基于ResNet模型的甲状腺SPECT影像诊断

Diagnosis of thyroid SPECT image based on ResNet model

为了降低医生利用SPECT影像对甲状腺疾病进行临床诊断时的误诊率,提高深度学习算法在核医学影像辅助诊断中识别交叉影像特征的准确率,提出了基于ResNet模型的甲状腺SPECT影像诊断方法。利用深度卷积生成对抗网络(DCGAN)和高分辨率生成对抗网络(SRGAN)生成影像并提高分辨率,弥补训练数据的不足。同时,将残差块输出信息加上具有交叉特征影像信息的x i,在保留已学习影像特征的基础上增加对交叉特征的学习,改进了模型。对于交叉影像特征,使用交叉训练集对经过单一特征影像训练完成的改进ResNet神经网络模型进行再训练。实验结果表明,经过100轮迭代,交叉训练集训练的改进ResNet神经网络模型验证精度高达0.9633,验证损失降到0.1187,并趋于稳定;识别结果,召回率、精确率、特异度和F 1分数都在93.8%以上。经过改进的神经网络模型和新的训练方法对甲状腺SPECT影像表现出的典型症状识别率较高,优于其他基于卷积神经网络(CNN)的方法,对临床影像诊断具有参考价值。

In order to reduce the clinical misdiagnosis rate of of thyroid disease by using SPECT images,and improve the accuracy of deep learning algorithm in recognizing the features of cross images in nuclear medical image-assisted diagnosis,a thyroid SPECT image diagnosis method based on ResNet model was proposed.Deep Convolution Generative Adversarial Network(DCGAN)and Super-Resolution Generative Adversarial Network(SRGAN)were used to generate images and improve the resolution to make up for the deficiency of training data.At the same time,x i with the cross-feature image information was added to the residual block output information,and the learning of the cross-feature on the basis of retaining the learned image features,so as to improve the model.As for cross-image features,a cross-training set was proposed to retrain the improved ResNet neural network model that had been trained with a single feature image.The experimental results show that after 100 rounds of iteration,the verification accuracy of the improved residual neural network model trained by the cross-training set is as high as 0.9633,and the verification loss is reduced to 0.1187,which tends to be stable.The recall rate,precision rate,specificity and F 1 score are all above 93.8%in the recognition results.The improved neural network model and the new training method show higher typical symptom recognition rate for thyroid SPECT images than other methods based on convolutional neural network(CNN),and have reference value for clinical image diagnosis.