EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules

Mayuresh Gulame, Deepthi D. Kulkarni, Priya Khune, Nilesh N. Thorat, Ashwini G. Shahapurkar, Vijaya S. Patil, Sumit Arun Hirve, Aarti Pimpalkar

Bulletin of Electrical Engineering and Informatics · 01.02.2026 · 15 (1) · 327-337

DOI: 10.11591/eei.v15i1.10447 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bulletin of Electrical Engineering and Informatics, online erschienen am 01.02.2026. Verfasst von Mayuresh Gulame und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ultrasonography is frequently used to identify thyroid nodules. Because of their internal features, variable appearances, and ill-defined borders, it might be difficult for a hospitalist to distinguish amongst benign and malignant forms of the nodule based solely on visual inspection. Although deep learning, a subset of artificial intelligence, has significantly advanced medical image recognition, challenges remain in achieving accurate and efficient diagnosis of thyroid nodules. To identify and classify thyroid nodules, this study uses an innovative hybrid DL-assisted multi-classification technique. A median blur eliminates salt-and-pepper noise, and this is followed by segmentation using a method based on enhanced pooling integrated U-Net (EPIU-Net). To produce a single histogram series, features are recovered from the segmented image, including multi-texton, and local ternary pattern (LTP) based patterns. Following feature extraction, the data is expanded and input into a fusion classification model utilizing Deep Maxout and convolutional neural network (CNN) to categorize nodules. This work uses 2 types of datasets and for both datasets, we achieved great results with our hybrid technique across all performance criteria. 0.976, 0.008, 0.992, and 0.017 are the corresponding values for accuracy, false discovery rate (FDR), sensitivity, false negative rate (FNR). Moreover proposed work is verified by k-fold method.

Zitieren

APA

Gulame, M., Kulkarni, D. D., Khune, P., Thorat, N. N., Shahapurkar, A. G., Patil, V. S., Hirve, S. A., & Pimpalkar, A. (2026). Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules. Bulletin of Electrical Engineering and Informatics, 15(1), 327-337. https://doi.org/10.11591/eei.v15i1.10447

Vancouver

Gulame M, Kulkarni DD, Khune P, Thorat NN, Shahapurkar AG, Patil VS, et al. Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules. Bulletin of Electrical Engineering and Informatics. 2026;15(1):327-337. doi:10.11591/eei.v15i1.10447

BibTeX
@article{Gulame2026,
  author = {Gulame, Mayuresh and Kulkarni, Deepthi D. and Khune, Priya and Thorat, Nilesh N. and Shahapurkar, Ashwini G. and Patil, Vijaya S. and Hirve, Sumit Arun and Pimpalkar, Aarti},
  title = {Improved feature-based hybrid deep learning for multiclassification of ultrasound thyroid nodules},
  journal = {Bulletin of Electrical Engineering and Informatics},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {327--337},
  doi = {10.11591/eei.v15i1.10447}
}
Kostenlos starten →