The effect of scan and patient parameters on the diagnostic performance of AI for detecting coronary stenosis on coronary CT angiography

Jonas, Rebecca; Barkovich, Emil Jernstedt; Choi, Andrew; Griffin, William F.; Riess, Joanna; Marques, Hugo; Chang, Hyuk‐Jae; Choi, Jung Hyun; Doh, Joon‐Hyung; Her, Ae-Young; Koo, Bon‐Kwon; Nam, Chang‐Wook; Park, Hyung‐Bok; Shin, Sanghoon; Cole, Jason; Gimelli, Alessia; Khan, Muhammad Akram; Lü, Bin; Gao, Yang; Nabi, Faisal; Nakazato, Ryota; Schoepf, U. Joseph; Driessen, Roel; Bom, Michiel J.; Thompson, Randall C.; Jang, James J.; Ridner, Michael; Rowan, Chris; Avelar, Erick; Généreux, Philippe; Knaapen, Paul; Waard, Guus A. de; Andreini, Daniele; Guglielmo, Marco; Al‐Mallah, Mouaz H.; Jennings, Robert J.; Crabtree, Tami; Earls, James P.

doi:10.1016/j.clinimag.2022.01.016

Cited by 7 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We, therefore, recommend harmonization of the routinely used workflows by interprofessional communication and training. Moreover, studies are evolving, which evaluate the feasibility of AI models and algorithms implemented in analysis software even for small cardiac structures, to detect moderate to high-grade coronary stenosis ( 6 , 7 ). In the future, it might be promising to validate and standardize AI algorithms to overcome discrepancies in the measurement of complex structures and choose the prothesis with the best hemodynamic and prognostic outcome in patients with aortic valve stenosis scheduled for TAVR.…”

Section: Discussionmentioning

confidence: 99%

Multi-Slice Computed Tomography Analysis in Patients Undergoing Transcatheter Aortic Valve Replacement – Impact of Workflows on Measurement of Virtual Aortic Annulus and Valve Size

Piayda

Hellhammer

Veulemans

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

Exact and reliable measurements of anatomical dimensions in pre-procedural multi-slice computed tomography (MSCT) scans are crucial for optimal valve sizing and clinical results of transcatheter aortic valve replacement (TAVR). This study aimed to investigate interrater reliability between routinely used workflows for pre-procedural analysis. MSCT scans of 329 patients scheduled for TAVR were analyzed using both a 3mensio and SECTRA IDS7 platform. The results were retrospectively compared using the intraclass correlation coefficient, revealing excellent correlation in the analysis of simple diameters and poor correlation in the assessment of more complex structures with impact on calculated valve size.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Slice Computed Tomography Analysis in Patients Undergoing Transcatheter Aortic Valve Replacement – Impact of Workflows on Measurement of Virtual Aortic Annulus and Valve Size

Piayda

Hellhammer

Veulemans

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

show abstract

“…They concluded that the performance is only transferable between kernel types if all options are included in the training step of the algorithm. Recently, the impact of acquisition and patient parameters on an AI-guided CAD assessment system was evaluated 17 . The underlying pipeline consists of ML-based centerline extraction and labeling, inner and outer wall segmentation and lesion detection and scoring systems.…”

Section: Introductionmentioning

confidence: 99%

How scan parameter choice affects deep learning-based coronary artery disease assessment from computed tomography

Denzinger

Wels

Breininger

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Recently, algorithms capable of assessing the severity of Coronary Artery Disease (CAD) in form of the Coronary Artery Disease-Reporting and Data System (CAD-RADS) grade from Coronary Computed Tomography Angiography (CCTA) scans using Deep Learning (DL) were proposed. Before considering to apply these algorithms in clinical practice, their robustness regarding different commonly used Computed Tomography (CT)-specific image formation parameters—including denoising strength, slab combination, and reconstruction kernel—needs to be evaluated. For this study, we reconstructed a data set of 500 patient CCTA scans under seven image formation parameter configurations. We select one default configuration and evaluate how varying individual parameters impacts the performance and stability of a typical algorithm for automated CAD assessment from CCTA. This algorithm consists of multiple preprocessing and a DL prediction step. We evaluate the influence of the parameter changes on the entire pipeline and additionally on only the DL step by propagating the centerline extraction results of the default configuration to all others. We consider the standard deviation of the CAD severity prediction grade difference between the default and variation configurations to assess the stability w.r.t. parameter changes. For the full pipeline we observe slight instability (± 0.226 CAD-RADS) for all variations. Predictions are more stable with centerlines propagated from the default to the variation configurations (± 0.122 CAD-RADS), especially for differing denoising strengths (± 0.046 CAD-RADS). However, stacking slabs with sharp boundaries instead of mixing slabs in overlapping regions (called true stack ± 0.313 CAD-RADS) and increasing the sharpness of the reconstruction kernel (± 0.150 CAD-RADS) leads to unstable predictions. Regarding the clinically relevant tasks of excluding CAD (called rule-out; AUC default 0.957, min 0.937) and excluding obstructive CAD (called hold-out; AUC default 0.971, min 0.964) the performance remains on a high level for all variations. Concluding, an influence of reconstruction parameters on the predictions is observed. Especially, scans reconstructed with the true stack parameter need to be treated with caution when using a DL-based method. Also, reconstruction kernels which are underrepresented in the training data increase the prediction uncertainty.

show abstract

AI-Based Automated Quantification of Arterial Stenosis in Head and Neck CT Angiography: A Comparison with Manual Measurements from Digital Subtraction Angiography and CT Angiography

Huan,

Yang,

Niu

et al. 2024

Clin Neuroradiol

View full text Add to dashboard Cite

The effect of scan and patient parameters on the diagnostic performance of AI for detecting coronary stenosis on coronary CT angiography

Cited by 7 publications

References 33 publications

Multi-Slice Computed Tomography Analysis in Patients Undergoing Transcatheter Aortic Valve Replacement – Impact of Workflows on Measurement of Virtual Aortic Annulus and Valve Size

Multi-Slice Computed Tomography Analysis in Patients Undergoing Transcatheter Aortic Valve Replacement – Impact of Workflows on Measurement of Virtual Aortic Annulus and Valve Size

How scan parameter choice affects deep learning-based coronary artery disease assessment from computed tomography

AI-Based Automated Quantification of Arterial Stenosis in Head and Neck CT Angiography: A Comparison with Manual Measurements from Digital Subtraction Angiography and CT Angiography

Contact Info

Product

Resources

About