Key result
The CNNcc deep learning model achieved an 89.1% classification accuracy with the lowest loss parameter (0.29) on carotid artery intima-media thickness ultrasound images, avoiding the overfitting seen in other models.
Why the study?
Carotid artery disease can lead to stroke, which causes significant disability and death if not diagnosed early, motivating the comparison of deep learning architectures for early diagnosis using ultrasound images.
Which deep learning architecture provides the best classification performance for Carotid Artery Intima-Media Thickness ultrasound images?
Which deep learning architecture provides the best classification performance for Carotid Artery Intima-Media Thickness ultrasound images?
Deep learning architectures, particularly the proposed CNNcc model, can effectively classify carotid artery intima-media thickness on ultrasound images without overfitting, potentially aiding in early stroke risk assessment.
May aid automated CIMT classification on ultrasound; hypothesis-generating pending prospective validation.
Deep learning is a machine learning technique that uses deep neural networks, which are multilayer neural networks that contain two or more hidden layers. In recent years, deep learning algorithms are also used to solve machine learning problems in medicine. Carotid artery disease is a type of cardiovascular disease that can result in a stroke. If a stroke is not diagnosed early, it is in the first place among the disabling diseases and the third place for the most common cause of death after cancer and heart disease. In this study, the classification performances of deep learning architectures in the biomedical field are compared, and Carotid Artery (CA) Intima-Media Thickness (IMT) Ultrasound (US) images were used. For an early diagnosis, AlexNet, ZFNet, VGGNet (16-19), which had successful results in the ImageNet competition, and authors’ original CNNcc models were used for comparison. An image database of CA-IMT-US which contains 501 ultrasound images from 153 patients was used to test the models' classification performances. It is seen that AlexNet, ZFNet, VGG16, VGG19, and CNNcc models achieved rates of 91%, 89.1%, 93%, 90%, and 89.1% respectively. The CNNcc model was found to produce successful classification results on CAIMTUS images when different performance indicators are also taken into account. In addition, different performance indicators including confusion matrices were investigated and the results were announced. The results showed that deep architectures are promising in the biomedical field and can provide proper classification on biomedical images so; this can help clinics to diagnose the disease early.
No takes yet. Share an insight, caveat, or question.
Savaş et al. (2022) studied Carotid Artery Disease (n=153). CNNcc deep learning model vs. AlexNet, ZFNet, VGG16, and VGG19 models was evaluated on Classification accuracy. The CNNcc deep learning model achieved an 89.1% classification accuracy with the lowest loss parameter (0.29) on carotid artery intima-media thickness ultrasound images, avoiding the overfitting seen in other models.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: