Bone Cancer Detection and Classification Using Owl Search Algorithm With Deep Learning on X-Ray Images

• Published in: IEEE access Vol. 11; pp. 109095 - 109103
• Main Authors: Alabdulkreem, Eatedal, Saeed, Muhammad Kashif, Alotaibi, Saud S., Allafi, Randa, Mohamed, Abdullah, Hamza, Manar Ahmed
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial intelligence; Biomedical image processing; Bone cancer; Bone diseases; Bones; Cancer; Cancer detection; Classification; Deep learning; Feature extraction; Image enhancement; Image segmentation; Machine learning; Manuals; Medical imaging; OWL; owl search algorithm; Search algorithms; Search methods; Tumors; X-ray imaging
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3319293

Bone cancer is treated as a severe health problem, and, in many cases, it causes patient death. Early detection of bone cancer is efficient in reducing the spread of malignant cells and decreasing mortality. Since the manual detection process is a laborious task, it is needed to design an automated system to classify and identify the cancerous bone and the healthy bone. Therefore, this article develops an Owl Search Algorithm with a Deep Learning-Driven Bone Cancer Detection and Classification (OSADL-BCDC) technique. The OSADL-BCDC algorithm follows the principle of transfer learning with a hyperparameter tuning strategy for bone cancer detection. The OSADL-BCDC model employs Inception v3 as a pretrained model for the feature extraction process which does not necessitate a manual segmentation of X-ray images. Besides, the OSA is applied as a hyperparameter optimizer for enhancing the efficacy of the Inception v3 method. Finally, the long short-term memory (LSTM) approach is used for identifying the presence of bone cancer. The proposed OSADL-BCDC technique reduces diagnosis time and achieves faster convergence. The experimental analysis of the OSADL-BCDC algorithm is tested using a set of medical images and the outcomes were measured under different aspects. The comparison study highlighted the improved performance of the OSADL-BCDC model over existing algorithms.