Diagnostic value of MR and CT enterography in post-operative recurrence of Crohn's disease: a systematic review and meta-analysis.

Post-operative recurrence is a critical issue in the surveillance of Crohn's disease after ileocecal resection. This meta-analysis aims to assess the diagnostic yield of enterography techniques in post-operative recurrence of Crohn's disease. A systematic electronic bibliographic databases search was conducted. The inclusion criteria of original articles were: Utilized MR enterography or CT enterography after ileocolonic resection; Documented recurrence by ileo-colonoscopy (Rutgeerts' score ≥ i2); Provided crude data of diagnostic performance. A random-effect method was used for analysis. Relative risk and diagnostic value of each imaging feature were calculated. Eleven studies (11 populations and 589 patients) were included (4 CTE and 7 MRE with 248 and 341 patients, respectively). The pooled sensitivity and specificity of the enterography were 91% (95% CI: 0.85-0.95) and 75% (95% CI: 0.56-0.87), respectively. The pooled sensitivity and specificity of CTE were 93% (95% CI: 0.87-0.96) and 67% (95% CI: 0.35-0.90), respectively. MRE revealed pooled sensitivity and specificity of 90% (95% CI: 0.78-0.96) and 78% (95% CI: 0.57-0.90), respectively. The inter-study heterogeneity was low for sensitivity (I2 = 29%, p-value = 0.17) and high for specificity (I2 = 85%, p-value < 0.01). Wall enhancement, anastomosis wall thickening, anastomosis stenosis, pre-anastomotic dilatation, penetrating lesion, comb sign, and perivisceral edema were significantly higher in POR patients. Wall thickening and penetrating lesion were the most sensitive (81%) and specific (97%) findings, respectively. MRE and CTE exhibit high sensitivity and acceptable specificity (especially MRE) for detection of recurrence in Crohn's disease which makes them an effective initial screening tool and reserves ileo-colonoscopy for those patients with inconclusive enterography results.

Clinical Phenotype and Disease Course of Inflammatory Bowel Disease in Iran: Results of the Iranian Registry of Crohn's and Colitis (IRCC).

BACKGROUND: Data on the epidemiology of inflammatory bowel disease (IBD) in the Middle East are scarce. We aimed to describe the clinical phenotype, disease course, and medication usage of IBD cases from Iran in the Middle East. METHODS: We conducted a cross-sectional study of registered IBD patients in the Iranian Registry of Crohn's and Colitis (IRCC) from 2017 until 2022. We collected information on demographic characteristics, past medical history, family history, disease extent and location, extra-intestinal manifestations, IBD medications, and activity using the IBD-control-8 questionnaire and the Manitoba IBD index, admissions history, history of colon cancer, and IBD-related surgeries. RESULTS: In total, 9746 patients with ulcerative colitis (UC) (n=7793), and Crohn's disease (CD) (n=1953) were reported. The UC to CD ratio was 3.99. The median age at diagnosis was 29.2 (IQR: 22.6,37.6) and 27.6 (IQR: 20.6,37.6) for patients with UC and CD, respectively. The male-to-female ratio was 1.28 in CD patients. A positive family history was observed in 17.9% of UC patients. The majority of UC patients had pancolitis (47%). Ileocolonic involvement was the most common type of involvement in CD patients (43.7%), and the prevalence of stricturing behavior was 4.6%. A prevalence of 0.3% was observed for colorectal cancer among patients with UC. Moreover,15.2% of UC patients and 38.4% of CD patients had been treated with anti-tumor necrosis factor (anti-TNF). CONCLUSION: In this national registry-based study, there are significant differences in some clinical phenotypes such as the prevalence of extra-intestinal manifestations and treatment strategies such as biological use in different geographical locations.

Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset.

BACKGROUND: Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model. PURPOSE: This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images. METHODS: After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences. RESULTS: The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501. CONCLUSION: The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

Posterior Reversible Encephalopathy Syndrome in Pediatric Hematopoietic Stem Cell Transplantation with Beta Major Thalassemia: The Association between the PRES Occurrence and Class of Beta Major Thalassemia.

