Hierarchical Temporal Attention Network for Thyroid Nodule Recognition Using Dynamic CEUS Imaging

Wan, Pengfei; Chen, Fang; Liu, Chunrui; Kong, Wencheng; Zhang, Daoqiang

doi:10.1109/tmi.2021.3063421

Cited by 20 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Being a non-invasive, less time consuming and relatively cheap procedure, nowadays CEUS investigation is used for various pathologies ranging from liver lesions [ 18 ], thyroid nodules [ 19 , 20 ] prostate cancer [ 21 , 22 ], rectal cancer [ 23 , 24 ] breast cancer [ 25 , 26 ] to kidney cystic lesions or tumors, [ 27 , 28 ]. In order to diagnose these pathologies from CEUS imaging, different methods can be used, but only few approaches for some pathologies take advantage of DNN and its associate learning paradigm DL, as follows.…”

Section: State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis

Căleanu

Sîrbu

Simion

2021

Sensors

View full text Add to dashboard Cite

Computer vision, biomedical image processing and deep learning are related fields with a tremendous impact on the interpretation of medical images today. Among biomedical image sensing modalities, ultrasound (US) is one of the most widely used in practice, since it is noninvasive, accessible, and cheap. Its main drawback, compared to other imaging modalities, like computed tomography (CT) or magnetic resonance imaging (MRI), consists of the increased dependence on the human operator. One important step toward reducing this dependence is the implementation of a computer-aided diagnosis (CAD) system for US imaging. The aim of the paper is to examine the application of contrast enhanced ultrasound imaging (CEUS) to the problem of automated focal liver lesion (FLL) diagnosis using deep neural networks (DNN). Custom DNN designs are compared with state-of-the-art architectures, either pre-trained or trained from scratch. Our work improves on and broadens previous work in the field in several aspects, e.g., a novel leave-one-patient-out evaluation procedure, which further enabled us to formulate a hard-voting classification scheme. We show the effectiveness of our models, i.e., 88% accuracy reported against a higher number of liver lesion types: hepatocellular carcinomas (HCC), hypervascular metastases (HYPERM), hypovascular metastases (HYPOM), hemangiomas (HEM), and focal nodular hyperplasia (FNH).

show abstract

Section: State Of the Artmentioning

confidence: 99%

“…Thyroid nodules diagnosis is performed in [ 20 ] on CEUS images using a hierarchical temporal attention network (HiTAN). The authors divided the algorithm in two categories: one is for the enhancement representation learning, and the other is for hierarchical lesion recognition.…”

Section: State Of the Artmentioning

confidence: 99%

Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis

Căleanu

Sîrbu

Simion

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In the field of thyroid nodules, ML is mostly based on 2D-US images, with an accuracy (ACC) of approximately 0.88–0.92 ( 25 , 26 ). To our knowledge, only two studies have used CEUS images to build AI models for diagnosing thyroid nodules ( 27 , 28 ). Wan et al.…”

