EUVIMEDEUVIMED entdecken
Crossref

Identification of Knee Osteoarthritis Disease using Convolutional Neural Networks

Muni Ratnam S, Ragulamma D, Tejaswani P, Swathi G, Vijayalakshmi K

International Journal of Computational Science and Engineering Research · 29.11.2024 · 1 (4) · 73

DOI: 10.63328/ijcser-v1ri4p14 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computational Science and Engineering Research, online erschienen am 29.11.2024. Verfasst von Muni Ratnam S und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knee Osteoarthritis (KOA), commonly referred to as degenerative joint disease of the knee, is usually caused by articular cartilage gradually losing its structure due to wear and stress. Worldwide, patients with osteoarthritis (OA), especially those with knee OA, have significant disability as a result of this most frequent form of arthritis. Osteoarthritis (OA) is a prevalent degenerative musculoskeletal condition. This illness impacts about 5% of the global population. Arthritis (OA) most commonly affects the knee, where articular cartilage at the ends of bones permanently deteriorates. Over time, the condition known as knee osteoarthritis (OA) worsens and affects the whole knee joint. Despite their time-consuming nature and sensitivity to user variable, manual diagnosis, segmentation, and annotation of knee joints are still employed in clinical practice to diagnose osteoarthritis. The proposed system effectively detects knee osteoarthritis in the MRI images in which median filter is used in the image pre-processing to reduce the noise, Fuzzy C- Means algorithm is used image segmentation, Fuzzy C-Means algorithm is used for segmentation and Convolutional Neural Network (CNN) is used for disease identification. Contrast, Homogeneity, Energy, Entropy and Correlation features were extracted from the Region of Interest (ROI) of the segmented image for training and testing the CNN classifier. MATLAB (R2021a) software were used to implement the proposed system or method. The performance parameters sensitivity, specificity, accuracy, and precision of the proposed system are obtained as 94.19%, 92.60%, 95.77%, and 93.4%, respectively.

Zitieren

APA

S, M. R., D, R., P, T., G, S., & K, V. (2024). Identification of Knee Osteoarthritis Disease using Convolutional Neural Networks. International Journal of Computational Science and Engineering Research, 1(4), 73. https://doi.org/10.63328/ijcser-v1ri4p14

Vancouver

S MR, D R, P T, G S, K V. Identification of Knee Osteoarthritis Disease using Convolutional Neural Networks. International Journal of Computational Science and Engineering Research. 2024;1(4):73. doi:10.63328/ijcser-v1ri4p14

BibTeX
@article{S2024,
  author = {S, Muni Ratnam and D, Ragulamma and P, Tejaswani and G, Swathi and K, Vijayalakshmi},
  title = {Identification of Knee Osteoarthritis Disease using Convolutional Neural Networks},
  journal = {International Journal of Computational Science and Engineering Research},
  year = {2024},
  volume = {1},
  number = {4},
  pages = {73},
  doi = {10.63328/ijcser-v1ri4p14}
}
Kostenlos starten →