Background: Osteoporosis is the most common metabolic bone disease and can cause fragility fractures. Despite this, screening utilization rates for osteoporosis remain low among populations at risk. Automated bone mineral density (BMD) estimation using computed tomography (CT) can help bridge this gap and serve as an alternative screening method to dual-energy X-ray absorptiometry (DXA). Methods: The feasibility of an opportunistic and population agnostic screening method for osteoporosis using abdominal CT scans without bone densitometry phantom-based calibration was investigated in this retrospective study. A total of 268 abdominal CT-DXA pairs and 99 abdominal CT studies without DXA scores were obtained from an oncology specialty clinic in the Republic of Korea. The center axial CT slices from the L1, L2, L3, and L4 lumbar vertebrae were annotated with the CT slice level and spine segmentation labels for each subject. Deep learning models were trained to localize the center axial slice from the CT scan of the torso, segment the vertebral bone, and estimate BMD for the top four lumbar vertebrae. Results: Automated vertebra-level DXA measurements showed a mean absolute error (MAE) of 0.079, Pearson’s r of 0.852 (P<0.001), and R2 of 0.714. Subject-level predictions on the held-out test set had a MAE of 0.066, Pearson’s r of 0.907 (P<0.001), and R2 of 0.781. Conclusion CT scans collected during routine examinations without bone densitometry calibration can be used to generate DXA BMD predictions.

Purpose: We present a dehazing algorithm using dark channel prior (DCP) and bright channel prior (BCP) to enhance the quality of retinal images obtained through conventional fundus photography. Methods: A retrospective analysis was conducted on retinal images from patients who visited Gangnam Sacred Heart Hospital between January 2000 and September 2022. These images were captured using a digital fundus camera (KOWA Nonmyd 8S Fundus Camera, KOWA Company, Nagoya, Japan) without pupil dilation. We used two mathematical algorithms: DCP only and DCP and BCP combined. The original, DCP-processed, and DCP & BCP-processed images were compared. Fisher's exact test was used to identify significant quality improvements. Results: The DCP and the newly proposed DCP plus BCP algorithm effectively eliminated haze and enhanced the contrast of cataract images. Notably, DCP demonstrated limited improvements in fundus photographs from patients with small pupils, whereas the proposed DCP plus BCP method effectively revealed previously obscured retinal details and vessels. However, these methods exhibited limited performance in severe cataracts compared to the clear images obtained after surgery. The quality enhancement with the proposed method was significant in photographs of patients with cataracts (p = 0.032) and small pupils (p < 0.01). Conclusions Our algorithm produced clearer images of blood vessels and optic disc structures, while significantly reducing artifacts in fundus images from patients with small pupils or cataracts. The proposed algorithm can provide visually enhanced images, potentially aiding physicians in the diagnosis of retinal diseases in patients with cataracts.

Objective: To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. Materials and Methods: This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1–7 according to acquisition conditions. CT images in groups 2–7 were converted into the target CT sty le (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. Results: Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2–7 improved after CT conversion (original vs. converted: 0.63vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists’ scores were significantly higher (P < 0.001) and less variable on converted CT. Conclusion CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD.

Purpose: To develop a denoising convolutional neural network-based image processing technique and investigate its efficacy in diagnosing breast cancer using low-dose mammography imaging. Materials and Methods: A total of 6 breast radiologists were included in this prospective study. All radiologists independently evaluated low-dose images for lesion detection and rated them for diagnostic quality using a qualitative scale. After application of the denoising network, the same radiologists evaluated lesion detectability and image quality. For clinical application, a consensus on lesion type and localization on preoperative mammographic examinations of breast cancer patients was reached after discussion. Thereafter, coded low-dose, reconstructed full-dose, and full-dose images were presented and assessed in a random order. Results: Lesions on 40% reconstructed full-dose images were better perceived when compared with low-dose images of mastectomy specimens as a reference. In clinical application, as compared to 40% reconstructed images, higher values were given on full-dose images for resolution (p < 0.001); diagnostic quality for calcifications (p < 0.001); and for masses, asymmetry, or architectural distortion (p = 0.037). The 40% reconstructed images showed comparable values to 100% full-dose images for overall quality (p = 0.547), lesion visibility (p = 0.120), and contrast (p = 0.083), without significant differences. Conclusion Effective denoising and image reconstruction processing techniques can enable breast cancer diagnosis with substantial radiation dose reduction.

