Diagnostic Improvements of Deep Learning-Based Image Reconstruction for Assessing Calcification-Related Obstructive Coronary Artery Disease

Recent advances in artificial intelligence for cardiac CT: Enhancing diagnosis and prognosis prediction

Recent advances in artificial intelligence (AI) for cardiac computed tomography (CT) have shown great potential in enhancing diagnosis and prognosis prediction in patients with cardiovascular disease. Deep learning, a type of machine learning, has revolutionized radiology by enabling automatic feature extraction and learning from large datasets, particularly in image-based applications. Thus, AI-driven techniques have enabled a faster analysis of cardiac CT examinations than when they are analyzed by humans, while maintaining reproducibility. However, further research and validation are required to fully assess the diagnostic performance, radiation dose-reduction capabilities, and clinical correctness of these AI-driven techniques in cardiac CT. This review article presents recent advances of AI in the field of cardiac CT, including deep-learning-based image reconstruction, coronary artery motion correction, automatic calcium scoring, automatic epicardial fat measurement, coronary artery stenosis diagnosis, fractional flow reserve prediction, and prognosis prediction, analyzes current limitations of these techniques and discusses future challenges.

Artificial Intelligence, Computational Simulations, and Extended Reality in Cardiovascular Interventions

Artificial intelligence, computational simulations, and extended reality, among other 21st century computational technologies, are changing the health care system. To collectively highlight the most recent advances and benefits of artificial intelligence, computational simulations, and extended reality in cardiovascular therapies, we coined the abbreviation AISER. The review particularly focuses on the following applications of AISER: 1) preprocedural planning and clinical decision making; 2) virtual clinical trials, and cardiovascular device research, development, and regulatory approval; and 3) education and training of interventional health care professionals and medical technology innovators. We also discuss the obstacles and constraints associated with the application of AISER technologies, as well as the proposed solutions. Interventional health care professionals, computer scientists, biomedical engineers, experts in bioinformatics and visualization, the device industry, ethics committees, and regulatory agencies are expected to streamline the use of AISER technologies in cardiovascular interventions and medicine in general.

Developing a Deep-Learning-Based Coronary Artery Disease Detection Technique Using Computer Tomography Images

Coronary artery disease (CAD) is one of the major causes of fatalities across the globe. The recent developments in convolutional neural networks (CNN) allow researchers to detect CAD from computed tomography (CT) images. The CAD detection model assists physicians in identifying cardiac disease at earlier stages. The recent CAD detection models demand a high computational cost and a more significant number of images. Therefore, this study intends to develop a CNN-based CAD detection model. The researchers apply an image enhancement technique to improve the CT image quality. The authors employed You look only once (YOLO) V7 for extracting the features. Aquila optimization is used for optimizing the hyperparameters of the UNet++ model to predict CAD. The proposed feature extraction technique and hyperparameter tuning approach reduces the computational costs and improves the performance of the UNet++ model. Two datasets are utilized for evaluating the performance of the proposed CAD detection model. The experimental outcomes suggest that the proposed method achieves an accuracy, recall, precision, F1-score, Matthews correlation coefficient, and Kappa of 99.4, 98.5, 98.65, 98.6, 95.35, and 95 and 99.5, 98.95, 98.95, 98.95, 96.35, and 96.25 for datasets 1 and 2, respectively. In addition, the proposed model outperforms the recent techniques by obtaining the area under the receiver operating characteristic and precision-recall curve of 0.97 and 0.95, and 0.96 and 0.94 for datasets 1 and 2, respectively. Moreover, the proposed model obtained a better confidence interval and standard deviation of [98.64-98.72] and 0.0014, and [97.41-97.49] and 0.0019 for datasets 1 and 2, respectively. The study's findings suggest that the proposed model can support physicians in identifying CAD with limited resources.

Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects

Filtered back projection (FBP) has been the standard CT image reconstruction method for 4 decades. A simple, fast, and reliable technique, FBP has delivered high-quality images in several clinical applications. However, with faster and more advanced CT scanners, FBP has become increasingly obsolete. Higher image noise and more artifacts are especially noticeable in lower-dose CT imaging using FBP. This performance gap was partly addressed by model-based iterative reconstruction (MBIR). Yet, its "plastic" image appearance and long reconstruction times have limited widespread application. Hybrid iterative reconstruction partially addressed these limitations by blending FBP with MBIR and is currently the state-of-the-art reconstruction technique. In the past 5 years, deep learning reconstruction (DLR) techniques have become increasingly popular. DLR uses artificial intelligence to reconstruct high-quality images from lower-dose CT faster than MBIR. However, the performance of DLR algorithms relies on the quality of data used for model training. Higher-quality training data will become available with photon-counting CT scanners. At the same time, spectral data would greatly benefit from the computational abilities of DLR. This review presents an overview of the principles, technical approaches, and clinical applications of DLR, including metal artifact reduction algorithms. In addition, emerging applications and prospects are discussed.

