Performance changes due to differences among annotating radiologists for training data in computerized lesion detection.

PURPOSE: The quality and bias of annotations by annotators (e.g., radiologists) affect the performance changes in computer-aided detection (CAD) software using machine learning. We hypothesized that the difference in the years of experience in image interpretation among radiologists contributes to annotation variability. In this study, we focused on how the performance of CAD software changes with retraining by incorporating cases annotated by radiologists with varying experience. METHODS: We used two types of CAD software for lung nodule detection in chest computed tomography images and cerebral aneurysm detection in magnetic resonance angiography images. Twelve radiologists with different years of experience independently annotated the lesions, and the performance changes were investigated by repeating the retraining of the CAD software twice, with the addition of cases annotated by each radiologist. Additionally, we investigated the effects of retraining using integrated annotations from multiple radiologists. RESULTS: The performance of the CAD software after retraining differed among annotating radiologists. In some cases, the performance was degraded compared to that of the initial software. Retraining using integrated annotations showed different performance trends depending on the target CAD software, notably in cerebral aneurysm detection, where the performance decreased compared to using annotations from a single radiologist. CONCLUSIONS: Although the performance of the CAD software after retraining varied among the annotating radiologists, no direct correlation with their experience was found. The performance trends differed according to the type of CAD software used when integrated annotations from multiple radiologists were used.

Voxel-based Morphometry of Alzheimer's Disease Using a Localizer Image: A Comparative Study with Magnetization Prepared Rapid Acquisition with Gradient Echo.

PURPOSE: Magnetization prepared rapid acquisition with gradient echo (MPRAGE) sequence is a gold-standard technique for voxel-based morphometry (VBM) because of high spatial resolution and excellent tissue contrast, especially between gray matter (GM) and white matter (WM). Despite its benefits, MPRAGE exhibits distinct challenge for VBM in some patients with neurological disease because of long scan time and motion artifacts. Speedily acquired localizer images may alleviate this problem. This study aimed to evaluate the feasibility of VBM using 3D Fast Low Angle Shot image captured for localizer (L3DFLASH). METHODS: Consecutive 13 patients with pathologically confirmed Alzheimer's disease (AD) (82 ± 9 years) and 21 healthy controls (HC) (79 ± 4 years) were included in this study. Whole-brain L3DFLASH and MPRAGE were captured and preprocessed using the Computational Anatomy Toolbox 12 (CAT12). Agreement with MPRAGE was evaluated for L3DFLASH using regional normalized volume for segmented brain areas. In addition to brain volume difference on VBM and Bland-Altman analysis, atrophic pattern of AD on VBM was evaluated using L3DFLASH and MPRAGE. RESULTS: Acquisition time was 18 s for L3DFLASH and 288 s for MPRAGE. There was a slight systematic difference in all regional normalized volumes from L3DFLASH and MPRAGE. For the whole cohort, GM volume measured from MPRAGE was greater than that from L3DFLASH in most of the region on VBM. When AD and HC were compared, AD-related atrophic pattern was demonstrated in both L3DFLASH and MPRAGE on VBM, although the difference was noted in significant clusters between them. CONCLUSION: Although systematic difference was noted in regional brain volume measured from L3DFLASH and MPRAGE, AD-related atrophic pattern was preserved in L3DFLASH on VBM. VBM, using speedily acquired localizer image, may provide limited but useful information for evaluating brain atrophy.

The influence of limbic-predominant age-related TDP-43 encephalopathy on argyrophilic grain disease: A voxel-based morphometry analysis of pathologically confirmed cases.

BACKGROUND: The influence of limbic-predominant age-related TAR DNA-binding protein of 43 kDa encephalopathy neuropathological change (LATE-NC) on structural alterations in argyrophilic grain disease (AGD) have not been documented. This study aimed to investigate the morphological impact of LATE-NC on AGD through voxel-based morphometry (VBM) technique. MATERIALS AND METHODS: Fifteen individuals with pathologically verified AGD, comprising 6 with LATE-NC (comorbid AGD [cAGD]) and 9 without LATE-NC (pure AGD [pAGD]), along with 10 healthy controls (HC) were enrolled. Whole-brain 3D-T1-weighted images were captured and preprocessed utilizing the Computational Anatomy Toolbox 12. VBM was employed to compare gray matter volume among (i) pAGD and HC, (ii) cAGD and HC, and (iii) pAGD and cAGD. RESULTS: In comparison to HC, the pAGD group exhibited slightly asymmetric gray matter volume loss, particularly in the ambient gyrus, amygdala, hippocampus, anterior cingulate gyrus, and insula. Alternatively, the cAGD group exhibited greater gray matter volume loss, with a predominant focus on the inferolateral regions encompassing the ambient gyrus, amygdala, hippocampus, and the inferior temporal area, including the anterior temporal pole. The atrophy of the bilateral anterior temporal pole and right inferior temporal gyrus persisted when contrasting the pAGD and cAGD groups. CONCLUSION: Comorbidity with LATE-NC is linked to different atrophic distribution, particularly affecting the inferolateral regions in AGD. Consequently, the consideration of comorbid LATE-NC is crucial in individuals with AGD exhibiting more widespread temporal atrophy.