INTRODUCTION: Allogeneic hematopoietic stem cell transplantation (HSCT) is the only definitive curative option for ß-major thalassemia patients (ß-MT). Posterior reversible encephalopathy syndrome (PRES) is a pervasive neurological complication which typically occurs following HSCT. ß-MT patients are prone to a higher PRES incidence due to long-term immunosuppression; thus, it is imperative that these patients are closely monitored for PRES after HSCT. PATIENTS AND METHODS: We included 148 pediatric patients with ß-MT who underwent HSCT between March 2015 and August 2022 in Children's Medical Center. Patients in this study were divided into two groups. The association between PRES and class of ß-MT and other risk factors were assessed and the overall survival rate was determined. RESULTS: Fourteen out of 112 patients (12%) with class I and II ß-MT developed PRES. However, PRES occurred in 11 out of 36 patients (30.5%) with ß-MT-III. Our results indicated that there was a significant association between class III ß-MT and the occurrence of (P = .004). Additionally, acute graft-versus-host disease (aGVHD) occurred in 80% and 44.7% of patients in the PRES and non-PRES groups, respectively (P = .001). The results of the Kaplan-Meier analysis revealed that the 5-year overall survival (OS) was 75.6% in the PRES group versus 95% in the non-PRES group, which was statistically significant (P = .001). CONCLUSION: Based on our results, pediatric ß-MT III patients are at a higher risk of developing PRES. Additionally, pediatric ß-MT patients with a history of aGVHD, regardless of disease class, are more likely to develop PRES. Considering these results, PRES has a higher chance of being the etiology of symptoms and should be considered more often in these patients.

MR Enterography in Ulcerative Colitis: Beyond Endoscopy.

Ulcerative colitis (UC) is a chronic idiopathic inflammatory bowel disease (IBD) that progressively affects mucosa and submuccosa of the colon and rectum in a continual pattern. In comparison, Crohn disease (CD), the other type of IBD, is a chronic transmural inflammatory disorder that can involve any part of the gastrointestinal tract. MR enterography (MRE) has emerged as an important imaging modality for the diagnosis and detection of disease activity and complications in CD, with comparable results to those of endoscopy. But MRE has been underused for assessment of UC in recent years, and clinicians heavily rely on endoscopic findings for management of UC. Despite UC being considered an endoscopically assessable disease, MRE can provide useful information beyond that obtained with endoscopy about mural or extramural abnormalities, inaccessible parts of the colonic lumen, associated extraintestinal diseases, and superimposed pathologic conditions. Moreover, endoscopy might be contraindicated in some clinical settings due to the risk of colonic perforation. In addition to depicting the features of UC activity in different phases, MRE demonstrates findings of disease chronicity that cannot be achieved with endoscopy, particularly in a patient with colitis of unknown cause. The valuable diagnostic role of MRE to exclude undiagnosed CD in patients with UC who have refractory disease or those with postproctocolectomy complications is also emphasized. Radiologists can play a crucial role in the management of UC with MRE by addressing what is beyond endoscopy. ©RSNA, 2023 Test Your Knowledge questions are available in the supplemental material.

Whole-body low-dose CT can be of value in prostate cancer decision-making: a retrospective study on 601 patients.

OBJECTIVES: To evaluate the diagnostic value of whole-body low-dose computed tomography (CT) to detect bone metastasis in prostate cancer (PCa) patients and its possible utility in therapeutic decision-making. Also, to determine the valuable CT features for lesion characterisation. METHODS: This IRB-approved retrospective study reviewed PCa patients who underwent 68Ga-PSMA PET/CT in our centre from March 2017 to August 2022. Two board-certified radiologists and one nuclear medicine specialist reported all whole-body low-dose CT scans separately, unaware of the 68Ga-PSMA-PET results. The per-lesion and per-patient diagnostic performances were calculated. Also, the significance of CT features was evaluated. Moreover, the inter-observer agreement was analysed. A two-tailed p value < 0.05 was considered significant. RESULTS: From 727 reviewed PCa patients, 601 (mean age = 68.7 ± 8.1) were found to be eligible, including 211 (35.1%) referrals for initial staging and 390 (64.9%) for evaluating the extent of the disease after biochemical recurrence. Per-patient diagnostic analysis for three reviewers showed 81.0-89.4% sensitivity and 96.6-98.5% specificity in detecting osteo-metastasis. It was able to correctly detect high-burden disease based on both CHAARTED and LATITUDE criteria. Regarding the value of underlying CT features, size > 1 cm, ill-defined borders, presence of soft-tissue component, and cortical destruction were statistically in favour of metastasis. Also, Hu > 900 was in favour of benign entities with 93% specificity. CONCLUSIONS: Although not as accurate as 68Ga-PSMA PET/CT, whole-body low-dose CT might precisely classify PCa patients considering therapeutic decision-making. Additionally, we proposed diagnostic CT features that could help radiologists with better characterisation of the detected lesions. CRITICAL RELEVANCE STATEMENT: The whole-body low-dose CT can be considered valuable in the clinical decision-making of prostate cancer patients. This modality may obviate performing multiple imaging sessions and high-cost scans in patients diagnosed with the high-burden disease.

