Thyroid Nodule Segmentation in Ultrasound Images Based on Cascaded Convolutional Neural Network

Xiang, Ying; Yu, Zhihui; Yu, Ruiguo; Li, Xueming; Yu, Mo; Zhao, Mankun; Li, Kai

doi:10.1007/978-3-030-04224-0_32

Cited by 46 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, there is no case of mixing the same lesion data in the training set and the testing set 18 . In order to remove the irrelevant information in the edges, we complete edge cropping based on the supervised method based on Cascaded Convolutional Neural Network 19 . The thyroid lesion area is retained.…”

Section: Methodsmentioning

confidence: 99%

Thyroid nodules risk stratification through deep learning based on ultrasound images

Bai

Chang

et al. 2020

Medical Physics

Self Cite

View full text Add to dashboard Cite

Purpose Clinically, the risk stratification of thyroid nodules is usually used to formulate the next treatment plan. The American College of Radiology (ACR) thyroid imaging reporting and data system (TI‐RADS) is a type of medical standard widely used in classification diagnosis. It divides the nodule’s ACR TI‐RADS level into five levels by quantitative scoring, from benign to high suspicion of malignancy. However, such assessment often relies on the radiologists’ experience and is time consuming. So computer‐aided diagnosis is necessary. But many deep learning (DL) models are difficult for doctors to understand, limiting their applicability in clinical practice. In this work, we mainly focus on how to achieve automatic thyroid nodules risk stratification based on deep integration of deep learning and clinical experience. Methods An automatic hierarchical method of thyroid nodules risk based on deep learning is proposed, called risk stratification network (RS‐Net). It incorporates medical experience based on ACR TI‐RADS. The convolutional neural network (CNN) is used to classify the five categories in ACR TI‐RADS and assign their points respectively. According to the point totals, the level of risk can be obtained. In addition, a dataset involving 13 984 thyroid ultrasound images is established to develop and evaluate the proposed method. Results We have extensively compared the results of this paper with the evaluation results of sonographers. The accuracy of the risk stratification (TR1 to TR5) of the proposed method is 65%, and the mean absolute error (MAE) is 0.54. The MAE of the point totals (0 to 13 points) is 1.67. The Pearson's correlation between our method evaluation and doctor evaluation reached 0.84. For the benign and malignant classification, the performance indices accuracy, sensitivity, specificity, PPV, and NPV were 88.0%, 98.1%, 79.1%, 80.5%, and 97.9%, respectively. Our method's level of thyroid nodules risk stratification is comparable to that of a senior doctor. Conclusions This work provides a way to automate the risk stratification of thyroid nodules. Our method can effectively avoid missed diagnosis and misdiagnosis caused by the difference of observers so as to assist doctors to improve efficiency and diagnosis rate. Compared with the previous benign and malignant classification, the proposed method incorporates clinical experience. So it can greatly increase the clinicians’ trust in the DL model, thereby improving the applicability of the model in clinical practice.

show abstract

Section: Methodsmentioning

confidence: 99%

Thyroid nodules risk stratification through deep learning based on ultrasound images

Bai

Chang

et al. 2020

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the ROI of thyroid nodules was specified by experts and lacked automaton. Literature [13] designed a CNNs framework guided by clinical knowledge to achieve semi-automatic detection and classification of thyroid nodules in ultrasound images, achieving better classification results than previous automatic methods, but the detection speed of nodules is slow and there are limitations in clinical application. Literature [15] constructed a knowledge-guided auxiliary classifier generative adjoint network (KAC-GAN) for medical image enhancement, which improved the classification performance of ultrasonic thyroid nodules with good generalization ability and robustness.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

“…In recent years, deep learning has become a hot topic in the study of thyroid ultrasound image classification, especially the deep learning method based on convolutional neural Network (CNN) [10]. By introducing technologies such as local connection weight sharing pooling operation and nonlinear activation, this kind of method enables the network to automatically learn features from data, thus avoiding the constraints of traditional machine learning manual extraction of features and achieving good results [11][12][13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Deep Learning Networks for Classification of Ultrasonic Thyroid Nodules

Wang¹,

Yuan²,

Lv³

et al. 2022

jist

View full text Add to dashboard Cite

Thyroid nodules classification in ultrasound images is actively researched in the field of medical image processing. However, due to the low quality of ultrasound images, severe speckle noise, the complexity and diversity of nodules, etc., the classification and diagnosis of thyroid nodules are extremely challenging. At present, deep learning has been widely used in the field of medical image processing, and has achieved good results. However, there are still many problems to be solved. To address these issues, we propose a mask-guided hierarchical deep learning (MHDL) framework for the thyroid nodules classification. Specifically, we first develop a Mask RCNN network to locate thyroid nodules as the region of interest (ROI) for each image, to remove confounding information from input ultrasound images and extract texture, shape and radiology features as the low dimensional features. We then design a residual attention network to extract depth feature map of ROI, and combine the above low dimensional features to form a mixed feature space via dimension alignment technology. Finally, we present an AttentionDrop-based convolutional neural network to implement the classification of benign and malignant thyroid nodules in the mixed feature space. The experimental results show that our proposed method can obtain accurate nodule classification results, and hierarchical deep learning network can further improve the classification performance, which has immense clinical application value.

show abstract

“…Because the ultrasound imaging is noninvasive, realtime, and radiation-free, it is the key tool for diagnosis of thyroid nodules. However, the cumulative errors collected from blurring boundaries and significant changes in the appearance or intensity of thyroid nodules among different ultrasound images, make it challenging to analyze and recognize the subtle difference between malignant and benign nodules [ 2 ]. In this paper, we propose an efficient cascaded segmentation network and a dual-attention ResNet-based classification network to achieve automatic and accurate segmentation and classification of thyroid nodules, respectively.…”

Section: Introductionmentioning

confidence: 99%

Automatic Segmentation and Classification of Thyroid Nodules in Ultrasound Images with Convolutional Neural Networks

Wang

Yuan

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Ultrasound image plays an important role in the diagnosis of thyroid disease. Accurate segmentation and classification of thyroid nodules are challenging due to their heterogeneous appearance. In this paper, we propose an efficient cascaded segmentation framework and a dual-attention ResNet-based classification network to automatically achieve the accurate segmentation and classification of thyroid nodules, respectively. We evaluate our methods on the training dataset TN-SCUI 2020 Challenge. The 5-fold cross validation results demonstrate that the proposed methods achieve average IoU of 81.43% in segmentation task, and average F1 score of 83.22% in classification task. Finally, our method ranks the first place of segmentation task on the test set through the final online verification. The source code of the proposed methods is available at https://github.com/WAM AWAMA/TNSCUI2020-Seg-Rank1st.

show abstract

Thyroid Nodule Segmentation in Ultrasound Images Based on Cascaded Convolutional Neural Network

Cited by 46 publications

References 11 publications

Thyroid nodules risk stratification through deep learning based on ultrasound images

Thyroid nodules risk stratification through deep learning based on ultrasound images

Hierarchical Deep Learning Networks for Classification of Ultrasonic Thyroid Nodules

Automatic Segmentation and Classification of Thyroid Nodules in Ultrasound Images with Convolutional Neural Networks

Contact Info

Product

Resources

About