Supplementation with organic yeast-derived selenium provides immune protection against experimental necrotic enteritis in broiler chickens.

Necrotic enteritis (NE) is a potentially fatal poultry disease that causes enormous economic losses in the poultry industry worldwide. The study aimed to evaluate the effects of dietary organic yeast-derived selenium (Se) on immune protection against experimental necrotic enteritis (NE) in commercial broilers. Chickens were fed basal diets supplemented with different Se levels (0.25, 0.50, and 1.00 Se mg/kg). To induce NE, Clostridium perfringens (C. perfringens) was orally administered at 14 days of age post hatch. The results showed that birds fed 0.25 Se mg/kg exhibited significantly increased body weight gain compared with the non-supplemented/infected birds. There were no significant differences in gut lesions between the Se-supplemented groups and the non-supplemented group. The antibody levels against α-toxin and NetB toxin increased with the increase between 0.25 Se mg/kg and 0.50 Se mg/kg. In the jejunal scrapings and spleen, the Se-supplementation groups up-regulated the transcripts for pro-inflammatory cytokines IL-1ß, IL-6, IL-8, iNOS, and LITAF and avian ß-defensin 6, 8, and 13 (AvBD6, 8 and 13). In conclusion, supplementation with organic yeast-derived Se alleviates the negative consequences and provides beneficial protection against experimental NE.

Deep Learning for Detecting Cerebral Aneurysms with CT Angiography.

Background Cerebral aneurysm detection is a challenging task. Deep learning may become a supportive tool for more accurate interpretation. Purpose To develop a highly sensitive deep learning-based algorithm that assists in the detection of cerebral aneurysms on CT angiography images. Materials and Methods Head CT angiography images were retrospectively retrieved from two hospital databases acquired across four different scanners between January 2015 and June 2019. The data were divided into training and validation sets; 400 additional independent CT angiograms acquired between July and December 2019 were used for external validation. A deep learning-based algorithm was constructed and assessed. Both internal and external validation were performed. Jackknife alternative free-response receiver operating characteristic analysis was performed. Results A total of 1068 patients (mean age, 57 years ± 11 [standard deviation]; 660 women) were evaluated for a total of 1068 CT angiograms encompassing 1337 cerebral aneurysms. Of these, 534 CT angiograms (688 aneurysms) were assigned to the training set, and the remaining 534 CT angiograms (649 aneurysms) constituted the validation set. The sensitivity of the proposed algorithm for detecting cerebral aneurysms was 97.5% (633 of 649; 95% CI: 96.0, 98.6). Moreover, eight new aneurysms that had been overlooked in the initial reports were detected (1.2%, eight of 649). With the aid of the algorithm, the overall performance of radiologists in terms of area under the weighted alternative free-response receiver operating characteristic curve was higher by 0.01 (95% CI: 0.00, 0.03). Conclusion The proposed deep learning algorithm assisted radiologists in detecting cerebral aneurysms on CT angiography images, resulting in a higher detection rate. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kallmes and Erickson in this issue.

MED12 variants associated with X-linked recessive partial epilepsy without intellectual disability.

OBJECTIVES: The MED12 gene encodes mediator complex subunit 12, which is a component of the mediator complex involved in the transcriptional regulation of nearly all RNA polymerase II-dependent genes. MED12 variants have previously been associated with developmental disorders with or without nonspecific intellectual disability. This study aims to explore the association between MED12 variants and epilepsy. MATERIALS AND METHODS: Trios-based whole-exome sequencing was performed in a cohort of 349 unrelated cases with partial (focal) epilepsy without acquired causes. The genotype-phenotype correlations of MED12 variants were analyzed. RESULTS: Five hemizygous missense MED12 variants, including c.958A>G/p.Ile320Val, c.1757G>A/p.Ser586Asn, c.2138C>T/p.Pro713Leu, c.3379T>C/p.Ser1127Pro, and c.4219A>C/p.Met1407Leu were identified in five unrelated males with partial epilepsy. All patients showed infrequent focal seizures and achieved seizure free without developmental abnormalities or intellectual disability. All the hemizygous variants were inherited from asymptomatic mothers (consistent with the X-linked recessive inheritance pattern) and were absent in the general population. The two variants with damaging hydrogen bonds were associated with early-onset seizures. Further genotype-phenotype analysis revealed that congenital anomaly disorder (Hardikar syndrome) was associated with (de novo) destructive variants in an X-linked dominant inheritance pattern, whereas epilepsy was associated with missense variants in an X-linked recessive inheritance pattern. Phenotypic features of intellectual disability appeared as the intermediate phenotype in terms of both genotype and inheritance. Epilepsy-related variants were located at the MED12-LCEWAV domain and the regions between MED12-LCEWAV and MED12-POL. CONCLUSION: MED12 is a potentially causative gene for X-linked recessive partial epilepsy without developmental or intellectual abnormalities. The genotype-phenotype correlation of MED12 variants explains the phenotypic variations and can help the genetic diagnosis.

