Identification of key genes increasing susceptibility to atrial fibrillation in nonalcoholic fatty liver disease and the potential mechanisms: mitochondrial dysfunction and systemic inflammation.

Background: Non-alcoholic fatty liver disease (NAFLD) and atrial fibrillation (AF) are major health burdens, with emerging evidence suggesting NAFLD as a significant risk factor for AF, but the mechanism is remain unclear. Methods: In this study, we analyzed gene expression data from NAFLD (GSE89632) and AF (GSE75092) datasets from the Gene Expression Omnibus. We identified co-upregulated and co-downregulated genes between NAFLD and AF, assessed diagnostic potential of specific genes, conducted immune infiltration analysis, and performed molecular docking studies with sodium glucose co-transporter 2 inhibitors (SGLT2i). Results: We identified eight co-upregulated and 31 co-downregulated genes between NAFLD and AF. Genes such as AMOT, PDE11A, TYMS, TMEM98, and PTGS2 demonstrated substantial diagnostic potential for identifying NAFLD patients at risk of AF. Immune infiltration analysis discovered an elevated presence of CD8 T cells, γδ T cells, and M2 macrophages in NAFLD livers, linking systemic inflammation to NAFLD and AF. Additionally, studies have shown that a connection between mitochondrial dysfunction and several hub genes like DGAT1, TYMS, and PTGS2, suggesting that mitochondrial disturbances may underpin the systemic inflammation in NAFLD, which possibly exacerbating AF. Molecular docking studies indicated that empagliflozin's binding affinity with key genes such as DGAT1, TYMS, and PTGS2 presents a novel therapeutic avenue for NAFLD-associated AF. Conclusion: Our study firstly discovered that AMOT, PDE11A, TYMS, TMEM98, and PTGS2 are associated with NAFLD-related AF and hold strong diagnostic values. Our study also indicates that mitochondrial dysfunction and systemic inflammation may be potential mechanisms bridging NAFLD and AF. Additionally, we identified empagliflozin as a potentially effective therapeutic agent for NAFLD-related AF at the molecular structure level. These novel insights contribute to the further understanding, diagnosis, and intervention of NAFLD-related AF.

Advances in research on molecular markers in immune checkpoint inhibitor-associated myocarditis.

Immune checkpoint inhibitors (ICIs) play a crucial role in the immunotherapy of malignant tumors, preventing immune evasion by tumor cells and activating autoimmune cells to eliminate the tumor. Despite their proven effectiveness in antitumor therapy, potential immune-related adverse effects must be recognized, particularly ICI-associated myocarditis (ICIAM). ICIAM is the most lethal form of organ immunotoxicity, with a significant impact on short-term mortality. However, ICIAM is predominantly asymptomatic or mildly nonspecific. It is difficult to diagnose, especially due to the lack of unique molecular markers. This article aims to provide a comprehensive overview of the progress made in identifying molecular markers for ICIAM.

Prototypical Matching Networks for Video Object Segmentation.

Semi-supervised video object segmentation is the task of segmenting the target in sequential frames given the ground truth mask in the first frame. The modern approaches usually utilize such a mask as pixel-level supervision and typically exploit pixel-to-pixel matching between the reference frame and current frame. However, the matching at pixel level, which overlooks the high-level information beyond local areas, often suffers from confusion caused by similar local appearances. In this paper, we present Prototypical Matching Networks (PMNet) - a novel architecture that integrates prototypes into matching-based video objection segmentation frameworks as high-level supervision. Specifically, PMNet first divides the foreground and background areas into several parts according to the similarity to the global prototypes. The part-level prototypes and instance-level prototypes are generated by encapsulating the semantic information of identical parts and identical instances, respectively. To model the correlation between prototypes, the prototype representations are propagated to each other by reasoning on a graph structure. Then, PMNet stores both the pixel-level features and prototypes in the memory bank as the target cues. Three affinities, i.e., pixel-to-pixel affinity, prototype-to-pixel affinity, and prototype-to-prototype affinity, are derived to measure the similarity between the query frame and the features in the memory bank. The features aggregated from the memory bank using these affinities provide powerful discrimination from both the pixel-level and prototype-level perspectives. Extensive experiments conducted on four benchmarks demonstrate superior results than the state-of-the-art video object segmentation techniques.

Identification and validation of key genes associated with atrial fibrillation in the elderly.

