Hierarchical decomposed dual-domain deep learning for sparse-view CT reconstruction.

Objective. X-ray computed tomography employing sparse projection views has emerged as a contemporary technique to mitigate radiation dose. However, due to the inadequate number of projection views, an analytic reconstruction method utilizing filtered backprojection results in severe streaking artifacts. Recently, deep learning (DL) strategies employing image-domain networks have demonstrated remarkable performance in eliminating the streaking artifact caused by analytic reconstruction methods with sparse projection views. Nevertheless, it is difficult to clarify the theoretical justification for applying DL to sparse view computed tomography (CT) reconstruction, and it has been understood as restoration by removing image artifacts, not reconstruction.Approach. By leveraging the theory of deep convolutional framelets (DCF) and the hierarchical decomposition of measurement, this research reveals the constraints of conventional image and projection-domain DL methodologies, subsequently, the research proposes a novel dual-domain DL framework utilizing hierarchical decomposed measurements. Specifically, the research elucidates how the performance of the projection-domain network can be enhanced through a low-rank property of DCF and a bowtie support of hierarchical decomposed measurement in the Fourier domain.Main results. This study demonstrated performance improvement of the proposed framework based on the low-rank property, resulting in superior reconstruction performance compared to conventional analytic and DL methods.Significance. By providing a theoretically justified DL approach for sparse-view CT reconstruction, this study not only offers a superior alternative to existing methods but also opens new avenues for research in medical imaging. It highlights the potential of dual-domain DL frameworks to achieve high-quality reconstructions with lower radiation doses, thereby advancing the field towards safer and more efficient diagnostic techniques. The code is available athttps://github.com/hanyoseob/HDD-DL-for-SVCT.

Multi-planar 2.5D U-Net for image quality enhancement of dental cone-beam CT.

Cone-beam computed tomography (CBCT) can provide 3D images of a targeted area with the advantage of lower dosage than multidetector computed tomography (MDCT; also simply referred to as CT). However, in CBCT, due to the cone-shaped geometry of the X-ray source and the absence of post-patient collimation, the presence of more scattering rays deteriorates the image quality compared with MDCT. CBCT is commonly used in dental clinics, and image artifacts negatively affect the radiology workflow and diagnosis. Studies have attempted to eliminate image artifacts and improve image quality; however, a vast majority of that work sacrificed structural details of the image. The current study presents a novel approach to reduce image artifacts while preserving details and sharpness in the original CBCT image for precise diagnostic purposes. We used MDCT images as reference high-quality images. Pairs of CBCT and MDCT scans were collected retrospectively at a university hospital, followed by co-registration between the CBCT and MDCT images. A contextual loss-optimized multi-planar 2.5D U-Net was proposed. Images corrected using this model were evaluated quantitatively and qualitatively by dental clinicians. The quantitative metrics showed superior quality in output images compared to the original CBCT. In the qualitative evaluation, the generated images presented significantly higher scores for artifacts, noise, resolution, and overall image quality. This proposed novel approach for noise and artifact reduction with sharpness preservation in CBCT suggests the potential of this method for diagnostic imaging.

End-to-end deep learning for interior tomography with low-dose x-ray CT.

Objective.There are several x-ray computed tomography (CT) scanning strategies used to reduce radiation dose, such as (1) sparse-view CT, (2) low-dose CT and (3) region-of-interest (ROI) CT (called interior tomography). To further reduce the dose, sparse-view and/or low-dose CT settings can be applied together with interior tomography. Interior tomography has various advantages in terms of reducing the number of detectors and decreasing the x-ray radiation dose. However, a large patient or a small field-of-view (FOV) detector can cause truncated projections, and then the reconstructed images suffer from severe cupping artifacts. In addition, although low-dose CT can reduce the radiation exposure dose, analytic reconstruction algorithms produce image noise. Recently, many researchers have utilized image-domain deep learning (DL) approaches to remove each artifact and demonstrated impressive performances, and the theory of deep convolutional framelets supports the reason for the performance improvement.Approach.In this paper, we found that it is difficult to solve coupled artifacts using an image-domain convolutional neural network (CNN) based on deep convolutional framelets.Significance.To address the coupled problem, we decouple it into two sub-problems: (i) image-domain noise reduction inside the truncated projection to solve low-dose CT problem and (ii) extrapolation of the projection outside the truncated projection to solve the ROI CT problem. The decoupled sub-problems are solved directly with a novel proposed end-to-end learning method using dual-domain CNNs.Main results.We demonstrate that the proposed method outperforms the conventional image-domain DL methods, and a projection-domain CNN shows better performance than the image-domain CNNs commonly used by many researchers.