Background/Aims: The prospective Crohn’s Disease Clinical Network and Cohort Study is a nationwide multicenter cohort study of patients with Crohn’s disease (CD) in Korea, aiming to prospectively investigate the clinical features and long-term prognosis associated with CD. Methods: Patients diagnosed with CD between January 2009 and September 2019 were prospectively enrolled. They were divided into two cohorts according to the year of diagnosis: cohort 1 (diagnosed between 2009 and 2011) versus cohort 2 (between 2012 and 2019). Results: A total of 1,175 patients were included, and the median follow-up duration was 68 months (interquartile range, 39.0 to 91.0 months). The treatment-free durations for thiopurines (p<0.001) and anti-tumor necrosis factor agents (p=0.018) of cohort 2 were shorter than those of cohort 1. Among 887 patients with B1 behavior at diagnosis, 149 patients (16.8%) progressed to either B2 or B3 behavior during follow-up. Early use of thiopurine was associated with a reduced risk of behavioral progression (adjusted hazard ratio [aHR], 0.69; 95% confidence interval [CI], 0.50 to 0.90), and family history of inflammatory bowel disease was associated with an increased risk of behavioral progression (aHR, 2.29; 95% CI, 1.16 to 4.50). One hundred forty-one patients (12.0%) underwent intestinal resection, and the intestinal resection-free survival time was significantly longer in cohort 2 than in cohort 1 (p=0.003). The early use of thiopurines (aHR, 0.35;95% CI, 0.23 to 0.51) was independently associated with a reduced risk of intestinal resection. Conclusions The prognosis of CD in Korea appears to have improved over time, as evidenced by the decreasing intestinal resection rate. Early use of thiopurines was associated with an improved prognosis represented by a reduced risk of intestinal resection.

Background: and Purpose Previous studies have assessed the relationship between cerebral vessel tortuosity and intracranial aneurysm (IA) based on two-dimensional brain image analysis. We evaluated the relationship between cerebral vessel tortuosity and IA according to the hemodynamic location using three-dimensional (3D) analysis and studied the effect of tortuosity on the recurrence of treated IA. Methods: We collected clinical and imaging data from patients with IA and disease-free controls. IAs were categorized into outer curvature and bifurcation types. Computerized analysis of the images provided information on the length of the arterial segment and tortuosity of the cerebral arteries in 3D space. Results: Data from 95 patients with IA and 95 controls were analyzed. Regarding parent vessel tortuosity index (TI; P<0.01), average TI (P<0.01), basilar artery (BA; P=0.02), left posterior cerebral artery (P=0.03), both vertebral arteries (VAs; P<0.01), and right internal carotid artery (P<0.01), there was a significant difference only in the outer curvature type compared with the control group. The outer curvature type was analyzed, and the occurrence of an IA was associated with increased TI of the parent vessel, average, BA, right middle cerebral artery, and both VAs in the logistic regression analysis. However, in all aneurysm cases, recanalization of the treated aneurysm was inversely associated with increased TI of the parent vessels. Conclusions TIs of intracranial arteries are associated with the occurrence of IA, especially in the outer curvature type. IAs with a high TI in the parent vessel showed good outcomes with endovascular treatment.