Polypill protects MAFLD patients from cardiovascular events and mortality: a prospective trial.

BACKGROUND: Metabolic dysfunction-associated fatty liver disease (MAFLD) is a novel term that distinguishes patients at risk of adverse clinical outcomes with higher accuracy than those with non-alcoholic fatty liver disease (NAFLD). Cardiovascular mortality is the leading cause of death in MAFLD. The current literature lacks large-scale prospective studies that address preventive approaches for cardiovascular health in MAFLD. We investigated whether MAFLD patients benefit from a fixed-dose combination therapy (Aspirin, hydrochlorothiazide, atorvastatin, valsartan), known as a Polypill. METHODS: Analysis was performed (stratified based on MAFLD status) of a clinical trial that included 1596 individuals randomly allocated to an intervention (polypill) or a control (usual care) group. Patients were followed up for five years for any adverse drug reaction, major cardiovascular events, and mortality. Univariable and multivariable survival analyses were performed, and the interaction level was assessed by R programming. RESULTS: Patients who consumed the polypill had significantly lower hazard ratios of major cardiovascular events incidence (HR 0.56, 95% CI 0.41-0.78) and cardiovascular mortality (HR 0.41, 95% CI 0.2-0.86) compared to the control group. Polypill showed significantly better results in lowering cardiovascular events in MAFLD patients than in the general population. (p-value for interaction: 0.028). Moreover, comparing those patients who had high adherence to the Polypill, with the control group, further enhanced the results. CONCLUSIONS: Major cardiovascular events are prevented in MAFLD patients who consume the Polypill. MAFLD patients benefit from the Polypill more than the general population.

A Practical Index to Distinguish Backwash Ileitis From Crohn's Terminal Ileitis in MR Enterography.

BACKGROUND: Differentiating ulcerative colitis-associated "backwash" ileitis (BWI) from Crohn's terminal ileitis (CTI) is a diagnostic challenge and highly affects patient's management. This study aimed to investigate magnetic resonance enterography (MRE) features including ileocecal valve patency index (ICPI) in patients with BWI and CTI and distinguish these entities based on MRE findings. METHODS: After obtaining institutional review board approval, we reviewed 1654 MREs; 60 patients with pathologically proven BWI (n = 30) and CTI (n = 30) were enrolled. Two radiologists who were blinded to the clinical diagnosis analyzed MREs. We evaluated bowel wall thickness and enhancement pattern, ileocecal valve (ICV) diameter, and lip thickness. Ileocecal valve patency index-T and ICPI-C were calculated to normalize the ICV diameter with respect to terminal ileum (TI) and cecum, respectively. An additional group of non-BWI-UC patients (n = 30) was also included to validate indices. RESULTS: Circumferential mural thickening (90% vs 1%, P < .001) and inner-wall enhancement (P < .001) of TI were more frequent in BWI patients than CTI. Serosal irregularity (53% vs 13%, P = .002), higher mural thickness (5mm vs 3mm, P < .001), and asymmetric hyperenhancement (P < .001) of TI were more prevalent in CTI than BWI. Ileocecal valve patency and lip atrophy were significantly higher in BWI than CTI and non-BWI-UC groups (both P < .001). Ileocecal valve patency indices-C and ICPI-T indices were able to accurately distinguish BWI from CTI (area under the ROC curve [AUC], 0.864 and 0.847 for ICPI-T and ICPI-C, respectively) and non-BWI-UC (AUC, 0.777 and 0.791 for ICPI-T and ICPI-C, respectively). Ileocecal valve patency indices-T  ≥31.5% were 100% specific to distinguish BWI from CTI, but sensitivity was 63%. CONCLUSIONS: Magnetic resonance enterography features of ICV and TI can accurately differentiate BWI from CTI. Two practical indices introduced in this study showed high specificity to distinguish BWI from CTI.

The clinical significance of biliary findings in magnetic resonance enterography of patients with inflammatory bowel disease.

