ObjectiveThe aim of this study is to develop a model using Deep Neural Network (DNN) to diagnose thyroid nodules in patients with Hashimoto’s Thyroiditis.MethodsIn this retrospective study, we included 2,932 patients with thyroid nodules who underwent thyroid ultrasonogram in our hospital from January 2017 to August 2019. 80% of them were included as training set and 20% as test set. Nodules suspected for malignancy underwent FNA or surgery for pathological results. Two DNN models were trained to diagnose thyroid nodules, and we chose the one with better performance. The features of nodules as well as parenchyma around nodules will be learned by the model to achieve better performance under diffused parenchyma. 10-fold cross-validation and an independent test set were used to evaluate the performance of the algorithm. The performance of the model was compared with that of the three groups of radiologists with clinical experience of <5 years, 5–10 years, >10 years respectively.ResultsIn total, 9,127 images were collected from 2,932 patients with 7,301 images for the training set and 1,806 for the test set. 56% of the patients enrolled had Hashimoto’s Thyroiditis. The model achieved an AUC of 0.924 for distinguishing malignant and benign nodules in the test set. It showed similar performance under diffused thyroid parenchyma and normal parenchyma with sensitivity of 0.881 versus 0.871 (p = 0.938) and specificity of 0.846 versus 0.822 (p = 0.178). In patients with HT, the model achieved an AUC of 0.924 to differentiate malignant and benign nodules which was significantly higher than that of the three groups of radiologists (AUC = 0.824, 0.857, 0.863 respectively, p < 0.05).ConclusionThe model showed high performance in diagnosing thyroid nodules under both normal and diffused parenchyma. In patients with Hashimoto’s Thyroiditis, the model showed a better performance compared to radiologists with various years of experience.
In recent years, deep convolutional neural networks have gradually become the preferred method for image processing. After the development of Classification, Detection and Segmentation, a large variety of state-of-the-art models and algorithms have emerged in the field. However, for some specific data sets or tasks, not all methods are applicable, which is inconvenient to researchers. This paper took the data set provided in the airbus ship detection challenge in Kaggle as an example to explore an easy and effective method for segmentation tasks of data sets with class imbalance. This paper used U-Net with a pre-trained ResNets model, and tried different methods to explore the feature of the set. In the process of training ResNets, this paper proposed a new convolutional block structure which is inspired by Fibonacci sequence, but the effect is not good. In the end, the mF2 values of the models this paper trained achieved good results, which is better than the model of the combined training of ResNets and ordinary U-Net34. Moreover, the training parameters are less than that. This paper believe that this simple and effective training method will bring convenience to researchers in related fields.
With the rapid development of Internet technology, various social networking platforms, especially mobile social networking platforms, continue to increase, resulting in a large amount of public opinion information. Internet public opinion has a clear emotional orientation, and its emotional orientation is very easy to spread and be infected, and even affect the development of the event. Aiming at the characteristics of lyric information rich and which are easy to change with time, the lyric theme analysis model and the lyric emotion evolution model are proposed. The LDA model is used to extract the topic from the lyric text in a period of time, and the sensational heat value is calculated according to the forwarding amount and the number of comments, and the lyrical theme with the highest heat is obtained. The relative entropy between sub-topics in the adjacent time slice of a specific hot topic is calculated, and the degree of association between the topics in the adjacent time slice is determined, thereby analyzing whether there is a split of the sub-topic and a new topic. Then the evaluation object is extracted, combined with the joint deep neural network model to judge the emotions of each evaluation object in different time, and the emotional evolution of the hot topic is analyzed from multiple dimensions. Finally, an example analysis of the network public opinion information from June to July 2018 is carried out to verify the validity of the above model. The model effectively solves the problems of immature emotion analysis model and low accuracy of emotion classification in the current public opinion analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.