Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy; Department of Informatics, Bioengineering, Robotics, and System Engineering, University of Genoa, Italy.
Department of Information and Communication Engineering, Faculty of Engineering, The Islamia University of Bahawalpur, Pakistan.
Comput Biol Med. 2022 May;144:105253. doi: 10.1016/j.compbiomed.2022.105253. Epub 2022 Feb 3.
Over the past two decades, medical imaging has been extensively apply to diagnose diseases. Medical experts continue to have difficulties for diagnosing diseases with a single modality owing to a lack of information in this domain. Image fusion may be use to merge images of specific organs with diseases from a variety of medical imaging systems. Anatomical and physiological data may be included in multi-modality image fusion, making diagnosis simpler. It is a difficult challenge to find the best multimodal medical database with fusion quality evaluation for assessing recommended image fusion methods. As a result, this article provides a complete overview of multimodal medical image fusion methodologies, databases, and quality measurements.
In this article, a compendious review of different medical imaging modalities and evaluation of related multimodal databases along with the statistical results is provided. The medical imaging modalities are organized based on radiation, visible-light imaging, microscopy, and multimodal imaging.
The medical imaging acquisition is categorized into invasive or non-invasive techniques. The fusion techniques are classified into six main categories: frequency fusion, spatial fusion, decision-level fusion, deep learning, hybrid fusion, and sparse representation fusion. In addition, the associated diseases for each modality and fusion approach presented. The quality assessments fusion metrics are also encapsulated in this article.
This survey provides a baseline guideline to medical experts in this technical domain that may combine preoperative, intraoperative, and postoperative imaging, Multi-sensor fusion for disease detection, etc. The advantages and drawbacks of the current literature are discussed, and future insights are provided accordingly.
在过去的二十年中，医学影像学已被广泛应用于疾病诊断。由于该领域信息的缺乏，医学专家在使用单一模式诊断疾病时仍然存在困难。图像融合可用于将特定器官的疾病图像与来自各种医学成像系统的图像融合。多模态图像融合可以包括解剖学和生理学数据，从而使诊断变得更加简单。找到具有融合质量评估的最佳多模态医学数据库来评估推荐的图像融合方法是一项具有挑战性的任务。因此，本文全面概述了多模态医学图像融合方法、数据库和质量评估。
本文对不同的医学成像模式进行了简明的回顾，并对相关的多模态数据库及其统计结果进行了评估。医学成像模式是根据辐射、可见光成像、显微镜和多模态成像进行组织的。
医学成像采集分为有创或无创技术。融合技术分为六大类：频率融合、空间融合、决策级融合、深度学习、混合融合和稀疏表示融合。此外，还介绍了每种模式和融合方法所涉及的相关疾病。本文还封装了融合质量评估指标。
本调查为该技术领域的医学专家提供了一个基准指南，可用于结合术前、术中、术后成像、多传感器融合进行疾病检测等。讨论了当前文献的优缺点，并相应提供了未来的见解。
