scholarly journals A New Classification Method in Ultrasound Images of Benign and Malignant Thyroid Nodules Based on Transfer Learning and Deep Convolutional Neural Network

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9 ◽  
Author(s):  
Weibin Chen ◽  
Zhiyang Gu ◽  
Zhimin Liu ◽  
Yaoyao Fu ◽  
Zhipeng Ye ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Thyroid Nodules ◽  
Ultrasound Image ◽  
Image Data ◽  
Data Sets ◽  
Thyroid Ultrasound ◽  
Joint Training ◽  
Secondary Transfer

Thyroid nodule is a clinical disorder with a high incidence rate, with large number of cases being detected every year globally. Early analysis of a benign or malignant thyroid nodule using ultrasound imaging is of great importance in the diagnosis of thyroid cancer. Although the b-mode ultrasound can be used to find the presence of a nodule in the thyroid, there is no existing method for an accurate and automatic diagnosis of the ultrasound image. In this pursuit, the present study envisaged the development of an ultrasound diagnosis method for the accurate and efficient identification of thyroid nodules, based on transfer learning and deep convolutional neural network. Initially, the Total Variation- (TV-) based self-adaptive image restoration method was adopted to preprocess the thyroid ultrasound image and remove the boarder and marks. With data augmentation as a training set, transfer learning with the trained GoogLeNet convolutional neural network was performed to extract image features. Finally, joint training and secondary transfer learning were performed to improve the classification accuracy, based on the thyroid images from open source data sets and the thyroid images collected from local hospitals. The GoogLeNet model was established for the experiments on thyroid ultrasound image data sets. Compared with the network established with LeNet5, VGG16, GoogLeNet, and GoogLeNet (Improved), the results showed that using GoogLeNet (Improved) model enhanced the accuracy for the nodule classification. The joint training of different data sets and the secondary transfer learning further improved its accuracy. The results of experiments on the medical image data sets of various types of diseased and normal thyroids showed that the accuracy rate of classification and diagnosis of this method was 96.04%, with a significant clinical application value.

scholarly journals Thyroid ultrasound image classification using a convolutional neural network

2021 ◽  
Vol 0 (0) ◽  
pp. 0-0
Author(s):  
Yi-Cheng Zhu ◽  
Peng-Fei Jin ◽  
Jie Bao ◽  
Quan Jiang ◽  
Ximing Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Ultrasound Image ◽  
Thyroid Ultrasound

Classification of Deep Convolutional Neural Network in Thyroid Ultrasound Images

2020 ◽  
Vol 10 (8) ◽  
pp. 1943-1948
Author(s):  
Ran Hui ◽  
Jiaxing Chen ◽  
Yu Liu ◽  
Lin Shi ◽  
Chao Fu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
System Analysis ◽  
Ultrasound Image ◽  
Deep Convolutional Neural Network ◽  
Image Feature ◽  
Ultrasound Images ◽  
Thyroid Ultrasound ◽  
Neural Network Learning ◽  
Neural Network Theory

Objective: To explore the application of deep convolutional neural network theory in thyroid ultrasound image system analysis and eigenvalue extraction to help medically predict the patient’s condition. Methods: The thyroid color ultrasound image dataset of our hospital was selected as the training and test samples. The comparison experiment was designed in the deep convolutional neural network learning framework to test the feasibility of the method. Results: Image information classification based on deep neural network algorithm can predict thyroid nodule lesions well, and has good accuracy in the classification test of benign and malignant nodules. Conclusion: The clinical application of deep learning method and thyroid ultrasound image feature value extraction and system analysis can improve the accuracy of clinical thyroid benign and malignant classification.

scholarly journals Nodule Localization in Thyroid Ultrasound Images with a Joint-Training Convolutional Neural Network

2020 ◽  
Vol 33 (5) ◽  
pp. 1266-1279
Author(s):  
Ruoyun Liu ◽  
Shichong Zhou ◽  
Yi Guo ◽  
Yuanyuan Wang ◽  
Cai Chang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Ultrasound Images ◽  
Thyroid Ultrasound ◽  
Joint Training

scholarly journals Pavement Crack Detection Using Convolutional Neural Network

10.29007/h4k6 ◽  
2020 ◽  
Author(s):  
Alaa Sheta ◽  
Hamza Turabieh ◽  
Sultan Aljahdali ◽  
Abdulaziz Alangari
Keyword(s):  
Neural Network ◽  
New York ◽  
Convolutional Neural Network ◽  
Crack Detection ◽  
Stable Condition ◽  
Image Data ◽  
Data Sets ◽  
Data Set ◽  
Data Division ◽  
The Usa