Improving the Reliability of Pharmacokinetic Parameters at Dynamic Contrast-enhanced MRI in Astrocytomas: A Deep Learning Approach.

Background Pharmacokinetic (PK) parameters obtained from dynamic contrast agent-enhanced (DCE) MRI evaluates the microcirculation permeability of astrocytomas, but the unreliability from arterial input function (AIF) remains a challenge. Purpose To develop a deep learning model that improves the reliability of AIF for DCE MRI and to validate the reliability and diagnostic performance of PK parameters by using improved AIF in grading astrocytomas. Materials and Methods This retrospective study included 386 patients (mean age, 52 years ± 16 [standard deviation]; 226 men) with astrocytomas diagnosed with histopathologic analysis who underwent dynamic susceptibility contrast (DSC)-enhanced and DCE MRI preoperatively from April 2010 to January 2018. The AIF was obtained from each sequence: AIF obtained from DSC-enhanced MRI (AIFDSC) and AIF measured at DCE MRI (AIFDCE). The model was trained to translate AIFDCE into AIFDSC, and after training, outputted neural-network-generated AIF (AIFgenerated DSC) with input AIFDCE. By using the three different AIFs, volume transfer constant (Ktrans), fractional volume of extravascular extracellular space (Ve), and vascular plasma space (Vp) were averaged from the tumor areas in the DCE MRI. To validate the model, intraclass correlation coefficients and areas under the receiver operating characteristic curve (AUCs) of the PK parameters in grading astrocytomas were compared by using different AIFs. Results The AIF-generated, DSC-derived PK parameters showed higher AUCs in grading astrocytomas than those derived from AIFDCE (mean Ktrans, 0.88 [95% confidence interval {CI}: 0.81, 0.93] vs 0.72 [95% CI: 0.63, 0.79], P = .04; mean Ve, 0.87 [95% CI: 0.79, 0.92] vs 0.70 [95% CI: 0.61, 0.77], P = .049, respectively). Ktrans and Ve showed higher intraclass correlation coefficients for AIFgenerated DSC than for AIFDCE (0.91 vs 0.38, P < .001; and 0.86 vs 0.60, P < .001, respectively). In AIF analysis, baseline signal intensity (SI), maximal SI, and wash-in slope showed higher intraclass correlation coefficients with AIFgenerated DSC than AIFDCE (0.77 vs 0.29, P < .001; 0.68 vs 0.42, P = .003; and 0.66 vs 0.45, P = .01, respectively. Conclusion A deep learning algorithm improved both reliability and diagnostic performance of MRI pharmacokinetic parameters for differentiating astrocytoma grades. © RSNA, 2020 Online supplemental material is available for this article.

Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal.

Conebeam CT using a circular trajectory is quite often used for various applications due to its relative simple geometry. For conebeam geometry, Feldkamp, Davis and Kress algorithm is regarded as the standard reconstruction method, but this algorithm suffers from so-called conebeam artifacts as the cone angle increases. Various model-based iterative reconstruction methods have been developed to reduce the cone-beam artifacts, but these algorithms usually require multiple applications of computational expensive forward and backprojections. In this paper, we develop a novel deep learning approach for accurate conebeam artifact removal. In particular, our deep network, designed on the differentiated backprojection domain, performs a data-driven inversion of an ill-posed deconvolution problem associated with the Hilbert transform. The reconstruction results along the coronal and sagittal directions are then combined using a spectral blending technique to minimize the spectral leakage. Experimental results under various conditions confirmed that our method generalizes well and outperforms the existing iterative methods despite significantly reduced runtime complexity.

Reconstruction of multicontrast MR images through deep learning.

