Yang Mei, Zheng Yiming, Xie Zhiying, Wang Zhaoxia, Xiao Jiangxi, Zhang Jue, Yuan Yun
Department of Neurology, Peking University First Hospital, Beijing, China.
Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China.
BMC Neurol. 2021 Jan 11;21(1):13. doi: 10.1186/s12883-020-02036-0.
Dystrophinopathies are the most common type of inherited muscular diseases. Muscle biopsy and genetic tests are effective to diagnose the disease but cost much more than primary hospitals can reach. The more available muscle MRI is promising but its diagnostic results highly depends on doctors' experiences. This study intends to explore a way of deploying a deep learning model for muscle MRI images to diagnose dystrophinopathies.
This study collected 2536 T1WI images from 432 cases who had been diagnosed by genetic analysis and/or muscle biopsy, including 148 cases with dystrophinopathies and 284 cases with other diseases. The data was randomly divided into three sets: the data from 233 cases were used to train the CNN model, the data from 97 cases for the validation experiments, and the data from 102 cases for the test experiments. We also validated our models expertise at diagnosing by comparing the model's results on the 102 cases with those of three skilled radiologists.
The proposed model achieved 91% (95% CI: 0.88, 0.93) accuracy on the test set, higher than the best accuracy of 84% in radiologists. It also performed better than the skilled radiologists in sensitivity : sensitivities of the models and the doctors were 0.89 (95% CI: 0.85 0.93) versus 0.79 (95% CI:0.73, 0.84; p = 0.190).
The deep model achieved excellent accuracy and sensitivity in identifying cases with dystrophinopathies. The comparable performance of the model and skilled radiologists demonstrates the potential application of the model in diagnosing dystrophinopathies through MRI images.
肌营养不良症是最常见的遗传性肌肉疾病类型。肌肉活检和基因检测对该疾病的诊断有效，但费用远超基层医院承受范围。更易获取的肌肉磁共振成像（MRI）很有前景，但其诊断结果高度依赖医生经验。本研究旨在探索一种利用深度学习模型对肌肉MRI图像进行分析以诊断肌营养不良症的方法。
本研究收集了432例经基因分析和/或肌肉活检确诊患者的2536张T1加权成像（T1WI）图像，其中包括148例肌营养不良症患者和284例其他疾病患者。数据被随机分为三组：233例患者的数据用于训练卷积神经网络（CNN）模型，97例患者的数据用于验证实验，102例患者的数据用于测试实验。我们还通过将模型在这102例患者上的结果与三位经验丰富的放射科医生的结果进行比较，来验证模型的诊断专业能力。
所提出的模型在测试集上的准确率达到了91%（95%置信区间：0.88，0.93），高于放射科医生的最高准确率84%。在敏感性方面，该模型也比经验丰富的放射科医生表现更好：模型和医生的敏感性分别为0.89（95%置信区间：0.85，0.93）和0.79（95%置信区间：0.73，0.84；p = 0.190）。
该深度模型在识别肌营养不良症病例方面具有出色的准确率和敏感性。模型与经验丰富的放射科医生相当的表现证明了该模型在通过MRI图像诊断肌营养不良症方面的潜在应用价值。