Quantification of Iron Deposition in the Brain of Hypertensive Patients Using 3D-enhanced Susceptibility-weighted Angiography (ESWAN).

BACKGROUND: Cerebral microbleeds (CMBs) are commonly present in patients with hypertension, producing iron-containing metabolites. A small amount of regional iron deposition is hardly discernible on conventional magnetic resonance imaging (MRI). Three-dimensional enhanced susceptibility-weighted angiography (ESWAN) provides tissue images with high spatial resolution and signal-noise ratio, and has been widely used to measure brain iron deposition in neurodegenerative diseases and intracranial hemorrhage. OBJECTIVE: The study aimed to demonstrate iron deposition in the brain of hypertensive patients using ESWAN. METHOD: Twenty-seven hypertension patients, with or without CMBs, and 16 matched healthy controls (HCs) were enrolled. From the post-processed ESWAN images, phase and magnitude values of the regions of interest (ROIs) were calculated. Two-sample t-test and one-way variance analysis were applied to compare groups. The relationship between ESWAN parameters and clinical variables was assessed using Pearson's correlation coefficient. RESULTS: Compared to HCs, the phase value of the hippocampus, head of caudate nucleus (HCN), and substantia nigra (SN) was decreased in hypertension with the CMBs subgroup, while that of HCN and SN was decreased in hypertension without CMBs subgroup. Similarly, the magnitude value of the hippocampus, HCN, thalamus red nucleus, and SN was significantly lower in the hypertension group than HCs. In addition, the phase and magnitude values showed a correlation with clinical variables, including disease duration and blood pressure. CONCLUSION: Deep grey matter nuclei displayed greater iron content in hypertension patients. Iron deposition may precede the appearance of CMBs on MRI, serving as a potential marker of microvascular damage.

Erratum: Author Correction: Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence.

[This corrects the article DOI: 10.1038/s42256-021-00421-z.].

Affinity Space Adaptation for Semantic Segmentation Across Domains.

Semantic segmentation with dense pixel-wise annotation has achieved excellent performance thanks to deep learning. However, the generalization of semantic segmentation in the wild remains challenging. In this paper, we address the problem of unsupervised domain adaptation (UDA) in semantic segmentation. Motivated by the fact that source and target domain have invariant semantic structures, we propose to exploit such invariance across domains by leveraging co-occurring patterns between pairwise pixels in the output of structured semantic segmentation. This is different from most existing approaches that attempt to adapt domains based on individual pixel-wise information in image, feature, or output level. Specifically, we perform domain adaptation on the affinity relationship between adjacent pixels termed affinity space of source and target domain. To this end, we develop two affinity space adaptation strategies: affinity space cleaning and adversarial affinity space alignment. Extensive experiments demonstrate that the proposed method achieves superior performance against some state-of-the-art methods on several challenging benchmarks for semantic segmentation across domains. The code is available at https://github.com/idealwei/ASANet.

CT Angiography-Based Radiomics for Classification of Intracranial Aneurysm Rupture.

Background: Intracranial aneurysm rupture is a devastating medical event with a high morbidity and mortality rate. Thus, timely detection and management are critical. The present study aimed to identify the aneurysm radiomics features associated with rupture and to build and evaluate a radiomics classification model of aneurysm rupture. Methods: Radiomics analysis was applied to CT angiography (CTA) images of 393 patients [152 (38.7%) with ruptured aneurysms]. Patients were divided at a ratio of 7:3 into retrospective training (n = 274) and prospective test (n = 119) cohorts. A total of 1,229 radiomics features were automatically calculated from each aneurysm. The feature number was systematically reduced, and the most important classifying features were selected. A logistic regression model was constructed using the selected features and evaluated on training and test cohorts. Radiomics score (Rad-score) was calculated for each patient and compared between ruptured and unruptured aneurysms. Results: Nine radiomics features were selected from the CTA images and used to build the logistic regression model. The radiomics model has shown good performance in the classification of the aneurysm rupture on training and test cohorts [area under the receiver operating characteristic curve: 0.92 [95% confidence interval CI: 0.89-0.95] and 0.86 [95% CI: 0.80-0.93], respectively, p < 0.001]. Rad-score showed statistically significant differences between ruptured and unruptured aneurysms (median, 2.50 vs. -1.60 and 2.35 vs. -1.01 on training and test cohorts, respectively, p < 0.001). Conclusion: The results indicated the potential of aneurysm radiomics features for automatic classification of aneurysm rupture on CTA images.

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence.

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence.

Artificial intelligence provides a promising solution for streamlining COVID-19 diagnoses; however, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalized model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the artificial intelligence (AI) model can be distributedly trained and independently executed at each host institution under a federated learning framework without data sharing. Here we show that our federated learning framework model considerably outperformed all of the local models (with a test sensitivity/specificity of 0.973/0.951 in China and 0.730/0.942 in the United Kingdom), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals without the federated learning framework) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans from 3,336 patients collected from 23 hospitals located in China and the United Kingdom. Collectively, our work advanced the prospects of utilizing federated learning for privacy-preserving AI in digital health.