Deep-Learning Reconstruction of High-Resolution CT Improves Interobserver Agreement for the Evaluation of Pulmonary Fibrosis.

Objective: This study aimed to investigate whether deep-learning reconstruction (DLR) improves interobserver agreement in the evaluation of honeycombing for patients with interstitial lung disease (ILD) who underwent high-resolution computed tomography (CT) compared with hybrid iterative reconstruction (HIR). Methods: In this retrospective study, 35 consecutive patients suspected of ILD who underwent CT including the chest region were included. High-resolution CT images of the unilateral lung with DLR and HIR were reconstructed for the right and left lungs. A radiologist placed regions of interest on the lung and measured standard deviation of CT attenuation (i.e., quantitative image noise). In the qualitative image analyses, 5 blinded readers assessed the presence of honeycombing and reticulation, qualitative image noise, artifacts, and overall image quality using a 5-point scale (except for artifacts which was evaluated using a 3-point scale). Results: The quantitative and qualitative image noise in DLR was remarkably reduced compared to that in HIR (P < .001). Artifacts and overall DLR quality were significantly improved compared to those of HIR (P < .001 for 4 out of 5 readers). Interobserver agreement in the evaluations of honeycombing and reticulation for DLR (0.557 [0.450-0.693] and 0.525 [0.470-0.541], respectively) were higher than those for HIR (0.321 [0.211-0.520] and 0.470 [0.354-0.533], respectively). A statistically significant difference was found for honeycombing (P = .014). Conclusions: DLR improved interobserver agreement in the evaluation of honeycombing in patients with ILD on CT compared to HIR.

The importance of ethnic-specific cut-offs of low muscle mass for survival prediction in oncology.

BACKGROUND & AIMS: While skeletal muscle index (SMI) is the most widely used indicator of low muscle mass (or sarcopenia) in oncology, optimal cut-offs (or definitions) to better predict survival are not standardized. METHODS: We compared five major definitions of SMI-based low muscle mass using an Asian patient cohort with gastrointestinal or genitourinary cancers. We analyzed 2015 patients with surgically-treated gastrointestinal (n = 1382) or genitourinary (n = 633) cancer with pre-surgical computed tomography images. We assessed the associations of clinical parameters, including low muscle mass by each definition, with cancer-specific survival (CSS) and overall survival (OS). RESULTS: During a median follow-up period of 61 months, 303 (15%) died of cancer, and 147 died of other causes. An Asian-based definition diagnosed 17.8% of patients as having low muscle mass, while the other Caucasian-based ones classified most (>70%) patients as such. All definitions significantly discriminated both CSS and OS between patients with low or normal muscle mass. Low muscle mass using any definition but one predicted a lower CSS on multivariate Cox regression analyses. All definitions were independent predictors of lower OS. The original multivariate model without incorporating low muscle mass had c-indices of 0.63 for CSS and 0.66 for OS, which increased to 0.64-0.67 for CSS and 0.67-0.70 for OS when low muscle mass was considered. The model with an Asian-based definition had the highest c-indices (0.67 for CSS and 0.70 for OS). CONCLUSIONS: The Asian-specific definition had the best predictive ability for mortality in this Asian patient cohort.

Asymmetric Cerebral Peduncle Atrophy: A Simple Diagnostic Clue for Distinguishing Frontotemporal Lobar Degeneration from Alzheimer's Disease.

