Dataset Information

3D Deep Learning Angiography (3D-DLA) from C-arm Conebeam CT.

ABSTRACT:

Background and purpose

Deep learning is a branch of artificial intelligence that has demonstrated unprecedented performance in many medical imaging applications. Our purpose was to develop a deep learning angiography method to generate 3D cerebral angiograms from a single contrast-enhanced C-arm conebeam CT acquisition in order to reduce image artifacts and radiation dose.

Materials and methods

A set of 105 3D rotational angiography examinations were randomly selected from an internal data base. All were acquired using a clinical system in conjunction with a standard injection protocol. More than 150 million labeled voxels from 35 subjects were used for training. A deep convolutional neural network was trained to classify each image voxel into 3 tissue types (vasculature, bone, and soft tissue). The trained deep learning angiography model was then applied for tissue classification into a validation cohort of 8 subjects and a final testing cohort of the remaining 62 subjects. The final vasculature tissue class was used to generate the 3D deep learning angiography images. To quantify the generalization error of the trained model, we calculated the accuracy, sensitivity, precision, and Dice similarity coefficients for vasculature classification in relevant anatomy. The 3D deep learning angiography and clinical 3D rotational angiography images were subjected to a qualitative assessment for the presence of intersweep motion artifacts.

Results

Vasculature classification accuracy and 95% CI in the testing dataset were 98.7% (98.3%-99.1%). No residual signal from osseous structures was observed for any 3D deep learning angiography testing cases except for small regions in the otic capsule and nasal cavity compared with 37% (23/62) of the 3D rotational angiographies.

Conclusions

Deep learning angiography accurately recreated the vascular anatomy of the 3D rotational angiography reconstructions without a mask. Deep learning angiography reduced misregistration artifacts induced by intersweep motion, and it reduced radiation exposure required to obtain clinically useful 3D rotational angiography.

SUBMITTER: Montoya JC

PROVIDER: S-EPMC6758552 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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:The authors have developed a method to enable cerebral perfusion CT imaging using C-arm based conebeam CT (CBCT). This allows intraprocedural monitoring of brain perfusion during treatment of stroke. Briefly, the technique consists of acquiring multiple scans (each scan comprised of six sweeps) acquired at different time delays with respect to the start of the x-ray contrast agent injection. The projections are then reconstructed into angular blocks and interpolated at desired time points. The authors have previously demonstrated its feasibility in vivo using an animal model. In this paper, the authors describe an in vitro technique to evaluate the accuracy of their method for measuring the relevant temporal signals.The authors' evaluation method is based on the concept that any temporal signal can be represented by a Fourier series of weighted sinusoids. A sinusoidal phantom was developed by varying the concentration of iodine as successive steps of a sine wave. Each step corresponding to a different dilution of iodine contrast solution contained in partitions along a cylinder. By translating the phantom along the axis at different velocities, sinusoidal signals at different frequencies were generated. Using their image acquisition and reconstruction algorithm, these sinusoidal signals were imaged with a C-arm system and the 3D volumes were reconstructed. The average value in a slice was plotted as a function of time. The phantom was also imaged using a clinical CT system with 0.5 s rotation. C-arm CBCT results using 6, 3, 2, and 1 scan sequences were compared to those obtained using CT. Data were compared for linear velocities of the phantom ranging from 0.6 to 1 cm∕s. This covers the temporal frequencies up to 0.16 Hz corresponding to a frequency range within which 99% of the spectral energy for all temporal signals in cerebral perfusion imaging is contained.The errors in measurement of temporal frequencies are mostly below 2% for all multiscan sequences. For single scan sequences, the errors increase sharply beyond 0.10 Hz. The amplitude errors increase with frequency and with decrease in the number of scans used.Our multiscan perfusion CT approach allows low errors in signal frequency measurement. Increasing the number of scans reduces the amplitude errors. A two-scan sequence appears to offer the best compromise between accuracy and the associated total x-ray and iodine dose.