Background: Atrial fibrillation (AF) is the most common cardiac arrhythmia and significantly increases the risk of stroke and heart failure (HF), contributing to a higher mortality rate. Increasing age is a major risk factor for AF; however, the mechanisms of how aging contributes to the occurrence and progression of AF remain unclear. This study conducted weighted gene co-expression network analysis (WGCNA) to identify key modules and hub genes and determine their potential associations with aging-related AF. Materials and methods: WGCNA was performed using the AF dataset GSE2240 obtained from the Gene Expression Omnibus, which contained data from atrial myocardium in cardiac patients with permanent AF or sinus rhythm (SR). Hub genes were identified in clinical samples. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were also performed. Results: Green and pink were the most critical modules associated with AF, from which nine hub genes, PTGDS, COLQ, ASTN2, VASH1, RCAN1, AMIGO2, RBP1, MFAP4, and ALDH1A1, were hypothesized to play key roles in the AF pathophysiology in elderly and seven of them have high diagnostic value. Functional enrichment analysis demonstrated that the green module was associated with the calcium, cyclic adenosine monophosphate (cAMP), and peroxisome proliferator-activated receptors (PPAR) signaling pathways, and the pink module may be associated with the transforming growth factor beta (TGF-ß) signaling pathway in myocardial fibrosis. Conclusion: We identified nine genes that may play crucial roles in the pathophysiological mechanism of aging-related AF, among which six genes were associated with AF for the first time. This study provided novel insights into the impact of aging on the occurrence and progression of AF, and identified biomarkers and potential therapeutic targets for AF.

Identification and Verification of Biomarkers and Immune Infiltration in Obesity-Related Atrial Fibrillation.

Obesity is an independent risk factor for atrial fibrillation (AF). However, the mechanisms underlying this crosstalk are still being uncovered. Co-differentially expressed genes (co-DEGs) of AF and obesity microarrays were identified by bioinformatics analysis. Subsequently, functional enrichment, cell-type enrichment, and protein-protein interaction network analyses of co-DEGs were carried out. Then, we validated the hub genes by qRT-PCR of patients' blood samples. Finally, CIBERSORT was utilized to evaluate the AF microarray to determine immune infiltration and the correlation between validated hub genes and immune cells. A total of 23 co-up-regulated DEGs in AF and obesity microarrays were identified, and these genes were enriched in inflammation- and immune-related function. The enriched cells were whole blood, CD33+ myeloid, and CD14+ monocytes. The hub genes were identified as MNDA, CYBB, CD86, FCGR2C, NCF2, LCP2, TLR8, HLA-DRA, LCP1, and PTPN22. All hub genes were only elevated in blood samples of obese-AF patients. The CIBERSORT analysis revealed that the AF patients' left atrial appendage had increased infiltration of naïve B cells and decreased infiltration of memory B cells. The hub genes were related positively to naïve B cells and negatively to memory B cells. Ten hub genes may serve as biomarkers for obesity-related AF. These findings may also aid in comprehending pathophysiological mechanisms for obesity-related AF.

Multi-task hourglass network for online automatic diagnosis of developmental dysplasia of the hip.

Developmental dysplasia of the hip (DDH) is one of the most common diseases in children. Due to the experience-requiring medical image analysis work, online automatic diagnosis of DDH has intrigued the researchers. Traditional implementation of online diagnosis faces challenges with reliability and interpretability. In this paper, we establish an online diagnosis tool based on a multi-task hourglass network, which can accurately extract landmarks to detect the extent of hip dislocation and predict the age of the femoral head. Our method utilizes a multi-task hourglass network, which trains an encoder-decoder network to regress the landmarks and predict the developmental age for online DDH diagnosis. With the support of precise image analysis and fast GPU computing, our method can help overcome the shortage of medical resources and enable telehealth for DDH diagnosis. Applying this approach to a dataset of DDH X-ray images, we demonstrate 4.64 mean pixel error of landmark detection compared to the results of human experts. Moreover, we can improve the accuracy of the age prediction of femoral heads to 89%. Our online automatic diagnosis system has provided service to 112 patients, and the results demonstrate the effectiveness of our method.

Pyruvate Dehydrogenase Kinase 2 Accelerates Endotoxin Shock by Promoting Mitogen-Activated Protein Kinase Activation.

