Coronary artery segmentation from intravascular optical coherence tomography using deep capsules

Balaji, Arjun; Kelsey, Lachlan J.; Majeed, Kamran; Schultz, Carl; Doyle, Barry

doi:10.1016/j.artmed.2021.102072

Cited by 7 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods to automate the classification and segmentation of pathological and non-pathological formations in intravascular OCT images are emerging as clinically feasible. To automatically segment the lumen, the deep capsules approach presented by Balaji et al, showed impressive accuracy, speed and efficient computational use which make it an ideal candidate to make it to clinical use [ 93 ]. This approach built upon the useful characteristics of the U-Net to maintain high-level feature accuracy and shows strong promise to be expanded to plaque component analysis.…”

Section: Discussionmentioning

confidence: 99%

“…With improvements in classification and segmentation capability, there is a growing need to integrate these advances into automated 3D reconstructions in a sufficient framework for biomechanical simulation. Lumen and stent-based investigations have already begun developing this ability for clinical application [ 91 , 93 ]. However, structural based analysis still lags due to the added complications of generating smooth and sufficiently connected regions for finite element mesh generation.…”

Section: Discussionmentioning

confidence: 99%

“…This compared to 1080 sec previously, with added robustness in cases with artefacts and noise, resulting in excellent agreement between manual and automated WSS computations (R 2 = 0.95). Computational speed and efficiency were further improved during the development of DeepCap, which further focused on using a small memory footprint [ 93 ]. Their approach was based on a U-Net architecture, using upsampling, downsampling and skip connections to improve network gradient propagation [ 94 ].…”

Section: Coronary Lumenmentioning

confidence: 99%

“…The automated DeepCap segmentation was able to process the 200-image pullback in just 0.8 s on a GPU (19 s on CPU). Reprinted from [ 93 ], with permission from Elsevier.…”

Section: Figurementioning

confidence: 99%

“…Articles varied their use of manual segmentation and expert annotation and we match the description given in each article. First Author [Ref] Aim Dataset Morphological/Filtering Operations Feature Detection/Classification Outcome Comparison * Akbar et al [ 65 ] Automated lumen extraction and 3D FFR modelling 5931 images (40 patients) Polar transform, Bilateral smoothing filter, dilation, erosion L- & C-mode interpolation and Sobel edge detection R: 0.99 FFR R: 0.98 Manual segmentation and individual L- and C-mode interpolation Athanasiou et al [ 91 ] Lumen detection through optimized segmentation and 3D WSS modelling 11 patients, 613 annotated images Polar transform, Bilateral smoothing filter B-spline curve fit, K-means 3D HD: 0.05 mm (±0.19) R: 0.98 R 2 : 0.96 WSS R 2 : 0.95 Expert annotation and WSS results between expert annotated reconstruction Balaji et al [ 93 ] Efficient and low memory automated lumen segmentation for clinical application 12,011 images (22 patients) Gaussian derivative PyTorch based deep capsules with ADAM optimizer DICE: 0.97 ± 0.06 HD: 3.30 ±1.51 µm SEN: 93.00 ± 8.00% SPE: 99.00 ± 1.00% Expert annotation, UNet-ResNet18, FCNResNet50 and DeepLabV3-ResNet50 Cao et al [ 74 ] Automated lumen segmentation in challenging geometries 880 images (five patients) ...…”

Section: Table A1mentioning

confidence: 99%

See 4 more Smart Citations

Automated Coronary Optical Coherence Tomography Feature Extraction with Application to Three-Dimensional Reconstruction

et al. 2022

View full text Add to dashboard Cite

Coronary optical coherence tomography (OCT) is an intravascular, near-infrared light-based imaging modality capable of reaching axial resolutions of 10–20 µm. This resolution allows for accurate determination of high-risk plaque features, such as thin cap fibroatheroma; however, visualization of morphological features alone still provides unreliable positive predictive capability for plaque progression or future major adverse cardiovascular events (MACE). Biomechanical simulation could assist in this prediction, but this requires extracting morphological features from intravascular imaging to construct accurate three-dimensional (3D) simulations of patients’ arteries. Extracting these features is a laborious process, often carried out manually by trained experts. To address this challenge, numerous techniques have emerged to automate these processes while simultaneously overcoming difficulties associated with OCT imaging, such as its limited penetration depth. This systematic review summarizes advances in automated segmentation techniques from the past five years (2016–2021) with a focus on their application to the 3D reconstruction of vessels and their subsequent simulation. We discuss four categories based on the feature being processed, namely: coronary lumen; artery layers; plaque characteristics and subtypes; and stents. Areas for future innovation are also discussed as well as their potential for future translation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Coronary Lumenmentioning

confidence: 99%

“…The automated DeepCap segmentation was able to process the 200-image pullback in just 0.8 s on a GPU (19 s on CPU). Reprinted from [ 93 ], with permission from Elsevier.…”

Section: Figurementioning

confidence: 99%