Using Neural Networks for Diagnosing in Dermatology

Margarita Bobrova, Maksim Taranik, Georgy Kopanitsa

Research output: Contribution to journalArticle

Abstract

The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9%. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64%. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.

Original languageEnglish
Pages (from-to)211-216
Number of pages6
JournalStudies in Health Technology and Informatics
Volume261
Publication statusPublished - 1 Jan 2019
Externally publishedYes

Fingerprint

Pityriasis Rosea
Pityriasis Rubra Pilaris
Dermatitis
Dermatology
Boidae
Seborrheic Dermatitis
Lichen Planus
Psoriasis
Skin Diseases
Libraries
Language
Neural networks
Skin

Keywords

  • dermatology
  • Keras
  • Neural networks

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Using Neural Networks for Diagnosing in Dermatology. / Bobrova, Margarita; Taranik, Maksim; Kopanitsa, Georgy.

In: Studies in Health Technology and Informatics, Vol. 261, 01.01.2019, p. 211-216.

Research output: Contribution to journalArticle

Bobrova, Margarita ; Taranik, Maksim ; Kopanitsa, Georgy. / Using Neural Networks for Diagnosing in Dermatology. In: Studies in Health Technology and Informatics. 2019 ; Vol. 261. pp. 211-216.
@article{50f140fc82cf47a3bced9fbf07e4a5e6,
title = "Using Neural Networks for Diagnosing in Dermatology",
abstract = "The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9{\%}. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64{\%}. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.",
keywords = "dermatology, Keras, Neural networks",
author = "Margarita Bobrova and Maksim Taranik and Georgy Kopanitsa",
year = "2019",
month = "1",
day = "1",
language = "English",
volume = "261",
pages = "211--216",
journal = "Studies in Health Technology and Informatics",
issn = "0926-9630",
publisher = "IOS Press",

}

TY - JOUR

T1 - Using Neural Networks for Diagnosing in Dermatology

AU - Bobrova, Margarita

AU - Taranik, Maksim

AU - Kopanitsa, Georgy

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9%. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64%. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.

AB - The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9%. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64%. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.

KW - dermatology

KW - Keras

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85067093405&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067093405&partnerID=8YFLogxK

M3 - Article

C2 - 31156118

AN - SCOPUS:85067093405

VL - 261

SP - 211

EP - 216

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

SN - 0926-9630

ER -