BACKGROUND: Due to confusing clinicoradiological features such as amnestic symptoms and hippocampal atrophy in frontotemporal lobar degeneration (FTLD), antemortem differentiation between FTLD and Alzheimer's disease (AD) can be challenging. Although asymmetric atrophy of the cerebral peduncle is regarded as a representative imaging finding in some disorders of the FTLD spectrum, the utility of this finding has not been sufficiently evaluated for differentiating between FTLD and AD. OBJECTIVE: This study aimed to explore the diagnostic performance of asymmetric cerebral peduncle atrophy on axial magnetic resonance imaging as a simple radiological discriminator between FTLD and AD. METHODS: Seventeen patients with pathologically confirmed FTLD, including six with progressive supranuclear palsy, three with corticobasal degeneration, eight with TAR DNA-binding protein 43 (FTLD-TDP), and 11 with pathologically confirmed AD, were investigated. Quantitative indices representing the difference between the volumes of the bilateral cerebral peduncles (i.e., cerebral peduncular asymmetry index [CPAI]), the voxel-based specific regional analysis system for Alzheimer's disease (VSRAD) Z-score representing the degree of hippocampal atrophy, and semiquantitative visual analysis to evaluate the asymmetry of the cerebral peduncle (visual assessment of cerebral peduncular asymmetry: VACPA) were compared between the two groups. RESULTS: Contrary to the VSRAD Z-score, the CPAI and VACPA scores demonstrated higher diagnostic performance in differentiating patients with FTLD from those with AD (areas under the receiver operating characteristic curve of 0.88, 082, and 0.60, respectively). CONCLUSIONS: Quantitative and visual analytical techniques can differentiate between FTLD and AD. These simple methods may be useful in daily clinical practice.

Generative adversarial network for automatic quantification of Coronavirus disease 2019 pneumonia on chest radiographs.

PURPOSE: To develop a generative adversarial network (GAN) to quantify COVID-19 pneumonia on chest radiographs automatically. MATERIALS AND METHODS: This retrospective study included 50,000 consecutive non-COVID-19 chest CT scans in 2015-2017 for training. Anteroposterior virtual chest, lung, and pneumonia radiographs were generated from whole, segmented lung, and pneumonia pixels from each CT scan. Two GANs were sequentially trained to generate lung images from radiographs and to generate pneumonia images from lung images. GAN-driven pneumonia extent (pneumonia area/lung area) was expressed from 0% to 100%. We examined the correlation of GAN-driven pneumonia extent with semi-quantitative Brixia X-ray severity score (one dataset, n = 4707) and quantitative CT-driven pneumonia extent (four datasets, n = 54-375), along with analyzing a measurement difference between the GAN and CT extents. Three datasets (n = 243-1481), where unfavorable outcomes (respiratory failure, intensive care unit admission, and death) occurred in 10%, 38%, and 78%, respectively, were used to examine the predictive power of GAN-driven pneumonia extent. RESULTS: GAN-driven radiographic pneumonia was correlated with the severity score (0.611) and CT-driven extent (0.640). 95% limits of agreements between GAN and CT-driven extents were -27.1% to 17.4%. GAN-driven pneumonia extent provided odds ratios of 1.05-1.18 per percent for unfavorable outcomes in the three datasets, with areas under the receiver operating characteristic curve (AUCs) of 0.614-0.842. When combined with demographic information only and with both demographic and laboratory information, the prediction models yielded AUCs of 0.643-0.841 and 0.688-0.877, respectively. CONCLUSION: The generative adversarial network automatically quantified COVID-19 pneumonia on chest radiographs and identified patients with unfavorable outcomes.

Voxel-Based and Surface-Based Morphometry Analysis in Patients with Pathologically Confirmed Argyrophilic Grain Disease and Alzheimer's Disease.

BACKGROUND: Due to clinicoradiological similarities, including amnestic cognitive impairment and limbic atrophy, differentiation of argyrophilic grain disease (AGD) from Alzheimer's disease (AD) is often challenging. Minimally invasive biomarkers, especially magnetic resonance imaging (MRI), are valuable in routine clinical practice. Although it is necessary to explore radiological clues, morphometry analyses using new automated analytical methods, including whole-brain voxel-based morphometry (VBM) and surface-based morphometry (SBM), have not been sufficiently investigated in patients with pathologically confirmed AGD and AD. OBJECTIVE: This study aimed to determine the volumetric differences in VBM and SBM analyses between patients with pathologically confirmed AGD and AD. METHODS: Eight patients with pathologically confirmed AGD with a lower Braak neurofibrillary tangle stage (

Comparison of Deep-Learning Image Reconstruction With Hybrid Iterative Reconstruction for Evaluating Lung Nodules With High-Resolution Computed Tomography.

