EUVIMEDEUVIMED entdecken
Open Access

Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features

Akanksha Maurya, R Joe Stanley iD, Hemanth Y Aradhyula, Norsang Lama, Anand K Nambisan, Gehana Patel, Daniyal Saeed, Samantha Swinfard, Colin Smith, Sadhika Jagannathan, Jason R Hagerty, William V Stoecker

Journal of Imaging Informatics in Medicine · 08.02.2024 · 37 (3) · 1137-1150

DOI: 10.1007/s10278-024-00969-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 08.02.2024. Verfasst von Akanksha Maurya und 11 weiteren Autor:innen. Beteiligte Einrichtung: Missouri University of Science &Technology, Rolla, MO, 65209, USA. Hauptthemen laut MEDLINE: Deep Learning, Basal Cell Carcinoma, Skin Neoplasms, Telangiectasis. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, deep learning (DL) has been used extensively and successfully to diagnose different cancers in dermoscopic images. However, most approaches lack clinical inputs supported by dermatologists that could aid in higher accuracy and explainability. To dermatologists, the presence of telangiectasia, or narrow blood vessels that typically appear serpiginous or arborizing, is a critical indicator of basal cell carcinoma (BCC). Exploiting the feature information present in telangiectasia through a combination of DL-based techniques could create a pathway for both, improving DL results as well as aiding dermatologists in BCC diagnosis. This study demonstrates a novel "fusion" technique for BCC vs non-BCC classification using ensemble learning on a combination of (a) handcrafted features from semantically segmented telangiectasia (U-Net-based) and (b) deep learning features generated from whole lesion images (EfficientNet-B5-based). This fusion method achieves a binary classification accuracy of 97.2%, with a 1.3% improvement over the corresponding DL-only model, on a holdout test set of 395 images. An increase of 3.7% in sensitivity, 1.5% in specificity, and 1.5% in precision along with an AUC of 0.99 was also achieved. Metric improvements were demonstrated in three stages: (1) the addition of handcrafted telangiectasia features to deep learning features, (2) including areas near telangiectasia (surround areas), (3) discarding the noisy lower-importance features through feature importance. Another novel approach to feature finding with weak annotations through the examination of the surrounding areas of telangiectasia is offered in this study. The experimental results show state-of-the-art accuracy and precision in the diagnosis of BCC, compared to three benchmark techniques. Further exploration of deep learning techniques for individual dermoscopy feature detection is warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBasal Cell CarcinomaSkin NeoplasmsTelangiectasisHumansImage Interpretation, Computer-AssistedDermoscopySensitivity and Specificity

Stichwörter der Autor:innen

Basal cell carcinomaDeep learningDermoscopyFusionTelangiectasiaTransfer learning

Autor:innen und Institutionen

  • Missouri University of Science &Technology, Rolla, MO, 65209, USA.
  • Missouri University of Science &Technology, Rolla, MO, 65209, USA. stanleyj@mst.edu.
  • Ford Motor Company, Mt. Pleasant, Michigan, USA.
  • University of Missouri, Columbia, MO, USA.
  • A.T. Still University of Health Sciences, Kirksville, MO, USA.
  • Kansas City Medical School, University of Missouri, Kansas City, MO, USA.

ORCID-Profile: R Joe Stanley

Zitieren

APA

Maurya, A., Stanley, R. J., Aradhyula, H. Y., Lama, N., Nambisan, A. K., Patel, G., Saeed, D., Swinfard, S., Smith, C., Jagannathan, S., Hagerty, J. R., & Stoecker, W. V. (2024). Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features. Journal of Imaging Informatics in Medicine, 37(3), 1137-1150. https://doi.org/10.1007/s10278-024-00969-3

Vancouver

Maurya A, Stanley RJ, Aradhyula HY, Lama N, Nambisan AK, Patel G, et al. Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features. Journal of Imaging Informatics in Medicine. 2024;37(3):1137-1150. doi:10.1007/s10278-024-00969-3

BibTeX
@article{Maurya2024,
  author = {Maurya, Akanksha and Stanley, R Joe and Aradhyula, Hemanth Y and Lama, Norsang and Nambisan, Anand K and Patel, Gehana and Saeed, Daniyal and Swinfard, Samantha and Smith, Colin and Jagannathan, Sadhika and Hagerty, Jason R and Stoecker, William V},
  title = {Basal Cell Carcinoma Diagnosis with Fusion of Deep Learning and Telangiectasia Features},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  volume = {37},
  number = {3},
  pages = {1137--1150},
  doi = {10.1007/s10278-024-00969-3}
}
Kostenlos starten →