Pulmonary Vascular Morphology as an Imaging Biomarker in Chronic Thromboembolic Pulmonary Hypertension

Rahaghi, F.N.; Ross, James C.; Agarwal, Manyoo; González, Germán; Come, Carolyn E.; Díaz, Alejandro A.; Vegas-Sánchez-Ferrero, Gonzalo; Hunsaker, Andetta R.; Estépar, R. San José; Waxman, Aaron B.; Washko, George R.

doi:10.1086/685081

Cited by 50 publications

(46 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an example, recent studies show that A/V classification allows for better assessment of pulmonary emboli [3], whereas changes in the arterial tree have been associated with the development of chronic thromboembolic pulmonary hypertension (CTEPH) [4]. Also, changes in intraparenchymal pulmonary arteries have been associated with evidence of right ventricular dysfunction [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Pulmonary Artery–Vein Classification in CT Images Using Deep Learning

Nardelli

Jiménez-Carretero

Bermejo-Peláez

et al. 2018

IEEE Trans. Med. Imaging

144

View full text Add to dashboard Cite

Recent studies show that pulmonary vascular diseases may specifically affect arteries or veins through different physiologic mechanisms. To detect changes in the two vascular trees, physicians manually analyze the chest computed tomography (CT) image of the patients in search of abnormalities. This process is time-consuming, difficult to standardize and thus not feasible for large clinical studies or useful in real-world clinical decision making. Therefore, automatic separation of arteries and veins in CT images is becoming of great interest, as it may help physicians accurately diagnose pathological conditions. In this work, we present a novel, fully automatic approach to classifying vessels from chest CT images into arteries and veins. The algorithm follows three main steps: first, a scale-space particles segmentation to isolate vessels; then a 3D convolutional neural network (CNN) to obtain a first classification of vessels; finally, graph-cuts (GC) optimization to refine the results. To justify the usage of the proposed CNN architecture, we compared different 2D and 3D CNNs that may use local information from bronchus- and vessel-enhanced images provided to the network with different strategies. We also compared the proposed CNN approach with a Random Forests (RF) classifier. The methodology was trained and evaluated on the superior and inferior lobes of the right lung of eighteen clinical cases with non-contrast chest CT scans, in comparison with manual classification. The proposed algorithm achieves an overall accuracy of 94%, which is higher than the accuracy obtained using other CNN architectures and RF. Our method was also validated with contrast-enhanced CT scans of patients with Chronic Thromboembolic Pulmonary Hypertension (CTEPH) to demonstrate that our model generalizes well to contrast-enhanced modalities. The proposed method outperforms state-of-the-art methods, paving the way for future use of 3D CNN for A/V classification in CT images.

show abstract

Section: Introductionmentioning

confidence: 99%

Pulmonary Artery–Vein Classification in CT Images Using Deep Learning

Nardelli

Jiménez-Carretero

Bermejo-Peláez

et al. 2018

IEEE Trans. Med. Imaging

144

View full text Add to dashboard Cite

show abstract

“…This procedure was added to treatment algorithms in the ESC/ERS guideline (23). However, its efficacy for long-term prognosis has not been for CTEPH in a recent study (25), in which the ratio of small-vessels volume (blood volume of vessels with a cross-sectional area of ≤ 5mm 2 , BV5) and total blood vessel volume (TBV) was measured for small-vessels pruning, and the ratio of large-vessels (a cross-sectional area of >10mm 2 , BV>10) and TBV was quantified for large-vessels dilation. The measurements were extracted in CTPA for 18 patients with CTEPH and 15 control patients.…”

Section: Discussionmentioning

confidence: 99%

Treatment Effect of Balloon Pulmonary Angioplasty in Chronic Thromboembolic Pulmonary Hypertension Quantified by Automatic Comparative Imaging in Computed Tomography Pulmonary Angiography

Zhai¹,

Ota²,

Staring³

et al. 2018

Invest Radiol

View full text Add to dashboard Cite

show abstract

“…Pulmonary vascular alterations have been described as narrowing and pruning of distal vessels, which increases vascular resistance and cause hypertension . The dilation of proximal vessels is also an essential morphological feature, as increasing pulmonary vascular resistance affects proximal vessels . Investigation of changes in pulmonary vascular morphology, such as pruning of small vessels or dilation of large vessels, may provide assessments of pulmonary vascular remodeling.…”

Section: Introductionmentioning

confidence: 99%

Automatic quantitative analysis of pulmonary vascular morphology in CT images

et al. 2019

View full text Add to dashboard Cite

PurposeVascular remodeling is a significant pathological feature of various pulmonary diseases, which may be assessed by quantitative computed tomography (CT) imaging. The purpose of this study was therefore to develop and validate an automatic method for quantifying pulmonary vascular morphology in CT images.MethodsThe proposed method consists of pulmonary vessel extraction and quantification. For extracting pulmonary vessels, a graph‐cuts‐based method is proposed which considers appearance (CT intensity) and shape (vesselness from a Hessian‐based filter) features, and incorporates distance to the airways into the cost function to prevent false detection of airway walls. For quantifying the extracted pulmonary vessels, a radius histogram is generated by counting the occurrence of vessel radii, calculated from a distance transform‐based method. Subsequently, two biomarkers, slope α and intercept β, are calculated by linear regression on the radius histogram. A public data set from the VESSEL12 challenge was used to independently evaluate the vessel extraction. The quantitative analysis method was validated using images of a three‐dimensional (3D) printed vessel phantom, scanned by a clinical CT scanner and a micro‐CT scanner (to obtain a gold standard). To confirm the association between imaging biomarkers and pulmonary function, 77 scleroderma patients were investigated with the proposed method.ResultsIn the independent evaluation with the public data set, our vessel segmentation method obtained an area under the receiver operating characteristic (ROC) curve of 0.976. The median radius difference between clinical and micro‐CT scans of a 3D printed vessel phantom was 0.062 ± 0.020 mm, with interquartile range of 0.199 ± 0.050 mm. In the studied patient group, a significant correlation between diffusion capacity for carbon monoxide and the biomarkers, α (R = −0.27, P = 0.018) and β (R = 0.321, P = 0.004), was obtained.ConclusionIn conclusion, the proposed method was validated independently using a public data set resulting in an area under the ROC curve of 0.976 and using a 3D printed vessel phantom data set, showing a vessel sizing error of 0.062 mm (0.16 in‐plane pixel units). The correlation between imaging biomarkers and diffusion capacity in a clinical data set confirmed an association between lung structure and function. This quantification of pulmonary vascular morphology may be helpful in understanding the pathophysiology of pulmonary vascular diseases.

show abstract

Pulmonary Vascular Morphology as an Imaging Biomarker in Chronic Thromboembolic Pulmonary Hypertension

Cited by 50 publications

References 22 publications

Pulmonary Artery–Vein Classification in CT Images Using Deep Learning

Pulmonary Artery–Vein Classification in CT Images Using Deep Learning

Treatment Effect of Balloon Pulmonary Angioplasty in Chronic Thromboembolic Pulmonary Hypertension Quantified by Automatic Comparative Imaging in Computed Tomography Pulmonary Angiography

Automatic quantitative analysis of pulmonary vascular morphology in CT images

Contact Info

Product

Resources

About