OBJECTIVE: This study aimed to investigate the impact of deep-learning reconstruction (DLR) on the detailed evaluation of solitary lung nodule using high-resolution computed tomography (HRCT) compared with hybrid iterative reconstruction (hybrid IR). METHODS: This retrospective study was approved by our institutional review board and included 68 consecutive patients (mean ± SD age, 70.1 ± 12.0 years; 37 men and 31 women) who underwent computed tomography between November 2021 and February 2022. High-resolution computed tomography images with a targeted field of view of the unilateral lung were reconstructed using filtered back projection, hybrid IR, and DLR, which is commercially available. Objective image noise was measured by placing the regions of interest on the skeletal muscle and recording the SD of the computed tomography attenuation. Subjective image analyses were performed by 2 blinded radiologists taking into consideration the subjective noise, artifacts, depictions of small structures and nodule rims, and the overall image quality. In subjective analyses, filtered back projection images were used as controls. Data were compared between DLR and hybrid IR using the paired t test and Wilcoxon signed-rank sum test. RESULTS: Objective image noise in DLR (32.7 ± 4.2) was significantly reduced compared with hybrid IR (35.3 ± 4.4) ( P < 0.0001). According to both readers, significant improvements in subjective image noise, artifacts, depictions of small structures and nodule rims, and overall image quality were observed in images derived from DLR compared with those from hybrid IR ( P < 0.0001 for all). CONCLUSIONS: Deep-learning reconstruction provides a better high-resolution computed tomography image with improved quality compared with hybrid IR.

Brain structural changes in patients with chronic methylmercury poisoning in Minamata.

Exploratory whole-brain studies in patients suffering from methylmercury (MeHg) poisoning have not been conducted. We aimed to evaluate the neuroanatomical differences between patients with chronic MeHg poisoning and healthy volunteers via magnetic resonance (MR) imaging. Patients included in this case-control study were divided into three categories based on whether MeHg exposure occurred in utero, under 15 years of age, or over 15 years of age, as fetal-, pediatric-, and adult-type patients, respectively. This study analyzed MR imaging data from 10 patients each of fetal, pediatric, and adult types of chronic MeHg poisoning in Minamata and corresponding 53, 37, and 15 age- and sex-matched healthy volunteers. Whole-brain voxel-based morphometry (VBM) analysis was used to determine the volumetric gray and white matter (GM and WM) differences in patients with chronic MeHg poisoning. Compared to healthy individuals, VBM revealed a significant reduction in GM in the cerebellar and calcarine areas in pediatric- and adult-type cases and in the thalamus of fetal-type cases. A significant reduction in WM volume was also noted in the cerebral and the cerebellar regions, especially in pediatric-type cases. Patients with chronic MeHg poisoning develop structural differences in the GM of the calcarine, the cerebellum, and the thalamus and in the WM of the cerebrum and cerebellum. These changes can appear, depending on the timing of MeHg exposure.

Alteration of chronic inflammatory status by transarterial embolization in frozen shoulder evaluated by fluorine-18 fluorodeoxyglucose positron-emission tomography/computed tomography.

BACKGROUND: Frozen shoulder (FS) is speculated to have an inflammatory etiology. On angiography, abnormal angiogenesis is observed around the affected shoulder, suggesting a possible source of inflammation and pain. The effectiveness and safety of transarterial embolization (TAE) targeting abnormally proliferating blood vessels have been reported. This study investigated changes in chronic inflammatory and hypoxic status before and after TAE in FS by [18F]-fluoro-2-deoxyglucose (FDG) positron-emission tomography/computed tomography as a possible mechanism of the therapeutic response to TAE. METHODS: Fifteen patients with unilateral FS, persistent for more than 6 months, who were refractory to conservative treatments, underwent TAE using the temporary embolic agent imipenem/cilastatin. Patients underwent positron-emission tomography/computed tomography with FDG (as a biomarker of inflammation) before and 8 weeks after TAE. Regional uptake was evaluated by the maximum standardized uptake value. The lesion-side-to-(contralateral-) normal-side uptake ratio was also calculated. Pain and functional scales, range-of-motion, and laboratory tests, including white blood cell, C-reactive protein, interleukin 6, vascular endothelial growth factor, and tumor necrosis factor α were evaluated. RESULTS: On FDG-PET, the average maximum standardized uptake value of the lesion-side was significantly greater than that of the normal-side (maximum standardized uptake value before TAE: 3.11 ± 1.25 vs 1.95 ± 1.15, P = .0001; 8-weeks post-TAE: 2.36 ± 0.74 vs 1.78 ± 0.69, P = .0002). The mean lesion-side-to-(contralateral-) normal-side uptake ratios before TAE (1.71 ± 0.60) decreased after TAE (1.37 ± 0.29, P = .011). The decrease of FDG uptake (-21.1 ± 12.2%) showed a significant correlation with the change in the pain scale score (r = -0.56, P = .039) and extension score (r = -0.59, P = .026). CONCLUSION: Chronic inflammation in FS, as demonstrated by FDG uptake, was decreased after TAE. Thus, chronic inflammation is likely to be an underlying mechanism that should be targeted for symptomatic improvement of frozen shoulder.