PURPOSE: Magnetic resonance (MR) imaging with a long scan time can lead to degraded images due to patient motion, patient discomfort, and increased costs. For these reasons, the role of rapid MR imaging is important. In this study, we propose the joint reconstruction of multicontrast brain MR images from down-sampled data to accelerate the data acquisition process using a novel deep-learning network. METHODS: Twenty-one healthy volunteers (female/male = 7/14, age = 26 ± 4 yr, range 22-35 yr) and 16 postoperative patients (female/male = 7/9, age = 49 ± 9 yr, range 37-62 yr) were scanned on a 3T whole-body scanner for prospective and retrospective studies, respectively, using both T1-weighted spin-echo (SE) and T2-weighted fast spin-echo (FSE) sequences. We proposed a network which we term "X-net" to reconstruct both T1- and T2-weighted images from down-sampled images as well as a network termed "Y-net" which reconstructs T2-weighted images from highly down-sampled T2-weighted images and fully sampled T1-weighted images. Both X-net and Y-net are composed of two concatenated subnetworks. We investigate optimal sampling patterns, the optimal patch size for augmentation, and the optimal acceleration factors for network training. An additional Y-net combined with a generative adversarial network (GAN) was also implemented and tested to investigate the effects of the GAN on the Y-net performance. Single- and joint-reconstruction parallel-imaging and compressed-sensing algorithms along with a conventional U-net were also tested and compared with the proposed networks. For this comparison, the structural similarity (SSIM), normalized mean square error (NMSE), and Fréchet inception distance (FID) were calculated between the outputs of the networks and fully sampled images. The statistical significance of the performance was evaluated by assessing the interclass correlation and in paired t-tests. RESULTS: The outputs from the two concatenated subnetworks were closer to the fully sampled images compared to those from one subnetwork, with this result showing statistical significance. Uniform down-sampling led to a statically significant improvement in the image quality compared to random or central down-sampling patterns. In addition, the proposed networks provided higher SSIM and NMSE values than U-net, compressed-sensing, and parallel-imaging algorithms, all at statistically significant levels. The GAN-based Y-net showed a better FID and more realistic images compared to a non-GAN-based Y-net. The performance capabilities of the networks were similar between normal subjects and patients. CONCLUSIONS: The proposed X-net and Y-net effectively reconstructed full images from down-sampled images, outperforming the conventional parallel-imaging, compressed-sensing and U-net methods and providing more realistic images in combination with a GAN. The developed networks potentially enable us to accelerate multicontrast anatomical MR imaging in routine clinical studies including T1-and T2-weighted imaging.

One network to solve all ROIs: Deep learning CT for any ROI using differentiated backprojection.

PURPOSE: Computed tomography for the reconstruction of region of interest (ROI) has advantages in reducing the x-ray dose and the use of a small detector. However, standard analytic reconstruction methods such as filtered back projection (FBP) suffer from severe cupping artifacts, and existing model-based iterative reconstruction methods require extensive computations. Recently, we proposed a deep neural network to learn the cupping artifacts, but the network was not generalized well for different ROIs due to the singularities in the corrupted images. Therefore, there is an increasing demand for a neural network that works well for any ROI size. METHOD: Two types of neural networks are designed. The first type learns ROI size-specific cupping artifacts from FBP images, whereas the second type network is for the inversion of the truncated Hilbert transform from the truncated differentiated backprojection (DBP) data. Their generalizabilities for different ROI sizes, pixel sizes, detector pitch and starting angles for a short scan are then investigated. RESULTS: Experimental results show that the new type of neural networks significantly outperform existing iterative methods for all ROI sizes despite significantly lower runtime complexity. In addition, performance improvement is consistent across different acquisition scenarios. CONCLUSIONS: Since the proposed method consistently surpasses existing methods, it can be used as a general CT reconstruction engine for many practical applications without compromising possible detector truncation.

k-Space deep learning for reference-free EPI ghost correction.

