EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images

Amin Tajerian iD, Mohsen Kazemian, Mohammad Tajerian, Ava Akhavan Malayeri

PLOS ONE · 14.04.2023 · 18 (4) · e0284437

DOI: 10.1371/journal.pone.0284437 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 14.04.2023. Verfasst von Amin Tajerian und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, Arak University of Medical Sciences, Arak, Iran. Hauptthemen laut MEDLINE: Skin Neoplasms, Melanoma, Basal Cell Carcinoma, Skin Diseases. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Arak University of Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Skin cancer is the most common cancer in the United States. Current estimates are that one in five Americans will develop skin cancer in their lifetime. A skin cancer diagnosis is challenging for dermatologists requiring a biopsy from the lesion and histopathological examinations. In this article, we used the HAM10000 dataset to develop a web application that classifies skin cancer lesions.

Method

This article presents a methodological approach that utilizes dermoscopy images from the HAM10000 dataset, a collection of 10015 dermatoscopic images collected over 20 years from two different sites, to improve the diagnosis of pigmented skin lesions. The study design involves image pre-processing, which includes labelling, resizing, and data augmentation techniques to increase the instances of the dataset. Transfer learning, a machine learning technique, was used to create a model architecture that includes EfficientNET-B1, a variant of the baseline model EfficientNET-B0, with a global average pooling 2D layer and a softmax layer with 7 nodes added on top. The results of the study offer a promising method for dermatologists to improve their diagnosis of pigmented skin lesions.

Results

The model performs best in detecting melanocytic nevi lesions with an F1 score of 0.93. The F1 score for Actinic Keratosis, Basal Cell Carcinoma, Benign Keratosis, Dermatofibroma, Melanoma, and Vascular lesions was consecutively 0.63, 0.72, 0.70, 0.54, 0.58, and 0.80.

Conclusions

We classified seven distinct skin lesions in the HAM10000 dataset with an EfficientNet model reaching an accuracy of 84.3%, which provides a promising outlook for further development of more accurate models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin NeoplasmsMelanomaBasal Cell CarcinomaSkin DiseasesKeratosis, ActinicPigmentation DisordersHumansMachine LearningCell DifferentiationDermoscopy

Autor:innen und Institutionen

  • School of Medicine, Arak University of Medical Sciences, Arak, Iran.
  • School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran.

ORCID-Profile: Amin Tajerian

Förderung

  • Arak University of Medical Sciences

Zitieren

APA

Tajerian, A., Kazemian, M., Tajerian, M., & Akhavan Malayeri, A. (2023). Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images. PLOS ONE, 18(4), e0284437. https://doi.org/10.1371/journal.pone.0284437

Vancouver

Tajerian A, Kazemian M, Tajerian M, Akhavan Malayeri A. Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images. PLOS ONE. 2023;18(4):e0284437. doi:10.1371/journal.pone.0284437

BibTeX
@article{Tajerian2023,
  author = {Tajerian, Amin and Kazemian, Mohsen and Tajerian, Mohammad and Akhavan Malayeri, Ava},
  title = {Design and validation of a new machine-learning-based diagnostic tool for the differentiation of dermatoscopic skin cancer images},
  journal = {PLOS ONE},
  year = {2023},
  volume = {18},
  number = {4},
  pages = {e0284437},
  doi = {10.1371/journal.pone.0284437}
}
Kostenlos starten →