Scholarlink

Cancer is an unusual growth of cells that lose their normal control mechanisms and are able to increase exponentially. Acute lymphoblastic leukemia (ALL) is more prevalent in children but also affects adults and can lead to death. It is a type of blood and bone marrow cancer which has an effect on white blood cells (WBC) whose early detection can increase the chances of survival. Therefore, it is important to develop a system to detect ALL. In this paper, four classification models: Bootstrap aggregating (bagging), adaptive boosting (AdaBoost), voting classifier (VC), and extreme gradient boosting (XGBoost) are integrated into a stacking ensemble to detect ALL using a dataset obtained from Kaggle. ResNet50 is used for feature extraction. The results demonstrated that the proposed ensemble model Stack_Bagging has outperformed other models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Acute Lymphoblastic Leukemia Classification Using Stacking Ensemble Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ananya Arya,
  • Anushree Sharma,
  • Ritika Kumari

摘要

Cancer is an unusual growth of cells that lose their normal control mechanisms and are able to increase exponentially. Acute lymphoblastic leukemia (ALL) is more prevalent in children but also affects adults and can lead to death. It is a type of blood and bone marrow cancer which has an effect on white blood cells (WBC) whose early detection can increase the chances of survival. Therefore, it is important to develop a system to detect ALL. In this paper, four classification models: Bootstrap aggregating (bagging), adaptive boosting (AdaBoost), voting classifier (VC), and extreme gradient boosting (XGBoost) are integrated into a stacking ensemble to detect ALL using a dataset obtained from Kaggle. ResNet50 is used for feature extraction. The results demonstrated that the proposed ensemble model Stack_Bagging has outperformed other models.