Section: Introductionmentioning

confidence: 99%

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

Chen,

Zhang,

Zhu

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

ObjectivesTo apply machine learning to extract radiomics features from thyroid two-dimensional ultrasound (2D-US) combined with contrast-enhanced ultrasound (CEUS) images to classify and predict benign and malignant thyroid nodules, classified according to the Chinese version of the thyroid imaging reporting and data system (C-TIRADS) as category 4.Materials and methodsThis retrospective study included 313 pathologically diagnosed thyroid nodules (203 malignant and 110 benign). Two 2D-US images and five CEUS key frames (“2nd second after the arrival time” frame, “time to peak” frame, “2nd second after peak” frame, “first-flash” frame, and “second-flash” frame) were selected to manually label the region of interest using the “Labelme” tool. A total of 7 images of each nodule and their annotates were imported into the Darwin Research Platform for radiomics analysis. The datasets were randomly split into training and test cohorts in a 9:1 ratio. Six classifiers, namely, support vector machine, logistic regression, decision tree, random forest (RF), gradient boosting decision tree and extreme gradient boosting, were used to construct and test the models. Performance was evaluated using a receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), and F1-score were calculated. One junior radiologist and one senior radiologist reviewed the 2D-US image and CEUS videos of each nodule and made a diagnosis. We then compared their AUC and ACC with those of our best model.ResultsThe AUC of the diagnosis of US, CEUS and US combined CEUS by junior radiologist and senior radiologist were 0.755, 0.750, 0.784, 0.800, 0.873, 0.890, respectively. The RF classifier performed better than the other five, with an AUC of 1 for the training cohort and 0.94 (95% confidence interval 0.88–1) for the test cohort. The sensitivity, specificity, accuracy, PPV, NPV, and F1-score of the RF model in the test cohort were 0.82, 0.93, 0.90, 0.85, 0.92, and 0.84, respectively. The RF model with 2D-US combined with CEUS key frames achieved equivalent performance as the senior radiologist (AUC: 0.94 vs. 0.92, P = 0.798; ACC: 0.90 vs. 0.92) and outperformed the junior radiologist (AUC: 0.94 vs. 0.80, P = 0.039, ACC: 0.90 vs. 0.81) in the test cohort.ConclusionsOur model, based on 2D-US and CEUS key frames radiomics features, had good diagnostic efficacy for thyroid nodules, which are classified as C-TIRADS 4. It shows promising potential in assisting less experienced junior radiologists.

show abstract

“…However, the attention network only acts on high-level semantic features and does not give attention to low-level textures, so clinical features of nodules are easily lost. In literature 16 uses dynamic contrast-enhanced ultrasound (CEUS) imaging to diagnose nodules and combines dynamic enhanced feature learning with hierarchical nodule classification to effectively improve the accuracy of nodule identification, but its dataset is too small, and the network is too large. However, there is a risk of overfitting.…”

Section: Introductionmentioning

confidence: 99%

A novel ultrasound image diagnostic method for thyroid nodules

Zheng

Wang

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The incidence of thyroid nodules is increasing year by year. Accurate determination of benign and malignant nodules is an important basis for formulating treatment plans. Ultrasonography is the most widely used methodology in the diagnosis of benign and malignant nodules, but diagnosis by doctors is highly subjective, and the rates of missed diagnosis and misdiagnosis are high. To improve the accuracy of clinical diagnosis, this paper proposes a new diagnostic model based on deep learning. The diagnostic model adopts the diagnostic strategy of localization-classification. First, the distribution laws of the nodule size and nodule aspect ratio are obtained through data statistics, a multiscale localization network structure is a priori designed, and the nodule aspect ratio is obtained from the positioning results. Then, uncropped ultrasound images and nodule area image are correspondingly input into a two-way classification network, and an improved attention mechanism is used to enhance the feature extraction performance. Finally, the deep features, the shallow features, and the nodule aspect ratio are fused, and a fully connected layer is used to complete the classification of benign and malignant nodules. The experimental dataset consists of 4021 ultrasound images, where each image has been labeled under the guidance of doctors, and the ratio of the training set, validation set, and test set sizes is close to 3:1:1. The experimental results show that the accuracy of the multiscale localization network reaches 93.74%, and that the accuracy, specificity, and sensitivity of the classification network reach 86.34%, 81.29%, and 90.48%, respectively. Compared with the champion model of the TNSCUI 2020 classification competition, the accuracy rate is 1.52 points higher. Therefore, the network model proposed in this paper can effectively diagnose benign and malignant thyroid nodules.

show abstract

Hierarchical Temporal Attention Network for Thyroid Nodule Recognition Using Dynamic CEUS Imaging

Cited by 20 publications

References 54 publications

Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis

Deep Neural Architectures for Contrast Enhanced Ultrasound (CEUS) Focal Liver Lesions Automated Diagnosis

Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames

A novel ultrasound image diagnostic method for thyroid nodules

Contact Info

Product

Resources

About