Image quality comparison of lower extremity CTA between CT routine reconstruction algorithms and deep learning reconstruction

BACKGROUND

To evaluate the image quality of lower extremity computed tomography angiography (CTA) with deep learning-based reconstruction (DLR) compared to model-based iterative reconstruction (MBIR), hybrid-iterative reconstruction (HIR), and filtered back projection (FBP).

METHODS

Fifty patients (38 males, average age 59.8 ± 19.2 years) who underwent lower extremity CTA between January and May 2021 were included. Images were reconstructed with DLR, MBIR, HIR, and FBP. The standard deviation (SD), contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), noise power spectrum (NPS) curves, and the blur effect, were calculated. The subjective image quality was independently evaluated by two radiologists. The diagnostic accuracy of DLR, MBIR, HIR, and FBP reconstruction algorithms was calculated.

RESULTS

The CNR and SNR were significantly higher in DLR images than in the other three reconstruction algorithms, and the SD was significantly lower in DLR images of the soft tissues. The noise magnitude was the lowest with DLR. The NPS average spatial frequency (f_av) values were higher using DLR than HIR. For blur effect evaluation, DLR and FBP were similar for soft tissues and the popliteal artery, which was better than HIR and worse than MBIR. In the aorta and femoral arteries, the blur effect of DLR was worse than MBIR and FBP and better than HIR. The subjective image quality score of DLR was the highest. The sensitivity and specificity of the lower extremity CTA with DLR were the highest in the four reconstruction algorithms with 98.4% and 97.2%, respectively.

CONCLUSIONS

Compared to the other three reconstruction algorithms, DLR showed better objective and subjective image quality. The blur effect of the DLR was better than that of the HIR. The diagnostic accuracy of lower extremity CTA with DLR was the best among the four reconstruction algorithms.

Coronary Artery Stent Evaluation by CTA: Impact of Deep Learning Reconstruction and Subtraction Technique

BACKGROUND. Coronary CTA with hybrid iterative reconstruction (HIR) is prone to false-positive results for in-stent restenosis due to stent-related blooming artifact. OBJECTIVE. The purpose of this study is to assess the impact of deep learning reconstruction (DLR), subtraction images, and the combination of DLR and subtraction images on the diagnostic performance of coronary CTA for the detection of in-stent restenosis. METHODS. This prospective study included patients with coronary stents who underwent coronary CTA between March 2020 and August 2021. CTA used a technique with two breath-holds (noncontrast and contrast-enhanced acquisitions). Conventional and subtraction images were reconstructed for HIR and DLR. The maximum visible instent lumen diameter was measured. Two readers independently evaluated images for in-stent restenosis (≥ 50% stenosis). A simulated assessment of combined conventional and subtraction images was generated, reflecting assessment of conventional and subtraction images in the presence or absence of severe misregistration artifact, respectively. Invasive angiography served as reference standard. RESULTS. The study enrolled 30 patients (22 men and eight women; mean age, 63.6 ± 7.4 [SD] years) with a total of 59 stents; severe misregistration artifact was present for 32 stents. Maximum visible in-stent lumen diameter was higher for DLR than for HIR (2.3 ± 0.5 vs 2.1 ± 0.5 mm, p < .001), and among stents without severe misregistration artifact, it was higher for subtraction than conventional DLR (3.0 ± 0.5 vs 2.4 ± 0.5, p < .001). Among conventional CTA with HIR, conventional CTA with DLR, combination (conventional and subtraction) approach with HIR, and combination (conventional and subtraction) approach with DLR, the highest patient-level diagnostic performance measures were as follows: for reader 1, sensitivity was identical (62.5%), specificity was highest for combination with DLR (90.1%), PPV was highest for combination with DLR (71.4%), NPV was highest for combination with DLR (87.0%), and accuracy was highest for combination with DLR (83.3%); for reader 2, sensitivity was identical (50.0%), specificity was highest for combination with HIR or DLR (both 95.5%), PPV was highest for combination with HIR or DLR (both 80.0%), NPV was highest for combination with HIR or DLR (84.0%), and accuracy was highest for combination with HIR or DLR (both 83.3%). CONCLUSION. The combined DLR and subtraction technique yielded optimal diagnostic performance for detecting in-stent restenosis by coronary CTA. CLINICAL IMPACT. The described technique could guide patient selection for invasive coronary stent evaluation.

The impact of deep learning reconstruction on image quality and coronary CT angiography-derived fractional flow reserve values

OBJECTIVES

To explore the impact of deep learning reconstruction (DLR) on image quality and machine learning-based coronary CT angiography (CTA)-derived fractional flow reserve (CT-FFR_ML) values.

METHODS

Thirty-three consecutive patients with known or suspected coronary artery disease who underwent coronary CTA and subsequent invasive coronary angiography were enrolled. DLR was compared with filtered back projection (FBP), statistical-based iterative reconstruction (SBIR), model-based iterative reconstruction (MBIR) Cardiac, and MBIR Cardiac sharp for objective image qualities of coronary CTA. Invasive fractional flow reserve (FFR) and quantitative flow ratio (QFR) were used as the reference standards. The diagnostic performances of different reconstruction approach-based CT-FFR_ML were calculated.

RESULTS

A total of 182 lesions in 33 patients were enrolled for analysis. The image quality of DLR was superior to the others. There were no significant differences in the CT-FFR_ML values among these five approaches (all p > 0.05). Of the 182 lesions, 17 had invasive FFR results, and 70 had QFR results. Using FFR as a reference, MBIR Cardiac, MBIR Cardiac sharp, and DLR achieved equal diagnostic performance, slightly higher than the other reconstruction approaches (MBIR Cardiac, MBIR Cardiac sharp, and DLR: AUC = 0.82, FBP and AIDR: AUC = 0.78, all p > 0.05). Using QFR as a reference, the AUCs of FBP, SBIR, MBIR Cardiac, MBIR Cardiac sharp, and DLR were 0.83, 0.81, 0.86, 0.84, and 0.83, respectively (all p > 0.05).

CONCLUSIONS

Our study showed that the DLR algorithm improved image quality, but there were no significant differences in the CT-FFR_ML values and diagnostic performance among different reconstruction approaches.

KEY POINTS

• Deep learning-based image reconstruction (DLR) improves the image quality of coronary CTA. • CT-FFR_ML values and diagnostic performance of DLR revealed no significant differences compared to other reconstruction approaches.

Finetuned Super-Resolution Generative Adversarial Network (Artificial Intelligence) Model for Calcium Deblooming in Coronary Computed Tomography Angiography

The purpose of this study was to finetune a deep learning model, real-enhanced super-resolution generative adversarial network (Real-ESRGAN), and investigate its diagnostic value in calcified coronary plaques with the aim of suppressing blooming artifacts for the further improvement of coronary lumen assessment. We finetuned the Real-ESRGAN model and applied it to 50 patients with 184 calcified plaques detected at three main coronary arteries (left anterior descending [LAD], left circumflex [LCx] and right coronary artery [RCA]). Measurements of coronary stenosis were collected from original coronary computed tomography angiography (CCTA) and Real-ESRGAN-processed images, including Real-ESRGAN-high-resolution, Real-ESRGAN-average and Real-ESRGAN-median (Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M) with invasive coronary angiography as the reference. Our results showed specificity and positive predictive value (PPV) of the Real-ESRGAN-processed images were improved at all of the three coronary arteries, leading to significant reduction in the false positive rates when compared to those of the original CCTA images. The specificity and PPV of the Real-ESRGAN-M images were the highest at the RCA level, with values being 80% (95% CI: 64.4%, 90.9%) and 61.9% (95% CI: 45.6%, 75.9%), although the sensitivity was reduced to 81.3% (95% CI: 54.5%, 95.9%) due to false negative results. The corresponding specificity and PPV of the Real-ESRGAN-M images were 51.9 (95% CI: 40.3%, 63.5%) and 31.5% (95% CI: 25.8%, 37.8%) at LAD, 62.5% (95% CI: 40.6%, 81.2%) and 43.8% (95% CI: 30.3%, 58.1%) at LCx, respectively. The area under the receiver operating characteristic curve was also the highest at the RCA with value of 0.76 (95% CI: 0.64, 0.89), 0.84 (95% CI: 0.73, 0.94), 0.85 (95% CI: 0.75, 0.95) and 0.73 (95% CI: 0.58, 0.89), corresponding to original CCTA, Real-ESRGAN-HR, Real-ESRGAN-A and Real-ESRGAN-M images, respectively. This study proves that the finetuned Real-ESRGAN model significantly improves the diagnostic performance of CCTA in assessing calcified plaques.

Artificial Intelligence (Enhanced Super-Resolution Generative Adversarial Network) for Calcium Deblooming in Coronary Computed Tomography Angiography: A Feasibility Study

Background: The presence of heavy calcification in the coronary artery always presents a challenge for coronary computed tomography angiography (CCTA) in assessing the degree of coronary stenosis due to blooming artifacts associated with calcified plaques. Our study purpose was to use an advanced artificial intelligence (enhanced super-resolution generative adversarial network [ESRGAN]) model to suppress the blooming artifact in CCTA and determine its effect on improving the diagnostic performance of CCTA in calcified plaques. Methods: A total of 184 calcified plaques from 50 patients who underwent both CCTA and invasive coronary angiography (ICA) were analysed with measurements of coronary lumen on the original CCTA, and three sets of ESRGAN-processed images including ESRGAN-high-resolution (ESRGAN-HR), ESRGAN-average and ESRGAN-median with ICA as the reference method for determining sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Results: ESRGAN-processed images improved the specificity and PPV at all three coronary arteries (LAD-left anterior descending, LCx-left circumflex and RCA-right coronary artery) compared to original CCTA with ESRGAN-median resulting in the highest values being 41.0% (95% confidence interval [CI]: 30%, 52.7%) and 26.9% (95% CI: 22.9%, 31.4%) at LAD; 41.7% (95% CI: 22.1%, 63.4%) and 36.4% (95% CI: 28.9%, 44.5%) at LCx; 55% (95% CI: 38.5%, 70.7%) and 47.1% (95% CI: 38.7%, 55.6%) at RCA; while corresponding values for original CCTA were 21.8% (95% CI: 13.2%, 32.6%) and 22.8% (95% CI: 20.8%, 24.9%); 12.5% (95% CI: 2.6%, 32.4%) and 27.6% (95% CI: 24.7%, 30.7%); 17.5% (95% CI: 7.3%, 32.8%) and 32.7% (95% CI: 29.6%, 35.9%) at LAD, LCx and RCA, respectively. There was no significant effect on sensitivity and NPV between the original CCTA and ESRGAN-processed images at all three coronary arteries. The area under the receiver operating characteristic curve was the highest with ESRGAN-median images at the RCA level with values being 0.76 (95% CI: 0.64, 0.89), 0.81 (95% CI: 0.69, 0.93), 0.82 (95% CI: 0.71, 0.94) and 0.86 (95% CI: 0.76, 0.96) corresponding to original CCTA and ESRGAN-HR, average and median images, respectively. Conclusions: This feasibility study shows the potential value of ESRGAN-processed images in improving the diagnostic value of CCTA for patients with calcified plaques.

Diagnostic Accuracy of Subtraction Coronary CT Angiography in Severely Calcified Segments: Comparison Between Readers With Different Levels of Experience

Purpose

Subtraction coronary CT angiography (CCTA) may reduce blooming and beam-hardening artifacts. This study aimed to assess its value in improving the diagnostic accuracy of readers with different experience levels.

Method

We prospectively enrolled patients with target segment who underwent CCTA and invasive coronary angiography (ICA). Target segment images were independently evaluated by three groups of radiologists with different experience levels with CCTA using ICA as the standard reference. Diagnostic accuracy was measured by the area under the curve (AUC), using ≥50% stenosis as the cut-off value.

Results

In total, 134 target segments with severe calcification from 47 patients were analyzed. The mean specificity of conventional CCTA for each group ranged from 22.4 to 42.2%, which significantly improved with subtraction CCTA, ranging from 81.3 to 85.7% (all p &lt; 0.001). The mean sensitivity of conventional CCTA for each group ranged from 83.3 to 88.0%. Following calcification subtraction, the mean sensitivity decreased for the novice (p &lt; 0.001) and junior (p = 0.017) radiologists but was unchanged for the senior radiologists (p = 0.690). With subtraction CCTA, the mean AUCs of CCTA significantly increased: values ranged from 0.53, 0.54, and 0.61 to 0.70, 0.74, and 0.85 for the novice, junior, and senior groups (all p &lt; 0.001).

Conclusion

Subtraction CCTA could improve the diagnostic accuracy of radiologists at all experience levels of CCTA interpretation.