Development of a deep learning method for improving diagnostic accuracy for uterine sarcoma cases.

Uterine sarcomas have very poor prognoses and are sometimes difficult to distinguish from uterine leiomyomas on preoperative examinations. Herein, we investigated whether deep neural network (DNN) models can improve the accuracy of preoperative MRI-based diagnosis in patients with uterine sarcomas. Fifteen sequences of MRI for patients (uterine sarcoma group: n = 63; uterine leiomyoma: n = 200) were used to train the models. Six radiologists (three specialists, three practitioners) interpreted the same images for validation. The most important individual sequences for diagnosis were axial T2-weighted imaging (T2WI), sagittal T2WI, and diffusion-weighted imaging. These sequences also represented the most accurate combination (accuracy: 91.3%), achieving diagnostic ability comparable to that of specialists (accuracy: 88.3%) and superior to that of practitioners (accuracy: 80.1%). Moreover, radiologists' diagnostic accuracy improved when provided with DNN results (specialists: 89.6%; practitioners: 92.3%). Our DNN models are valuable to improve diagnostic accuracy, especially in filling the gap of clinical skills between interpreters. This method can be a universal model for the use of deep learning in the diagnostic imaging of rare tumors.

Diverse limbic comorbidities cause limbic and temporal atrophy in lewy body disease.

BACKGROUND: In contrast to Alzheimer's disease (AD)-related pathology, the influence of comorbid limbic-predominant age-related TDP-43 encephalopathy neuropathological change (LATE-NC) or argyrophilic grains (AG) on structural imaging in Lewy body disease (LBD) has seldom been evaluated. OBJECTIVE: This study aimed to investigate whether non-AD limbic comorbidities, including LATE-NC and AG, cause cortical atrophy in LBD. METHODS: Seventeen patients with pathologically confirmed LBD with lower Braak neurofibrillary tangle stage (

Comparison of CT findings of coronavirus disease 2019 (COVID-19) pneumonia caused by different major variants.

PURPOSE: To explore the CT findings and pneumonnia progression pattern of the Alpha and Delta variants of SARS-CoV-2 by comparing them with the pre-existing wild type. METHOD: In this retrospective comparative study, a total of 392 patients with COVID-19 were included: 118 patients with wild type (70 men, 56.8 ± 20.7 years), 137 with Alpha variant (93 men, 49.4 ± 17.0 years), and 137 with Delta variant (94 men, 45.4 ± 12.4). Chest CT evaluation included opacities and repairing changes as well as lesion distribution and laterality. Chest CT severity score was also calculated. These parameters were statistically compared across the variants. RESULTS: Ground glass opacity (GGO) with consolidation and repairing changes were more frequent in the order of Delta variant, Alpha variant, and wild type throughout the disease course. Delta variant showed GGO with consolidation more conspicuously than did the other two on days 1-4 (vs. wild type, Bonferroni corrected p = 0.01; vs. Alpha variant, Bonferroni corrected p = 0.003) and days 5-8 (vs. wild type, Bonferroni corrected p < 0.001; vs. Alpha variant, Bonferroni corrected-p = 0.003). Total lung CT severity scores of Delta variant were higher than those of wild type on days 1-4 and 5-8 (Bonferroni corrected p = 0.01 and Bonferroni corrected p = 0.005, respectively) and that of Alpha variant on days 1-4 (Bonferroni corrected p = 0.002). There was no difference in the CT findings between wild type and Alpha variant. CONCLUSIONS: Pneumonia progression of Delta variant may be more rapid and severe in the early stage than in the other two.

