Key result
Deep learning automatically detects and segments carotid ultrasound plaques with ~80% overlap versus manual annotation.
Why the study?
Carotid B-mode ultrasound interpretation is limited by high inter-operator and skill-dependent variability in detecting and assessing atherosclerotic plaques.
Does a deep CNN-based workflow accurately detect and quantify carotid atherosclerotic plaques from B-mode ultrasound images compared to manual annotation in patients with severe carotid atherosclerosis?
Does a deep CNN-based workflow accurately detect and quantify carotid atherosclerotic plaques from B-mode ultrasound images compared to manual annotation in patients with severe carotid atherosclerosis?
A deep learning CNN workflow can rapidly and accurately segment and quantify carotid atherosclerotic plaques from B-mode ultrasound images, potentially reducing inter-operator variability.
Answers are grounded in this paper and cite their sources.
May support automated plaque segmentation to reduce variability; leaves open larger prospective validation before clinical use.
Carotid atherosclerosis is a major cause of cerebrovascular events, including ischemic strokes. B-mode ultrasound (US) is a safe, widely available, and cost-effective imaging modality used to detect and assess atherosclerotic plaques. However, it has limitations, namely, high inter-operator and skill-dependent variability in interpretation. We developed a time-efficient deep convolutional neural network (CNN)-based workflow to automatically 1) detect and segment plaques from US (longitudinal/transverse), and 2) quantify plaque parameters: thickness (T), total plaque area (TPA), and total plaque volume (TPV). Patients (n=141) with severe carotid atherosclerotic plaques underwent US examination prior to carotid endarterectomy. A radiologist annotated US images (467), longitudinal (326) and transverse (141). The Intersection Over Union between manual and algorithm-based segmentation was 0.80±0.18 (mean±standard deviation) on 46 unseen US images. The mean absolute error of (∆T), (∆TPA), and (∆ V) were 0.22 mm, 0.73 mm2, and 0.89 mm3. The total time (detection/quantifications) was <1 second per image.
No takes yet. Share an insight, caveat, or question.
Khameneh et al. (2024) studied severe carotid atherosclerotic plaques (n=141). Deep convolutional neural network (CNN)-based workflow vs. Manual annotation by a radiologist was evaluated on Intersection Over Union between manual and algorithm-based segmentation. A deep convolutional neural network automatically detected and segmented carotid plaques from ultrasound images with an Intersection Over Union of 0.80±0.18 compared to manual annotation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: