EUVIMEDEUVIMED entdecken
Crossref

Hybrid of Deep Feature Extraction and Machine Learning Ensembles for Imbalanced Skin Cancer Datasets

Neetu Verma, Ranvijay, Dharmendra Kumar Yadav

Experimental Dermatology · 2024-12 · 33 (12)

DOI: 10.1111/exd.70020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Experimental Dermatology, online erschienen am 23.12.2024. Verfasst von Neetu Verma und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science & Engineering Department, MNNIT Allahabad, Prayagraj, Uttar Pradesh, India. Hauptthemen laut MEDLINE: Skin Neoplasms, Deep Learning. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 43 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer remains one of the most common and deadly forms of cancer, necessitating accurate and early diagnosis to improve patient outcomes. In order to improve classification performance on unbalanced datasets, this study proposes a distinctive approach for classifying skin cancer that utilises both machine learning (ML) and deep learning (DL) methods. We extract features from three different DL models (DenseNet201, Xception, Mobilenet) and concatenate them to create an extensive feature set. Afterwards, several ML algorithms are given these features to be classified. We utilise ensemble techniques to aggregate the predictions from several classifiers, significantly improving the classification's resilience and accuracy. To address the problem of data imbalance, we employ class weight updates and data augmentation strategies to ensure that the model is thoroughly trained across all classes. Our method shows significant improvements over recent existing approaches in terms of classification accuracy and generalisation. The proposed model successfully received 98.7%, 94.4% accuracy, 99%, 95%, precision, 99%, 96% recall, 99%, and 96% f1‐score for the HAM10000 and ISIC datasets, respectively. This study offers dermatologists and other medical practitioners' valuable insights into the classification of skin cancer.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin NeoplasmsDeep LearningHumansMachine LearningAlgorithmsDatabases, Factual

Stichwörter der Autor:innen

data balancingensemble learningfeature concatenationfeatures extractionskin cancer

Autor:innen und Institutionen

  • Computer Science & Engineering Department, MNNIT Allahabad, Prayagraj, Uttar Pradesh, India.

Zitieren

APA

Verma, N., Ranvijay, & Yadav, D. K. (2024). Hybrid of Deep Feature Extraction and Machine Learning Ensembles for Imbalanced Skin Cancer Datasets. Experimental Dermatology, 33(12). https://doi.org/10.1111/exd.70020

Vancouver

Verma N, Ranvijay, Yadav DK. Hybrid of Deep Feature Extraction and Machine Learning Ensembles for Imbalanced Skin Cancer Datasets. Experimental Dermatology. 2024;33(12). doi:10.1111/exd.70020

BibTeX
@article{Verma2024,
  author = {Verma, Neetu and Ranvijay and Yadav, Dharmendra Kumar},
  title = {Hybrid of Deep Feature Extraction and Machine Learning Ensembles for Imbalanced Skin Cancer Datasets},
  journal = {Experimental Dermatology},
  year = {2024},
  volume = {33},
  number = {12},
  doi = {10.1111/exd.70020}
}
Kostenlos starten →