Endotoxin shock remains one of the major causes of mortality worldwide. Pyruvate dehydrogenase kinase (PDK) 2 is an important regulatory enzyme involved in glucose metabolism. The purpose of this study was to determine the regulatory effect of PDK2 on LPS-induced endotoxin shock and explore the mechanisms in vivo and in vitro. Here, we showed that PDK2 contributed to Toll-like receptor (TLR)-mediated inflammation. Lipopolysaccharide (LPS) activation of TLR4 pathways resulted in PDK2 upregulation in macrophages and dendritic cells (DCs). PDK2 overexpression enhanced TLR4 signaling pathway activation, whereas downregulating PDK2 expression inhibited TLR4 signaling pathway activation. Pharmacological inhibition of PDK2 significantly decreased the mortality rate and alleviated pathological injury in the lungs and livers of LPS-challenged mice, while significantly suppressing proinflammatory cytokine production. Thus, we confirmed that PDK2 is involved in LPS-induced endotoxin shock by modulating TLR4-mitogen-activated protein kinase signaling and inducing the production of proinflammatory cytokines in macrophages and DCs. Our findings highlight the importance of PDK2 as a novel target to treat septic shock.

Pyruvate dehydrogenase kinase regulates macrophage polarization in metabolic and inflammatory diseases.

Macrophages are highly heterogeneous and plastic, and have two main polarized phenotypes that are determined by their microenvironment, namely pro- and anti-inflammatory macrophages. Activation of pro-inflammatory macrophages is closely associated with metabolic reprogramming, especially that of aerobic glycolysis. Mitochondrial pyruvate dehydrogenase kinase (PDK) negatively regulates pyruvate dehydrogenase complex activity through reversible phosphorylation and further links glycolysis to the tricarboxylic acid cycle and ATP production. PDK is commonly associated with the metabolism and polarization of macrophages in metabolic and inflammatory diseases. This review examines the relationship between PDK and macrophage metabolism and discusses the mechanisms by which PDK regulates macrophage polarization, migration, and inflammatory cytokine secretion in metabolic and inflammatory diseases. Elucidating the relationships between the metabolism and polarization of macrophages under physiological and pathological conditions, as well as the regulatory pathways involved, may provide valuable insights into the etiology and treatment of macrophage-mediated inflammatory diseases.

Application of deep-learning-based artificial intelligence in acetabular index measurement.

Objective: To construct an artificial intelligence system to measure acetabular index and evaluate its accuracy in clinical application. Methods: A total of 10,219 standard anteroposterior pelvic radiographs were collected retrospectively from April 2014 to December 2018 in our hospital. Of these, 9,219 radiographs were randomly selected to train and verify the system. The remaining 1,000 radiographs were used to compare the system's and the clinicians' measurement results. All plain pelvic films were labeled by an expert committee through PACS system based on a uniform standard to measure acetabular index. Subsequently, eight other clinicians independently measured the acetabular index from 200 randomly selected radiographs from the test radiographs. Bland-Altman test was used for consistency analysis between the system and clinician measurements. Results: The test set included 1,000 cases (2,000 hips). Compared with the expert committee measurement, the 95% limits of agreement (95% LOA) of the system was -4.02° to 3.45° (bias = -0.27°, P < 0.05). The acetabular index measured by the system within all age groups, including normal and abnormal groups, also showed good credibility according to the Bland-Altman principle. Comparison of the measurement evaluations by the system and eight clinicians vs. that of, the expert committee, the 95% LOA of the clinician with the smallest measurement error was -2.76° to 2.56° (bias = -0.10°, P = 0.126). The 95% LOA of the system was -0.93° to 2.86° (bias = -0.03°, P = 0.647). The 95% LOA of the clinician with the largest measurement error was -3.41° to 4.25° (bias = 0.42°, P < 0.05). The measurement error of the system was only greater than that of a senior clinician. Conclusion: The newly constructed artificial intelligence system could quickly and accurately measure the acetabular index of standard anteroposterior pelvic radiographs. There is good data consistency between the system in measuring standard anteroposterior pelvic radiographs. The accuracy of the system is closer to that of senior clinicians.

The prognostic significance of left atrial appendage peak flow velocity in the recurrence of persistent atrial fibrillation following first radiofrequency catheter ablation.

