Translating Intravascular Optical Coherence Tomography from a Research to a Clinical Tool

Phipps, Jennifer E.; Hoyt, Taylor; Milner, Thomas E.; Feldman, Marc D.

doi:10.1007/s12410-015-9347-8

Cited by 7 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, early diagnosis and localization of TCFAs (the extent of TCFAs) are crucial for the clinical assessment of plaque vulnerability to provide appropriate treatments. Currently, intravascular optical coherence tomography (IVOCT) and intravascular ultrasound (IVUS) are two intracoronary imaging modalities for diagnosing cardiovascular disease [3,4]. Because IVOCT Abbreviations: ACS, acute coronary syndrome; CNN, convolution neural network; IVOCT, intravascular optical coherence tomography; IVUS, intravascular ultrasound; MIL, multiple instance learning; TCFA, thin-cap fibroatheroma; VP, vulnerable plaque; WSOD, weakly supervised object detection.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, early diagnosis and localization of TCFAs (the extent of TCFAs) are crucial for the clinical assessment of plaque vulnerability to provide appropriate treatments. Currently, intravascular optical coherence tomography (IVOCT) and intravascular ultrasound (IVUS) are two intracoronary imaging modalities for diagnosing cardiovascular disease [3, 4]. Because IVOCT has a higher spatial resolution (axial: 10 μm, lateral: 20‐40 μm) than IVUS (100‐200 μm), it is used as the primary image modality for diagnosis of TCFAs [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of thin‐cap fibroatheroma in IVOCT images based on weakly supervised learning and domain knowledge

Shi

Xin

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Automatic detection of thin‐cap fibroatheroma (TCFA) on intravascular optical coherence tomography images is essential for the prevention of acute coronary syndrome. However, existing methods need to mark the exact location of TCFAs on each frame as supervision, which is extremely time‐consuming and expensive. Hence, a new weakly supervised framework is proposed to detect TCFAs using only image‐level tags as supervision. The framework comprises cut, feature extraction, relation, and detection modules. First, based on prior knowledge, a cut module was designed to generate a small number of specific region proposals. Then, to learn global information, a relation module was designed to learn the spatial adjacency and order relationships at the feature level, and an attention‐based strategy was introduced in the detection module to effectively aggregate the classification results of region proposals as the image‐level predicted score. The results demonstrate that the proposed method surpassed the state‐of‐the‐art weakly supervised detection methods.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Hence, early diagnosis and localization of TCFAs (the extent of TCFAs) are crucial for the clinical assessment of plaque vulnerability to provide appropriate treatments. Currently, intravascular optical coherence tomography (IVOCT) and intravascular ultrasound (IVUS) are two intracoronary imaging modalities for diagnosing cardiovascular disease [3, 4]. Because IVOCT has a higher spatial resolution (axial: 10 μm, lateral: 20‐40 μm) than IVUS (100‐200 μm), it is used as the primary image modality for diagnosis of TCFAs [5].…”

Section: Introductionmentioning

confidence: 99%

Detection of thin‐cap fibroatheroma in IVOCT images based on weakly supervised learning and domain knowledge

Shi

Xin

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

show abstract

“…X‐ray computed coronary angiography and cardiac magnetic resonance imaging allow noninvasive imaging but are very limited in their ability to assess the structure of the artery walls [5]. Intravascular optical coherence tomography (IVOCT) and intravascular ultrasound (IVUS) are two invasive imaging modalities, which provide cross‐sectional imaging of the artery walls [6, 7]. Because IVOCT has a higher spatial resolution (axial: 10 μm, lateral: 20–40 μm) than IVUS (100–200 μm) and can present the internal structure of blood vessels, it is used as the primary image modality for imaging of the vasculature [8–10].…”

Section: Introductionmentioning

confidence: 99%

Automatic lumen and anatomical layers segmentation in IVOCT images using meta learning

Shi

Xin

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Automated analysis of the vessel structure in intravascular optical coherence tomography (IVOCT) images is critical to assess the health status of vessels and monitor coronary artery disease progression. However, deep learning‐based methods usually require well‐annotated large datasets, which are difficult to obtain in the field of medical image analysis. Hence, an automatic layers segmentation method based on meta‐learning was proposed, which can simultaneously extract the surfaces of the lumen, intima, media, and adventitia using a handful of annotated samples. Specifically, we leverage a bi‐level gradient strategy to train a meta‐learner for capturing the shared meta‐knowledge among different anatomical layers and quickly adapting to unknown anatomical layers. Then, a Claw‐type network and a contrast consistency loss were designed to better learn the meta‐knowledge according to the characteristic of annotation of the lumen and anatomical layers. Experimental results on the two cardiovascular IVOCT datasets show that the proposed method achieved state‐of‐art performance.

show abstract

“…Phipps et al have identified four areas where IV OCT can positively affect diagnosis (erosion and spontaneous dissection plaque) and therapy (optimizing stenting results and proper sizing of drug‐eluting stents) for patients with coronary pathology. Further, researchers are exploring whether IV OCT can be used to identify finer, more detailed features associated with plaque vulnerability (risk of instability) such as macrophages, and they whether bright spots in IV OCT images are caused exclusively by macrophages .…”

Section: Introductionmentioning

confidence: 99%

Multi-modal optical imaging characterization of atherosclerotic plaques

et al. 2015

View full text Add to dashboard Cite

We combined cross-polarization optical coherence tomography (CP OCT) and non-linear microscopy based on second harmonic generation (SHG) and two-photon-excited fluorescence (2PEF) to assess collagen and elastin fibers and other vascular structures in the development of atherosclerosis, including identification of vulnerable plaques, which remains an important clinical problem and imaging application. CP OCT's ability to visualize tissue birefringence and cross-scattering adds new information about the microstructure and composition of the plaque. However its interpretation can be ambiguous, because backscattering contrast may have a similar appearance to the birefringence related fringes. Our results represent a step towards minimally invasive characterization and monitoring of different stages of atherosclerosis, including vulnerable plaques. CP OCT image of intimal thickening in the human coronary artery. The dark stripe in the cross-polarization channel (arrow) is a polarization fringe related to the phase retardation between two eigen polarization states. It is histologically located in the area of the lipid pool, however this stripe is a polarization artifact, rather than direct visualization of the lipid pool.

show abstract

Translating Intravascular Optical Coherence Tomography from a Research to a Clinical Tool

Cited by 7 publications

References 22 publications

Detection of thin‐cap fibroatheroma in IVOCT images based on weakly supervised learning and domain knowledge

Detection of thin‐cap fibroatheroma in IVOCT images based on weakly supervised learning and domain knowledge

Automatic lumen and anatomical layers segmentation in IVOCT images using meta learning

Multi-modal optical imaging characterization of atherosclerotic plaques

Contact Info

Product

Resources

About