Automated location of thyroid nodules in ultrasound images with improved YOLOV3 network

2020 ◽  
pp. 1-16
Author(s):  
Ling Zhang ◽  
Yan Zhuang ◽  
Zhan Hua ◽  
Lin Han ◽  
Cheng Li ◽  
...  
Keyword(s):  
Thyroid Nodule ◽  
Thyroid Nodules ◽  
Automatic Segmentation ◽  
Ultrasound Image ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Ultrasound Images ◽  
Semantic Features ◽  
Low Contrast ◽  
Automated Method

BACKGROUND: Thyroid ultrasonography is widely used to diagnose thyroid nodules in clinics. Automatic localization of nodules can promote the development of intelligent thyroid diagnosis and reduce workload of radiologists. However, besides the ultrasound image has low contrast and high noise, the thyroid nodules are diverse in shape and vary greatly in size. Thus, thyroid nodule detection in ultrasound images is still a challenging task. OBJECTIVE: This study proposes an automatic detection algorithm to locate nodules in B ultrasound images and Doppler ultrasound images. This method can be used to screen thyroid nodules and provide a basis for subsequent automatic segmentation and intelligent diagnosis. METHODS: We develop and optimize an improved YOLOV3 model for detecting thyroid nodules in ultrasound images with B-mode and Doppler mode. Improvements include (1) using the high-resolution network (HRNet) as the basic network for gradually extracting high-level semantic features to reduce the missed detection and misdetection, (2) optimizing the loss function for single target detection like nodules, and (3) obtaining the anchor boxes by clustering the candidate frames of real nodules in the dataset. RESULTS: The experimental results of applying to 8000 clinical ultrasound images show that the new method developed and tested in this study can effectively detect thyroid nodules. The method achieves 94.53% mean precision and 95.00% mean recall. CONCLUTIONS: The study demonstrates a new automated method that enables to achieve high detection accuracy and effectively locate thyroid nodules in various ultrasound images without any user interaction, which indicates its potential clinical application value for the thyroid nodule screening.

Detection of Thyroid Nodules with Ultrasound Images Based on Deep Learning

2020 ◽  
Vol 16 (2) ◽  
pp. 174-180 ◽  
Author(s):  
Xia Yu ◽  
Hongjie Wang ◽  
Liyong Ma
Keyword(s):  
Deep Learning ◽  
Thyroid Nodule ◽  
Thyroid Nodules ◽  
Detection Method ◽  
Ultrasound Images ◽  
True Negative ◽  
Automated Method ◽  
High Incidence ◽  
Sensitivity Specificity ◽  
Physician Workload

Background: Thyroid nodules are a common clinical entity with high incidence. Ultrasound is often employed to detect and evaluate thyroid nodules. The development of an efficient automated method to detect thyroid nodules using ultrasound has the potential to reduce both physician workload and operator-dependence. Objective: To study the method of automatic detection of thyroid nodules based on deep learning using ultrasound, and to obtain the detection method with higher accuracy and better performance. Methods: A total of 1200 ultrasound images of thyroid nodules and 800 ultrasound thyroid images without nodule are collected. An improved faster R-CNN based detection method of thyroid nodule is proposed. Instead of using VGG16 as the backbone, ResNet is employed as the backbone for faster R-CNN. SVM, CNN and Faster-RCNN methods are used for thyroid nodule detection test. Precision, sensitivity, specificity and F1-score indicators are used to evaluate the detection performance of different methods. Results: The method based on deep learning is superior to that based on SVM. Faster R-CNN method and the improved method are better than CNN method. Compared with VGG16 as the backbone, RestNet101 backbone based faster R-CNN method achieves better thyroid detection effect. From the accuracy index, the proposed method is 0.084, 0.032 and 0.019 higher than SVM, CNN and faster R-CNN, respectively. Similar results can be seen in precision, sensitivity, specificity and F1-Score indicators. Conclusion: The proposed method of deep learning achieves the best performance values with the highest true positive and true negative detection compared to other methods and performs best in the detection of thyroid nodules.

scholarly journals Automatic Malignant Thyroid Nodule Recognition in Ultrasound Images based on Deep Learning

2020 ◽  
Vol 185 ◽  
pp. 03021
Author(s):  
Meng Zhou ◽  
Rui Wang ◽  
Peng Fu ◽  
Yang Bai ◽  
Ligang Cui
Keyword(s):  
Deep Learning ◽  
Thyroid Nodule ◽  
Thyroid Nodules ◽  
Data Augmentation ◽  
Medical Training ◽  
Ultrasound Image ◽  
Learning Model ◽  
Training Data ◽  
Ultrasound Images ◽  
Deep Learning Model

