EuroIntervention

2021

DOI: 10.4244/eij-d-20-01355

|View full text |Cite

|

Sign up to set email alerts

|

Artificial intelligence and optical coherence tomography for the automatic characterisation of human atherosclerotic plaques

¹

,

Juan Luis Gutiérrez‐Chico³

et al.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Discussion1

Future Of Oct1

Intravascular Imaging Modalities For Biomechanical Modeling1

Oct Plaque Analysis1

Citation Types

Supporting

0

Mentioning

41

Contrasting

0

Year Published

2021

2021

2024

2024

Publication Types

Select...

Article6

Book2

Preprint1

Other1

Relationship

Self Cite4

Independent6

Authors

Journals

Cited by 75 publications

(47 citation statements)

References 18 publications

Supporting

0

Mentioning

41

Contrasting

0

Order By: Relevance

“…Facing a large number of images, it takes too much time to manually identify the coronary lesions for clinical expertise. Besides, the manual method could not solve the subjective difference and provide a good reproducibility [9]. Many previous studies have applied arti cial intelligence to automatically identify the plaque characteristics in OCT images [10][11][12][13].…”

Section: Discussionmentioning

confidence: 99%

Automatic Assessment of Calcified Plaque and Nodule by Optical Coherence Tomography Adopting Deep Learning Mode

¹

,

²

,

³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Optical coherence tomography (OCT) has become the best imaging tool in assessment of calcified plaque and nodule. However, every OCT pullback has large number of images and artificial analysis need too much time and energy, so it is not suitable for clinical application. This study aimed to develop and validate an automatic assessment of calcified plaque and nodule by OCT using deep learning model.Methods: The OCT images of calcified plaque and nodule were labeled by two expert readers based on the consensus. A deep learning model with a Multi-Scale and Multi-Task u-net network (MS-MT u-net) was developed. Then with the ground truth labeled by expert readers as reference, the diagnostic accuracy and agreement of the model would be validated.Results: For the pixel-wise evaluation of calcified plaque, the model had a high performance with precision (93.95%), recall (88.95%) and F1 score (91.38%). For the lesion-level evaluation of calcified plaque, the quantitative metrics by the model correlated excellent with the ground truth (calcium score, r=0.90, p< 0.01; calcified volume, r=0.99, p＜0.01). For calcified nodules, the model showed an excellent diagnostic performance of model including sensitivity (91.7%), specificity (89.3%) and accuracy (91.0%).Conclusions: We developed a novel deep learning model for identifying attributes of calcified plaque and nodule. This model provides an excellent diagnostic accuracy and agreement with the ground truth, which reduces subjectivity of manual measurements and saves lots of time. These findings would help practitioners efficiently adopting appropriate therapeutic strategy in the treatment of calcified lesions.

“…Facing a large number of images, it takes too much time to manually identify the coronary lesions for clinical expertise. Besides, the manual method could not solve the subjective difference and provide a good reproducibility [9]. Many previous studies have applied arti cial intelligence to automatically identify the plaque characteristics in OCT images [10][11][12][13].…”

Section: Discussionmentioning

confidence: 99%

Automatic Assessment of Calcified Plaque and Nodule by Optical Coherence Tomography Adopting Deep Learning Mode

¹

,

²

,

³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: Optical coherence tomography (OCT) has become the best imaging tool in assessment of calcified plaque and nodule. However, every OCT pullback has large number of images and artificial analysis need too much time and energy, so it is not suitable for clinical application. This study aimed to develop and validate an automatic assessment of calcified plaque and nodule by OCT using deep learning model.Methods: The OCT images of calcified plaque and nodule were labeled by two expert readers based on the consensus. A deep learning model with a Multi-Scale and Multi-Task u-net network (MS-MT u-net) was developed. Then with the ground truth labeled by expert readers as reference, the diagnostic accuracy and agreement of the model would be validated.Results: For the pixel-wise evaluation of calcified plaque, the model had a high performance with precision (93.95%), recall (88.95%) and F1 score (91.38%). For the lesion-level evaluation of calcified plaque, the quantitative metrics by the model correlated excellent with the ground truth (calcium score, r=0.90, p< 0.01; calcified volume, r=0.99, p＜0.01). For calcified nodules, the model showed an excellent diagnostic performance of model including sensitivity (91.7%), specificity (89.3%) and accuracy (91.0%).Conclusions: We developed a novel deep learning model for identifying attributes of calcified plaque and nodule. This model provides an excellent diagnostic accuracy and agreement with the ground truth, which reduces subjectivity of manual measurements and saves lots of time. These findings would help practitioners efficiently adopting appropriate therapeutic strategy in the treatment of calcified lesions.

