Scholarlink

The area of medical imaging has seen a revolution in recent years due to the rapid advancement of deep learning (DL) techniques. Medical image analysis plays a key role in modern healthcare, helping in the accurate diagnosis and treatment of various conditions. Using deep learning, it is possible to solve complex medical image analysis problems with unparalleled accuracy and efficiency. In this research, we explore the potential of deep learning models for multi-class image classification of abdominal organ structures within 2D Computed Tomography (CT) images. We focus on the 2D views, namely axial, coronal, and sagittal, to facilitate lightweight model evaluation and deployment. Our paper presents a comprehensive analysis of the classification performance, with a particular emphasis on model generalizability, algorithm selection, and interpretability. In this paper, we investigate the classification of 11 distinct abdominal organs like the bladder, heart, kidneys, liver, etc., using state-of-the-art deep neural networks with an attention feature integrated. The results of this research contribute to the growing body of knowledge in medical image analysis, showcasing the potential of deep learning models in the context of multi-class organ classification. By offering improved accuracy, our findings may have implications for clinical practice, computer-aided diagnosis, and healthcare automation.

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

Attention-Based Deep Neural Networks for Automatic Organ Classification from 2D CT Scan Images

  • 章节

  • 发表日期：

    2025年

查看全文
  • Rajat Rajoria,
  • Balmukund Kanodia,
  • Debam Saha,
  • Ekaterina Kopets,
  • Alexander Voznesensky,
  • Dmitrii Kaplun,
  • Pawan Kumar Singh

摘要

The area of medical imaging has seen a revolution in recent years due to the rapid advancement of deep learning (DL) techniques. Medical image analysis plays a key role in modern healthcare, helping in the accurate diagnosis and treatment of various conditions. Using deep learning, it is possible to solve complex medical image analysis problems with unparalleled accuracy and efficiency. In this research, we explore the potential of deep learning models for multi-class image classification of abdominal organ structures within 2D Computed Tomography (CT) images. We focus on the 2D views, namely axial, coronal, and sagittal, to facilitate lightweight model evaluation and deployment. Our paper presents a comprehensive analysis of the classification performance, with a particular emphasis on model generalizability, algorithm selection, and interpretability. In this paper, we investigate the classification of 11 distinct abdominal organs like the bladder, heart, kidneys, liver, etc., using state-of-the-art deep neural networks with an attention feature integrated. The results of this research contribute to the growing body of knowledge in medical image analysis, showcasing the potential of deep learning models in the context of multi-class organ classification. By offering improved accuracy, our findings may have implications for clinical practice, computer-aided diagnosis, and healthcare automation.