VASCULAR AND INTERVENTIONAL RADIOLOGYT horacic aortic aneurysm (TAA) is common and is increasing in prevalence worldwide, with approximately 3% of patients older than 50 years having a dilated thoracic aorta (1-3) and recommended to undergo imaging surveillance (4). Most patients with TAA have an indolent disease course, with aortic growth occurring either slowly or not at all over a period of years or decades (5). However, life-threatening complications, such as aortic dissection and rupture, can occur in otherwise asymptomatic patients at presurgical aneurysm sizes (6,7), emphasizing the need for better techniques with which to assess disease progression, inform surgical candidacy, and predict complications. A fundamental limitation to improved management of TAA is the lack of image analysis techniques with which to accurately assess aortic growth.Current assessment techniques are based on measurements of maximal aortic diameter. However, the degree of variability associated with aortic diameter measurements (within 1-5 mm despite optimal measurement technique) frequently prevents confident assessment of disease progression at typical TAA growth rates (,1 mm per year) (8-11). Also, diameter measurements are inherently two dimensional and are performed in fixed anatomic locations; thus, they are unable to capture the three-dimensional (3D) nature of TAA growth.To overcome these limitations, prior research has described the feasibility of a medical image analysis technique, termed vascular deformation mapping (VDM), in 3D assessment of aortic growth using deformable image registration techniques (12,13). This approach uses high Background: Aortic diameter measurements in patients with a thoracic aortic aneurysm (TAA) show wide variation. There is no technique to quantify aortic growth in a three-dimensional (3D) manner.Purpose: To validate a CT-based technique for quantification of 3D growth based on deformable registration in patients with TAA. Materials and Methods:Patients with ascending and descending TAA with two or more CT angiography studies between 2006 and 2020 were retrospectively identified. The 3D aortic growth was quantified using vascular deformation mapping (VDM), a technique that uses deformable registration to warp a mesh constructed from baseline aortic anatomy. Growth assessments between VDM and clinical CT diameter measurements were compared. Aortic growth was quantified as the ratio of change in surface area at each mesh element (area ratio). Manual segmentations were performed by independent raters to assess interrater reproducibility. Registration error was assessed using manually placed landmarks. Agreement between VDM and clinical diameter measurements was assessed using Pearson correlation and Cohen k coefficients.Results: A total of 38 patients (68 surveillance intervals) were evaluated (mean age, 69 years 6 9 [standard deviation]; 21 women), with TAA involving the ascending aorta (n = 26), descending aorta (n = 10), or both (n = 2). VDM was technically successful in 35 of 38 (92%) pati...

We systematically evaluate the training methodology and efficacy of two inpainting-based pretext tasks of context prediction and context restoration for medical image segmentation using self-supervised learning (SSL). Multiple versions of self-supervised U-Net models were trained to segment MRI and CT datasets, each using a different combination of design choices and pretext tasks to determine the effect of these design choices on segmentation performance. The optimal design choices were used to train SSL models that were then compared with baseline supervised models for computing clinically-relevant metrics in label-limited scenarios. We observed that SSL pretraining with context restoration using 32 × 32 patches and Poission-disc sampling, transferring only the pretrained encoder weights, and fine-tuning immediately with an initial learning rate of 1 × 10−3 provided the most benefit over supervised learning for MRI and CT tissue segmentation accuracy (p< 0.001). For both datasets and most label-limited scenarios, scaling the size of unlabeled pretraining data resulted in improved segmentation performance. SSL models pretrained with this amount of data outperformed baseline supervised models in the computation of clinically-relevant metrics, especially when the performance of supervised learning was low. Our results demonstrate that SSL pretraining using inpainting-based pretext tasks can help increase the robustness of models in label-limited scenarios and reduce worst-case errors that occur with supervised learning.

Purpose: Accurate assessment of thoracic aortic aneurysm (TAA) growth is important for appropriate clinical management. Maximal aortic diameter is the primary metric that is used to assess growth, but it suffers from substantial measurement variability. A recently proposed technique, termed Vascular Deformation Mapping (VDM), is able to quantify three-dimensional aortic growth using clinical computed tomography angiography (CTA) data using an approach based on deformable image registration (DIR). However, the accuracy and robustness of VDM remains undefined given the lack of a ground truth from clinical CTA data, and furthermore the performance of VDM relative to standard manual diameter measurements is unknown.Methods: To evaluate the performance of the VDM pipeline for quantifying aortic growth we developed a novel and systematic evaluation process to generate 31 unique synthetic CTA growth phantoms with variable degrees and locations of aortic wall deformation. Aortic deformation was quantified using two metrics: Area Ratio (AR), defined as the ratio of surface area in triangular mesh elements, and the magnitude of deformation in the normal direction (DiN) relative to the aortic surface. Using these phantoms, we further investigated the effects on VDM's measurement accuracy resulting from factors that influence quality of clinical CTA data such as respiratory translations, slice thickness and image noise. Lastly, we compare the measurement error of VDM TAA growth assessments against two expert raters performing standard diameter measurements of synthetic phantom images.Results: Across our population of 31 synthetic growth phantoms, the median absolute error was 0.048 (IQR: 0.077-0.037) for AR and 0.138mm (IQR: 0.227-0.107mm) for DiN. Median relative error was 1.9% for AR and < 6.4% for DiN at the highest tested noise level (CNR = 2.66). Error in VDM output increased with slice thickness, i with highest median relative error of 1.4% for AR and 6.3% for DiN at slice thickness of 2.0 mm. Respiratory motion of the aorta resulted in maximal absolute error of 3% AR and 0.6 mm in DiN, but bulk translations in aortic position had a very small effect on measured AR and DiN values (relative errors < 1%). VDM-derived measurements of magnitude and location of maximal diameter change demonstrated significantly high accuracy and lower variability compared to two expert manual raters (p < 0.03 across all comparisons).Conclusions: VDM yields accurate, three-dimensional assessment of aortic growth in TAA patients and is robust to factors such as image noise, respiration-induced translations and differences in patient position. Further, VDM significantly outperformed two expert manual raters in assessing the magnitude and location of aortic growth despite optimized experimental measurement conditions. These results support validation of the VDM technique for accurate quantification of aortic growth in patients and highlight important several advantages over current measurement techniques.

No abstract

No abstract