MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS
Skin diseases diagnosed with dermatoscopy are becoming more and more common. The use of computerized diagnostic systems becomes extremely effective. Non-invasive methods of diagnostics, such as deep neural networks, are an increasingly common tool studied by scientists. The article presents an over...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Lublin University of Technology
2022-06-01
|
| Series: | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| Subjects: | |
| Online Access: | https://ph.pollub.pl/index.php/iapgos/article/view/2963 |
| _version_ | 1818531189465546752 |
|---|---|
| author | Magdalena Michalska |
| author_facet | Magdalena Michalska |
| author_sort | Magdalena Michalska |
| collection | DOAJ |
| description |
Skin diseases diagnosed with dermatoscopy are becoming more and more common. The use of computerized diagnostic systems becomes extremely effective. Non-invasive methods of diagnostics, such as deep neural networks, are an increasingly common tool studied by scientists. The article presents an overview of selected main issues related to the multi-class classification process: the stage of database selection, initial image processing, selection of the learning data set, classification tools, network training stage and obtaining final results. The described actions were implemented using available deep neural networks. The article pay attention to the final results of available models, such as effectiveness, specificity, classification accuracy for different numbers of classes and available data sets.
|
| first_indexed | 2024-12-11T17:29:13Z |
| format | Article |
| id | doaj.art-9e7a7b1f7d904ece9a1bbddd87df42b4 |
| institution | Directory Open Access Journal |
| issn | 2083-0157 2391-6761 |
| language | English |
| last_indexed | 2024-12-11T17:29:13Z |
| publishDate | 2022-06-01 |
| publisher | Lublin University of Technology |
| record_format | Article |
| series | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| spelling | doaj.art-9e7a7b1f7d904ece9a1bbddd87df42b42022-12-22T00:56:53ZengLublin University of TechnologyInformatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska2083-01572391-67612022-06-0112210.35784/iapgos.2963MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKSMagdalena Michalska0Lublin University of Technology, Department of Electronics and Information Technology Skin diseases diagnosed with dermatoscopy are becoming more and more common. The use of computerized diagnostic systems becomes extremely effective. Non-invasive methods of diagnostics, such as deep neural networks, are an increasingly common tool studied by scientists. The article presents an overview of selected main issues related to the multi-class classification process: the stage of database selection, initial image processing, selection of the learning data set, classification tools, network training stage and obtaining final results. The described actions were implemented using available deep neural networks. The article pay attention to the final results of available models, such as effectiveness, specificity, classification accuracy for different numbers of classes and available data sets. https://ph.pollub.pl/index.php/iapgos/article/view/2963dermatoscopic imagesmulticlass classificationskin lesionsdeep neural networks |
| spellingShingle | Magdalena Michalska MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska dermatoscopic images multiclass classification skin lesions deep neural networks |
| title | MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS |
| title_full | MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS |
| title_fullStr | MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS |
| title_full_unstemmed | MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS |
| title_short | MULTICLASS SKIN LESS IONS CLASSIFICATION BASED ON DEEP NEURAL NETWORKS |
| title_sort | multiclass skin less ions classification based on deep neural networks |
| topic | dermatoscopic images multiclass classification skin lesions deep neural networks |
| url | https://ph.pollub.pl/index.php/iapgos/article/view/2963 |
| work_keys_str_mv | AT magdalenamichalska multiclassskinlessionsclassificationbasedondeepneuralnetworks |