EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Skin Lesion Segmentation with Self-Training

Aleksandra Dzieniszewska iD, Piotr Garbat, Ryszard Piramidowicz iD

Cancers · 11.03.2024 · 16 (6) · 1120

DOI: 10.3390/cancers16061120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 11.03.2024. Verfasst von Aleksandra Dzieniszewska und 2 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Microelectronics and Optoelectronics, Warsaw University of Technology, 00-662 Warsaw, Poland. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Warsaw University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin lesion segmentation plays a key role in the diagnosis of skin cancer; it can be a component in both traditional algorithms and end-to-end approaches. The quality of segmentation directly impacts the accuracy of classification; however, attaining optimal segmentation necessitates a substantial amount of labeled data. Semi-supervised learning allows for employing unlabeled data to enhance the results of the machine learning model. In the case of medical image segmentation, acquiring detailed annotation is time-consuming and costly and requires skilled individuals so the utilization of unlabeled data allows for a significant mitigation of manual segmentation efforts. This study proposes a novel approach to semi-supervised skin lesion segmentation using self-training with a Noisy Student. This approach allows for utilizing large amounts of available unlabeled images. It consists of four steps—first, training the teacher model on labeled data only, then generating pseudo-labels with the teacher model, training the student model on both labeled and pseudo-labeled data, and lastly, training the student* model on pseudo-labels generated with the student model. In this work, we implemented DeepLabV3 architecture as both teacher and student models. As a final result, we achieved a mIoU of 88.0% on the ISIC 2018 dataset and a mIoU of 87.54% on the PH2 dataset. The evaluation of the proposed approach shows that Noisy Student training improves the segmentation performance of neural networks in a skin lesion segmentation task while using only small amounts of labeled data.

Schlagwörter

Stichwörter der Autor:innen

deep learningdermoscopy imagessemi-supervised learningskin cancerskin lesion segmentation

Autor:innen und Institutionen

  • Institute of Microelectronics and Optoelectronics, Warsaw University of Technology, 00-662 Warsaw, Poland.

ORCID-Profile: Aleksandra Dzieniszewska, Ryszard Piramidowicz

Förderung

  • Warsaw University of Technology

Zitieren

APA

Dzieniszewska, A., Garbat, P., & Piramidowicz, R. (2024). Improving Skin Lesion Segmentation with Self-Training. Cancers, 16(6), 1120. https://doi.org/10.3390/cancers16061120

Vancouver

Dzieniszewska A, Garbat P, Piramidowicz R. Improving Skin Lesion Segmentation with Self-Training. Cancers. 2024;16(6):1120. doi:10.3390/cancers16061120

BibTeX
@article{Dzieniszewska2024,
  author = {Dzieniszewska, Aleksandra and Garbat, Piotr and Piramidowicz, Ryszard},
  title = {Improving Skin Lesion Segmentation with Self-Training},
  journal = {Cancers},
  year = {2024},
  volume = {16},
  number = {6},
  pages = {1120},
  doi = {10.3390/cancers16061120}
}
Kostenlos starten →