现如今膝关节骨性关节炎(knee osteoarthritis, KOA)的患病率逐年升高,评估KOA主要通过MRI。膝骨关节本身结构复杂,目前依靠专业医师的临床经验通过对膝关节MRI图像进行诊断判别,不仅效率较低,而且可能存在仅凭肉眼观察难以判断的微小病灶,导致精度较低。近年来深度学习发展迅速,在图像分割、图像合成等计算机视觉领域取得了一定进展,人们开始通过深度学习的方法去处理复杂的医学图像,如MRI图像、CT图像以及X光图像等,以此提高临床诊疗的精确度和效率。现在也有很多相关研究引入深度学习处理膝骨关节MRI图像以辅助KOA的诊断,本文将这些研究进行归纳与整理,总结出了近年来深度学习在KOA的MRI图像分割、重建、合成等方面的研究进展,并分析了现有研究的局限性,以期为未来KOA的诊断与治疗提供新思路。
Currently, the prevalence rate of knee osteoarthritis (KOA) is increasing year by year, and the evaluation of KOA is mainly conducted by MRI. However, the structure of the knee joint itself is complex. At present, clinical experts rely on their experience to diagnose and distinguish knee joint MRI images, which not only has low efficiency but may also result in low accuracy due to the difficulty of identifying tiny lesions with the naked eye. In recent years, deep learning has developed rapidly and has made significant achievements in the field of computer vision, such as image segmentation and synthesis. People have begun to use deep learning methods to process complex medical images such as MRI, CT, and X-ray images, thus improving the accuracy and efficiency of clinical diagnosis and treatment. Nowadays, many relevant studies have introduced deep learning to assist in the diagnosis of KOA by processing knee joint MRI images. We summarized and organized these studies, summarized the research progress of deep learning in KOA MRI image segmentation, reconstruction, synthesis, and analyzed the limitations of existing studies in this paper, in order to provide new ideas for the diagnosis and treatment of KOA in the future.
高曦,谢希,王文韬. MRI深度学习在膝关节骨性关节炎中的研究进展[J]. 磁共振成像,2023,14(06):192-197.
DOI:10.12015/issn.1674-8034.2023.06.035本刊刊出的所有论文不代表本刊编委会的观点,除非特别声明
高曦设计了本研究的方案,撰写和修改了稿件的重要内容;谢希进行文献资料的收集与整理,起草和撰写了主要内容,王文韬对稿件的重要内容进行了修改;高曦获得了黑龙江省自然科学基金资助。全体作者都同意发表最后的修改稿,同意对本研究的所有方面负责,确保本研究的准确性和诚信。

你好,我可以帮助您更好的了解本文,请向我提问您关注的问题。