Clinicoradiological Features in Progressive Supranuclear Palsy Comorbid with Argyrophilic Grains.

Background: Contrary to pure cases, the influence of comorbid argyrophilic grain disease (AGD) in progressive supranuclear palsy (PSP) has not been sufficiently evaluated. Objectives: We compared the clinicoradiological features of 12 patients with PSP with (PSPw/AG) and 8 patients without AGD (PSPw/oAG). Methods: Medical records and magnetic resonance imaging were checked retrospectively from a single brain bank database. Results: Other than AGD, no differences were observed in any other neurodegenerative pathologies between the 2 groups. Ages at onset and deaths of patients with PSPw/AG were higher than those of patients with PSPw/oAG (77.9 ± 4.9 vs. 68.9 ± 5.9, and 87.0 ± 5.7 vs. 78.1 ± 5.0; P = 0.003 and P = 0.002, respectively). In addition to the later onset of motor symptoms, initial amnestic presentations were limited to 5 patients with PSPw/AG. Both characteristic midbrain atrophy and severe ambient gyrus atrophy were detected exclusively in 8 patients with PSPw/AG. Conclusions: Initial amnestic presentations and ambient gyrus atrophy may be characteristic of PSPw/AG.

Deep Learning-Based Automatic CT Quantification of Coronavirus Disease 2019 Pneumonia: An International Collaborative Study.

OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.

Impaired pulmonary ventilation beyond pneumonia in COVID-19: A preliminary observation.

BACKGROUND: Coronavirus disease 2019 (COVID-19) may severely impair pulmonary function and cause hypoxia. However, the association of COVID-19 pneumonia on CT with impaired ventilation remains unexplained. This pilot study aims to demonstrate the relationship between the radiological findings on COVID-19 CT images and ventilation abnormalities simulated in a computational model linked to the patients' symptoms. METHODS: Twenty-five patients with COVID-19 and four test-negative healthy controls who underwent a baseline non-enhanced CT scan: 7 dyspneic patients, 9 symptomatic patients without dyspnea, and 9 asymptomatic patients were included. A 2D U-Net-based CT segmentation software was used to quantify radiological futures of COVID-19 pneumonia. The CT image-based full-scale airway network (FAN) flow model was employed to assess regional lung ventilation. Functional and radiological features were compared across groups and correlated with the clinical symptoms. Heterogeneity in ventilation distribution and ventilation defects associated with the pneumonia and the patients' symptoms were assessed. RESULTS: Median percentage ventilation defects were 0.2% for healthy controls, 0.7% for asymptomatic patients, 1.2% for symptomatic patients without dyspnea, and 11.3% for dyspneic patients. The median of percentage pneumonia was 13.2% for dyspneic patients and 0% for the other groups. Ventilation defects preferentially affected the posterior lung and worsened with increasing pneumonia linearly (y = 0.91x + 0.99, R2 = 0.73) except for one of the nine dyspneic patients who had disproportionally large ventilation defects (7.8% of the entire lung) despite mild pneumonia (1.2%). The symptomatic and dyspneic patients showed significantly right-skewed ventilation distributions (symptomatic without dyspnea: 0.86 ± 0.61, dyspnea 0.91 ± 0.79) compared to the patients without symptom (0.45 ± 0.35). The ventilation defect analysis with the FAN model provided a comparable diagnostic accuracy to the percentage pneumonia in identifying dyspneic patients (area under the receiver operating characteristic curve, 0.94 versus 0.96). CONCLUSIONS: COVID-19 pneumonia segmentations from CT scans are accompanied by impaired pulmonary ventilation preferentially in dyspneic patients. Ventilation analysis with CT image-based computational modelling shows it is able to assess functional impairment in COVID-19 and potentially identify one of the aetiologies of hypoxia in patients with COVID-19 pneumonia.

Machine learning trained with quantitative susceptibility mapping to detect mild cognitive impairment in Parkinson's disease.

