The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions
Dermatoscopic images are also increasingly used to train artificial neural networks for the future to provide fully automatic diagnostic systems capable of determining the type of pigmented skin lesion. Therefore, fractal analysis was used in this study to measure the irregularity of pigmented skin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/10/1773 |
| _version_ | 1797514889381543936 |
|---|---|
| author | Monika Styła Tomasz Giżewski |
| author_facet | Monika Styła Tomasz Giżewski |
| author_sort | Monika Styła |
| collection | DOAJ |
| description | Dermatoscopic images are also increasingly used to train artificial neural networks for the future to provide fully automatic diagnostic systems capable of determining the type of pigmented skin lesion. Therefore, fractal analysis was used in this study to measure the irregularity of pigmented skin lesion surfaces. This paper presents selected results from individual stages of preliminary processing of the dermatoscopic image on pigmented skin lesion, in which fractal analysis was used and referred to the effectiveness of classification by fuzzy or statistical methods. Classification of the first unsupervised stage was performed using the method of analysis of scatter graphs and the fuzzy method using the Kohonen network. The results of the Kohonen network learning process with an input vector consisting of eight elements prove that neuronal activation requires a larger learning set with greater differentiation. For the same training conditions, the final results are at a higher level and can be classified as weaker. Statistics of factor analysis were proposed, allowing for the reduction in variables, and the directions of further studies were indicated. |
| first_indexed | 2024-03-10T06:37:55Z |
| format | Article |
| id | doaj.art-c39692591bce49f9ae8ceeb2476253bc |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T06:37:55Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-c39692591bce49f9ae8ceeb2476253bc2023-11-22T17:56:32ZengMDPI AGDiagnostics2075-44182021-09-011110177310.3390/diagnostics11101773The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin LesionsMonika Styła0Tomasz Giżewski1Chair and Department of Biophysics, Medical University of Lublin, 20-090 Lublin, PolandDepartment of Electrical Engineering and Electrotechnologies, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, 20-618 Lublin, PolandDermatoscopic images are also increasingly used to train artificial neural networks for the future to provide fully automatic diagnostic systems capable of determining the type of pigmented skin lesion. Therefore, fractal analysis was used in this study to measure the irregularity of pigmented skin lesion surfaces. This paper presents selected results from individual stages of preliminary processing of the dermatoscopic image on pigmented skin lesion, in which fractal analysis was used and referred to the effectiveness of classification by fuzzy or statistical methods. Classification of the first unsupervised stage was performed using the method of analysis of scatter graphs and the fuzzy method using the Kohonen network. The results of the Kohonen network learning process with an input vector consisting of eight elements prove that neuronal activation requires a larger learning set with greater differentiation. For the same training conditions, the final results are at a higher level and can be classified as weaker. Statistics of factor analysis were proposed, allowing for the reduction in variables, and the directions of further studies were indicated.https://www.mdpi.com/2075-4418/11/10/1773dermatologyclassificationspigmented skin lesionsfractal analysis |
| spellingShingle | Monika Styła Tomasz Giżewski The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions Diagnostics dermatology classifications pigmented skin lesions fractal analysis |
| title | The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions |
| title_full | The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions |
| title_fullStr | The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions |
| title_full_unstemmed | The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions |
| title_short | The Study of Usefulness of a Set of Fractal Parameters to Build Classes of Disease Units Based on Images of Pigmented Skin Lesions |
| title_sort | study of usefulness of a set of fractal parameters to build classes of disease units based on images of pigmented skin lesions |
| topic | dermatology classifications pigmented skin lesions fractal analysis |
| url | https://www.mdpi.com/2075-4418/11/10/1773 |
| work_keys_str_mv | AT monikastyła thestudyofusefulnessofasetoffractalparameterstobuildclassesofdiseaseunitsbasedonimagesofpigmentedskinlesions AT tomaszgizewski thestudyofusefulnessofasetoffractalparameterstobuildclassesofdiseaseunitsbasedonimagesofpigmentedskinlesions AT monikastyła studyofusefulnessofasetoffractalparameterstobuildclassesofdiseaseunitsbasedonimagesofpigmentedskinlesions AT tomaszgizewski studyofusefulnessofasetoffractalparameterstobuildclassesofdiseaseunitsbasedonimagesofpigmentedskinlesions |