Purpose: Given the association of inflammatory bowel disease (IBD) and primary sclerosing cholangitis (PSC), we aimed to investigate the clinical relevance of abnormal hepatobiliary findings on magnetic resonance enterography (MRE) of IBD patients considering the risk of over- or underestimation of PSC at MRE. Material and methods: Using the MRE dataset of patients referring to a tertiary hospital and the National Registry of Crohn's and Colitis, 69 MREs, including 23 IBD-PSC, 23 IBD-without PSC, and 23 healthy controls (HC), were retrospectively reviewed by 2 experienced radiologists blinded to the clinical data, to evaluate hepatobiliary abnormalities. Sensitivity, specificity, and likelihood ratios were calculated. Results: Bile duct irregularities were the most common finding in the IBD-PSC group, with a frequency of 91%. Intra- and extrahepatic bile duct (IHBD and EHBD) irregularities were observed in 87% and 78% of PSC patients, respectively. Higher frequency of IHBD and EHBD wall thickening, bile duct dilation, EHBD stricture, and periportal oedema were observed in the IBD-PSC group. Peribiliary T2-weighted hyperintensities and contrast-enhancement were significantly more common in the IBD-PSC group than in the IBD and HC groups (48% and 35%, respectively) (p < 0.001). Detection of biliary irregularities on MRE had a specificity of 94% (95% CI: 82-99%), a sensitivity of 91% (95% CI: 72-99%), and a positive likelihood ratio of 14.0 (95% CI: 4.7-42.1) for the diagnosis of PSC. Conclusions: This study emphasizes the importance of assessing and reporting hepatobiliary abnormalities visible in the MRE of patients with IBD to avoid a delayed diagnosis of PSC.

Differentiation between Pancreatic Ductal Adenocarcinoma and Normal Pancreatic Tissue for Treatment Response Assessment using Multi-Scale Texture Analysis of CT Images.

Background: Pancreatic ductal adenocarcinoma (PDAC) is the most prevalent type of pancreas cancer with a high mortality rate and its staging is highly dependent on the extent of involvement between the tumor and surrounding vessels, facilitating treatment response assessment in PDAC. Objective: This study aims at detecting and visualizing the tumor region and the surrounding vessels in PDAC CT scan since, despite the tumors in other abdominal organs, clear detection of PDAC is highly difficult. Material and Methods: This retrospective study consists of three stages: 1) a patch-based algorithm for differentiation between tumor region and healthy tissue using multi-scale texture analysis along with L1-SVM (Support Vector Machine) classifier, 2) a voting-based approach, developed on a standard logistic function, to mitigate false detections, and 3) 3D visualization of the tumor and the surrounding vessels using ITK-SNAP software. Results: The results demonstrate that multi-scale texture analysis strikes a balance between recall and precision in tumor and healthy tissue differentiation with an overall accuracy of 0.78±0.12 and a sensitivity of 0.90±0.09 in PDAC. Conclusion: Multi-scale texture analysis using statistical and wavelet-based features along with L1-SVM can be employed to differentiate between healthy and pancreatic tissues. Besides, 3D visualization of the tumor region and surrounding vessels can facilitate the assessment of treatment response in PDAC. However, the 3D visualization software must be further developed for integrating with clinical applications.

Imaging of intestinal vasculitis focusing on MR and CT enterography: a two-way street between radiologic findings and clinical data.

Diagnosis of intestinal vasculitis is often challenging due to the non-specific clinical and imaging findings. Vasculitides with gastrointestinal (GI) manifestations are rare, but their diagnosis holds immense significance as late or missed recognition can result in high mortality rates. Given the resemblance of radiologic findings with some other entities, GI vasculitis is often overlooked on small bowel studies done using computed tomography/magnetic resonance enterography (CTE/MRE). Hereon, we reviewed radiologic findings of vasculitis with gastrointestinal involvement on CTE and MRE. The variety of findings on MRE/CTE depend upon the size of the involved vessels. Signs of intestinal ischemia, e.g., mural thickening, submucosal edema, mural hyperenhancement, and restricted diffusion on diffusion-weighted imaging, are common in intestinal vasculitis. Involvement of the abdominal aorta and the major visceral arteries is presented as concentric mural thickening, transmural calcification, luminal stenosis, occlusion, aneurysmal changes, and collateral vessels. Such findings can be observed particularly in large- and medium-vessel vasculitis. The presence of extra-intestinal findings, including within the liver, kidneys, or spleen in the form of focal areas of infarction or heterogeneous enhancement due to microvascular involvement, can be another radiologic clue in diagnosis of vasculitis. The link between the clinical/laboratory findings and MRE/CTE abnormalities needs to be corresponded when it comes to the diagnosis of intestinal vasculitis.