Background: and Purpose Previous studies have assessed the relationship between cerebral vessel tortuosity and intracranial aneurysm (IA) based on two-dimensional brain image analysis. We evaluated the relationship between cerebral vessel tortuosity and IA according to the hemodynamic location using three-dimensional (3D) analysis and studied the effect of tortuosity on the recurrence of treated IA. Methods: We collected clinical and imaging data from patients with IA and disease-free controls. IAs were categorized into outer curvature and bifurcation types. Computerized analysis of the images provided information on the length of the arterial segment and tortuosity of the cerebral arteries in 3D space. Results: Data from 95 patients with IA and 95 controls were analyzed. Regarding parent vessel tortuosity index (TI; P<0.01), average TI (P<0.01), basilar artery (BA; P=0.02), left posterior cerebral artery (P=0.03), both vertebral arteries (VAs; P<0.01), and right internal carotid artery (P<0.01), there was a significant difference only in the outer curvature type compared with the control group. The outer curvature type was analyzed, and the occurrence of an IA was associated with increased TI of the parent vessel, average, BA, right middle cerebral artery, and both VAs in the logistic regression analysis. However, in all aneurysm cases, recanalization of the treated aneurysm was inversely associated with increased TI of the parent vessels. Conclusions TIs of intracranial arteries are associated with the occurrence of IA, especially in the outer curvature type. IAs with a high TI in the parent vessel showed good outcomes with endovascular treatment.

OBJECTIVE: To compare the image quality of low-dose (LD) computed tomography (CT) obtained using a deep learning-based denoising algorithm (DLA) with LD CT images reconstructed with a filtered back projection (FBP) and advanced modeled iterative reconstruction (ADMIRE).MATERIALS AND METHODS: One hundred routine-dose (RD) abdominal CT studies reconstructed using FBP were used to train the DLA. Simulated CT images were made at dose levels of 13%, 25%, and 50% of the RD (DLA-1, -2, and -3) and reconstructed using FBP. We trained DLAs using the simulated CT images as input data and the RD CT images as ground truth. To test the DLA, the American College of Radiology CT phantom was used together with 18 patients who underwent abdominal LD CT. LD CT images of the phantom and patients were processed using FBP, ADMIRE, and DLAs (LD-FBP, LD-ADMIRE, and LD-DLA images, respectively). To compare the image quality, we measured the noise power spectrum and modulation transfer function (MTF) of phantom images. For patient data, we measured the mean image noise and performed qualitative image analysis. We evaluated the presence of additional artifacts in the LD-DLA images.RESULTS: LD-DLAs achieved lower noise levels than LD-FBP and LD-ADMIRE for both phantom and patient data (all p < 0.001). LD-DLAs trained with a lower radiation dose showed less image noise. However, the MTFs of the LD-DLAs were lower than those of LD-ADMIRE and LD-FBP (all p < 0.001) and decreased with decreasing training image dose. In the qualitative image analysis, the overall image quality of LD-DLAs was best for DLA-3 (50% simulated radiation dose) and not significantly different from LD-ADMIRE. There were no additional artifacts in LD-DLA images.CONCLUSION: DLAs achieved less noise than FBP and ADMIRE in LD CT images, but did not maintain spatial resolution. The DLA trained with 50% simulated radiation dose showed the best overall image quality.
Artifacts ; Humans ; Noise ; Tomography, X-Ray Computed

Purpose: Image registration is a fundamental task in various medical imaging studies and clinical image analyses, such as comparison of patient data with anatomical structures. In order to solve the problems of conventional image registration approaches, such as long computational time, recent deep-learning supervised and unsupervised methods have been extensively studied because of their excellent performance and fast computational time. In this study, we propose a deep-learningbased network for deformable medical image registration using unsupervised learning. Materials and Methods: In this paper, we solve the image-registration optimization problem by modelling a function using a convolutional neural network with polyphase decomposition to learn the spatial transformable parameters based on the input images and to generate the registration field. A spatial transformer is used to reconstruct the output warped image while imposing smoothness constraints on the registration field. With polyphase decomposition, our proposed method learns more features based on the input image pairs without the need for any ground-truth registration field. Results: Experimental results using 3D T1 brain MRI volume scans and compared with state-of-the-art image-registration methods demonstrated that our method provides better 3D-image registration. Conclusion Our proposed method uses less computational time in registering unseen pairs of input images during inference and can be applied for other unimodal image registration tasks, and the hyper-parameters can be adjusted for the specific task.