Novel Method for Border Irregularity Assessment in Dermoscopic Color Images
Background. One of the most important lesion features predicting malignancy is border irregularity. Accurate assessment of irregular borders is clinically important due to significantly different occurrence in benign and malignant skin lesions. Method. In this research, we present a new approach for...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2015-01-01
|
| Series: | Computational and Mathematical Methods in Medicine |
| Online Access: | http://dx.doi.org/10.1155/2015/496202 |
| Summary: | Background. One of the most important lesion features predicting malignancy is border irregularity. Accurate assessment of irregular borders is clinically important due to significantly different occurrence in benign and malignant skin lesions. Method. In this research, we present a new approach for the detection of border irregularities, as one of the major parameters in a widely used diagnostic algorithm the ABCD rule of dermoscopy. The proposed work is focused on designing an efficient automatic algorithm containing the following steps: image enhancement, lesion segmentation, borderline calculation, and irregularities detection. The challenge lies in determining the exact borderline. For solving this problem we have implemented a new method based on lesion rotation and borderline division. Results. The algorithm has been tested on 350 dermoscopic images and achieved accuracy of 92% indicating that the proposed computational approach captured most of the irregularities and provides reliable information for effective skin mole examination. Compared to the state of the art, we obtained improved classification results. Conclusions. The current study suggests that computer-aided system is a practical tool for dermoscopic image assessment and could be recommended for both research and clinical applications. The proposed algorithm can be applied in different fields of medical image analysis including, for example, CT and MRI images. |
|---|---|
| ISSN: | 1748-670X 1748-6718 |