BACKGROUND: Atrial fibrillation (AF) relapse following radiofrequency catheter ablation (RFCA) for persistent atrial fibrillation (PeAF) continues to be a concern. This study establishes a connection between left atrial appendage peak flow velocity (LAAV) and recurrence of AF in individuals having PeAF following first RFCA. METHODS: We retrospectively studied 164 successive PeAF patients who had first RFCA between January 2018 and December 2019. Before the ablation, the LAAV was recorded using transesophageal echocardiography (TEE). The demographic and clinical data of the individuals were gathered. Participants were monitored at regular intervals to monitor for recurrence of AF. We employed Cox proportional hazards regression to determine if LAAV, as well as other clinical indicators, were predictive of AF recurrence in follow-up. RESULTS: In this study, AF relapse was seen in 43 patients (26.2%) following a median follow-up of 15 [interquartile range (IQR): 12-18] months. It was shown that the LAAV was decreased in individuals who had recurrences of AF (0.36±0.05 vs. 0.45±0.17 m/s, P=0.004). Using Kaplan-Meier analysis, it was discovered that the low LAAV (0.37 m/s) group had a poorer event-free survival rate compared to the high LAAV (>0.37 m/s) group (17.6 vs. 21.2 months, log-rank P=0.002) group. Based on the results of the multivariate Cox regression analysis, a LAAV of fewer than 0.37 m/s [hazard ratio (HR): 2.32; 95% confidence interval (CI): 1.177-4.227; P=0.014] was shown to be an independent predictor of AF recurrence following RFCA. CONCLUSIONS: A low LAAV is associated with AF relapse, and it is a predictor of AF relapse following the first RFCA for PeAF. This discovery may be useful in the optimization of treatment strategies and the care of patients with PeAF.

Three-dimensional quantitative assessment of myocardial infarction via multimodality fusion imaging: methodology, validation, and preliminary clinical application.

BACKGROUND: The precise assessment of myocardial infarction (MI) is crucial both for therapeutic interventions in old MI and the development of new and effective techniques to repair injured myocardium. A novel method was developed to assess left ventricular (LV) quantitatively infarction through three-dimensional (3D) multimodality fusion based on computed tomography angiography (CTA) and technetium-99m methoxyisobutylisonitrile (99mTc-MIBI) single-photon emission computed tomography (SPECT) images. This study sought to develop a 3D quantitative method for MI for pre-clinical study and clinical application. METHODS: Three months after the MI models were established in 20 minipigs, CTA and SPECT images were acquired separately, which were then aligned automatically with the constraints of the shape and the whole heart and LV myocardium position. Infarct ratios were quantified based on the 3D fusion images. The quantitative assessment was then experimentally validated via an ex vivo histology analysis using triphenyl-tetrazolium-chloride staining and subsequently applied to post-MI patients (n=8). RESULTS: The location of an infarct identified by the SPECT was consistent with that identified by an ex vivo heart in a 3D space. Infarct size determined by CTA-SPECT was correlated with infarct size assessed by triphenyl-tetrazolium-chloride pathology {27.6% [interquartile range (IQR) 17.1-34.7%] vs. 24.1% (IQR 14.7-32.5%), r2=0.99, P<0.01}. In clinical cases, the CTA-SPECT 3D fusion quantitative results were significantly correlated with the quantitative perfusion SPECT results (r=0.976, P<0.01). CONCLUSIONS: The proposed 3D fusion quantitative assessment method provides reliable and intuitive evaluations of infarction. This novel quantification technique enables whole heart quantification for the pre-operation evaluation and post-diagnosis management of old MI patients. It could also be applied to the design of 3D-printed cardiac patches.

Hip Landmark Detection With Dependency Mining in Ultrasound Image.

Developmental dysplasia of the hip (DDH) is a common and serious disease in infants. Hip landmark detection plays a critical role in diagnosing the development of neonatal hip in the ultrasound image. However, the local confusion and the regional weakening make this task challenging. To solve these challenges, we explore the stable hip structure and the distinguishable local features to provide dependencies for hip landmark detection. In this paper, we propose a novel architecture named Dependency Mining ResNet (DM-ResNet), which investigates end-to-end dependency mining for more accurate and much faster hip landmark detection. First of all, we convert the landmark detection to the heatmap estimation by ResNet to build a strong baseline architecture for fast and accurate detection. Secondly, a dependency mining module is explored to mine the dependencies and leverage both the local and global information to decline the local confusion and strengthen the weakening region. Thirdly, we propose a simple but effective local voting algorithm (LVA) that seeks trade-off between long-range and short-range dependencies in the hip ultrasound image. Besides, a dataset with 2000 annotated hip ultrasound images is constructed in our work. It is the first public hip ultrasound dataset for open research. Experimental results show that our method achieves excellent precision in hip landmark detection (average point error of 0.719mm and successful detection rate within 1mm of 79.9%).