Black Fungus and beyond: COVID-19 associated infections.

Globally, many hospitalized COVID-19 patients can experience an unexpected acute change in status, prompting rapid and expert clinical assessment. Superimposed infections can be a significant cause of clinical and radiologic deviations in this patient population, further worsening clinical outcome and muddling the differential diagnosis. As thrombotic, inflammatory, and medication-induced complications can also trigger an acute change in COVID-19 patient status, imaging early and often plays a vital role in distinguishing the cause of patient decline and monitoring patient outcome. While the common radiologic findings of COVID-19 infection are now widely reported, little is known about the clinical manifestations and imaging findings of superimposed infection. By discussing case studies of patients who developed bacterial, fungal, parasitic, and viral co-infections and identifying the most frequently reported imaging findings of superimposed infections, physicians will be more familiar with common infectious presentations and initiate a directed workup sooner. Ultimately, any abrupt changes in the expected COVID-19 imaging presentation, such as the presence of new consolidations or cavitation, should prompt further workup to exclude superimposed opportunistic infection.

Pancreaticoduodenal Groove: Spectrum of Disease and Imaging Features.

The pancreaticoduodenal groove (PDG) is a small space between the pancreatic head and duodenum where vital interactions between multiple organs and physiologic processes take place. Muscles, nerves, and hormones perform a coordinated dance, allowing bile and pancreatic enzymes to aid in digestion and absorption of critical nutrition. Given the multitude of organs and cells working together, a variety of benign and malignant entities can arise in or adjacent to this space. Management of lesions in this region is also complex and can involve observation, endoscopic resection, or challenging surgeries such as the Whipple procedure. The radiologist plays an important role in evaluation of abnormalities involving the PDG. While CT is usually the first-line examination for evaluation of this complex region, MRI offers complementary information. Although features of abnormalities involving the PDG can often overlap, understanding the characteristic imaging and pathologic features generally allows categorization of disease entities based on the suspected organ of origin and the presence of ancillary features. The goal of the authors is to provide radiologists with a conceptual approach to entities implicating the PDG to increase the accuracy of diagnosis and assist in appropriate management or presurgical planning. They briefly discuss the anatomy of the PDG, followed by a more in-depth presentation of the features of disease categories. A table summarizing the entities that occur in this region by underlying cause and anatomic location is provided. ©RSNA, 2022.

Anti-inflammatory function of apolipoprotein B-depleted plasma is impaired in non-alcoholic fatty liver disease.

BACKGROUND: Non-alcoholic fatty liver disease (NAFLD) is associated with an increased risk of cardiovascular events. HDL exerts various protective functions on the cardiovascular system including anti-inflammatory activity by suppressing adhesion molecules expression in inflammation-induced endothelial cells. This study was designed to search if the anti-inflammatory capacity of apolipoprotein B-depleted plasma (apoB-depleted plasma) is altered in NAFLD patients. METHODS: A total of 83 subjects including 42 NAFLD and 41 control subjects were included in this cross-sectional study. Anti-inflammatory function of HDL was determined as the ability of apoB-depleted plasma to inhibit tumor necrosis factor-α (TNF-α)-induced expression of adhesion molecules in human umbilical vein endothelial cells (HUVECs). RESULTS: Incubation of inflammation-stimulated HUVECs with the NAFLD patients' apo-B depleted plasma led to higher levels of expression of adhesion molecules compared to the control subjects' plasma samples, reflecting an impaired anti-inflammatory capacity of apoB-depleted plasma in the NAFLD patients. Impaired anti-inflammatory capacity of apoB-depleted plasma was correlated with fatty liver and obesity indices. After adjustment with obesity indices, the association of anti-inflammatory capacity of apoB-depleted plasma with NAFLD remained significant. CONCLUSION: Impaired anti-inflammatory activity of apoB-depleted plasma was independently associated with NAFLD.

COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients.

BACKGROUND: We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients. METHODS: Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported. RESULTS: In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance. CONCLUSION: Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.

Proposing a novel deep network for detecting COVID-19 based on chest images.

