Impact of a Deep Learning-based Super-resolution Image Reconstruction Technique on High-contrast Computed Tomography: A Phantom Study.

RATIONALE AND OBJECTIVES: Deep-learning-based super-resolution image reconstruction (DLSRR) is a novel image reconstruction technique that is expected to contribute to improvement in spatial resolution as well as noise reduction through learning from high-resolution computed tomography (CT). This study aims to evaluate image quality obtained with DLSRR and assess its clinical potential. MATERIALS AND METHODS: CT images of a Mercury CT 4.0 phantom were obtained using a 320-row multi-detector scanner at tube currents of 100, 200, and 300 mA. Image data were reconstructed by filtered back projection (FBP), hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), deep-learning-based image reconstruction (DLR), and DLSRR at image reconstruction strength levels of mild, standard, and strong. Noise power spectrum (NPS), task transfer function (TTF), and detectability index were calculated. RESULTS: The magnitude of the noise-reducing effect in comparison with FBP was in the order MBIR

Use of a deep-learning-based lumen extraction method to detect significant stenosis on coronary computed tomography angiography in patients with severe coronary calcification.

BACKGROUND: Coronary computed tomography angiography examinations are increasingly becoming established as a minimally invasive method for diagnosing coronary diseases. However, although various imaging and processing methods have been developed, coronary artery calcification remains a major limitation in the evaluation of the vascular lumen. Subtraction coronary computed tomography angiography (Sub-CCTA) is a method known to be able to reduce the influence of coronary artery calcification and is therefore feasible for improving the diagnosis of significant stenosis in patients with severe calcification. However, Sub-CCTA still involves some problems, such as the increased radiation dose due to plain (mask) imaging, extended breath-holding time, and misregistration due to differences in the imaging phase. Therefore, we considered using artificial intelligence instead of Sub-CCTA to visualize the coronary lumen with high calcification. Given this background, the present study aimed to evaluate the diagnostic performance of a deep learning-based lumen extraction method (DL-LEM) to detect significant stenosis on CCTA in 99 consecutive patients (891 segments) with severe coronary calcification from November 2015 to March 2018. We also estimated the impact of DL-LEM on the medical economics in Japan. RESULTS: The DL-LEM slightly improved the per-segment diagnostic accuracy from 74.5 to 76.4%, and the area under the curve (AUC) slightly improved from 0.752 to 0.767 (p = 0.030). When analyzing the 228 segments that could not be evaluated because of severe calcification on the original CCTA images, the DL-LEM improved the accuracy from 35.5 to 42.5%, and the AUC improved from 0.500 to 0.587 (p = 0.00018). As a result, DL-LEM analysis could have avoided invasive coronary angiography in 4/99 cases (per patient). From the calculated results, it was estimated that the number of exams that can be avoided in Japan in one year is approximately 747 for invasive coronary angiography, 219 for fractional flow reserve, and 248 for nuclear exam. The total amount of medical fee that could be reduced was 225,629,368 JPY. CONCLUSIONS: These findings suggest that the DL-LEM may improve the diagnostic performance in detecting significant stenosis in patients with severe coronary calcification. In addition, the results suggest that not a small medical economic effect can be expected.

Efficacy of CO2 Infusion for Preoperative Computed Tomographic Angiography with Computed Tomographic Colonography.

BACKGROUND Computed tomographic colonography (CTC) is useful for patients for whom colonoscopy may be difficult to perform and is widely employed to examine the vasculature prior to colorectal cancer surgery. Computed tomographic angiography (CTA) was shown to be beneficial intraoperatively to manipulate blood vessels and prevent vascular injury. Three-dimensional (3D)-CTA combined with CTC (3D-CTA with CTC) is useful for preoperative evaluations of the anatomy of mesenteric vessels, colon, and lymph nodes. We observed that when the intestine was dilated with carbon dioxide (CO2), the arteriovenous delineation was often more pronounced than without CO2. To clarify the effects of gas injection with and without CO2 on hemodynamics and vascular passage, we compared the effect of contrast for blood vessels. MATERIAL AND METHODS Thirty patients with resectable colorectal cancer who underwent a preoperative CT examination at our institution from January to October 2019 were study participants. Of these, 15 underwent 3D-CTA and 15 had 3D-CTA with CTC. Three board-certified radiologists independently and blindly evaluated 18 blood vessels. CT values for each blood vessel were measured on each image. RESULTS CT values for 3D-CTA with CTC were significantly higher with CO2 than without CO2. The quality of 3D-CTA with CTC images for visualization of blood vessels was also significantly greater than that of 3D-CTA, especially those of arterial and intramesenteric venous systems. CONCLUSIONS Based on the higher image quality and CT values obtained by 3D-CTA with CTC for vessels, compared with by 3D-CTA imaging, 3D-CTA with CTC imaging might be useful in evaluating colorectal cancers.

