Convolutional Neural Networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR

Eroğlu, Yeşim; Yıldırım, Muhammed; Çınar, Ahmet

doi:10.1016/j.compbiomed.2021.104407

Cited by 81 publications

(40 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of MobileNet [13] and StyleGAN2-ADA shows the highest accuracy improvement of 21.6%. As to the comparison with previous methods [14,15,16,6] using the same dataset, the SSCE* structure shows a maximum of 23.9% improvement. We believe that our proposed state-of-the-art method can be potentially regarded as an on-the-fly medical US image diagnosis tool.…”

Section: Intorductionmentioning

confidence: 86%

Semi-supervised classification of medical ultrasound images based on generative adversarial network

Liu¹,

Lee²,

Shen³

2022

Preprint

View full text Add to dashboard Cite

Medical ultrasound (US) is one of the most widely used imaging modalities in clinical practice. However, its use presents unique challenges such as variable imaging quality. Deep learning (DL) can be used as an advanced medical US images analysis tool, while the performance of the DL model is greatly limited by the scarcity of big datasets. Here, we develop semi-supervised classification enhancement (SSCE) structures by constructing seven convolutional neural network (CNN) models and one of the most state-of-the-art generative adversarial network (GAN) models, StyleGAN2-ADA, to address this problem. A breast cancer dataset with 780 images is used as our base dataset. The results show that our SSCE structures obtain an accuracy of up to 97.9%, showing a maximum 21.6% improvement compared with utilizing CNN models alone and outperforming the previous methods using the same dataset by up to 23.9%. We believe our proposed state-of-the-art method can be regarded as a potential auxiliary tool for on-the-fly diagnoses of medical US images.

show abstract

Section: Intorductionmentioning

confidence: 86%

Semi-supervised classification of medical ultrasound images based on generative adversarial network

Liu¹,

Lee²,

Shen³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Note that, their sample sizes range from 45 to 359, whereas our sample size is 23,354. In 15 , 16 , they use the method of mRMR as the feature selection method and the similar architecture to classify the images. In 15 , they focus on the breast and use ultrasonography as input images.…”

Section: Conclusion and Comparisonmentioning

confidence: 99%

“…In 15 , 16 , they use the method of mRMR as the feature selection method and the similar architecture to classify the images. In 15 , they focus on the breast and use ultrasonography as input images. In 16 , they proposed the hybrid models with KNN to achieve great performance in F1-score and sensitivity.…”

Section: Conclusion and Comparisonmentioning

confidence: 99%

Ensemble classification and segmentation for intracranial metastatic tumors on MRI images based on 2D U-nets

Sun

et al. 2021

Sci Rep

View full text Add to dashboard Cite

The extraction of brain tumor tissues in 3D Brain Magnetic Resonance Imaging (MRI) plays an important role in diagnosis before the gamma knife radiosurgery (GKRS). In this article, the post-contrast T1 whole-brain MRI images had been collected by Taipei Veterans General Hospital (TVGH) and stored in DICOM format (dated from 1999 to 2018). The proposed method starts with the active contour model to get the region of interest (ROI) automatically and enhance the image contrast. The segmentation models are trained by MRI images with tumors to avoid imbalanced data problem under model construction. In order to achieve this objective, a two-step ensemble approach is used to establish such diagnosis, first, classify whether there is any tumor in the image, and second, segment the intracranial metastatic tumors by ensemble neural networks based on 2D U-Net architecture. The ensemble for classification and segmentation simultaneously also improves segmentation accuracy. The result of classification achieves a F1-measure of $$75.64\%$$ 75.64 % , while the result of segmentation achieves an IoU of $$84.83\%$$ 84.83 % and a DICE score of $$86.21\%$$ 86.21 % . Significantly reduce the time for manual labeling from 30 min to 18 s per patient.

show abstract

“…With cloud technology, the size of the data kept in databases is also increasing. It is important to evaluate this increasing amount of data with machine learning methods and produce results that can be used for technical and commercial purposes (Eroğlu et al, 2021).…”

Section: Internet Of Thinksmentioning

confidence: 99%

An in-depth exam of IoT, IoT Core Components, IoT Layers, and Attack Types

Yıldırım¹,

Demiroğlu²,

Şenol³

2021

European Journal of Science and Technology

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) is a global network of devices that can communicate with each other through different communication protocols and have the ability to detect and process data. Since the Internet of Things connects electronic devices to the Internet for efficient examination and execution of daily activities, it has a seriously positive effect on human life. These devices use some communication protocols to communicate with each other. The selection of these communication protocols is of great importance. The data obtained from these smart devices are stored with the help of cloud technology. These stored data reveal the concept of big data. The processing and analysis of these data are of great importance. Machine learning methods are of great importance in processing this large amount of data. In this study, IoT, the basic components of the IoT, layer structure, security attacks are examined.

show abstract

Convolutional Neural Networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR

Cited by 81 publications

References 36 publications

Semi-supervised classification of medical ultrasound images based on generative adversarial network

Semi-supervised classification of medical ultrasound images based on generative adversarial network

Ensemble classification and segmentation for intracranial metastatic tumors on MRI images based on 2D U-nets

An in-depth exam of IoT, IoT Core Components, IoT Layers, and Attack Types

Contact Info

Product

Resources

About