Interleukin-36γ aggravates macrophage foam cell formation and atherosclerosis progression in ApoE knockout mice.

Atherosclerosis-related cardiovascular diseases are the leading cause of mortality worldwide. Macrophage-derived foam cell formation is a critical early event in atherogenesis. However, the molecular pathways involved in this disease have not been fully elucidated. Interleukin (IL)-36 plays a crucial role in inflammation, and this study was conducted to investigate the possible role of IL-36γ in the pathogenesis and regulation of atherosclerosis. In this study, we show that IL-36γ regulates inflammatory responses and lipoprotein metabolic processes in macrophages and exerts its atherosclerosis-promoting effects by increasing macrophage foam cell formation and uptake of oxidized low-density lipoproteins. Mechanistically, IL-36γ specifically upregulates expression of the scavenger receptor CD36 through the phosphoinositide 3-kinase pathway in macrophages. These results contribute to our understanding of IL-36γ as a novel regulator of foam cell formation and atherogenesis progression.

Mitochondrial Dysfunction Contributes to Aging-Related Atrial Fibrillation.

The incidence of atrial fibrillation (AF) increases with age, and telomere length gradually shortens with age. However, whether telomere length is related to AF is still inconclusive, and the exact mechanism by which aging causes the increased incidence of AF is still unclear. We hypothesize that telomere length is correlated with aging-related AF and that mitochondrial dysfunction plays a role in this. This research recruited 96 elderly male patients with AF who were admitted to the Second Medical Center of Chinese PLA General Hospital from April to October 2018. After matching by age and gender, 96 non-AF elderly male patients who were admitted to the hospital for physical examination during the same period were selected as controls. Anthropometric, clinical, and laboratory analyses were performed on all subjects. The mitochondrial membrane potential (MMP) of peripheral blood leukocytes was detected as the indicator of mitochondrial function. Compared with the control group, the leukocyte telomere length (LTL) was significantly shorter (P < 0.001), and the level of PGC-1α in serum was significantly lower in AF patients. Additionally, in subjects without any other diseases, the AF patients had lower MMP when compared with the control. Multivariate logistic regression confirmed that LTL (OR 0.365; 95% CI 0.235-0.568; P < 0.001) and serum PGC-1α (OR 0.993; 95% CI 0.988-0.997; P = 0.002) were inversely associated with the presence of AF. In addition, ROC analysis indicated the potential diagnostic value of LTL and serum PGC-1α with AUC values of 0.734 and 0.633, respectively. This research concludes that LTL and serum PGC-1α are inversely correlated with the occurrence of aging-related AF and that mitochondrial dysfunction plays a role in this.

The Current Dilemma and Breakthrough of Stem Cell Therapy in Ischemic Heart Disease.

Ischemic heart disease (IHD) is the leading cause of mortality worldwide. Stem cell transplantation has become a promising approach for the treatment of IHD in recent decades. It is generally recognized that preclinical cell-based therapy is effective and have yielded encouraging results, which involves preventing or reducing myocardial cell death, inhibiting scar formation, promoting angiogenesis, and improving cardiac function. However, clinical studies have not yet achieved a desired outcome, even multiple clinical studies showing paradoxical results. Besides, many fundamental puzzles remain to be resolved, for example, what is the optimal delivery timing and approach? Additionally, limited cell engraftment and survival, challenging cell fate monitoring, and not fully understood functional mechanisms are defined hurdles to clinical translation. Here we review some of the current dilemmas in stem cell-based therapy for IHD, along with our efforts and opinions on these key issues.

Effects of Allicin on Late Sodium Current Caused by ΔKPQ-SCN5A Mutation in HEK293 Cells.

