Department of Orthopaedic, Wuhan Fourth Hospital, Wuhan, 430000 Hubei, China.
Comput Math Methods Med. 2022 Apr 29;2022:7643487. doi: 10.1155/2022/7643487. eCollection 2022.
The objective of this study was to investigate the application effect of deep learning model combined with different magnetic resonance imaging (MRI) sequences in the evaluation of cartilage injury of knee osteoarthritis (KOA). Specifically, an image superresolution algorithm based on an improved multiscale wide residual network model was proposed and compared with the single-shot multibox detector (SSD) algorithm, superresolution convolutional neural network (SRCNN) algorithm, and enhanced deep superresolution (EDSR) algorithm. Meanwhile, 104 patients with KOA diagnosed with cartilage injury were selected as the research subjects and underwent MRI scans, and the diagnostic performance of different MRI sequences was analyzed using arthroscopic results as the gold standard. It was found that the image reconstructed by the model in this study was clear enough, with minimum noise and artifacts, and the overall quality was better than that processed by other algorithms. Arthroscopic analysis found that grade I and grade II lesions concentrated on patella (26) and femoral trochlear (15). In addition to involving the patella and femoral trochlea, grade III and grade IV lesions gradually developed into the medial and lateral articular cartilage. The 3D-DS-WE sequence was found to be the best sequence for diagnosing KOA injury, with high diagnostic accuracy of over 95% in grade IV lesions. The consistency test showed that the 3D-DESS-WE sequence and T2∗ mapping sequence had a strong consistency with the results of arthroscopy, and the Kappa consistency test values were 0.748 and 0.682, respectively. In conclusion, MRI based on deep learning could clearly show the cartilage lesions of KOA. Of different MRI sequences, 3D-DS-WE sequence and T2∗ mapping sequence showed the best diagnosis results for different degrees of KOA injury.
本研究旨在探讨深度学习模型结合不同磁共振成像（MRI）序列在评估膝骨关节炎（KOA）软骨损伤中的应用效果。具体而言，提出了一种基于改进的多尺度宽残差网络模型的图像超分辨率算法，并与单帧多盒探测器（SSD）算法、超分辨率卷积神经网络（SRCNN）算法和增强型深度超分辨率（EDSR）算法进行了比较。同时，选择 104 例经 MRI 扫描诊断为软骨损伤的 KOA 患者作为研究对象，以关节镜结果为金标准分析不同 MRI 序列的诊断性能。结果发现，本研究模型重建的图像足够清晰，噪声和伪影最小，整体质量优于其他算法处理的图像。关节镜分析发现，I 级和 II 级病变主要集中在髌骨（26 例）和股骨滑车（15 例）。除了累及髌骨和股骨滑车外，III 级和 IV 级病变逐渐发展到内外侧关节软骨。3D-DS-WE 序列被发现是诊断 KOA 损伤的最佳序列，对 IV 级病变的诊断准确率超过 95%。一致性检验表明，3D-DESS-WE 序列和 T2映射序列与关节镜结果具有很强的一致性，Kappa 一致性检验值分别为 0.748 和 0.682。总之，基于深度学习的 MRI 能够清晰显示 KOA 的软骨病变。在不同的 MRI 序列中，3D-DS-WE 序列和 T2映射序列对不同程度的 KOA 损伤具有最佳的诊断效果。
