AN ENSEMBLE TEMPLATE MATCHING AND CONTENT-BASED IMAGE RETRIEVAL SCHEME TOWARDS EARLY STAGE DETECTION OF MELANOMA
| Autor: | Theophilos Sakkis, George Nikiforidis, George Sakellaropoulos, Pantelis A. Asvestas, Konstantinos Perakis, Dionisis Cavouras, Spyros Mantzouratos, Spiros Kostopoulos, Konstantinos Sidiropoulos, Dimitris Glotsos, Eirini-Konstantina Nikolatou, Christos Konstandinou, George Xenogiannopoulos |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Decision support system
Acoustics and Ultrasonics Computer science Materials Science (miscellaneous) General Mathematics Sample (statistics) computer.software_genre Content-based image retrieval 030207 dermatology & venereal diseases 03 medical and health sciences 0302 clinical medicine Radiology Nuclear Medicine and imaging 030212 general & internal medicine Cluster analysis Instrumentation lcsh:R5-920 Template matching lcsh:Mathematics Second opinion Photography Mutual information lcsh:QA1-939 template matching content-based image retrieval decision support system melanoma diagnosis self-skin examination Signal Processing Computer Vision and Pattern Recognition Data mining lcsh:Medicine (General) computer Biotechnology |
| Zdroj: | Image Analysis and Stereology, Vol 35, Iss 3, Pp 137-148 (2016) |
| ISSN: | 1854-5165 1580-3139 |
| Popis: | Malignant melanoma represents the most dangerous type of skin cancer. In this study we present an ensemble classification scheme, employing the mutual information, the cross-correlation and the clustering based on proximity of image features methods, for early stage assessment of melanomas on plain photography images. The proposed scheme performs two main operations. First, it retrieves the most similar, to the unknown case, image samples from an available image database with verified benign moles and malignant melanoma cases. Second, it provides an automated estimation regarding the nature of the unknown image sample based on the majority of the most similar images retrieved from the available database. Clinical material comprised 75 melanoma and 75 benign plain photography images collected from publicly available dermatological atlases. Results showed that the ensemble scheme outperformed all other methods tested in terms of accuracy with 94.9±1.5%, following an external cross-validation evaluation methodology. The proposed scheme may benefit patients by providing a second opinion consultation during the self-skin examination process and the physician by providing a second opinion estimation regarding the nature of suspicious moles that may assist towards decision making especially for ambiguous cases, safeguarding, in this way from potential diagnostic misinterpretations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|