Automating the process of detecting pavement cracks became a challenge mission. In the last few decades, many methods were proposed to solve this problem. The reason is that maintaining a stable condition of roads is essential for the safety of people and public properties. It was reported that maintaining one mile of roads in New York City in the USA might cost from four to ten thousand dollars. In this paper, we explore our initial idea of developing a lightweight Convolutional Neural Network (CNN or ConvNet) model that can be used to detect pavement cracks. The proposed CNN was trained using the AigleRN data set, which contains 400 images of road cracks of 480×320 resolution. The proposed lightweight CNN architecture performed a better fitting to the image data set due to the reduction in the number of parameters. The proposed CNN was capable of detecting cracks with a various number of sample images. We simulated the CNN architecture over different sizes of training/testing (i.e., 90/10, 80/20, and 70/30) data sets for 11 runs. The obtained results show that 90/10 data division for training and testing is outperformed other categories with an average accuracy of 97.27%.

scholarly journals Diagnostic Breast Cancer Image Data Classification using CNN

2021 ◽  
Vol 12 (2) ◽  
Author(s):  
K. Karthik, Et. al.
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
Image Data ◽  
Computer Assisted ◽  
Data Sets ◽  
Computer Assisted Detection ◽  
Deep Cnn ◽  
Image Data Classification

Breast cancer has been  dangerous form of cancer. In this report, we use a convolutional neural network to scan and separate infected cells.In this we diagnose if its benign or malignant cancer bulk using computer assisted detection(CAD). The productivity of open CAD has always been inadequate. Here, we use a deep CNN-based content detection method.We create narrower and broader images of histology patches with cell and tumour attributes. CNN constitutes unorganized data specifically for image data which has been said to be thriving in the area of image recognition .We use highly interconnected layer first cnn, in which those layers are incorporated before the first convolutional layer, since CNN does not support data sets.  

scholarly journals Differentiation of the Follicular Neoplasm on the Gray-Scale US by Image Selection Subsampling along with the Marginal Outline Using Convolutional Neural Network

2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Jeong-Kweon Seo ◽  
Young Jae Kim ◽  
Kwang Gi Kim ◽  
Ilah Shin ◽  
Jung Hee Shin ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Operating Characteristic ◽  
Thyroid Nodules ◽  
Follicular Adenoma ◽  
Training Data ◽  
Follicular Neoplasm ◽  
Learning Approach ◽  
Data Sets ◽  
Benign Adenoma

We conducted differentiations between thyroid follicular adenoma and carcinoma for 8-bit bitmap ultrasonography (US) images utilizing a deep-learning approach. For the data sets, we gathered small-boxed selected images adjacent to the marginal outline of nodules and applied a convolutional neural network (CNN) to have differentiation, based on a statistical aggregation, that is, a decision by majority. From the implementation of the method, introducing a newly devised, scalable, parameterized normalization treatment, we observed meaningful aspects in various experiments, collecting evidence regarding the existence of features retained on the margin of thyroid nodules, such as 89.51% of the overall differentiation accuracy for the test data, with 93.19% of accuracy for benign adenoma and 71.05% for carcinoma, from 230 benign adenoma and 77 carcinoma US images, where we used only 39 benign adenomas and 39 carcinomas to train the CNN model, and, with these extremely small training data sets and their model, we tested 191 benign adenomas and 38 carcinomas. We present numerical results including area under receiver operating characteristic (AUROC).

scholarly journals Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Young-Gon Kim ◽  
Sungchul Kim ◽  
Cristina Eunbee Cho ◽  
In Hye Song ◽  
Hee Jin Lee ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Frozen Section ◽  
Medical Center ◽  
External Validation ◽  
Model Performance ◽  
Classification Model ◽  
Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Sign in / Sign up

Export Citation Format

Share Document