Safety and Feasibility of Intravascular Optical Coherence Tomography Using a Nonocclusive Technique to Evaluate Carotid Plaques Before and After Stent Deployment

Introduction: Major calcifications are of great concern when performing percutaneous coronary intervention as they hinder stent deployment. Calcifications can lead to under-expansion and strut malapposition, with increased risk of thrombosis and in-stent restenosis. Therefore, accurate identification, visualization, and quantification of calcifications are important. Objective: In this study, we developed a 2-step deep learning approach to enable segmentation of major calcifications in a typical 500+ frame intravascular optical coherence tomography (IVOCT) images. Methods: The dataset consisted of a total of 12,551 IVOCT frames across 68 patients with 68 pullbacks. We applied a series of pre-processing steps including guidewire/shadow removal, lumen detection, pixel shifting, and Gaussian filtering. To detect the major calcifications in step 1, we implemented the 3D convolutional neural network consisting of 5 convolutional, 5 max-pooling, and 2 fully-connected layers. In step-2, SegNet deep learning model was used to segment calcified plaques. In both steps, classification errors were reduced using conditional random field. Results: Step-1 reliably identified major calcifications (sensitivity/specificity: 97.7%/87.7%). Semantic segmentation of calcifications following step-2 was typically visually quite good (Fig. 1) with (sensitivity/specificity: 86.2%/96.7%). Our method was superior to a single step approach and showed excellent reproducibility on repetitive IVOCT pullbacks, with very small differences of clinically relevant attributes (maximum angle, maximum thickness, and length) and the exact same IVOCT calcium scores for assessment of stent deployment. Conclusions: We developed the fully-automated method for identifying calcifications in IVOCT images based on a 2-step deep learning approach. Extensive analyses indicate that our method is very informative for both live-time treatment planning and research purposes.

Download Full-text

PS80. Safety and Feasibility of Intravascular Optical Coherence Tomography to Evaluate Lesions of Femoropopliteal Arterial Segment Before and After Endovascular Treatment

Journal of Vascular Surgery ◽

10.1016/j.jvs.2014.03.121 ◽

2014 ◽

Vol 59 (6) ◽

pp. 54S

Author(s):

Gianmarco de Donato ◽

Francesco Setacci ◽

Giuseppe Galzerano ◽

Maria Pia Borrelli ◽

Umberto Ruzzi ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Endovascular Treatment ◽

Optical Coherence ◽

Arterial Segment ◽

Before And After ◽

Intravascular Optical Coherence Tomography

Download Full-text

Automated segmentation of metal stent and bioresorbable vascular scaffold in intravascular optical coherence tomography images using deep learning architectures

Physics in Medicine and Biology ◽

10.1088/1361-6560/ac4348 ◽

2021 ◽

Author(s):

Yu Shi Lau ◽

Li Kuo Tan ◽

Chow Khuen Chan ◽

Kok Han Chee ◽

Yih Miin Liew

Keyword(s):

Optical Coherence Tomography ◽

Deep Learning ◽

Window Size ◽

Metal Stents ◽

Automated Segmentation ◽

Optical Coherence ◽

Metal Stent ◽

Bioresorbable Vascular Scaffold ◽

Stent Deployment ◽

Intravascular Optical Coherence Tomography

Abstract Percutaneous Coronary Intervention (PCI) with stent placement is a treatment effective for coronary artery diseases. Intravascular optical coherence tomography (OCT) with high resolution is used clinically to visualize stent deployment and restenosis, facilitating PCI operation and for complication inspection. Automated stent struts segmentation in OCT images is necessary as each pullback of OCT images could contain thousands of stent struts. In this paper, a deep learning framework is proposed and demonstrated for the automated segmentation of two major clinical stent types: metal stents and bioresorbable vascular scaffolds (BVS). U-Net, the current most prominent deep learning network in biomedical segmentation, was implemented for segmentation with cropped input. The architectures of MobileNetV2 and DenseNet121 were also adapted into U-Net for improvement in speed and accuracy. The results suggested that the proposed automated algorithm’s segmentation performance approaches the level of independent human observers and is feasible for both types of stents despite their distinct appearance. U-Net with DenseNet121 encoder (U-Dense) performed best with Dice’s coefficient of 0.86 for BVS segmentation, and precision/recall of 0.92/0.92 for metal stent segmentation under optimal crop window size of 256.

Download Full-text

Deep learning segmentation of coronary calcified plaque from intravascular optical coherence tomography (IVOCT) images with application to finite element modeling of stent deployment

Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling ◽

10.1117/12.2515256 ◽

2019 ◽

Cited By ~ 2

Author(s):

Yazan Gharaibeh ◽

Pengfei Dong ◽

David Prabhu ◽

Chaitanya Kolluru ◽

Juhwan Lee ◽

...

