Zhao Haichen, Zhang Xiaoya, Gao Yuanxiang, Wang Lili, Xiao Longyang, Liu Shunli, Huang Baoxiang, Li Zhiming
Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China.
College of Computer Science and Technology of Qingdao University, Qingdao, China.
Heliyon. 2024 Jul 27;10(15):e35115. doi: 10.1016/j.heliyon.2024.e35115. eCollection 2024 Aug 15.
Previous studies had confirmed that some deep learning models had high diagnostic performance in staging liver fibrosis. However, training efficiency of models predicting liver fibrosis need to be improved to achieve rapid diagnosis and precision medicine.
The deep learning framework of EfficientNetV2-S was noted because of its faster training speed and better parameter efficiency compared with other models. Our study sought to develop noninvasive predictive models based on EfficientNetV2-S framework for staging liver fibrosis.
Patients with chronic liver disease who underwent multi-parametric abdominal MRI were included in the retrospective study. Data augmentation methods including horizontal flip, vertical flip, perspective transformation and edge enhancement were applied to multi-parametric MR images to solve the data imbalance between different liver fibrosis groups. The EfficientNetV2-S models were used for the prediction of liver fibrosis stages F1-2, F1-3, F3, F4 and F3-4. We evaluated the diagnostic performance of our models in training, validation, and test sets by using receiver operating characteristic curve (ROC) analysis.
The total training time of EfficientNetV2-S was about 6 h. For differentiating of F1-2 vs F3, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 96.2 %, 96.4 % and 96.0 % in the test set. The AUC in test set was 0.559. The accuracy, sensitivity and specificity were 82.1 %, 74.5 % and 89.6 % in the test set by using EfficientNetV2-S model to differentiate F1-2 vs F3-4, and the AUC in test set were 0.763. For differentiating F1-3 vs F4, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 71.5 %, 73.4 % and 69.5 % in the test set. The AUC was 0.553 in test set. For differentiating F1-2 vs F4, the accuracy, sensitivity and specificity of our model were 84.3 %, 80.2 % and 88.3 % in the test set, and the AUC was 0.715, respectively. For differentiating F3 vs F4, the accuracy, sensitivity and specificity of EfficientNetV2-S model were 92.5 %, 89.1 % and 95.6 % in the test set, and the AUC was 0.696 in the test set.
The EfficientNetV2-S models based on multi-parametric MRI had the feasibility for staging of liver fibrosis because they showed high training speed and diagnostic performance in our study.
以往研究已证实，一些深度学习模型在肝纤维化分期方面具有较高的诊断性能。然而，预测肝纤维化的模型训练效率有待提高，以实现快速诊断和精准医疗。
EfficientNetV2-S的深度学习框架因其训练速度更快、参数效率更高而受到关注。我们的研究旨在基于EfficientNetV2-S框架开发用于肝纤维化分期的无创预测模型。
回顾性研究纳入了接受多参数腹部MRI检查的慢性肝病患者。将包括水平翻转、垂直翻转、透视变换和边缘增强在内的数据增强方法应用于多参数MR图像，以解决不同肝纤维化组之间的数据不平衡问题。使用EfficientNetV2-S模型预测肝纤维化分期F1-2、F1-3、F3、F4和F3-4。我们通过使用受试者操作特征曲线（ROC）分析评估模型在训练集、验证集和测试集中的诊断性能。
EfficientNetV2-S的总训练时间约为6小时。在测试集中，对于区分F1-2与F3，EfficientNetV2-S模型的准确率、灵敏度和特异度分别为96.2%、96.4%和96.0%。测试集中的AUC为0.559。使用EfficientNetV2-S模型区分F1-2与F3-4时，测试集中的准确率、灵敏度和特异度分别为82.1%、74.5%和89.6%，测试集中的AUC为0.763。对于区分F1-3与F4，EfficientNetV2-S模型在测试集中的准确率、灵敏度和特异度分别为71.5%、73.4%和69.5%。测试集中的AUC为0.553。对于区分F1-2与F4，我们模型在测试集中的准确率、灵敏度和特异度分别为84.3%、80.2%和88.3%，AUC分别为0.715。对于区分F3与F4，EfficientNetV2-S模型在测试集中的准确率、灵敏度和特异度分别为92.5%、89.1%和95.6%，测试集中的AUC为0.696。
基于多参数MRI的EfficientNetV2-S模型在肝纤维化分期方面具有可行性，因为在我们的研究中它们显示出较高的训练速度和诊断性能。