The rapid outbreak of coronavirus threatens humans' life all around the world. Due to the insufficient diagnostic infrastructures, developing an accurate, efficient, inexpensive, and quick diagnostic tool is of great importance. To date, researchers have proposed several detection models based on chest imaging analysis, primarily based on deep neural networks; however, none of which could achieve a reliable and highly sensitive performance yet. Therefore, the nature of this study is primary epidemiological research that aims to overcome the limitations mentioned above by proposing a large-scale publicly available dataset of chest computed tomography scan (CT-scan) images consisting of more than 13k samples. Secondly, we propose a more sensitive deep neural networks model for CT-scan images of the lungs, providing a pixel-wise attention layer on top of the high-level features extracted from the network. Moreover, the proposed model is extended through a transfer learning approach for being applicable in the case of chest X-Ray (CXR) images. The proposed model and its extension have been trained and evaluated through several experiments. The inclusion criteria were patients with suspected PE and positive real-time reverse-transcription polymerase chain reaction (RT-PCR) for SARS-CoV-2. The exclusion criteria were negative or inconclusive RT-PCR and other chest CT indications. Our model achieves an AUC score of 0.886, significantly better than its closest competitor, whose AUC is 0.843. Moreover, the obtained results on another commonly-used benchmark show an AUC of 0.899, outperforming related models. Additionally, the sensitivity of our model is 0.858, while that of its closest competitor is 0.81, explaining the efficiency of pixel-wise attention strategy in detecting coronavirus. Our promising results and the efficiency of the models imply that the proposed models can be considered reliable tools for assisting doctors in detecting coronavirus.

Segmentation of pancreatic ductal adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and texture descriptors.

Fully automated and volumetric segmentation of critical tumors may play a crucial role in diagnosis and surgical planning. One of the most challenging tumor segmentation tasks is localization of pancreatic ductal adenocarcinoma (PDAC). Exclusive application of conventional methods does not appear promising. Deep learning approaches has achieved great success in the computer aided diagnosis, especially in biomedical image segmentation. This paper introduces a framework based on convolutional neural network (CNN) for segmentation of PDAC mass and surrounding vessels in CT images by incorporating powerful classic features, as well. First, a 3D-CNN architecture is used to localize the pancreas region from the whole CT volume using 3D Local Binary Pattern (LBP) map of the original image. Segmentation of PDAC mass is subsequently performed using 2D attention U-Net and Texture Attention U-Net (TAU-Net). TAU-Net is introduced by fusion of dense Scale-Invariant Feature Transform (SIFT) and LBP descriptors into the attention U-Net. An ensemble model is then used to cumulate the advantages of both networks using a 3D-CNN. In addition, to reduce the effects of imbalanced data, a multi-objective loss function is proposed as a weighted combination of three classic losses including Generalized Dice Loss (GDL), Weighted Pixel-Wise Cross Entropy loss (WPCE) and boundary loss. Due to insufficient sample size for vessel segmentation, we used the above-mentioned pre-trained networks and fine-tuned them. Experimental results show that the proposed method improves the Dice score for PDAC mass segmentation in portal-venous phase by 7.52% compared to state-of-the-art methods in term of DSC. Besides, three dimensional visualization of the tumor and surrounding vessels can facilitate the evaluation of PDAC treatment response.

Outcomes of COVID-19 in Patients with Inflammatory Bowel Disease: Comparison with Household Members and the Role of IBD Medications.

BACKGROUND: Most data on the effect of inflammatory bowel disease (IBD) and its treatments on coronavirus disease 2019 (COVID-19) outcomes have not had non-IBD comparators. Hence, we aimed to describe COVID-19 outcomes in IBD compared to non-IBD patients. METHODS: We conducted a prospective cohort study of registered IBD patients with confirmed COVID-19 from six provinces in Iran from February to April 2020. Proven COVID-19 patients were followed up at four weeks and the frequency of outcomes was assessed. Multivariable logistic regression was used to assess associations between demographics, clinical characteristics and COVID-19 outcomes. RESULTS: Overall, 2159 IBD patients and 4721 household members were enrolled, with 84 (3.9%) and 49 (1.1%) participants having confirmed COVID-19, respectively. Household spread of COVID-19 was not common in this cohort (1.2%). While hospitalization was significantly more frequent in IBD patients compared with non-IBD household members (27.1% vs. 6.0%, P=0.002), there was no significant difference in the frequency of severe cases. Age and presence of IBD were positively associated with hospitalization in IBD compared with non-IBD household members (OR: 1.06, 95% CI: 1.03-1.10; OR: 5.7, 95% CI: 2.02- 16.07, respectively). Age, presence of new gastrointestinal symptoms, and 5-aminosalicylic acid (5-ASA) use were associated with higher hospitalization rate in IBD patients (OR: 1.13, 95% CI: 1.05-1.23; OR: 6.49, 95% CI: 1.87-22.54; OR: 6.22, 95% CI: 1.90-20.36, respectively). Anti-tumor necrosis factor (TNF) was not associated with more severe outcomes. CONCLUSION: Age, presence of new gastrointestinal symptoms and use of 5-ASA were associated with increased hospitalization rate among IBD patients, while anti-TNF therapy had no statistical association.