Diagnostic accuracy of 3D deep-learning-based fully automated estimation of patient-level minimum fractional flow reserve from coronary computed tomography angiography.

AIMS: Although deep-learning algorithms have been used to compute fractional flow reserve (FFR) from coronary computed tomography angiography (CCTA), no study has achieved 'fully automated' (i.e. free from human input) FFR calculation using deep-learning algorithms. The purpose of the study was to evaluate the accuracy of a fully automated 3D deep-learning model for estimating minimum FFR from CCTA data, with invasive FFR as the reference standard. METHODS AND RESULTS: This retrospective study of 1052 patients included 131 patients whose CCTA studies showed 30-90% stenosis and underwent invasive FFR (abnormal FFR observed in 72/131, 55%), and 921 patients who underwent clinically indicated CCTA without invasive FFR. We designed a fully automated 3D deep-learning model that inputs CCTA data and outputs minimum FFR without requiring human input. The model comprised a series of deep-learning algorithms: a conditional generative adversarial network, a 3D convolutional ladder network, and two independent neural networks with integrated virtual adversarial training. We used Monte Carlo cross-validation to evaluate the accuracy of the model for estimating FFR, with invasive FFR as the reference standard. The deep-learning FFR achieved area under the receiver-operating characteristic curve of 0.78 for detection of abnormal FFR; and was significantly higher than for visually determined CCTA >50% stenosis (area under the curve = 0.56). The deep-learning FFR model achieved 76% accuracy for detecting abnormal FFR, with sensitivity of 85% (79-89%) and specificity of 63% (54-70%). CONCLUSION: The 3D deep-learning model, which performs fully automatic estimation of minimum FFR from cardiac CT data, achieved 76% accuracy in detecting abnormal FFR.

[The Effect of Reconstruction Method on the Ability to Analyze of FFR Using CT].

BACKGROUND: Invasive-fractional flow reserve (FFR) is the reference standard to evaluate functional ischemia of coronary arteries, and is used to decide if percutaneous transluminal coronary angioplasty is necessary. Recently, computed tomography-derived FFR (CT-FFR) is emerged as an alternative non-invasive method. OBJECTIVES: To evaluate the effect of reconstruction methods and image parameters on the accuracy of CT-FFR calculation. METHODS: A total of 26 segments in the consecutive 10 coronary CT angiography (CCTA) studies were evaluated. All studies were reconstructed using three different techniques: 1) filtered back projection (FBP), 2) adaptive iterative dose reduction 3D (AIDR 3D), and 3) forward projected model-based iterative reconstruction solution (FIRST). Vessel segmentation was performed automatically by CT-FFR software, with manual adjustment if necessary. Calculated CT-FFR was compared with the invasive FFR data. RESULTS: Compared to FBP, AIDR 3D and FIRST resulted in more successful automatic segmentation. When using FIRST, 7 segments (27%) were completed without manual adjustment. These segments had relatively larger vessel diameter, higher CT number, and lower noise. The difference between the calculated CT-FFR and invasive-FFR was 0.02±0.01. Among the remaining, 10 segments (38%) required manual adjustments of centerline, 7 segments (27%) required manual adjustments of contour, and 2 segments (8%) did not reach to the CT-FFR calculation. CONCLUSION: AIDR 3D and FIRST were useful for reliable automatic segmentation and analysis of CT-FFR.