Project description:Background and purposeMicro-arteriovenous malformations are an underrecognized etiology of intracranial hemorrhage. Our study aimed to assess the adjunctive efficacy of intra-arterial conebeam CTA relative to DSA in the diagnosis and surgical planning of intracranial micro-AVMs.Materials and methodsWe performed a retrospective study of all micro-AVMs (≤1-cm nidus) at our institution. Blinded neuroradiologists qualitatively graded DSA and intra-arterial conebeam CTA images for the detection of specific micro-AVM anatomic parameters (arterial feeder, micronidus, and venous drainer) and defined an overall diagnostic value. Statistical and absolute differences in the overall diagnostic values defined the relative intra-arterial conebeam CTA diagnostic values, respectively. Blinded neurosurgeons reported their treatment approach after DSA and graded the adjunctive value of intra-arterial conebeam CTA to improve or modify treatment. Intra-arterial conebeam CTA efficacy was defined as interobserver agreement in the relative intra-arterial conebeam CTA diagnostic and/or treatment-planning value scores.ResultsTen patients with micro-AVMs presented with neurologic deficits and/or intracranial hemorrhages. Both neuroradiologists assigned a higher overall intra-arterial conebeam CTA diagnostic value (P < .05), secondary to improved evaluation of both arterial feeders and the micronidus, with good interobserver agreement (τ = 0.66, P = .018) in the relative intra-arterial conebeam CTA diagnostic value. Both neurosurgeons reported that integrating the intra-arterial conebeam CTA data into their treatment plan would allow more confident localization for surgical/radiation treatment (8/10; altering the treatment plan in 1 patient), with good interobserver agreement in the relative intra-arterial conebeam CTA treatment planning value (τ = 0.73, P = .025).ConclusionsAdjunctive intra-arterial conebeam CTA techniques are more effective in the diagnostic identification and anatomic delineation of micro-AVMs, relative to DSA alone, with the potential to improve microsurgical or radiosurgery treatment planning.

Project description:ObjectiveTo assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction.Materials and methodsWe retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction).ResultsObjective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons.ConclusionApplication of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

Project description:BackgroundGuidelines recommend that aortic dimension measurements in aortic dissection should include the aortic wall. This study aimed to evaluate two-dimensional (2D)- and three-dimensional (3D)-based deep learning approaches for extraction of outer aortic surface in computed tomography angiography (CTA) scans of Stanford type B aortic dissection (TBAD) patients and assess the speed of different whole aorta (WA) segmentation approaches.MethodsA total of 240 patients diagnosed with TBAD between January 2007 and December 2019 were retrospectively reviewed for this study; 206 CTA scans from 206 patients with acute, subacute, or chronic TBAD acquired with various scanners in multiple different hospital units were included. Ground truth (GT) WAs for 80 scans were segmented by a radiologist using an open-source software. The remaining 126 GT WAs were generated via semi-automatic segmentation process in which an ensemble of 3D convolutional neural networks (CNNs) aided the radiologist. Using 136 scans for training, 30 for validation, and 40 for testing, 2D and 3D CNNs were trained to automatically segment WA. Main evaluation metrics for outer surface extraction and segmentation accuracy were normalized surface Dice (NSD) and Dice coefficient score (DCS), respectively.Results2D CNN outperformed 3D CNN in NSD score (0.92 versus 0.90, p = 0.009), and both CNNs had equal DCS (0.96 versus 0.96, p = 0.110). Manual and semi-automatic segmentation times of one CTA scan were approximately 1 and 0.5 h, respectively.ConclusionsBoth CNNs segmented WA with high DCS, but based on NSD, better accuracy may be required before clinical application. CNN-based semi-automatic segmentation methods can expedite the generation of GTs.Relevance statementDeep learning can speeds up the creation of ground truth segmentations. CNNs can extract the outer aortic surface in patients with type B aortic dissection.Key points• 2D and 3D convolutional neural networks (CNNs) can extract the outer aortic surface accurately. • Equal Dice coefficient score (0.96) was reached with 2D and 3D CNNs. • Deep learning can expedite the creation of ground truth segmentations.