Open Access

ARTICLE

Symbiotic Organisms Search with Deep Learning Driven Biomedical Osteosarcoma Detection and Classification

Abdullah M. Basahel¹, Mohammad Yamin¹, Sulafah M. Basahel², Mona M. Abusurrah³, K.Vijaya Kumar⁴, E. Laxmi Lydia^5,*

1 Faculty of Economics and Administration, King Abdulaziz University, Jeddah, Saudi Arabia
2 E-Commerce Department, College of Administrative and Financial Sciences, Saudi Electronic University, Jeddah, Saudi Arabia
3 Department of Management Information Systems, College of Business Administration, Taibah University, Al-Madinah, Saudi Arabia
4 Department of Computer Science and Engineering, GITAM School of Technology, Visakhapatnam Campus, GITAM (Deemed to be a University), India
5 Department of Computer Science and Engineering, GMR Institute of Technology, Andhra Pradesh, Rajam, India

* Corresponding Author: E. Laxmi Lydia. Email:

Computers, Materials & Continua 2023, 75(1), 133-148. https://doi.org/10.32604/cmc.2023.031786

Received 27 April 2022; Accepted 24 June 2022; Issue published 06 February 2023

Abstract

Osteosarcoma is one of the rare bone cancers that affect the individuals aged between 10 and 30 and it incurs high death rate. Early diagnosis of osteosarcoma is essential to improve the survivability rate and treatment protocols. Traditional physical examination procedure is not only a time-consuming process, but it also primarily relies upon the expert’s knowledge. In this background, the recently developed Deep Learning (DL) models can be applied to perform decision making. At the same time, hyperparameter optimization of DL models also plays an important role in influencing overall classification performance. The current study introduces a novel Symbiotic Organisms Search with Deep Learning-driven Osteosarcoma Detection and Classification (SOSDL-ODC) model. The presented SOSDL-ODC technique primarily focuses on recognition and classification of osteosarcoma using histopathological images. In order to achieve this, the presented SOSDL-ODC technique initially applies image pre-processing approach to enhance the quality of image. Also, MobileNetv2 model is applied to generate a suitable group of feature vectors whereas hyperparameter tuning of MobileNetv2 model is performed using SOS algorithm. At last, Gated Recurrent Unit (GRU) technique is applied as a classification model to determine proper class labels. In order to validate the enhanced osteosarcoma classification performance of the proposed SOSDL-ODC technique, a comprehensive comparative analysis was conducted. The obtained outcomes confirmed the betterment of SOSDL-ODC approach than the existing approaches as the former achieved a maximum accuracy of 97.73%.

---

Keywords

---