School of Biomedical Engineering, Indian Institute of Technology (BHU), Varanasi, India.
Department of Radiology, Cagliari University Hospital, Cagliari, Italy.
Int Angiol. 2022 Feb;41(1):9-23. doi: 10.23736/S0392-9590.21.04771-4. Epub 2021 Nov 26.
The death due to stroke is caused by embolism of the arteries which is due to the rupture of the atherosclerotic lesions in carotid arteries. The lesion formation is over time, and thus, early screening is recommended for asymptomatic and moderate-risk patients. The previous techniques adopted conventional methods or semi-automated and, more recently, machine learning solutions. A handful of studies have emerged based on solo deep learning (SDL) models such as UNet architecture.
The proposed research is the first to adopt hybrid deep learning (HDL) artificial intelligence models such as SegNet-UNet. This model is benchmarked against UNet and advanced conventional models using scale-space such as AtheroEdge 2.0 (AtheroPoint, CA, USA). All our resultant statistics of the three systems were in the order of UNet, SegNet-UNet, and AtheroEdge 2.0.
Using the database of 379 ultrasound scans from a Japanese cohort of 190 patients having moderate risk and implementing the cross-validation deep learning framework, our system performance using area-under-the-curve (AUC) for UNet, SegNet-UNet, and AtheroEdge 2.0 were 0.93, 0.94, and 0.95 (P<0.001), respectively. The coefficient of correlation between the three systems and ground truth (GT) were: 0.82, 0.89, and 0.85 (P<0.001 for all three), respectively. The mean absolute area error for the three systems against manual GT was 4.07±4.70 mm, 3.11±3.92 mm, 3.72±4.76 mm, respectively, proving the superior performance SegNet-UNet against UNet and AtheroEdge 2.0, respectively. Statistical tests were also conducted for their reliability and stability.
The proposed study demonstrates a fast, accurate, and reliable solution for early detection and quantification of plaque lesions in common carotid artery ultrasound scans. The system runs on a test US image in <1 second, proving overall performance to be clinically reliable.
由于颈动脉粥样硬化病变的破裂导致动脉栓塞，从而导致中风死亡。病变的形成是一个长期的过程，因此建议对无症状和中危患者进行早期筛查。以前的技术采用了常规方法或半自动方法，最近则采用了机器学习解决方案。基于单一深度学习（SDL）模型（如 UNet 架构）已经出现了一些研究。
本研究首次采用了混合深度学习（HDL）人工智能模型，如 SegNet-UNet。该模型与 UNet 和使用尺度空间的先进常规模型（如 AtheroEdge 2.0（AtheroPoint，加利福尼亚州，美国））进行了基准测试。我们对这三个系统的所有结果统计数据均按照 UNet、SegNet-UNet 和 AtheroEdge 2.0 的顺序排列。
使用来自 190 名具有中危风险的日本队列的 379 个超声扫描的数据库，并实施了交叉验证深度学习框架，我们的系统性能使用 UNet、SegNet-UNet 和 AtheroEdge 2.0 的曲线下面积（AUC）分别为 0.93、0.94 和 0.95（P<0.001）。三个系统与真实数据（GT）之间的相关系数分别为：0.82、0.89 和 0.85（均 P<0.001）。三个系统相对于手动 GT 的平均绝对面积误差分别为 4.07±4.70mm、3.11±3.92mm 和 3.72±4.76mm，这证明了 SegNet-UNet 相对于 UNet 和 AtheroEdge 2.0 的优越性能。还对它们的可靠性和稳定性进行了统计测试。
本研究提出了一种快速、准确和可靠的方法，用于早期检测和量化颈总动脉超声扫描中的斑块病变。该系统在<1 秒内运行测试 US 图像，证明了整体性能的临床可靠性。