Polypill for prevention of cardiovascular diseases with focus on non-alcoholic steatohepatitis: the PolyIran-Liver trial.

AIMS: Individuals with non-alcoholic steatohepatitis or elevated liver enzymes have increased cardiovascular mortality but are often excluded from prevention trials. We investigated the effectiveness of fixed-dose combination therapy for the prevention of major cardiovascular events (MCVE) among individuals with and without presumed non-alcoholic steatohepatitis (pNASH). METHODS AND RESULTS: Two thousand four hundred participants over 50 were randomized into the intervention and control groups. Consent was obtained post-randomization. Consenting participants in the intervention group were given a pill containing aspirin, atorvastatin, hydrochlorothiazide, and valsartan (polypill). Participants were followed for 5 years. Presumed non-alcoholic steatohepatitis was diagnosed by ultrasonography and elevated liver enzymes. The primary outcome was MCVE. ClinicalTrials.gov: NCT01245608. Among the originally randomized population, 138 of 1249 in the intervention group (11.0%) and 137 of 1017 controls (13.5%) had MCVE during the 5-year follow-up [unadjusted risk ratio (RR) 0.83, 95% confidence interval (CI) 0.66-1.03]. Of the 1508 participants who consented to additional measurements and treatment, 63 of 787 (8.0%) intervention group participants and 86 of 721 (11.9%) controls had MCVE (adjusted RR 0.61, 95% CI 0.44-0.83). Although the adjusted relative risk of MCVE in participants with pNASH (0.35, 95% CI 0.17-0.74) was under half that for participants without pNASH (0.73, 95% CI 0.49-1.00), the difference did not reach statistical significance. There was no change in liver enzymes in participants taking polypill but among those with pNASH, there was a significant decrease after 60 months of follow-up (intragroup -12.0 IU/L, 95% CI -14.2 to -9.6). CONCLUSION: Among patients consenting to receive fixed-dose combination therapy, polypill is safe and effective for the prevention of MCVE, even among participants with fatty liver and increased liver enzymes.

Development of computer-aided model to differentiate COVID-19 from pulmonary edema in lung CT scan: EDECOVID-net.

The efforts made to prevent the spread of COVID-19 face specific challenges in diagnosing COVID-19 patients and differentiating them from patients with pulmonary edema. Although systemically administered pulmonary vasodilators and acetazolamide are of great benefit for treating pulmonary edema, they should not be used to treat COVID-19 as they carry the risk of several adverse consequences, including worsening the matching of ventilation and perfusion, impaired carbon dioxide transport, systemic hypotension, and increased work of breathing. This study proposes a machine learning-based method (EDECOVID-net) that automatically differentiates the COVID-19 symptoms from pulmonary edema in lung CT scans using radiomic features. To the best of our knowledge, EDECOVID-net is the first method to differentiate COVID-19 from pulmonary edema and a helpful tool for diagnosing COVID-19 at early stages. The EDECOVID-net has been proposed as a new machine learning-based method with some advantages, such as having simple structure and few mathematical calculations. In total, 13 717 imaging patches, including 5759 COVID-19 and 7958 edema images, were extracted using a CT incision by a specialist radiologist. The EDECOVID-net can distinguish the patients with COVID-19 from those with pulmonary edema with an accuracy of 0.98. In addition, the accuracy of the EDECOVID-net algorithm is compared with other machine learning methods, such as VGG-16 (Acc = 0.94), VGG-19 (Acc = 0.96), Xception (Acc = 0.95), ResNet101 (Acc = 0.97), and DenseNet20l (Acc = 0.97).