Key result
Pixel difference and transformer-based deep learning models achieve optimal IMC segmentation in carotid ultrasounds.
Why the study?
Common carotid intima-media thickness is a common measure of atherosclerosis, but the use of deep learning methods for medical image analysis, segmentation, and CIMT measurement in carotid ultrasound images has not been extensively explored.
Do advanced deep learning models improve the segmentation of the intima-media complex in carotid ultrasound images compared to conventional CNNs?
Do advanced deep learning models improve the segmentation of the intima-media complex in carotid ultrasound images compared to conventional CNNs?
Advanced deep learning models, particularly pixel difference- and transformer-based networks, provide superior segmentation of the carotid intima-media complex compared to conventional CNNs.
Advances automated carotid intima-media analysis in research; leaves open translation to improved clinical risk stratification or workflows.
Common carotid intima-media thickness (CIMT) is a common measure of atherosclerosis, often assessed through carotid ultrasound images. However, the use of deep learning methods for medical image analysis, segmentation and CIMT measurement in these images has not been extensively explored. This study aims to evaluate the performance of four recent deep learning models, including a convolutional neural network (CNN), a self-organizing operational neural network (self-ONN), a transformer-based network and a pixel difference convolution-based network, in segmenting the intima-media complex (IMC) using the CUBS dataset, which includes ultrasound images acquired from both sides of the neck of 1088 participants. The results show that the self-ONN model outperforms the conventional CNN-based model, while the pixel difference- and transformer-based models achieve the best segmentation performance.
No takes yet. Share an insight, caveat, or question.
Mohammed et al. (2023) studied Atherosclerosis (n=1,088). Deep learning models (self-ONN, transformer-based, pixel difference convolution-based) vs. Conventional convolutional neural network (CNN) was evaluated on Segmentation performance of the intima-media complex (IMC). Pixel difference- and transformer-based deep learning models achieved the best segmentation performance for the intima-media complex in carotid ultrasound images from 1088 participants.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: