An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images

Li, Hailiang; Weng, Jian; Shi, Yujian; Gu, Wanrong; Mao, Yijun; Wang, Yonghua; Liu, Weiwei; Zhang, Jiajie

doi:10.1038/s41598-018-25005-7

Cited by 118 publications

(71 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chi's method detected the location of thyroid nodules by manually gauging the position of the nodule, but failed to do so automatically. Li et al [33] and Wang et al [34] proposed an improved Fast R-CNN model for the detection of papillary thyroid carcinoma. Song et al [35] proposed a multitask cascade CNN model by using SSD framework and a spatial pyramid network to detect thyroid nodules coarsely and finely, respectively.…”

Section: Related Workmentioning

confidence: 99%

Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules

Duan

Zhang

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Ultrasonography is widely used in the clinical diagnosis of thyroid nodules. Ultrasound images of thyroid nodules have different appearances, interior features, and blurred borders that are difficult for a physician to diagnose into malignant or benign types merely through visual recognition. The development of artificial intelligence, especially deep learning, has led to great advances in the field of medical image diagnosis. However, there are some challenges to achieve precision and efficiency in the recognition of thyroid nodules. In this work, we propose a deep learning architecture, you only look once v3 dense multireceptive fields convolutional neural network (YOLOv3-DMRF), based on YOLOv3. It comprises a DMRF-CNN and multiscale detection layers. In DMRF-CNN, we integrate dilated convolution with different dilation rates to continue passing the edge and the texture features to deeper layers. Two different scale detection layers are deployed to recognize the different sizes of the thyroid nodules. We used two datasets to train and evaluate the YOLOv3-DMRF during the experiments. One dataset includes 699 original ultrasound images of thyroid nodules collected from a local health physical center. We obtained 10,485 images after data augmentation. Another dataset is an open-access dataset that includes ultrasound images of 111 malignant and 41 benign thyroid nodules. Average precision (AP) and mean average precision (mAP) are used as the metrics for quantitative and qualitative evaluations. We compared the proposed YOLOv3-DMRF with some state-of-the-art deep learning networks. The experimental results show that YOLOv3-DMRF outperforms others on mAP and detection time on both the datasets. Specifically, the values of mAP and detection time were 90.05 and 95.23% and 3.7 and 2.2 s, respectively, on the two test datasets. Experimental results demonstrate that the proposed YOLOv3-DMRF is efficient for detection and recognition of thyroid nodules for ultrasound images.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules

Duan

Zhang

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…[19] used the learning method of weakly supervise for the detection of nodules in lesions in mammography and chest radiography. [20] used CNNs for the detection of thyroid papillary cancer in thyroid ultrasound to detect thyroid papillary cancer. Reformulation of the same problem done by [21].…”

Section: Literature Surveymentioning

confidence: 99%

Mitral Valve Abnormality Detection by fully end to end with Deep Neural Network

Chandra¹,

Singh²,

Sarkar³

et al. 2020

IJEAT

View full text Add to dashboard Cite

The purpose of this research is to automatically identify normal and abnormal mitral leaflets in an apical four-chamber view.one of the widely spread valvular diseases is mitral valve disease in underdeveloped countries, still a burden for health sociality as well as countries. around 80 percent of valvular diseases are mitral valve disease problems. As far as World Heart Foundation Guidelines are concerned, It is totally based on mitral leaflets morphology. Due to the dependency on the sonographer's experience, it is highly subjective for argument. Measurement of thickness of leaflets, calcification detection, the pliability of leaflets required high experience about echocardiography as well as morphology. The motive of this research is to automatically identify the normal or abnormal mitral valve. If there is an abnormality in mitral leaflets then further investigation needed otherwise there is no further investigation that means measuring thickness, mitral valve area should not be required to measure. This research consists of two parts first automatically localize the region of interest second classifies the mitral leaflets whether normal or abnormal for localization yolo3 model mechanism with custom backend instead of darknet is used for taking area of interest automatically and for classification of normal and abnormal mitral leaflets, proposed pipeline is used, having f1, mAp score, and other matrices have measured.PR and ROC curves are drowned to support the results in the evaluation. the motive of this research is to serve nonexpert to identify abnormalities in mitral leaflets and sonographers to assess more efficiently. We used the Apical four-chamber view for this research.

show abstract

“…There is a considerable amount of interest in image processing through a network of neurons. To be more precise, several researchers [ 5 , 6 ] have explored the detection and assessment of severity of cancer in this manner. Figure 1 shows how, thanks to ConvNet, we can classify cancer as invasive or non-invasive.…”

Section: Previous Techniques and Commentsmentioning

confidence: 99%

Breast Cancer Detection Using Infrared Thermal Imaging and a Deep Learning Model

Mambou

Marešová

Krejcar

et al. 2018

Sensors

215

View full text Add to dashboard Cite

Women’s breasts are susceptible to developing cancer; this is supported by a recent study from 2016 showing that 2.8 million women worldwide had already been diagnosed with breast cancer that year. The medical care of a patient with breast cancer is costly and, given the cost and value of the preservation of the health of the citizen, the prevention of breast cancer has become a priority in public health. Over the past 20 years several techniques have been proposed for this purpose, such as mammography, which is frequently used for breast cancer diagnosis. However, false positives of mammography can occur in which the patient is diagnosed positive by another technique. Additionally, the potential side effects of using mammography may encourage patients and physicians to look for other diagnostic techniques. Our review of the literature first explored infrared digital imaging, which assumes that a basic thermal comparison between a healthy breast and a breast with cancer always shows an increase in thermal activity in the precancerous tissues and the areas surrounding developing breast cancer. Furthermore, through our research, we realized that a Computer-Aided Diagnostic (CAD) undertaken through infrared image processing could not be achieved without a model such as the well-known hemispheric model. The novel contribution of this paper is the production of a comparative study of several breast cancer detection techniques using powerful computer vision techniques and deep learning models.

show abstract

An improved deep learning approach for detection of thyroid papillary cancer in ultrasound images

Cited by 118 publications

References 33 publications

Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules

Efficient Deep Learning Architecture for Detection and Recognition of Thyroid Nodules

Mitral Valve Abnormality Detection by fully end to end with Deep Neural Network

Breast Cancer Detection Using Infrared Thermal Imaging and a Deep Learning Model

Contact Info

Product

Resources

About