Abstract
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.
Highlights
The skin is the body’s largest organ that covers the entire body and protects it against infection, sunlight, and injury
Malignant melanoma originates in pigment producing cells called melanocytes, which derive from neural crest [1,2,3]
The proposed and implemented algorithm for the diagnosis of the pigmented skin lesion has been tested on dermoscopic images provided by two university hospitals (University of Naples, Italy, and University of Graz, Austria), where they were stored on a CD-ROM in JPEG format [1] and by a private database
Summary
The skin is the body’s largest organ that covers the entire body and protects it against infection, sunlight, and injury. The most malignant type of skin cancer is melanoma. 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. 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 challenge lies in determining the exact borderline For solving this problem we have implemented a new method based on lesion rotation and borderline division. 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. The proposed algorithm can be applied in different fields of medical image analysis including, for example, CT and MRI images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
