Evaluation of a deep learning model on coronary CT angiography for automatic stenosis detection

Paul, Jean‐François; Rohnean, Adéla; Giroussens, Henri; Pressat-Laffouilhère, Thibaut; Wong, Tatiana

doi:10.1016/j.diii.2022.01.004

Cited by 30 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another aspect to elaborate on is whether the results reported here are transferable to other methods proposed in literature [22][23][24][25][26][27][28][29][30] . These mostly focus on the determination and detection of significant stenosis which is similar to the hold-out task.…”

Section: Discussionmentioning

confidence: 88%

“…Therefore, findings presented here should be largely transferable to different architecture embodiments. Exceptions may be the works of Muscoguiri et al 28 , who directly operate on the 3D data, and Paul et al 30 , who operate on the curved views instead. Furthermore, all of the above-mentioned approaches were trained from data collected from a respective single site.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Discussionmentioning

confidence: 88%

Section: Discussionmentioning

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

show abstract

“…Paul et al [ 23 ] valued a deep-learning model (DLM) trained with 10,800 curved multiplanar reformatted (cMPR) CCTA images for classifying coronary arteries on CCTA using the CAD-RADS. The results showed that sensitivity and specificity were 93% and 97%, respectively, and the negative predictive value was 97%.…”

Section: Ai In Coronary Computed Tomography Angiographymentioning

confidence: 99%

Artificial Intelligence in Cardiovascular CT and MR Imaging

Lanzafame

Bucolo

Muscogiuri

et al. 2023

Life

View full text Add to dashboard Cite

The technological development of Artificial Intelligence (AI) has grown rapidly in recent years. The applications of AI to cardiovascular imaging are various and could improve the radiologists’ workflow, speeding up acquisition and post-processing time, increasing image quality and diagnostic accuracy. Several studies have already proved AI applications in Coronary Computed Tomography Angiography and Cardiac Magnetic Resonance, including automatic evaluation of calcium score, quantification of coronary stenosis and plaque analysis, or the automatic quantification of heart volumes and myocardial tissue characterization. The aim of this review is to summarize the latest advances in the field of AI applied to cardiovascular CT and MR imaging.

show abstract

“…The authors developed a model that was able to predict stenosis <50 and ≥50% based on deep learning, CAD-RADS classification, and MPR reconstruction [ 53 ] which reached a sensitivity, specificity, positive predictive value, negative predictive value and accuracy, respectively, of 93%, 97%, 93%, 97% and 96% in a patient-based model [ 53 ].…”

Section: Ai In Cardiac Computed Tomographymentioning

confidence: 99%