As the most common malignancy in the endocrine system, thyroid cancer is usually diagnosed by discriminating the malignant nodules from the benign ones using ultrasonography, whose interpretation results primarily depends on the subjectivity judgement of the radiologists. In this study, we propose a novel cascade deep learning model to achieve automatic objective diagnose during ultrasound examination for assisting radiologists in recognizing benign and malignant thyroid nodules. First, the simplified U-net is employed to segment the region of interesting (ROI) of the thyroid nodules in each frame of the ultrasound image automatically. Then, to alleviate the limitation that medical training data are relatively small in size, the improved Conditional Variational Auto-Encoder (CVAE) learning the probability distribution of ROI images is trained to generate new images for data augmentation. Finally, ResNet50 is trained with both original and generated ROI images. As consequence, the deep learning model formed by the trained U-net and trained Resnet-50 cascade can achieve malignant thyroid nodule recognition with the accuracy of 87.4%, the sensitivity of 92%, and the specificity of 86.8%.

scholarly journals Segmentation of thyroid nodules using Improvised U-Net Architecture

2020 ◽  
Vol 9 (8) ◽  
pp. 56-60
Keyword(s):  
Thyroid Nodules ◽  
Performance Metrics ◽  
Automatic Segmentation ◽  
Research Work ◽  
Ultrasound Image ◽  
True Positive Rate ◽  
Medical Image Segmentation ◽  
Common Disease ◽  
Low Resolution ◽  
Feature Map

Thyroid nodules are considered as most common disease found in adults and thyroid cancer has increased over the years rapidly. Further automatic segmentation for ultrasound image is quite difficult due to the image poor quality, hence several researcher have focused and observed that U-Net achieves significant performance in medical image segmentation. However U-net faces the problem of low resolution which causes smoothness in image, hence in this research work we have proposed improvised U-Net which helps in achieving the better performance. The main aim of this research work is to achieve the probable Region of Interest through segmentation with better efficiency. In order to achieve that Improvised U-Net develops two distinctive feature map i.e. High level feature Map and low level feature map to avoid the problem of low resolution. Further proposed model is evaluated considering the standard dataset based on performance metrics such as Dice Coefficient and True positive Rate. Moreover our model achieves better performance than the existing model.

scholarly journals Thyroid Nodules Classification in Medical Ultrasound Images using Deep Learning

2020 ◽  
Vol 9 (7) ◽  
pp. 1211-1215
Keyword(s):  
Deep Learning ◽  
Thyroid Nodule ◽  
Thyroid Nodules ◽  
Second Opinion ◽  
Learning Approach ◽  
Ultrasound Images ◽  
Medical Ultrasound ◽  
Cad System ◽  
Improve Accuracy

Ultrasound scanning is most excellent significant diagnosis techniques utilized for thyroid nodules identification. A thyroid nodule is unnecessary cells that can develop in your base of neck which can be normal or cancerous. Many Computer added diagnosis systems (CAD) have been developed as a second opinion for radiologist. The thyroid nodules classification using machine learning and deep learning approach is latest trend which is using to improve accuracy for differentiation of thyroid nodules from benign and malignant type. In this paper we review the most recent work on CAD system which uses different feature extraction technique and classifier used for thyroid nodules classification with deep learning approach. This paper we illustrate the result obtained by these studies and highlight the limitation of each proposed methods. Moreover we summarize convolution neural network (CNN) architecture for classification of thyroid nodule. This literature review is meant at researcher but it also useful for radiologist who is interesting in CAD tool in ultrasound imaging for second opinion.

scholarly journals An Improved Object Detection Method using Feature Map Refinement and Anchor Optimization

2021 ◽  
Vol 15 ◽  
pp. 541-549
Author(s):  
Yuxia Wang ◽  
Wenzhu Yang ◽  
Tongtong Yuan ◽  
Qian Li
Keyword(s):  
Object Detection ◽  
Detection Method ◽  
Search Space ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Semantic Features ◽  
Feature Map ◽  
Input Size ◽  
Fusion Operation ◽  
Different Levels

Lower detection accuracy and insufficient detection ability for small objects are the main problems of the region-free object detection algorithm. Aiming at solving the abovementioned problems, an improved object detection method using feature map refinement and anchor optimization is proposed. Firstly, the reverse fusion operation is performed on each of the object detection layer, which can provide the lower layers with more semantic information by the fusion of detection features at different levels. Secondly, the self-attention module is used to refine each detection feature map, calibrates the features between channels, and enhances the expression ability of local features. In addition, the anchor optimization model is introduced on each feature layer associated with anchors, and the anchors with higher probability of containing an object and more closely match the location and size of the object are obtained. In this model, semantic features are used to confirm and remove negative anchors to reduce search space of the objects, and preliminary adjustments are made to the locations and sizes of anchors. Comprehensive experimental results on PASCAL VOC detection dataset demonstrate the effectiveness of the proposed method. In particular, with VGG-16 and lower dimension 300×300 input size, the proposed method achieves a mAP of 79.1% on VOC 2007 test set with an inference speed of 24.7 milliseconds per image.

