Performance of a deep learning tool to detect missed aortic dilatation in a large chest CT cohort

Artificial intelligence-powered solutions for automated aortic diameter measurement in computed tomography: a narrative review

Background and Objective

Patients with thoracic aortic aneurysm and dissection (TAAD) are often asymptomatic but present acutely with life threatening complications that necessitate emergency intervention. Aortic diameter measurement using computed tomography (CT) is considered the gold standard for diagnosis, surgical planning, and monitoring. However, manual measurement can create challenges in clinical workflows due to its time-consuming, labour-intensive nature and susceptibility to human error. With advancements in artificial intelligence (AI), several models have emerged in recent years for automated aortic diameter measurement. This article aims to review the performance and clinical relevance of these models in relation to clinical workflows.

Methods

We performed literature searches in PubMed, Scopus, and Web of Science to identify relevant studies published between 2014 and 2024, with the focus on AI and deep learning aortic diameter measurements in screening and diagnosis of TAAD.

Key Content and Findings

Twenty-four studies were retrieved in the past ten years, highlighting a significant knowledge gap in the field of translational medicine. The discussion included an overview of AI-powered models for aortic diameter measurement, as well as current clinical guidelines and workflows.

Conclusions

This article provides a thorough overview of AI and deep learning models designed for automatic aortic diameter measurement in the screening and diagnosis of thoracic aortic aneurysms (TAAs). We emphasize not only the performance of these technologies but also their clinical significance in enabling timely interventions for high-risk patients. Looking ahead, we envision a future where AI and deep learning-powered automatic aortic diameter measurement models will streamline TAAD clinical management.

An Artificial Intelligence-Based Automatic Classifier for the Presence of False Lumen Thrombosis After Frozen Elephant Trunk Operation

OBJECTIVE

To develop an unsupervised artificial intelligence algorithm for identifying and quantifying the presence of false lumen thrombosis (FL) after Frozen Elephant Trunk (FET) operation in computed tomography angiographic (CTA) images in an interdisciplinary approach.

METHODS

CTA datasets were retrospectively collected from eight patients after FET operation for aortic dissection from a single center. Of those, five patients had a residual aortic dissection with partial false lumen thrombosis, and three patients had no false lumen or thrombosis. Centerlines of the aortic lumen were defined, and images were calculated perpendicular to the centerline. Lumen and thrombosis were outlined and used as input for a variational autoencoder (VAE) using 2D convolutional neural networks (2D CNN). A 2D latent space was chosen to separate images containing false lumen patency, false lumen thrombosis and no presence of false lumen. Classified images were assigned a thrombus score for the presence or absence of FL thrombosis and an average score for each patient.

RESULTS

Images reconstructed by the trained 2D CNN VAE corresponded well to original images with thrombosis. Average thrombus scores for the five patients ranged from 0.05 to 0.36 where the highest thrombus scores coincided with the location of the largest thrombus lesion. In the three patients without large thrombus lesions, average thrombus scores ranged from 0.002 to 0.01.

CONCLUSIONS

The presence and absence of a FL thrombus can be automatically classified by the 2D CNN VAE for patient-specific CTA image datasets. As FL thrombosis is an indication for positive aortic remodeling, evaluation of FL status is essential in follow-up examinations. The presented proof-of-concept is promising for the automated classification and quantification of FL thrombosis.

New Directions in Diagnostics for Aortic Aneurysms: Biomarkers and Machine Learning

This review article presents an appraisal of pioneering technologies poised to revolutionize the diagnosis and management of aortic aneurysm disease, with a primary focus on the thoracic aorta while encompassing insights into abdominal manifestations. Our comprehensive analysis is rooted in an exhaustive survey of contemporary and historical research, delving into the realms of machine learning (ML) and computer-assisted diagnostics. This overview draws heavily upon relevant studies, including Siemens' published field report and many peer-reviewed publications. At the core of our survey lies an in-depth examination of ML-driven diagnostic advancements, dissecting an array of algorithmic suites to unveil the foundational concepts anchoring computer-assisted diagnostics and medical image processing. Our review extends to a discussion of circulating biomarkers, synthesizing insights gleaned from our prior research endeavors alongside contemporary studies gathered from the PubMed Central database. We elucidate the prevalent challenges and envisage the potential fusion of AI-guided aortic measurements and sophisticated ML frameworks with the computational analyses of pertinent biomarkers. By framing current scientific insights, we contemplate the transformative prospect of translating fundamental research into practical diagnostic tools. This narrative not only illuminates present strides, but also forecasts promising trajectories in the clinical evaluation and therapeutic management of aortic aneurysm disease.

Sex differences in ascending aortic size reporting and growth on chest computed tomography and magnetic resonance imaging

PURPOSE

Diameter-based guidelines for prophylactic repair of ascending aortic aneurysms have led to routine aortic evaluation in chest imaging. Despite sex differences in aneurysm outcomes, there is little understanding of sex-specific aortic growth rates. Our objective was to evaluate sex-specific temporal changes in radiologist-reported aortic size as well as sex differences in aortic reporting.

METHOD

In this cohort study, we queried radiology reports of chest computed tomography or magnetic resonance imaging at an academic medical center from 1994 to 2022, excluding type A dissection. Aortic diameter was extracted using a custom text-processing algorithm. Growth rates were estimated using mixed-effects modeling with fixed terms for sex, age, and imaging modality, and patient-level random intercepts. Sex, age, and modality were evaluated as predictors of aortic reporting by logistic regression.

RESULTS

This study included 89,863 scans among 46,622 patients (median [interquartile range] age, 64 [52-73]; 22,437 women [48%]). Aortic diameter was recorded in 14% (12,722/89,863 reports). Temporal trends were analyzed in 7194 scans among 1998 patients (age, 68 [60-75]; 677 women [34%]) with ≥2 scans. Aortic growth rate was significantly higher in women (0.22 mm/year [95% confidence interval 0.17-0.28] vs. 0.09 mm/year [0.06-0.13], respectively). Aortic reporting was significantly less common in women (odds ratio, 0.54; 95% CI, 0.52-0.56; p < 0.001).

CONCLUSIONS

While aortic growth rates were small overall, women had over twice the growth rate of men. Aortic dimensions were much less frequently reported in women than men. Sex-specific standardized assessment of aortic measurements may be needed to address sex differences in aneurysm outcomes.

Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT

PURPOSE/OBJECTIVE

Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams.

METHODS & MATERIALS

A cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters.

RESULTS

We evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively).

CONCLUSION

Re-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.