Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/545085
Title: | Certain investigations of melanoma classification systems in dermoscopy images using pattern recognition methods |
Researcher: | Sreekesh Namboodiri T |
Guide(s): | Jayachandran A |
Keywords: | Computer Science Computer Science Information Systems Dermoscopy images Engineering and Technology Feature extraction Skin cancer SVM |
University: | Anna University |
Completed Date: | 2021 |
Abstract: | Cancer is one of the biggest threats to human beings and is the second leading cause of death in the world. According to the statistical data from WHO(World Health Organization), cancer caused about 7.6 million people death worldwide in 2015, and it is predicted that the number of deaths caused by cancer will increase and the number will possibly reach 13.1 million in 2030. Based on related research, cancer will become the leading cause of death in next 20 years. Of all the known cancers, in world, skin cancer is the most prevalent form of cancer. It is found that each year, more new cases of skin cancer are diagnosed than all the cases of breast cancers, prostate cancers, lung cancers, and colon cancers diagnosed. newlineIn first work proposes an algorithm to detect the pigment network in dermoscopy images. The proposed algorithm achieves interesting performances on a dataset of 200 dermoscopy images (88 with pigment network): SE = 91.1% and SP = 82.1%. Besides classifying the lesion as with or without pigment network, the system is also capable of providing relevant medical information regarding the location of pigment network, since its output is a network mask that highlights the lines of the network. From this mask, it is also possible to extract the final pigment network region as well as the holes of the mesh. newlineDespite the promising results for network detection, it was not possible to reliably discriminate melanocytic and non-melanocytic lesions. Although the idea of using pigment network to distinguish the two types of lesions is supported by medical findings, the truth is that this structure is not visible in all melanocytic lesions. This means that the decision can not be made using only pigment network as a separating criteria. It seems that expert clinicians use other sources of information when classifying the image as melanocytic or not. newline newline |
Pagination: | xvi. 143p. |
URI: | http://hdl.handle.net/10603/545085 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 195.43 kB | Adobe PDF | View/Open |
02_prelim pages.pdf | 1.2 MB | Adobe PDF | View/Open | |
03_content.pdf | 298.02 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 181.32 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 1.11 MB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 447.9 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 999.57 kB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 1.02 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 806.26 kB | Adobe PDF | View/Open | |
10_annexures.pdf | 174.81 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 117.71 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: