Dataset Information

Deep learning-based motion correction algorithm for coronary CT angiography: Lowering the phase requirement for morphological and functional evaluation.

ABSTRACT:

Purpose

To investigate the performance of a deep learning-based motion correction algorithm (MCA) at various cardiac phases of coronary computed tomography angiography (CCTA), and determine the extent to which it may allow for reliable morphological and functional evaluation.

Materials and methods

The acquired image data of 53 CCTA cases, where the patient heart rate (HR) was ≥75 bpm, were reconstructed at 0, ±2, ±4, ±6, and ±8% deviations from each optimal systolic phase, with and without the MCA, yielding a total of 954 images (53 cases × 9 phases × 2 reconstructions). The overall image quality and diagnostic confidence were graded by two radiologists using a 5-point scale, with scores ≥3 being deemed clinically interpretable. Signal-to-noise ratio, contrast-to-noise ratio, vessel sharpness, and circularity were measured. The CCTA-derived fractional flow reserve (CT-FFR) was calculated in 38 vessels on 24 patients to identify functionally significant stenosis, using the invasive fractional flow reserve (FFR) as reference. All metrics were compared between two reconstructions at various phases.

Results

Inferior image quality was observed as the phase deviation was enlarged. However, MCA significantly improved the image quality at nonoptimal phases and the optimal phase. Coronary artery evaluation was feasible within 4% phase deviation using MCA, with interpretable overall image quality and high diagnostic confidence. With MCA, the performance of identifying functionally significant stenosis via CT-FFR was increased for images at various phase deviations. However, obvious decrease in accuracy, as compared to the image at the optimal phase, was found on those with deviations >4%.

Conclusion

The deep learning-based MCA allows up to 4% phase deviation in acquiring CCTA for reliable morphological and functional evaluation on patients with high HRs.

SUBMITTER: Yao X

PROVIDER: S-EPMC10476979 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-based motion correction algorithm for coronary CT angiography: Lowering the phase requirement for morphological and functional evaluation.

Yao Xiaoling X Zhong Sihua S Xu Maolan M Zhang Guozhi G Yuan Yuan Y Shuai Tao T Li Zhenlin Z

Journal of applied clinical medical physics 20230724 9

<h4>Purpose</h4>To investigate the performance of a deep learning-based motion correction algorithm (MCA) at various cardiac phases of coronary computed tomography angiography (CCTA), and determine the extent to which it may allow for reliable morphological and functional evaluation.<h4>Materials and methods</h4>The acquired image data of 53 CCTA cases, where the patient heart rate (HR) was ≥75 bpm, were reconstructed at 0, ±2, ±4, ±6, and ±8% deviations from each optimal systolic phase, with an ...[more]

PMID: 37485892

Similar Datasets

Project description:Patients with intermediate anatomical degree of coronary artery stenosis require determination of its functional significance. Currently, the reference standard for determining the functional significance of a stenosis is invasive measurement of the fractional flow reserve (FFR), which is associated with high cost and patient burden. To address these drawbacks, FFR can be predicted non-invasively from a coronary CT angiography (CCTA) scan. Hence, we propose a deep learning method for predicting the invasively measured FFR of an artery using a CCTA scan. The study includes CCTA scans of 569 patients from three hospitals. As reference for the functional significance of stenosis, FFR was measured in 514 arteries in 369 patients, and in the remaining 200 patients, obstructive coronary artery disease was ruled out by Coronary Artery Disease-Reporting and Data System (CAD-RADS) category 0 or 1. For prediction, the coronary tree is first extracted and used to reconstruct an MPR for the artery at hand. Thereafter, the coronary artery is characterized by its lumen, its attenuation and the area of the coronary artery calcium in each artery cross-section extracted from the MPR using a CNN. Additionally, characteristics indicating the presence of bifurcations and information indicating whether the artery is a main branch or a side-branch of a main artery are derived from the coronary artery tree. All characteristics are fed to a second network that predicts the FFR value and classifies the presence of functionally significant stenosis. The final result is obtained by merging the two predictions. Performance of our method is evaluated on held out test sets from multiple centers and vendors. The method achieves an area under the receiver operating characteristics curve (AUC) of 0.78, outperforming other works that do not require manual correction of the segmentation of the artery. This demonstrates that our method may reduce the number of patients that unnecessarily undergo invasive measurements.

Project description:PurposeRespiratory motion (RM) significantly impacts image quality in thoracoabdominal PET/CT imaging. This study introduces a unified data-driven respiratory motion correction (uRMC) method, utilizing deep learning neural networks, to solve all the major issues caused by RM, i.e., PET resolution loss, attenuation correction artifacts, and PET-CT misalignment.MethodsIn a retrospective study, 737 patients underwent [18F]FDG PET/CT scans using the uMI Panorama PET/CT scanner. Ninety-nine patients, who also had respiration monitoring device (VSM), formed the validation set. The remaining data of the 638 patients were used to train neural networks used in the uRMC. The uRMC primarily consists of three key components: (1) data-driven respiratory signal extraction, (2) attenuation map generation, and (3) PET-CT alignment. SUV metrics were calculated within 906 lesions for three approaches, i.e., data-driven uRMC (proposed), VSM-based uRMC, and OSEM without motion correction (NMC). RM magnitude of major organs were estimated.ResultsuRMC enhanced diagnostic capabilities by revealing previously undetected lesions, sharpening lesion contours, increasing SUV values, and improving PET-CT alignment. Compared to NMC, uRMC showed increases of 10% and 17% in SUVmax and SUVmean across 906 lesions. Sub-group analysis showed significant SUV increases in small and medium-sized lesions with uRMC. Minor differences were found between VSM-based and data-driven uRMC methods, with the SUVmax was found statistically marginal significant or insignificant between the two methods. The study observed varied motion amplitudes in major organs, typically ranging from 10 to 20 mm.ConclusionA data-driven solution for respiratory motion in PET/CT has been developed, validated and evaluated. To the best of our knowledge, this is the first unified solution that compensates for the motion blur within PET, the attenuation mismatch artifacts caused by PET-CT misalignment, and the misalignment between PET and CT.

Project description:ObjectivesCardiac computed tomography (CT) is essential in diagnosing coronary heart disease. However, a disadvantage is the associated radiation exposure to the patient which depends in part on the scan range. This study aimed to develop a deep neural network to optimize the delimitation of scan ranges in CT localizers to reduce the radiation dose.MethodsOn a retrospective training cohort of 1507 CT localizers randomly selected from calcium scoring and angiography scans and acquired between 2010 and 2017, optimized scan ranges were delimited by two radiologists in consensus. A neural network was trained to reproduce the scan ranges and was tested on two randomly selected and independent validation cohorts: an internal cohort of 233 CT localizers (January 2018-June 2020) and an external cohort from a nearby hospital of 298 CT localizers (July 2020-December 2020). Localizers where a bypass surgery was visible were excluded. The effective radiation dose to the patient was simulated using a Monte Carlo simulation. Scan ranges of radiographers, radiologists, and the network were compared using an equivalence test; likewise, the reduction in effective dose was tested using a superior test.ResultsThe network replicated the radiologists' scan ranges with a Dice score of 96.5 ± 0.02 (p < 0.001, indicating equivalence). The generated scan ranges resulted in an effective dose reduction of 10.0% (p = 0.002) in the internal cohort and 12.6% (p < 0.001) in the external cohort compared to the scan ranges delimited by radiographers in clinical routine.ConclusionsAutomatic delimitation of the scan range can result in a radiation dose reduction to the patient.Clinical relevance statementFully automated delimitation of the scan range using a deep neural network enables a significant reduction in radiation exposure during CT coronary angiography compared to manual examination planning. It can also reduce the workload of the radiographers.Key points• Scan range delimitation for coronary computed tomography angiography could be performed with high accuracy by a deep neural network. • Automated scan ranges showed a high agreement of 96.5% with the scan ranges of radiologists. • Using a Monte Carlo simulation, automated scan ranges reduced the effective dose to the patient by up to 12.6% (0.9 mSv) compared to the scan ranges of radiographers in clinical routine.

Project description:BackgroundGE Healthcare's new generation of deep-learning image reconstruction (DLIR), the Revolution Apex CT is the first CT image reconstruction engine based on a deep neural network to be approved by the US Food and Drug Administration (FDA). It can generate high-quality CT images that restore the true texture with a low radiation dose. The aim of the present study was to assess the image quality of coronary CT angiography (CCTA) at 70 kVp with the DLIR algorithm as compared to the adaptive statistical iterative reconstruction-Veo (ASiR-V) algorithm in patients of different weight.MethodsThe study group comprised 96 patients who underwent CCTA examination at 70 kVp and were subdivided by body mass index (BMI) into normal-weight patients [48] and overweight patients [48]. ASiR-V40%, ASiR-V80%, DLIR-low, DLIR-medium, and DLIR-high images were obtained. The objective image quality, radiation dose, and subjective score of the two groups of images with different reconstruction algorithms were compared and statistically analyzed.ResultsIn the overweight group, the noise of the DLIR image was lower than that of the routinely used ASiR-40%, and the contrast-to-noise ratio (CNR) of DLIR (H: 19.15±4.31; M: 12.68±2.91; L: 10.59±2.32) was higher than that of the ASiR-40% reconstructed image (8.39±1.46), with statistically significant differences (all P values <0.05). The subjective image quality evaluation of DLIR was significantly higher than that of ASiR-V reconstructed images (all P values <0.05), with the DLIR-H being the best. In a comparison of the normal-weight and overweight groups, the objective score of the ASiR-V-reconstructed image increased with increasing strength, but the subjective image evaluation decreased, and both differences (i.e., objective and subjective) were statistically significant (P<0.05). In general, the objective score of the DLIR reconstruction image between the two groups increased with increased noise reduction, and the DLIR-L image was the best. The difference between the two groups was statistically significant (P<0.05), but there was no significant difference in subjective image evaluation between the two groups. The effective dose (ED) of the normal-weight group and the overweight group was 1.36±0.42 and 1.59±0.46 mSv, respectively, and was significantly higher in the overweight group (P<0.05).ConclusionsAs the strength of the ASiR-V reconstruction algorithm increased, the objective image quality increased accordingly, but the high-strength ASiR-V changed the noise texture of the image, resulting in a decrease in the subjective score, which affected disease diagnosis. Compared with the ASiR-V reconstruction algorithm, the DLIR reconstruction algorithm improved the image quality and diagnostic reliability for CCTA in patients with different weights, especially in heavier patients.

Project description:PurposeTo determine the impact of low tube voltage coronary CT angiography on detection of subclinical atherosclerosis.Materials and methodsRetrospective sampling of an emergency department coronary CT angiography registry was performed. All patients in the registry underwent a noncontrast coronary artery calcium (CAC) scoring scan at 120 kV before coronary CT angiography. The study sample (n = 264) constituted patients with subclinical atherosclerosis (Coronary Artery Disease Reporting and Data System™ [CAD-RADS] 1 or 2) randomly mixed one-to-one with patients without atherosclerosis (CAD-RADS 0). The patients with coronary CT angiography performed at 70-90 kV were considered the low tube voltage group (n = 159) and patients with coronary CT angiography performed at 100-120 kV were considered the standard tube voltage group (n = 105). The number of coronary plaques and overall CAD-RADS classification (per patient) were evaluated twice: initially, by reading coronary CT angiography alone, and then, by coronary CT angiography in combination with a CAC scan. Considering the combined reading (CT angiography plus CAC scan) as the reference standard, the performance of coronary CT angiography alone was assessed for plaque detection and appropriate CAD-RADS (per patient) classification. The comparisons were made between the low tube voltage and standard tube voltage groups by using a Fisher exact test and χ2 test for proportions and a Mann-Whitney test and Kruskal-Wallis test for means.ResultsIn total, 455 plaques were identified in 118 patients (70 of 159 patients in the low tube voltage group; 48 of 105 in the standard tube voltage group). When reading coronary CT angiographic images alone, 97 of 455 (21%) plaques were missed that led to an incorrect CAD-RADS classification in 16 of 264 (6%) studies (interpreted as CAD-RADS 0 instead of CAD-RADS 1 or 2). Missed plaques were significantly more frequent in the low tube voltage group versus the standard tube voltage group (41% [85 of 206] vs 5% [12 of 249], respectively; P < .001). Incorrect CAD-RADS classification was also seen more commonly in the low tube voltage group (8.8% [14 of 159] vs 2% [two of 105]; P = .01), typically at low plaque burden (median CAC score, 1; range, 1-4). Calcified plaques that appeared isodense to luminal contrast material attenuation were seen more frequently in the low tube voltage group compared with the standard tube voltage group (20% [32 of 159] vs 7.6% [eight of 105], respectively; P = .005).ConclusionCoronary artery plaques may be missed at low tube voltage coronary CT angiographic examination performed without a concomitant CAC scan.© RSNA, 2019Supplemental material is available for this article.See also the commentary by Truong in this issue.

Dataset Information

Deep learning-based motion correction algorithm for coronary CT angiography: Lowering the phase requirement for morphological and functional evaluation.

Purpose

Materials and methods

Results

Conclusion

Publications

Deep learning-based motion correction algorithm for coronary CT angiography: Lowering the phase requirement for morphological and functional evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets