Gu Fen, Deng Mei, Chen Xi, An Li, Zhao Zhen
Department of Ultrasound, Xijing Hospital, Fourth Military Medical University, Xi'an 710032, China.
Department of Ultrasound, Yuncheng Central Hospital, Shanxi Medical University, Yuncheng 044000, China.
Comput Intell Neurosci. 2022 Nov 23;2022:8912566. doi: 10.1155/2022/8912566. eCollection 2022.
In clinical applications, the classification of ultrasound images needs to be processed as an aid to diagnosis. Based on this, a hybrid model of cascaded deep convolutional neural network consisting of two different CNNs and a new classification method are designed and evaluated for its feasibility and effectiveness in ultrasound image classification. A total of 1000 pathological slides of patients with thyroid nodular lesions kept in the Department of Pathology of the First Affiliated Hospital of Lanzhou University, China, were retrospectively collected. After image acquisition, the images were randomly divided into training set, validation set, and test set in the ratio of 4 : 3 : 3. Three convolutional neural network models (VGG 19 model, Inception V3 model, and DenseNet 161 model) with pretraining parameters acquired on the training set were trained, and the models were combined to construct an integrated learning model, and the performance of the models in recognizing pathological images was evaluated based on the test set data. The experimental results show that the VGG 19 model is less effective in classification, with a correct rate of 88.20%, which is lower than that of Inception V3 and DenseNet161 models (92.87% and 92.95%). InceptionV3 and DenseNet161 models have significant advantages in terms of accuracy, number of parameters, and training efficiency, where the DenseNet161 model has faster convergence and better generalization performance, but occupies more video memory in the operation; moreover, the DenseNet161 operation time (1986.48 s) and response time (16 s) are better than the other two models. In addition, the integrated learning of InceptionV3 and DenseNet161 can improve the recognition of pathological images by a single model. Compared with other methods, the performance of the cascaded CNNs proposed in this study is significantly improved, and the multiview strategy can improve the performance of cascaded CNNs. The experimental results demonstrate the potential clinical application of cascaded CNNs, which can provide physicians with an objective second opinion and reduce their heavy workload, in addition to making the diagnosis of thyroid nodules easy and reproducible for people without medical expertise.
在临床应用中，超声图像的分类需要进行处理以辅助诊断。基于此，设计了一种由两个不同的卷积神经网络组成的级联深度卷积神经网络混合模型以及一种新的分类方法，并对其在超声图像分类中的可行性和有效性进行了评估。回顾性收集了中国兰州大学第一附属医院病理科保存的1000例甲状腺结节性病变患者的病理切片。图像采集后，将图像按照4∶3∶3的比例随机分为训练集、验证集和测试集。在训练集上获取预训练参数后，对三种卷积神经网络模型（VGG 19模型、Inception V3模型和DenseNet 161模型）进行训练，并将这些模型组合构建一个集成学习模型，基于测试集数据评估模型在识别病理图像方面的性能。实验结果表明，VGG 19模型的分类效果较差，正确率为88.20%，低于Inception V3模型和DenseNet161模型（分别为92.87%和92.95%）。InceptionV3模型和DenseNet161模型在准确率、参数数量和训练效率方面具有显著优势，其中DenseNet161模型收敛速度更快，泛化性能更好，但在运行时占用更多的显存；此外，DenseNet161模型的运行时间（1986.48秒）和响应时间（16秒）优于其他两个模型。此外，InceptionV3模型和DenseNet161模型的集成学习可以提高单一模型对病理图像的识别能力。与其他方法相比，本研究提出的级联卷积神经网络的性能有显著提高，多视图策略可以提高级联卷积神经网络的性能。实验结果证明了级联卷积神经网络潜在的临床应用价值，它可以为医生提供客观的第二意见，减轻其繁重的工作量，此外还能使没有医学专业知识的人轻松且可重复地诊断甲状腺结节。
