融合医学影像与临床数据，用TOPSIS算法辅助医生诊断口腔癌。
CBIDR: A novel method for information retrieval combining image and data by means of TOPSIS applied to medical diagnosis
- 用TOPSIS整合图像与临床数据，实现多模态信息检索。
- Top-1准确率达97.44%，Top-5准确率100%。
- 适合需要多源信息支持的临床辅助诊断场景。
基于内容的图像检索（CBIR）在医疗诊断中展现出良好前景，旨在为医生或病理科医师提供决策支持。然而，最终诊断仍由专业人员根据经验作出。我们认为人工智能不应替代诊断，而应通过提供最相关的信息来辅助过程。传统CBIR方法利用卷积神经网络（CNN）生成的特征向量，通过相似性度量比较图像。除了医学图像外，患者的临床数据也对诊断至关重要。本文提出一种新方法CBIDR，结合患者医学图像与临床数据，通过TOPSIS排序算法实现融合检索。目标是帮助医生从数据库中找到与查询数据最相似的病例。以口腔癌诊断为例，包含组织病理图像和临床数据。实验结果表明，该方法在Top-1准确率达到97.44%，在Top-5达到100%，验证了其有效性。
原文摘要 · Abstract (English)
Content-Based Image Retrieval (CBIR) have shown promising results in the field of medical diagnosis, which aims to provide support to medical professionals (doctor or pathologist). However, the ultimate decision regarding the diagnosis is made by the medical professional, drawing upon their accumulated experience. In this context, we believe that artificial intelligence can play a pivotal role in addressing the challenges in medical diagnosis not by making the final decision but by assisting in the diagnosis process with the most relevant information. The CBIR methods use similarity metrics to compare feature vectors generated from images using Convolutional Neural Networks (CNNs). In addition to the information contained in medical images, clinical data about the patient is often available and is also relevant in the final decision-making process by medical professionals. In this paper, we propose a novel method named CBIDR, which leverage both medical images and clinical data of patient, combining them through the ranking algorithm TOPSIS. The goal is to aid medical professionals in their final diagnosis by retrieving images and clinical data of patient that are most similar to query data from the database. As a case study, we illustrate our CBIDR for diagnostic of oral cancer including histopathological images and clinical data of patient. Experimental results in terms of accuracy achieved 97.44% in Top-1 and 100% in Top-5 showing the effectiveness of the proposed approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。