PURPOSE: Nyquist ghost artifacts in echo planar imaging (EPI) are originated from phase mismatch between the even and odd echoes. However, conventional correction methods using reference scans often produce erroneous results especially in high-field MRI due to the nonlinear and time-varying local magnetic field changes. Recently, it was shown that the problem of ghost correction can be reformulated as k-space interpolation problem that can be solved using structured low-rank Hankel matrix approaches. Another recent work showed that data driven Hankel matrix decomposition can be reformulated to exhibit similar structures as deep convolutional neural network. By synergistically combining these findings, we propose a k-space deep learning approach that immediately corrects the phase mismatch without a reference scan in both accelerated and non-accelerated EPI acquisitions. THEORY AND METHODS: To take advantage of the even and odd-phase directional redundancy, the k-space data are divided into 2 channels configured with even and odd phase encodings. The redundancies between coils are also exploited by stacking the multi-coil k-space data into additional input channels. Then, our k-space ghost correction network is trained to learn the interpolation kernel to estimate the missing virtual k-space data. For the accelerated EPI data, the same neural network is trained to directly estimate the interpolation kernels for missing k-space data from both ghost and subsampling. RESULTS: Reconstruction results using 3T and 7T in vivo data showed that the proposed method outperformed the image quality compared to the existing methods, and the computing time is much faster. CONCLUSIONS: The proposed k-space deep learning for EPI ghost correction is highly robust and fast, and can be combined with acceleration, so that it can be used as a promising correction tool for high-field MRI without changing the current acquisition protocol.

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT.

X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, the main goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance.

Delta (13)C-urea breath test value is a useful indicator for Helicobacter pylori eradication in patients with functional dyspepsia.

BACKGROUND: Eradication of Helicobacter pylori is not routinely recommended for the symptomatic relief and the prevention of gastric cancer in patients with functional dyspepsia. The present study investigated a useful indicator of H. pylori eradication in such patients by determining the optimal cutoff value of a 13C-urea breath test (UBT). METHODS: One hundred dyspeptic patients participated in the study. Dyspepsia was scored, and a 13C-UBT administered. A level of delta 13C-UBT of>4 per thousand was diagnosed as H. pylori-positive. After the stomach was endoscopically sprayed with phenol red, biopsy specimens were taken from the antrum, body and cardia of the stomach for the assessment of H. pylori density, and activity (neutrophil infiltration) and degree (lymphocyte infiltration) of gastritis. RESULTS: Correlation between delta 13C-UBT and dyspepsia score was not found. Delta 13C-UBT significantly correlated with H. pylori density score in the total stomach (r = 0.53, P < 0.0001), neutrophil (r = 0.34, P = 0.0005) and lymphocyte score (r = 0.69, P < 0.0001). Twenty-six of the 100 subjects had a neutrophil score of >or=4, lymphocyte score of >or=4, and H. pylori score of >or=4. Their 95% confidence interval of mean was 58.2 per thousand, which reflects moderate to marked acute and chronic gastritis, and dense H. pylori colonization. CONCLUSIONS: The 13C-UBT is a reliable semiquantitative test to assess H. pylori density and the activity and degree of gastritis. It is proposed that H. pylori eradication therapy might be beneficial for patients with functional dyspepsia with a delta 13C-UBT of >58.2 per thousand.

Role of Helicobacter pylori infection among offspring or siblings of gastric cancer patients.

A positive family history is an increased risk factor for gastric cancer within family members, and one of the possible causes of this is the intrafamilial clustering of Helicobacter pylori infection. Our study examined the prevalence of H. pylori infection, serum antibodies to CagA and VacA and atrophic gastritis and/or intestinal metaplasia in the offspring or siblings of gastric cancer patients. A total of 726 subjects included 300 relatives of 300 separate gastric cancer patients and 426 controls. All subjects underwent upper gastrointestinal endoscopic examination with a rapid urease test. Blood samples were obtained to test for the presence of serum antibodies to the CagA and VacA proteins of H. pylori. The prevalence of H. pylori infection was higher in relatives of cancer patients (75.3%) than in controls (60.1%), and the adjusted odds ratio was 2.1 (95% CI 1.5-2.9). When either siblings or 2 or more family members were gastric cancer patients, the prevalence of H. pylori infection was much higher compared to the prevalence in controls. There was no specific relationship between CagA and VacA, and H. pylori infection. Atrophic gastritis and/or intestinal metaplasia were more frequently found in H. pylori-infected relatives of cancer patients (26.1%) than in H. pylori-infected controls (12.9%). These results strongly support a role for H. pylori infection in familial aggregation of gastric cancer. The prophylactic eradication of H. pylori infection in the offspring or siblings of gastric cancer patients may be clinically beneficial.