BACKGROUND: Cognitive decline is commonly observed in Parkinson's disease (PD). Identifying PD with mild cognitive impairment (PD-MCI) is crucial for early initiation of therapeutic interventions and preventing cognitive decline. OBJECTIVE: We aimed to develop a machine learning model trained with magnetic susceptibility values based on the multi-atlas label-fusion method to classify PD without dementia into PD-MCI and normal cognition (PD-CN). METHODS: This multicenter observational cohort study retrospectively reviewed 61 PD-MCI and 59 PD-CN cases for the internal validation cohort and 22 PD-MCI and 21 PD-CN cases for the external validation cohort. The multi-atlas method parcellated the quantitative susceptibility mapping (QSM) images into 20 regions of interest and extracted QSM-based magnetic susceptibility values. Random forest, extreme gradient boosting, and light gradient boosting were selected as machine learning algorithms. RESULTS: All classifiers demonstrated substantial performances in the classification task, particularly the random forest model. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve for this model were 79.1%, 77.3%, 81.0%, and 0.78, respectively. The QSM values in the caudate nucleus, which were important features, were inversely correlated with the Montreal Cognitive Assessment scores (right caudate nucleus: r = -0.573, 95% CI: -0.801 to -0.298, p = 0.003; left caudate nucleus: r = -0.659, 95% CI: -0.894 to -0.392, p < 0.001). CONCLUSIONS: Machine learning models trained with QSM values successfully classified PD without dementia into PD-MCI and PD-CN groups, suggesting the potential of QSM values as an auxiliary biomarker for early evaluation of cognitive decline in patients with PD.

Sloping Shoulders Sign: A Practical Radiological Sign for the Differentiation of Alzheimer's Disease and Argyrophilic Grain Disease.

BACKGROUND: Although hippocampal atrophy is a well-known imaging biomarker of Alzheimer's disease (AD), this finding is not useful to differentiate AD from argyrophilic grain disease (AGD) which is a common AD mimicker presenting with similar amnestic symptoms and medial temporal atrophy. Instead, we propose use of the "sloping shoulders sign", defined as a distinct configuration of the bilateral hippocampal heads showing lateral and downward slopes on axial magnetic resonance imaging (MRI). OBJECTIVE: We investigated the diagnostic utility of the "sloping shoulders sign" as a simple radiological discriminator of AD from AGD. METHODS: Using axial and coronal three-dimensional MRI, our newly proposed "sloping shoulders sign", other quantitative indices including the axial hippocampal head angle (AHHA), and well-known medial temporal atrophy (MTA) score were evaluated in pathologically-proven 24 AD and 11 AGD patients. RESULTS: Detection rate of the "sloping shoulders sign" was significantly higher in all AD groups (83%; 20/24) and AD with Braak neurofibrillary tangle V/VI stage subgroup (88%; 15/17) than in AGD patients (18% - 2/11; p < 0.001 and p < 0.001, respectively). In contrast to the MTA score, this sign as well as AHHA demonstrated higher diagnostic performance and reproducibility, especially to differentiate all AD patients from AGD ones (accuracies of 71.4% , 82.9% and 82.9%; Cohen's kappa of 0.70 and 0.81, and intraclass correlation coefficient of 0.96, respectively). CONCLUSION: The "sloping shoulders sign" is useful to differentiate advanced-stage AD from AGD. Its simplicity and reproducibility based on visual inspection using axial MRI make it suitable for routine clinical practice.

The role of chest imaging in the diagnosis, management, and monitoring of coronavirus disease 2019 (COVID-19).

Coronavirus disease 2019 (COVID-19) pandemic has posed a major public health crisis all over the world. The role of chest imaging, especially computed tomography (CT), has evolved during the pandemic paralleling the accumulation of scientific evidence. In the early stage of the pandemic, the performance of chest imaging for COVID-19 has widely been debated especially in the context of comparison to real-time reverse transcription polymerase chain reaction. Current evidence is against the use of chest imaging for routine screening of COVID-19 contrary to the initial expectations. It still has an integral role to play, however, in its work up and staging, especially when assessing complications or disease progression. Chest CT is gold standard imaging modality for COVID-19 pneumonia; in some situations, chest X-ray or ultrasound may be an effective alternative. The most important role of radiologists in this context is to be able to identify those patients at greatest risk of imminent clinical decompensation by learning to stratify cases of COVID-19 on the basis of radiologic imaging in the most efficient and timely fashion possible. The present availability of multiple and more refined CT grading systems and classification is now making this task easier and thereby contributing to the recent improvements achieved in COVID-19 treatment and outcomes. In this article, evidence of chest imaging regarding diagnosis, management and monitoring of COVID-19 will be chronologically reviewed.