A collaborative online AI engine for CT-based COVID-19 diagnosis.

Artificial intelligence can potentially provide a substantial role in streamlining chest computed tomography (CT) diagnosis of COVID-19 patients. However, several critical hurdles have impeded the development of robust AI model, which include deficiency, isolation, and heterogeneity of CT data generated from diverse institutions. These bring about lack of generalization of AI model and therefore prevent it from applications in clinical practices. To overcome this, we proposed a federated learning-based Unified CT-COVID AI Diagnostic Initiative (UCADI, http://www.ai-ct-covid.team/), a decentralized architecture where the AI model is distributed to and executed at each host institution with the data sources or client ends for training and inferencing without sharing individual patient data. Specifically, we firstly developed an initial AI CT model based on data collected from three Tongji hospitals in Wuhan. After model evaluation, we found that the initial model can identify COVID from Tongji CT test data at near radiologist-level (97.5% sensitivity) but performed worse when it was tested on COVID cases from Wuhan Union Hospital (72% sensitivity), indicating a lack of model generalization. Next, we used the publicly available UCADI framework to build a federated model which integrated COVID CT cases from the Tongji hospitals and Wuhan Union hospital (WU) without transferring the WU data. The federated model not only performed similarly on Tongji test data but improved the detection sensitivity (98%) on WU test cases. The UCADI framework will allow participants worldwide to use and contribute to the model, to deliver a real-world, globally built and validated clinic CT-COVID AI tool. This effort directly supports the United Nations Sustainable Development Goals' number 3, Good Health and Well-Being, and allows sharing and transferring of knowledge to fight this devastating disease around the world.

Genistein-triggered anticancer activity against liver cancer cell line HepG2 involves ROS generation, mitochondrial apoptosis, G2/M cell cycle arrest and inhibition of cell migration.

INTRODUCTION: Liver cancer is one of the most common malignancies across the globe and one of the major causes of cancer-related mortality. With limited available treatment options, there is an urgent need to look for new available options. Genistein is an important plant flavonoid and has been shown to possess tremendous pharmacological potential. The objective of the present study was therefore to evaluate the anticancer effect of the genistein. MATERIAL AND METHODS: The antiproliferative activity and IC50 of genistein were determined by MTT assay. Reactive oxygen species (ROS) and cycle distribution were investigated by flow cytometry. Apoptosis was detected by DAPI and annexin V/IP staining. Cell migration was investigated by wound healing assay. Protein expression was estimated by western blotting. RESULTS: MTT assay revealed that genistein reduced the cell viability of HepG2 cancer cells in a dose-dependent manner. Genistein also reduced the colony forming potential of the HepG2 cell concentration dependently. The IC50 of genistein was found to be 25 µM. Genistein caused G2/M cell cycle arrest and G2/M cells increased from 4.2% in the control to 56.4% at 100 µM concentration. Genistein prompted generation of significant (p < 0.01) amounts of ROS, ultimately favouring cell death. Genistein also triggered apoptosis which was associated with upregulation of cytosolic cytochrome c, Bax, cleaved caspase 3 and 9 expression and downregulation of Bcl-2 expression in HepG2 cells. CONCLUSIONS: We propose that genistein exhibits significant anticancer activity against liver cancer and therefore may prove beneficial in the management of liver cancer.

Chronic phototoxic maculopathy caused by welding arc in occupational welders.

OBJECTIVE: To investigate whether occupationally-related phototoxicity can occur from welding. DESIGN: Cross-sectional study. PARTICIPANTS: Forty welders from manufacturing enterprise and 40 age-matched nonwelder controls. METHODS: Participants underwent thorough ophthalmologic examination including fundus photography, automatic perimeter examination, and high definition optical coherence tomography (OCT) scan. The clinical history of all subjects was screened carefully before the study. RESULTS: There was no significant difference for best corrected distance visual acuity when comparing welders with nonwelders. Anterior segment, red reflex, Amsler grid test, and perimetric examinations were unremarkable. Fundus photographs revealed a small, round, or oval, dark-yellow macular lesion with an obscure boundary in 19 welder eyes (23.8%). OCT revealed an interruption or defect in the inner segment/outer segment (IS/OS) layer and the inner portion retinal pigment epithelium (RPE) layer in varying degrees in 30 welder eyes (38.0%), revealing a higher prevalence of maculopathy. All control examinations were unremarkable. We have also discovered that OCT is more sensitive than fundus photography in identifying macular lesions. CONCLUSIONS: Occupational welders exposed to a welding arc environment have a higher risk of phototoxic maculopathy than nonwelders, as diagnosed most effectively using OCT.