EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

KONet: Toward a Weighted Ensemble Learning Model for Knee Osteoporosis Classification

M. J. Aashik Rasool, Shabir Ahmad, Umirzakova Sabina, Taeg Keun Whangbo

IEEE Access · 2024 · 12 · 5731-5742

DOI: 10.1109/access.2023.3348817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von M. J. Aashik Rasool und 3 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: GRRC Program of Gyeonggi-do Province, Development of Healthcare Contents Based on AI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knee osteoporosis (KOP) is a skeletal disorder characterized by bone tissue degradation and low bone density, leading to a high risk of bone fractures in the knee area. The traditional method for identifying knee osteoporosis is knee radiography, which requires sufficient expertise from specialists. However, the sheer volume of X-rays and the subtle variations among them may lead to misinterpretation. In recent years, deep learning algorithms have revolutionized medical diagnosis and reduced misclassification. Specifically, convolutional neural network (CNN)-based algorithms have been utilized to automate the diagnostic process as they have the inherent ability to extract important features that are difficult to identify manually. However, relying on a single method may result in suboptimal performance, leading to ineffective deployment in the medical domain. To alleviate this issue, in this study, we propose a robust detection method, KONet, which utilizes a weighted ensemble approach to distinguish between normal and osteoporotic knee conditions, even when there are minor variations in the data. To validate the architectural choices in the ensemble approach, we conducted experiments on various state-of-the-art CNN-based models using transfer learning. Extensive experiments indicated that the proposed model achieves a higher accuracy than existing models, outperforming the state-of-the-art models by a significant margin.

Förderung

  • GRRC Program of Gyeonggi-do Province, Development of Healthcare Contents Based on AI

Zitieren

APA

Rasool, M. J. A., Ahmad, S., Sabina, U., & Whangbo, T. K. (2024). KONet: Toward a Weighted Ensemble Learning Model for Knee Osteoporosis Classification. IEEE Access, 12, 5731-5742. https://doi.org/10.1109/access.2023.3348817

Vancouver

Rasool MJA, Ahmad S, Sabina U, Whangbo TK. KONet: Toward a Weighted Ensemble Learning Model for Knee Osteoporosis Classification. IEEE Access. 2024;12:5731-5742. doi:10.1109/access.2023.3348817

BibTeX
@article{Rasool2024,
  author = {Rasool, M. J. Aashik and Ahmad, Shabir and Sabina, Umirzakova and Whangbo, Taeg Keun},
  title = {KONet: Toward a Weighted Ensemble Learning Model for Knee Osteoporosis Classification},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {5731--5742},
  doi = {10.1109/access.2023.3348817}
}
Kostenlos starten →