Keyword(s):

Finite Element ◽

Optical Coherence Tomography ◽

Deep Learning ◽

Finite Element Modeling ◽

Optical Coherence ◽

Stent Deployment ◽

Element Modeling ◽

Calcified Plaque ◽

Intravascular Optical Coherence Tomography

Download Full-text

Utilization potential of intraluminal optical coherence tomography for the Eustachian tube

Scientific Reports ◽

10.1038/s41598-021-85634-3 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Hayoung Byun ◽

Yeon Hoon Kim ◽

Jingchao Xing ◽

Su-Jin Shin ◽

Seung Hwan Lee ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Eustachian Tube ◽

Balloon Dilatation ◽

Optical Coherence ◽

Cross Sectional ◽

Anatomical Structures ◽

Complex Anatomy ◽

Before And After ◽

Tubal Lumen ◽

Oct Image

AbstractImaging the Eustachian tube is challenging because of its complex anatomy and limited accessibility. This study fabricated a fiber-based optical coherence tomography (OCT) catheter and investigated its potential for assessing the Eustachian tube anatomy. A customized OCT system and an imaging catheter, termed the Eustachian OCT, were developed for visualizing the Eustachian tube. Three male swine cadaver heads were used to study OCT image acquisition and for subsequent histologic correlation. The imaging catheter was introduced through the nasopharyngeal opening and reached toward the middle ear. The OCT images were acquired from the superior to the nasopharyngeal opening before and after Eustachian tube balloon dilatation. The histological anatomy of the Eustachian tube was compared with corresponding OCT images, The new, Eustachian OCT catheter was successfully inserted in the tubal lumen without damage. Cross-sectional images of the tube were successfully obtained, and the margins of the anatomical structures including cartilage, mucosa lining, and fat could be successfully delineated. After balloon dilatation, the expansion of the cross-sectional area could be identified from the OCT images. Using the OCT technique to assess the Eustachian tube anatomy was shown to be feasible, and the fabricated OCT image catheter was determined to be suitable for Eustachian tube assessment.

Download Full-text

Coronary Artery Segmentation from Intravascular Optical Coherence Tomography Using Deep Capsules

Artificial Intelligence in Medicine ◽

10.1016/j.artmed.2021.102072 ◽

2021 ◽

pp. 102072

Author(s):

Arjun Balaji ◽

Lachlan J. Kelsey ◽

Kamran Majeed ◽

Carl J. Schultz ◽

Barry J. Doyle

Keyword(s):

Optical Coherence Tomography ◽

Coronary Artery ◽

Optical Coherence ◽

Coronary Artery Segmentation ◽

Intravascular Optical Coherence Tomography

Download Full-text

Optical coherence tomography for elucidation of flow-diversion phenomena: The concept of endothelized mural thrombus behind reversible in-stent stenosis in flow-diverters

Interventional Neuroradiology ◽

10.1177/15910199211003432 ◽

2021 ◽

pp. 159101992110034

Author(s):

Andre Monteiro ◽

Demetrius K Lopes ◽

Amin Aghaebrahim ◽

Ricardo Hanel

Keyword(s):

Optical Coherence Tomography ◽

Intracranial Aneurysms ◽

Flow Diversion ◽

Optical Coherence ◽

Recurrence Rates ◽

Oct Imaging ◽

Intravascular Optical Coherence Tomography ◽

Stenotic Area ◽

Flow Diverters ◽

Stent Stenosis

Purpose Flow-diverters have revolutionized the endovascular treatment of intracranial aneurysms, offering a durable solution to aneurysms with high recurrence rates after conventional stent-assisted coiling. Events that occur after treatment with flow-diversion, such as in-stent stenosis (ISS) are not well understood and require further assessment. After assessing an animal model with Optical Coherence Tomography (OCT), we propose a concept that could explain the mechanism causing reversible ISS after treatment of intracranial aneurysms with flow-diverters. Methods Six Pipeline Flex embolization devices (PED-Flex), six PED with Shield technology (PED-Shield), and four Solitaire AB devices were implanted in the carotid arteries (two stents per vessel) of four pigs. Intravascular optical coherence tomography (OCT) and digital subtraction angiography (DSA) images obtained on day 21 were compared to histological specimens. Results A case of ISS in a PED-Flex device was assessed with OCT imaging. Neointima with asymmetrical topography completely covering the PED struts was observed. Histological preparations of the stenotic area demonstrated thrombus on the surface of device struts, covered by neointima. Conclusion This study provides a plausible concept for reversible ISS in flow-diverters. Based on an observation of a previous experiment, we propose that similar cases of ISS are related to thrombus presence underneath endothelization, but further experiments focused on this phenomenon are needed. Optical Coherence Tomography will be useful tool when available for clinical use.

Download Full-text