Yin Rui, Chen Hao, Wang Changjiang, Qin Chaoren, Tao Tianqi, Hao Yunjia, Wu Rui, Jiang Yiqiu, Gui Jianchao
Department of Sports Medicine and Joint Surgery, Nanjing First Hospital, Nanjing Medical University, Nanjing, China.
Department of Clinical Neuroscience, Cambridge University, Cambridge, U.K; School of Computer Science, University of Birmingham, Birmingham, U.K.
Arthroscopy. 2025 Mar;41(3):574-584.e4. doi: 10.1016/j.arthro.2024.05.027. Epub 2024 Jun 12.
To develop a deep learning (DL) model that can simultaneously detect lateral and medial collateral ligament injuries of the ankle, aiding in the diagnosis of chronic ankle instability (CAI), and assess its impact on clinicians' diagnostic performance.
DL models were developed and externally validated on retrospectively collected ankle magnetic resonance imaging (MRI) between April 2016 and March 2022 respectively at 3 centers. Included patients had confirmed diagnoses of CAI through arthroscopy, as well as individuals who had undergone MRI and physical examinations that ruled out ligament injuries. DL models were constructed based on a multilabel paradigm. A transformer-based multilabel DL model (AnkleNet) was developed and compared with 4 convolution neural network (CNN) models. Subsequently, a reader study was conducted to evaluate the impact of model assistance on clinicians when diagnosing challenging cases: identifying rotational CAI (RCAI). Diagnostic performance was assessed using area under the receiver operating characteristic curve (AUC).
Our transformer-based model achieved AUCs of 0.910 and 0.892 for detecting lateral and medial collateral ligament injury, respectively, both of which were significantly higher than those of CNN-based models (all P < .001). In terms of further CAI diagnosis, there was a macro-average AUC of 0.870 and a balanced accuracy of 0.805. The reader study indicated that incorporation with our model significantly enhanced the diagnostic accuracy of clinicians (P = .042), particularly junior clinicians, and led to a reduction in diagnostic variability. The code of the model can be accessed at https://github.com/ChiariRay/AnkleNet.
Our transformer-based model was able to detect lateral and medial collateral ligament injuries based on MRI and outperformed CNN-based models, demonstrating a promising performance in diagnosing CAI, especially patients with RCAI.
Developing such an algorithm can improve the diagnostic performance of clinicians, aiding in identifying patients who would benefit from arthroscopy, such as patients with RCAI.
开发一种深度学习（DL）模型，该模型能够同时检测踝关节的外侧和内侧副韧带损伤，辅助诊断慢性踝关节不稳（CAI），并评估其对临床医生诊断性能的影响。
分别在3个中心对2016年4月至2022年3月期间回顾性收集的踝关节磁共振成像（MRI）数据开发DL模型并进行外部验证。纳入的患者通过关节镜检查确诊为CAI，以及接受过MRI和体格检查排除韧带损伤的个体。基于多标签范式构建DL模型。开发了一种基于Transformer的多标签DL模型（AnkleNet），并与4种卷积神经网络（CNN）模型进行比较。随后，进行了一项阅片者研究，以评估模型辅助对临床医生诊断具有挑战性病例（识别旋转性CAI，RCAI）时的影响。使用受试者操作特征曲线下面积（AUC）评估诊断性能。
我们基于Transformer的模型检测外侧和内侧副韧带损伤的AUC分别为0.910和0.892，均显著高于基于CNN的模型（所有P <.001）。在进一步的CAI诊断方面，宏观平均AUC为0.870，平衡准确率为0.805。阅片者研究表明，结合我们的模型可显著提高临床医生的诊断准确性（P = 0.042），尤其是初级临床医生，并减少诊断变异性。该模型的代码可在https://github.com/ChiariRay/AnkleNet获取。
我们基于Transformer的模型能够根据MRI检测外侧和内侧副韧带损伤，并且优于基于CNN的模型，在诊断CAI方面表现出良好的性能，尤其是对于RCAI患者。
开发这样一种算法可以提高临床医生的诊断性能，有助于识别那些将从关节镜检查中获益的患者，如RCAI患者。
