EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods

Bernardo Petracchi iD, Emanuele Torti iD, Elisa Marenzi, Francesco Leporati

Sensors · 2024

DOI: 10.3390/s24051399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Bernardo Petracchi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical, Computer and Biomedical Engineering, University of Pavia, I-27100 Pavia, Italy. Hauptthemen laut MEDLINE: Algorithms, Skin Neoplasms. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral imaging (HSI) has become a very compelling technique in different scientific areas; indeed, many researchers use it in the fields of remote sensing, agriculture, forensics, and medicine. In the latter, HSI plays a crucial role as a diagnostic support and for surgery guidance. However, the computational effort in elaborating hyperspectral data is not trivial. Furthermore, the demand for detecting diseases in a short time is undeniable. In this paper, we take up this challenge by parallelizing three machine-learning methods among those that are the most intensively used: Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGB) algorithms using the Compute Unified Device Architecture (CUDA) to accelerate the classification of hyperspectral skin cancer images. They all showed a good performance in HS image classification, in particular when the size of the dataset is limited, as demonstrated in the literature. We illustrate the parallelization techniques adopted for each approach, highlighting the suitability of Graphical Processing Units (GPUs) to this aim. Experimental results show that parallel SVM and XGB algorithms significantly improve the classification times in comparison with their serial counterparts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsSkin NeoplasmsHumansMachine LearningHyperspectral ImagingAccelerationSupport Vector Machine

Stichwörter der Autor:innen

GPUeXtreme gradient boostinghyperspectral imagingmachine learningrandom forestsupport vector machine

Autor:innen und Institutionen

  • Department of Electrical, Computer and Biomedical Engineering, University of Pavia, I-27100 Pavia, Italy.

ORCID-Profile: Bernardo Petracchi, Emanuele Torti

Zitieren

APA

Petracchi, B., Torti, E., Marenzi, E., & Leporati, F. (2024). Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods. Sensors. https://doi.org/10.3390/s24051399

Vancouver

Petracchi B, Torti E, Marenzi E, Leporati F. Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods. Sensors. 2024. doi:10.3390/s24051399

BibTeX
@article{Petracchi2024,
  author = {Petracchi, Bernardo and Torti, Emanuele and Marenzi, Elisa and Leporati, Francesco},
  title = {Acceleration of Hyperspectral Skin Cancer Image Classification through Parallel Machine-Learning Methods},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24051399}
}
Kostenlos starten →