“…Both internal and external validation have also been obtained. Chu et al found that AI-enabled OCT had excellent consistency in quantifying plaque burden compared to manual measurements ( 109 ).…”

Section: Future Of Octmentioning

confidence: 99%

Optical Coherence Tomography: An Eye Into the Coronary Artery

²

,

³

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is slowly but surely gaining a foothold in the hands of interventional cardiologists. Intraluminal and transmural contents of the coronary arteries are no longer elusive to the cardiologist's probing eye. Although the graduation of an interventionalist in imaging techniques right from naked eye angiographies to ultrasound-based coronary sonographies to the modern light-based OCT has been slow, with the increasing regularity of complex coronary cases in practice, such a transition is inevitable. Although intravascular ultrasound (IVUS) due to its robust clinical data has been the preferred imaging modality in recent years, OCT provides a distinct upgrade over it in many imaging and procedural aspects. Better image resolution, accurate estimation of the calcified lesion, and better evaluation of acute and chronic stent failure are the distinct advantages of OCT over IVUS. Despite the obvious imaging advantages of OCT, its clinical impact remains subdued. However, upcoming newer trials and data have been encouraging for expanding the use of OCT to wider indications in clinical utility. During percutaneous coronary intervention (PCI), OCT provides the detailed information (dissection, tissue prolapse, thrombi, and incomplete stent apposition) required for optimal stent deployment, which is the key to successfully reducing the major adverse cardiovascular event (MACE) and stent-related morbidities. The increasing use of OCT in complex bifurcation stenting involving the left main (LM) is being studied. Also, the traditional pitfalls of OCT, such as additional contrast load for image acquisition and stenting involving the ostial and proximal LM, have also been overcome recently. In this review, we discuss the interpretation of OCT images and its clinical impact on the outcome of procedures along with current barriers to its use and newer paradigms in which OCT is starting to become a promising tool for the interventionalist and what can be expected for the immediate future in the imaging world.

“…In addition, OCT signals are highly attenuated by large lipid pools, preventing border identification. While new automatic methods are being developed to characterize plaque composition from OCT ( 23 , 24 ), their accuracy to define deep plaque structures and borders is unclear. OCT also performs poorly in larger lumen arteries, tissues behind the guidewire shadow cannot be visualized, and inability to progress the guidewire can restrict imaging with large plaques or stenosis.…”

Section: Intravascular Imaging Modalities For Biomechanical Modelingmentioning

confidence: 99%

Plaque Structural Stress: Detection, Determinants and Role in Atherosclerotic Plaque Rupture and Progression

¹

,

²

2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Atherosclerosis remains a major cause of death worldwide, with most myocardial infarctions being due to rupture or erosion of coronary plaques. Although several imaging modalities can identify features that confer risk, major adverse cardiovascular event (MACE) rates attributable to each plaque are low, such that additional biomarkers are required to improve risk stratification at plaque and patient level. Coronary arteries are exposed to continual mechanical forces, and plaque rupture occurs when plaque structural stress (PSS) exceeds its mechanical strength. Prospective studies have shown that peak PSS is correlated with acute coronary syndrome (ACS) presentation, plaque rupture, and MACE, and provides additional prognostic information to imaging. In addition, PSS incorporates multiple variables, including plaque architecture, plaque material properties, and haemodynamic data into a defined solution, providing a more detailed overview of higher-risk lesions. We review the methods for calculation and determinants of PSS, imaging modalities used for modeling PSS, and idealized models that explore structural and geometric components that affect PSS. We also discuss current experimental and clinical data linking PSS to the natural history of coronary artery disease, and explore potential for refining treatment options and predicting future events.

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Product

Browser Extension Assistant by scite Citation Statement Search Reference Check Visualizations Dashboards Explore Journals Explore Organizations Explore Funders Embedding Badge Embedding Citation Search Pricing

Resources

Blog Help & FAQ Accessibility Statement API Terms For Universities & Governments For Researchers For Publishers For Corporate, Pharma & Enterprise Author Marketing Become an Affiliate Get an organization trial or quote scite Data & Services

About

News & Press Careers Read our Paper Coverage

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Copyright © 2024 scite LLC. All rights reserved.

Made with 💙 for researchers

Part of the Research Solutions Family.