AIM: The aim was to study the effect of Allitridum (Allicin) on the heterologous expression of the late sodium current on the ΔKPQ-SCN5A mutations in HEK293 cells, with a view to screening new drugs for the treatment of long QT syndrome type 3 (LQT3). METHODS AND RESULTS: The ΔKPQ-SCN5A plasmid was transiently transferred into HEK293 cells by liposome technology and administered by extracellular perfusion, and the sodium current was recorded by whole-cell patch-clamp technology. Application of Allicin 30 µM reduced the late sodium current (I Na,L ) of the Nav1.5 channel current encoded by ΔKPQ-SCN5A from 1.92 ± 0.12 to 0.65 ± 0.03 pA/pF (P < 0.01, n = 15), which resulted in the decrease of I Na,L /I Na,P (from 0.94% ± 0.04% to 0.32% ± 0.02%). Furthermore, treatment with Allicin could move the steady-state inactivation of the channel to a more negative direction, resulting in an increase in channel inactivation at the same voltage, which reduced the increase in the window current and further increased the inactivation of the channel intermediate state. However, it had no effect on channel steady-state activation (SSA), inactivation mechanics, and recovery dynamics after inactivation. What's more, the Nav1.5 channel protein levels of membrane in the ΔKPQ-SCN5A mutation were enhanced from 0.49% ± 0.04% to 0.76% ± 0.02% with the effect of 30 mM Allicin, close to 0.89% ± 0.02% of the WT. CONCLUSION: Allicin reduced the late sodium current of ΔKPQ-SCN5A, whose mechanism may be related to the increase of channel steady-state inactivation (SSI) and intermediate-state inactivation (ISI) by the drug, thus reducing the window current.

Self-Supervised Attention Mechanism for Pediatric Bone Age Assessment With Efficient Weak Annotation.

Pediatric bone age assessment (BAA) is a common clinical practice to investigate endocrinology, genetic and growth disorders of children. Different specific bone parts are extracted as anatomical Regions of Interest (RoIs) during this task, since their morphological characters have important biological identification in skeletal maturity. Following this clinical prior knowledge, recently developed deep learning methods address BAA with an RoI-based attention mechanism, which segments or detects the discriminative RoIs for meticulous analysis. Great strides have been made, however, these methods strictly require large and precise RoIs annotations, which limits the real-world clinical value. To overcome the severe requirements on RoIs annotations, in this paper, we propose a novel self-supervised learning mechanism to effectively discover the informative RoIs without the need of extra knowledge and precise annotation-only image-level weak annotation is all we take. Our model, termed PEAR-Net for Part Extracting and Age Recognition Network, consists of one Part Extracting (PE) agent for discriminative RoIs discovering and one Age Recognition (AR) agent for age assessment. Without precise supervision, the PE agent is designed to discover and extract RoIs fully automatically. Then the proposed RoIs are fed into AR agent for feature learning and age recognition. Furthermore, we utilize the self-consistency of RoIs to optimize PE agent to understand the part relation and select the most useful RoIs. With this self-supervised design, the PE agent and AR agent can reinforce each other mutually. To the best of our knowledge, this is the first end-to-end bone age assessment method which can discover RoIs automatically with only image-level annotation. We conduct extensive experiments on the public RSNA 2017 dataset and achieve state-of-the-art performance with MAE 3.99 months. Project is available at http://imcc.ustc.edu.cn/project/ssambaa/.

Clinical application of artificial intelligence-assisted diagnosis using anteroposterior pelvic radiographs in children with developmental dysplasia of the hip.

AIMS: The diagnosis of developmental dysplasia of the hip (DDH) is challenging owing to extensive variation in paediatric pelvic anatomy. Artificial intelligence (AI) may represent an effective diagnostic tool for DDH. Here, we aimed to develop an anteroposterior pelvic radiograph deep learning system for diagnosing DDH in children and analyze the feasibility of its application. METHODS: In total, 10,219 anteroposterior pelvic radiographs were retrospectively collected from April 2014 to December 2018. Clinicians labelled each radiograph using a uniform standard method. Radiographs were grouped according to age and into 'dislocation' (dislocation and subluxation) and 'non-dislocation' (normal cases and those with dysplasia of the acetabulum) groups based on clinical diagnosis. The deep learning system was trained and optimized using 9,081 radiographs; 1,138 test radiographs were then used to compare the diagnoses made by deep learning system and clinicians. The accuracy of the deep learning system was determined using a receiver operating characteristic curve, and the consistency of acetabular index measurements was evaluated using Bland-Altman plots. RESULTS: In all, 1,138 patients (242 males; 896 females; mean age 1.5 years (SD 1.79; 0 to 10) were included in this study. The area under the receiver operating characteristic curve, sensitivity, and specificity of the deep learning system for diagnosing hip dislocation were 0.975, 276/289 (95.5%), and 1,978/1,987 (99.5%), respectively. Compared with clinical diagnoses, the Bland-Altman 95% limits of agreement for acetabular index, as determined by the deep learning system from the radiographs of non-dislocated and dislocated hips, were -3.27° - 2.94° and -7.36° - 5.36°, respectively (p < 0.001). CONCLUSION: The deep learning system was highly consistent, more convenient, and more effective for diagnosing DDH compared with clinician-led diagnoses. Deep learning systems should be considered for analysis of anteroposterior pelvic radiographs when diagnosing DDH. The deep learning system will improve the current artificially complicated screening referral process. Cite this article: Bone Joint J 2020;102-B(11):1574-1581.

