CT imaging features of carotid artery plaque vulnerability

Murgia, Alessandro; Erta, Marco; Suri, Jasjit S.; Gupta, Ajay; Wintermark, Max; Saba, Luca

doi:10.21037/atm-2020-cass-13

Cited by 31 publications

(29 citation statements)

References 91 publications

(88 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To summarize, our prime contributions in the proposed study are six types of innovation in the design of COVLIAS 2.0-cXAI: (i) automated HDL lung segmentation using the ResNet-UNet model; (ii) classification of COVID-19 vs. controls using three kinds of DenseNets, namely, DenseNet-121 [ 55 , 56 , 57 , 83 ], DenseNet-169, and DenseNet-201; the combination of segmentation and classification improved the overall performance of the system; (iii) using explainable AI to visualize and validate the prediction of the DenseNet models using four kinds of CAM, namely Grad-CAM, Grad-CAM++, Score-CAM, and FasterScore-CAM, for the first time. This helps us understand the AI model’s learning in the input CT image [ 35 , 84 , 85 , 86 ]. (iv) Mean alignment index (MAI) between heatmaps and the gold standard score from three trained senior radiologists, a score of four out of five, establishing the system for clinical applicability.…”

Section: Discussionmentioning

confidence: 99%

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Suri¹,

Agarwal²,

Chabert

et al. 2022

Diagnostics

Self Cite

View full text Add to dashboard Cite

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

show abstract

Section: Discussionmentioning

confidence: 99%

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Suri¹,

Agarwal²,

Chabert

et al. 2022

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The MRI cross-sectional scans of the carotid plaque are shown in Figure 6A (82). The CT cross-sectional scans of the carotid plaque are shown in Figure 6B (83). Figure 6C presents the plaque acquisition demonstrate in the US (40).…”

Section: Ultrasound Imaging For Carotid Plaquementioning

confidence: 99%

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application

Saba¹,

Skandha²,

Gupta³

et al. 2021

Ann Transl Med

Self Cite

View full text Add to dashboard Cite

Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type

show abstract

“…According to Class I, level A recommendation CT angiography (CTA) is suitable for extent and severity evaluation of extracranial carotid stenosis [1]. The advantages of CTA are wide accessibility in daily clinical routine, high spatial resolution, allowing delineation of arterial outlines, well-established imaging protocols, shorter scan times, ensuring reduced motion artefacts [3] and the capacity to accurately define plaque volume and subcomponents, especially when coupled with post-processing analysis techniques [4]. Furthermore, CTA-derived diameter stenosis measurements correlate well with catheter angiographic measurements [5].…”

Section: Imaging Of Carotid Artery Pathology and Its Clinical Relevancementioning

confidence: 99%

Comparison of Manual versus Semi-Automatic Segmentations of the Stenotic Carotid Artery Bifurcation

et al. 2021

View full text Add to dashboard Cite

Background: The image reconstruction of stenotic carotid bifurcation can be managed by medical practitioners and non-medical investigators with semi-automatic or manual segmentation. The outcome of blood flow simulations may vary because of a single mean voxel difference along the examined section, possibly more in the stenotic lesions, which can lead to conflicting results regarding other research findings. The aim of our project is computational geometry reconstruction for blood flow simulations to make it suitable for comparison with plaque image analysis performed by commercially available software. In this paper, a comparison is made between the manual and semi-automatic segmentations performed by non-medical and medical investigators, respectively. Methods: 30 patients were classified into three homogeneous groups. Our group classification was based on the following parameters: plaque calcification score, thickness, extent, remodeling and plaque localization. The images in the first group were segmented individually by medical practitioners and experienced non-medical investigators, the second group was segmented collectively, and the last group was segmented individually again. Cross-sections along the centerline were extracted, then geometrical and statistical analyses were performed. Exploratory flow simulations were carried out on two patients to showcase the effect of geometrical differences on the hemodynamic flow field. Results: The largest centerline-averaged voxel difference between the medical and non-medical investigators occurred in the first group with a positive difference of 1.16 voxels. In the second and third groups, the average voxel difference decreased to 0.65 and 0.75, respectively. The example case from the first group showed that the difference in maximum wall shear stress in the middle of the stenosis is 30% with an average voxel difference of 1.73. Meanwhile, it can decrease to 4% when the average voxel difference is 0.64 for the example case from the third group. Conclusions: A collective review of the medical images should preceded the manual segmentations before applying them in computational simulations in order to ensure a proper comparison with plaque image analysis. Especially complex pathology such as calcifications should be segmented under medical supervision or after specific training. Non-significant differences in the segmentation can lead to significant differences in the computed flow field.

show abstract

CT imaging features of carotid artery plaque vulnerability

Cited by 31 publications

References 91 publications

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application

Comparison of Manual versus Semi-Automatic Segmentations of the Stenotic Carotid Artery Bifurcation

Contact Info

Product

Resources

About