnostic (CAD) system for the early detection of endometrial cancer. The proposed CAD system supports reproducibility through texture feature standardization, standardized multifeature selection, and provides physicians with comparative distributions of the extracted texture features. The CAD system was validated using 516 regions of interest (ROIs) extracted from 52 subjects. The ROIs were equally distributed among normal and abnormal cases. To support reproducibility, the RGB images were first gamma corrected and then converted into HSV and YCrCb. From each channel of the gamma-corrected YCrCb, HSV, and RGB color systems, we extracted the following texture features: 1) statistical features (SFs), 2) spatial gray-level dependence matrices (SGLDM), and 3) gray-level difference statistics (GLDS). The texture features were then used as inputs with support vector machines (SVMs) and the probabilistic neural network (PNN) classifiers. After accounting for multiple comparisons, texture features extracted from abnormal ROIs were found to be significantly different than texture features extracted from normal ROIs. Compared to texture features extracted from normal ROIs, abnormal ROIs were characterized by lower image intensity, while variance, entropy, and contrast gave higher values. In terms of ROI classification, the best results were achieved by using SF and GLDS features with an SVM classifier. For this combination, the proposed CAD system achieved an 81% correct classification rate. 2168-2194 © 2014 IEEE. 19 3 1129 1136 Cited By :2 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|