Open Access

ARTICLE

Novel Feature Extractor Framework in Conjunction with Supervised Three Class-XGBoost Algorithm for Osteosarcoma Detection from Whole Slide Medical Histopathology Images

Tanzila Saba¹, Muhammad Mujahid¹, Shaha Al-Otaibi², Noor Ayesha³, Amjad Rehman Khan^1,*

1 Artificial Intelligence & Data Analytics Lab, College of Computer & Information Sciences, Prince Sultan University, Riyadh, 11586, Saudi Arabia
2 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, 11671, Saudi Arabia
3 Center of Excellence in Cyber Security (CYBEX), Prince Sultan University, Riyadh, 11586, Saudi Arabia

* Corresponding Author: Amjad Rehman Khan. Email:

(This article belongs to the Special Issue: Data and Image Processing in Intelligent Information Systems)

Computers, Materials & Continua 2025, 82(2), 3337-3353. https://doi.org/10.32604/cmc.2025.060163

Received 25 October 2024; Accepted 25 December 2024; Issue published 17 February 2025

Abstract

Osteosarcomas are malignant neoplasms derived from undifferentiated osteogenic mesenchymal cells. It causes severe and permanent damage to human tissue and has a high mortality rate. The condition has the capacity to occur in any bone; however, it often impacts long bones like the arms and legs. Prompt identification and prompt intervention are essential for augmenting patient longevity. However, the intricate composition and erratic placement of osteosarcoma provide difficulties for clinicians in accurately determining the scope of the afflicted area. There is a pressing requirement for developing an algorithm that can automatically detect bone tumors with tremendous accuracy. Therefore, in this study, we proposed a novel feature extractor framework associated with a supervised three-class XGBoost algorithm for the detection of osteosarcoma in whole slide histopathology images. This method allows for quicker and more effective data analysis. The first step involves preprocessing the imbalanced histopathology dataset, followed by augmentation and balancing utilizing two techniques: SMOTE and ADASYN. Next, a unique feature extraction framework is used to extract features, which are then inputted into the supervised three-class XGBoost algorithm for classification into three categories: non-tumor, viable tumor, and non-viable tumor. The experimental findings indicate that the proposed model exhibits superior efficiency, accuracy, and a more lightweight design in comparison to other current models for osteosarcoma detection.

---

Keywords

---