Detecting vulnerable plaque with vulnerability index based on convolutional neural networks

Cao, Yankun; Xiao, Xiaoyan; Liu, Zhi; Yang, Meijun; Sun, Dianmin; Guo, Wei; Cui, Lizhen; Zhang, Pengfei

doi:10.1016/j.compmedimag.2020.101711

Cited by 10 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 4 presents a graphical flowchart of the designed method for the quantitative characterization of plaque vulnerability by histogram analysis based on GdGM NCs enhanced HR-VWI in vivo . The pathology vulnerability index (VI P ), which can be defined as the ratio of the destabilizing components (macrophage plus lipid) to the stabilizing components (smooth muscle cell plus collagen), was used as the gold standard for quantifying plaque vulnerability, with stable (VI P < 1.024) and vulnerable (VI P ≥ 1.024) groups 19 . VI P emphasized the destabilized role of macrophage in plaque vulnerability, which additionally reflected the plaque heterogeneity comprehensively.…”

Section: Resultsmentioning

confidence: 99%

Sophisticated Prediction of Carotid-Plaque Vulnerability by Nanocluster Sensitized High-resolution Vessel-Wall-Imaging Profile in Rabbit Atherosclerotic Model

Gong

et al. 2023

Preprint

View full text Add to dashboard Cite

OBJECTIVE: To innovatively developed a macrophage-target nanoparticle based contrast-enhanced high-resolution magnetic resonance vessel wall imaging (HR-VWI) strategy to characterize the plaques vulnerable features on rabbits.<break><break> <break><break>BACKGROUND: Lacking of sensitive and specific image-marker of HR-VWI leads this technique depending upon the plaque morphological characteristics. Nanoparticle-based contrast agents modified with targeting ligands allow amplifying MR signals of the interested components. The key to successful translation is the requirement that conducting studies in larger animals to provide reasonable diagnostic readouts.<break><break> <break><break>METHODS: The HR-VWI enhanced with macrophage-targeted PP1-Au@GSH@Gd (GdMG) nanoclusters (NCs) and the conventional Gadovist were utilized for the plaque vulnerability evaluation by a systematic histogram analysis in atherosclerosis (AS) rabbit model.<break><break> <break><break>RESULTS: Due to the compelling targeting capacity of GdMG NCs to foamy macrophages, the contrast-to-noise ratio (CNR) from pre-injection baseline dramatically raised from 6.50 to 36.91 (p<0.001), with an increment of 1.39-fold higher than that of the Gadovist approach. Spearman s correlation test confirmed that the coefficient of variation (CV) derived from the histogram analysis based on GdMG NCs HR-VWI was indeed positively linearly correlated with pathology vulnerability index (VIP) significantly (p < 0.05) with adjusted R2 = 0.775. Finally, mathematic formulas with histogram-derived parameters as variables were fitted to quantitatively calculate the histogram vulnerability index (VIH) with the strength of the adjusted R2 = 0.952 (p<0.001), and Area under the curve (AUC) of 0.875 (p<0.001) to realize the in vivo and quantitative calculation of the plaque vulnerability.<break><break> <break><break>CONCLUSION: Profiting from the splendid inflammation targeted capacity and excellent MRI performance of GdMG NCs, as well as the highly quantitative characteristics of histogram analysis, we disclosed that our established imaging protocol was able to identify the plaques vulnerability index that were comparable to pathological examinations in both retrospective and prospective experiments.

show abstract

Section: Resultsmentioning

confidence: 99%

Sophisticated Prediction of Carotid-Plaque Vulnerability by Nanocluster Sensitized High-resolution Vessel-Wall-Imaging Profile in Rabbit Atherosclerotic Model

Gong

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Cao [ 69 ] proposed a neural network-based method to determine the critical point of a vulnerability index, which distinguishes the fragile plaque from the stable plaque, AUC = 0.7143. Zhang [ 70 ] reported a machine learning approach for predicting the location and type of high-risk coronary plaque in patients treated with statins therapy.…”

Section: Application Of Ai In Coronary Atherosclerotic Plaque Analysismentioning

confidence: 99%

Artificial Intelligence in Cardiovascular Atherosclerosis Imaging

Zhang¹,

Han

Shao

et al. 2022

JPM

View full text Add to dashboard Cite

At present, artificial intelligence (AI) has already been applied in cardiovascular imaging (e.g., image segmentation, automated measurements, and eventually, automated diagnosis) and it has been propelled to the forefront of cardiovascular medical imaging research. In this review, we presented the current status of artificial intelligence applied to image analysis of coronary atherosclerotic plaques, covering multiple areas from plaque component analysis (e.g., identification of plaque properties, identification of vulnerable plaque, detection of myocardial function, and risk prediction) to risk prediction. Additionally, we discuss the current evidence, strengths, limitations, and future directions for AI in cardiac imaging of atherosclerotic plaques, as well as lessons that can be learned from other areas. The continuous development of computer science and technology may further promote the development of this field.

show abstract

“…It enables the evaluation of vessel wall structures, such as plaque burden, the extent of calcification and minimal lumen area, for the decision of revascularization and selection of stent sizing, and post-PCI assessment for postoperative complications, such as malposition and underexpansion. Several studies have been dedicated to improving the ability of IVUS on plaque feature detections, including texture feature recognition 38,39 and vessel boundary delineation. 40,41 With the aid of machine learning, 38 new framework algorithms, 40,41 and other models, 39 IVUS has been continuously optimized.…”

Section: Intravascular Ultrasound (Ivus)mentioning

confidence: 99%

The Chinese Experience of Imaging in Cardiac Intervention

Liu

Yang

Chen

2022

Journal of Thoracic Imaging

View full text Add to dashboard Cite

Recent scientific and technological advances have greatly contributed to the development of medical imaging that could enable specific functions. It has become the primary focus of cardiac intervention in preoperative assessment, intraoperative guidance, and postoperative follow-up. This review provides a contemporary overview of the Chinese experience of imaging in cardiac intervention in recent years.

show abstract

Detecting vulnerable plaque with vulnerability index based on convolutional neural networks

Cited by 10 publications

References 20 publications

Sophisticated Prediction of Carotid-Plaque Vulnerability by Nanocluster Sensitized High-resolution Vessel-Wall-Imaging Profile in Rabbit Atherosclerotic Model

Sophisticated Prediction of Carotid-Plaque Vulnerability by Nanocluster Sensitized High-resolution Vessel-Wall-Imaging Profile in Rabbit Atherosclerotic Model

Artificial Intelligence in Cardiovascular Atherosclerosis Imaging

The Chinese Experience of Imaging in Cardiac Intervention

Contact Info

Product

Resources

About