2019
DOI: 10.17586/2226-1494-2019-19-2-333-338
|View full text |Cite
|
Sign up to set email alerts
|

Image classification of primary morphological elements of skin lesions

Abstract: Рассмотрена задача классификации изображений методами глубокого обучения для выявления первичных морфологических элементов кожной сыпи. Одним из перспективных направлений повышения качества медицинской помощи больным дерматовенерологического профиля является создание информационно-диагностических систем и систем поддержки принятия решений. В качестве одного из компонентов таких систем может выступать модуль автоматического определения первичных элементов сыпи на изображениях пораженных участков кожи. Предложен… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 7 publications
0
1
0
Order By: Relevance
“…In deep learning methods for skin lesion classification, primary morphological elements are a module in the automatic detection system. The result of this classification was the 76.00% accuracy for 5 classes of the primary morphological elements and the 81.67% accuracy for 3 classes [18]. In our study, dilation and erosion in the morphological approach are applied for removing unwanted small objects and connecting dotted lines in skin disease areas.…”
Section: Introductionmentioning
confidence: 86%
“…In deep learning methods for skin lesion classification, primary morphological elements are a module in the automatic detection system. The result of this classification was the 76.00% accuracy for 5 classes of the primary morphological elements and the 81.67% accuracy for 3 classes [18]. In our study, dilation and erosion in the morphological approach are applied for removing unwanted small objects and connecting dotted lines in skin disease areas.…”
Section: Introductionmentioning
confidence: 86%