Breast Ultrasound Image Processing

2021 ◽  
pp. 44-69
Author(s):  
Strivathsav Ashwin Ramamoorthy ◽  
Varun P. Gopi
Keyword(s):  
Ultrasound Image ◽  
Breast Ultrasound ◽  
Ultrasound Images ◽  
Low Contrast ◽  
Cad Systems ◽  
Cad System ◽  
Ultrasound Image Processing ◽  
Serious Disease ◽  
Aided Diagnosis ◽  
Enhancement Algorithm

Breast cancer is a serious disease among women, and its early detection is very crucial for the treatment of cancer. To assist radiologists who manually delineate the tumour from the ultrasound image an automatic computerized method of detection called CAD (computer-aided diagnosis) is developed to provide valuable inputs for radiologists. The CAD systems is divided into many branches like pre-processing, segmentation, feature extraction, and classification. This chapter solely focuses on the first two branches of the CAD system the pre-processing and segmentation. Ultrasound images acquired depends on the operator expertise and is found to be of low contrast and fuzzy in nature. For the pre-processing branch, a contrast enhancement algorithm based on fuzzy logic is implemented which could help in the efficient delineation of the tumour from ultrasound image.

Segmentation Methods in Ultrasound Images

2011 ◽  
pp. 377-390
Author(s):  
Farhang Sahba
Keyword(s):  
Image Segmentation ◽  
Automatic Segmentation ◽  
Transrectal Ultrasound ◽  
Ultrasound Image ◽  
The Body ◽  
Ultrasound Images ◽  
Sound Waves ◽  
Medical Test ◽  
Segmentation Methods ◽  
Segmentation Task

Ultrasound imaging now has widespread clinical use. It involves exposing a part of the body to highfrequency sound waves in order to generate images of the inside of the body. Because it is a real-time procedure, the ultrasound images show the movement of the body’s internal structure as well. It is usually a painless medical test and its procedures seem to be safe. Despite recent improvement in the quality of information from an ultrasound device, these images are still a challenging case for segmentation. Thus, there is much interest in understanding how to apply an image segmentation task to ultrasound data and any improvements in this regard are desirable. Many methods have been introduced in existing literature to facilitate more accurate automatic or semi-automatic segmentation of ultrasound images. This chapter is a basic review of the works on ultrasound image segmentation classified by application areas, including segmentation of prostate transrectal ultrasound (TRUS), breast ultrasound, and intravascular ultrasound (IVUS) images.

Segmentation Methods in Ultrasound Images

2009 ◽  
pp. 473-487
Author(s):  
Farhang Sahba
Keyword(s):  
Image Segmentation ◽  
Automatic Segmentation ◽  
Transrectal Ultrasound ◽  
Ultrasound Image ◽  
The Body ◽  
Ultrasound Images ◽  
Sound Waves ◽  
Medical Test ◽  
Segmentation Methods ◽  
Segmentation Task

Ultrasound imaging now has widespread clinical use. It involves exposing a part of the body to highfrequency sound waves in order to generate images of the inside of the body. Because it is a real-time procedure, the ultrasound images show the movement of the body’s internal structure as well. It is usually a painless medical test and its procedures seem to be safe. Despite recent improvement in the quality of information from an ultrasound device, these images are still a challenging case for segmentation. Thus, there is much interest in understanding how to apply an image segmentation task to ultrasound data and any improvements in this regard are desirable. Many methods have been introduced in existing literature to facilitate more accurate automatic or semi-automatic segmentation of ultrasound images. This chapter is a basic review of the works on ultrasound image segmentation classified by application areas, including segmentation of prostate transrectal ultrasound (TRUS), breast ultrasound, and intravascular ultrasound (IVUS) images.

AUTOMATIC THYROID NODULE SEGMENTATION AND COMPONENT ANALYSIS IN ULTRASOUND IMAGES

2010 ◽  
Vol 22 (02) ◽  
pp. 81-89 ◽  
Author(s):  
Chuan-Yu Chang ◽  
Hsin-Cheng Huang ◽  
Shao-Jer Chen
Keyword(s):  
Support Vector Machines ◽  
Decision Tree ◽  
Thyroid Nodule ◽  
Thyroid Nodules ◽  
Support Vector ◽  
Automatic Process ◽  
Ultrasound Images ◽  
Decision Tree Algorithm ◽  
Vector Machines ◽  
Refinement Process

Heterogeneous thyroid nodules have distinct components and vague boundaries in ultrasound (US) images. It is difficult for radiologists and physicians to manually draw the complete shape of a nodule, or distinguish what kind of components a nodule has. Hence, this article presents an automatic process for nodule segmentation and component classification. A decision-tree algorithm is used to segment the possible nodular area. A refinement process is then applied to recover the nodular shape. Finally, a hierarchical method based on support vector machines (SVMs) is used to identify the components in the nodular lesion. Experimental results of the proposed approach were compared with those of other methods.

Sign in / Sign up

Export Citation Format

Share Document