Scholarlink

This study presents three innovative AI-based methodologies designed to enhance the diagnostic accuracy of infectious diseases through medical imaging. These methodologies integrate artificial intelligence with Multi-Criteria Decision-Making (MCDM) frameworks to address the complexities and uncertainties inherent in medical data. The three methodologies include: Intuitionistic Hypersoft Set (IFHSS) method utilizes distance and similarity measures to improve the visual quality and diagnostic usability of medical images by effectively handling uncertainties and imprecisions. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) approach establishes a robust system for evaluating and ranking diagnostic outcomes using predefined criteria, aiding in more precise clinical decision-making. Integrated AI-MCDM Diagnostic framework combines IFHSS and TOPSIS methodologies to leverage the full potential of AI in transforming medical imaging data into actionable clinical insights. These methodologies were validated using a diverse dataset of medical images covering various modalities and diseases, showing substantial improvements in diagnostic accuracy over traditional methods. The IFHSS method notably enhanced the handling of image ambiguities, while the TOPSIS method provided a dependable system for ranking diagnoses.

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

AI-Based Decision Support Systems to Improve Diagnostic Accuracy via Medical Imaging

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Muhammad Ahsan,
  • Robertas Damaševičius

摘要

This study presents three innovative AI-based methodologies designed to enhance the diagnostic accuracy of infectious diseases through medical imaging. These methodologies integrate artificial intelligence with Multi-Criteria Decision-Making (MCDM) frameworks to address the complexities and uncertainties inherent in medical data. The three methodologies include: Intuitionistic Hypersoft Set (IFHSS) method utilizes distance and similarity measures to improve the visual quality and diagnostic usability of medical images by effectively handling uncertainties and imprecisions. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) approach establishes a robust system for evaluating and ranking diagnostic outcomes using predefined criteria, aiding in more precise clinical decision-making. Integrated AI-MCDM Diagnostic framework combines IFHSS and TOPSIS methodologies to leverage the full potential of AI in transforming medical imaging data into actionable clinical insights. These methodologies were validated using a diverse dataset of medical images covering various modalities and diseases, showing substantial improvements in diagnostic accuracy over traditional methods. The IFHSS method notably enhanced the handling of image ambiguities, while the TOPSIS method provided a dependable system for ranking diagnoses.