Misshapen Pelvis Landmark Detection With Local-Global Feature Learning for Diagnosing Developmental Dysplasia of the Hip.

Developmental dysplasia of the hip (DDH) is one of the most common orthopedic disorders in infants and young children. Accurately detecting and identifying the misshapen anatomical landmarks plays a crucial role in the diagnosis of DDH. However, the diversity during the calcification and the deformity due to the dislocation lead it a difficult task to detect the misshapen pelvis landmarks for both human expert and computer. Generally, the anatomical landmarks exhibit stable morphological features in part regions and rigid structural features in long ranges, which can be strong identification for the landmarks. In this paper, we investigate the local morphological features and global structural features for the misshapen landmark detection with a novel Pyramid Non-local UNet (PN-UNet). Firstly, we mine the local morphological features with a series of convolutional neural network (CNN) stacks, and convert the detection of a landmark to the segmentation of the landmark's local neighborhood by UNet. Secondly, a non-local module is employed to capture the global structural features with high-level structural knowledge. With the end-to-end and accurate detection of pelvis landmarks, we realize a fully automatic and highly reliable diagnosis of DDH. In addition, a dataset with 10,000 pelvis X-ray images is constructed in our work. It is the first public dataset for diagnosing DDH and has been already released for open research. To the best of our knowledge, this is the first attempt to apply deep learning method in the diagnosis of DDH. Experimental results show that our approach achieves an excellent precision in landmark detection (average point to point error of 0.9286mm) and illness diagnosis over human experts. Project is available at http://imcc.ustc.edu.cn/project/ddh/.

Regulation of the cerebrovascular smooth muscle cell phenotype by mitochondrial oxidative injury and endoplasmic reticulum stress in simulated microgravity rats via the PERK-eIF2α-ATF4-CHOP pathway.

Microgravity exposure results in vascular remodeling and cardiovascular dysfunction. Here, the effects of mitochondrial oxidative stress on vascular smooth muscle cells (VSMCs) in rat cerebral arteries under microgravity simulated by hindlimb unweighting (HU) was studied. Endoplasmic reticulum (ER)-resident transmembrane sensor proteins and phenotypic markers of rat cerebral VSMCs were examined. In HU rats, CHOP expression was increased gradually, and the upregulation of the PERK-eIF2α-ATF4 pathway was the most pronounced in cerebral arteries. Furthermore, PERK/p-PERK signaling, CHOP, GRP78 and reactive oxygen species were augmented by PERK overexpression but attenuated by the mitochondria-targeting antioxidant MitoTEMPO. Meanwhile, p-PI3K, p-Akt and p-mTOR protein levels in VSMCs were increased in HU rat cerebral arteries. Compared with the control, HU rats exhibited lower α-SMA, calponin, SM-MHC and caldesmon protein levels but higher OPN and elastin levels in cerebral VSMCs. The cerebral VSMC phenotype transition from a contractile to synthetic phenotype in HU rats was augmented by PERK overexpression and 740Y-P but reversed by MitoTEMPO and the ER stress inhibitors tauroursodeoxycholic acid (TUDCA) and 4-phenylbutyric acid (4-PBA). In summary, mitochondrial oxidative stress and ER stress induced by simulated microgravity contribute to phenotype transition of cerebral VSMCs through the PERK-eIF2a-ATF4-CHOP pathway in a rat model.