The Outcome of Sac Filling With Fibrin Sealant and Gentamicin After Endovascular Aortic Repair of Brucella-Related Aorto-Iliac Artery Aneurysms: A Retrospective Single-Center Study.

PURPOSE: This study aimed to analyze the experience of our center and assess the efficacy of sac filling with fibrin sealant (FS) and gentamicin after endovascular aortic repair (EVAR) in patients with Brucella-related aorto-iliac artery aneurysms. MATERIALS AND METHODS: All patients who received sac filling with FS and gentamicin after EVAR for Brucella-related aorto-iliac artery aneurysms between March 2019 and September 2022 were reviewed. Before and after sac filling with FS and gentamicin, aneurysm sac thrombosis and endoleak were evaluated using a preloaded catheter to monitor immediate repair outcome. Short- to mid-term outcomes were assessed by the incidence of vascular graft infection (VGI), all-cause mortality, maximum aneurysm diameter, aneurysm sac thrombosis, and other adverse events. RESULTS: There were 14 patients with Brucella-related aorto-iliac artery aneurysms who underwent sac filling with FS and gentamicin after EVAR. Perioperative death due to myocardial infarction in 1 patient resulted in a postoperative all-cause mortality rate of 7.1% (1/14). All patients received anti-Brucella drugs for a median of 6.0 (range: 3-12) months postoperatively. During a median follow-up period of 15.0 (range 0.5-36) months, the absolute and sagittal maximum diameters of the aorto-iliac aneurysm sac were significantly smaller than preoperation (from 46.3 ± 17.0 to 27.2 ± 16.3 mm, P<.001, and from 39.2 ± 13.1 to 24.0 ± 13.8 mm, P<.001). Two of these patients had a postoperative disappearance of the pseudoaneurysm. One patient was reintervened for bilateral femoral artery bypass surgery. Except for sac filling with gentamicin, all patients received anti-brucella medication for a median of 6.0 (range: 3-12) months. There were no allergic reactions, nephrotoxicity, endoleak, recurrence, VGI, aorta-related or infection-related deaths during the perioperative period and follow-up. CONCLUSIONS: Sac filling with FS and gentamicin adjunctive to EVAR, with targeted drug delivery to the sites of Brucella-related aorto-iliac artery aneurysm infection lesions, may be an effective solution to control pseudoaneurysm infection and rupture. CLINICAL IMPACT: Previous Brucella-associated aorto-iliac artery aneurysms have been limited to case reports. This study significantly increased the number of Brucella-associated aorto-iliac aneurysms by 19.7% (14/71) and extended the follow-up to 3 years. In this retrospective study of 14 patients with Brucella-associated aorto-iliac aneurysms treated endovascularly with fibrin sealant and gentamicin for sac filling and targeted administration to infection-related aneurysms, there were no aneurysm-related deaths or infection-related complications and may be an effective solution for controlling aneurysm infection and rupture. And, this approach is an attractive treatment for moving away from long-term dependence on antibiotics but still needs further evaluation.

Outcomes of Castor Single-Branched Stent Graft for Reconstruction of Multiple Supra-Aortic Branches in Aortic Arch Disease.

PURPOSE: To report the outcomes of a combination of Castor single-branched stent grafts with other techniques for the reconstruction of multiple supra-aortic branches in aortic arch disease. MATERIALS AND METHODS: Between December 2019 and December 2021, 20 patients with aortic arch disease underwent thoracic endovascular aortic repair (TEVAR) at our institution using a Castor single-branched stent graft combined with the fenestration, chimney, or bypass techniques. Thoracic endovascular aortic repair is indicated for complicated or acute type B aortic dissection (TBAD), nonruptured aneurysms with a maximum aneurysm diameter >5.5 cm or showing rapidly expanded, ruptured, or threatened aneurysms, and penetrating aortic ulcers (PAUs) with a maximal aortic diameter >5.5 cm or with PAUs >10 mm deep or >20 mm in diameter. Preoperative, intraoperative, and postoperative clinical data were recorded. RESULTS: The median age of the patients was 56 (range=52-69 years) years, and 19 patients were men. Seven patients underwent the Castor single-branched stent graft and left common carotid artery (LCCA) chimney technique, 8 patients underwent the Castor single-branched stent graft and fenestration technique, and 5 patients underwent the Castor single-branched stent graft and bypass technique. The technical success rate was 100%. Major adverse events included 2 endoleaks, 1 spinal cord ischemia, and 1 early-stage retrograde type A aortic dissection. No cerebral stroke-related complications were observed. The mortality rate was 10% (2/20 patients). One patient with thoracic aortic aneurysm (TAA) died because of a sudden decrease in oxygen saturation and blood pressure after surgery. Relatives declined autopsy, and the cause of death was not determined. Another patient died of a retrograde type A dissection after surgery. The median follow-up period was 6 months (range=3.5-12 months). During follow-up, 1 patient with type I endoleak underwent thoracotomy again after a year. The remaining patients recovered well. CONCLUSIONS: The combination of a Castor single-branched stent graft with fenestration, chimney, or bypass techniques may be an effective treatment for preserving multiple supra-aortic branches in aortic arch disease. CLINICAL IMPACT: This study introduced three methods of reconstruction of multiple supra-aortic branches using a Castor single-branched stent graft (Castor single-branched stent graft combined with fenestration, chimney, or bypass technique) and analysed their advantages and shortcomings to provide experience for the future treatment of aortic arch diseases.

Heterogeneous temporal representation for diabetic blood glucose prediction.

Background and aims: Blood glucose prediction (BGP) has increasingly been adopted for personalized monitoring of blood glucose levels in diabetic patients, providing valuable support for physicians in diagnosis and treatment planning. Despite the remarkable success achieved, applying BGP in multi-patient scenarios remains problematic, largely due to the inherent heterogeneity and uncertain nature of continuous glucose monitoring (CGM) data obtained from diverse patient profiles. Methodology: This study proposes the first graph-based Heterogeneous Temporal Representation (HETER) network for multi-patient Blood Glucose Prediction (BGP). Specifically, HETER employs a flexible subsequence repetition method (SSR) to align the heterogeneous input samples, in contrast to the traditional padding or truncation methods. Then, the relationships between multiple samples are constructed as a graph and learned by HETER to capture global temporal characteristics. Moreover, to address the limitations of conventional graph neural networks in capturing local temporal dependencies and providing linear representations, HETER incorporates both a temporally-enhanced mechanism and a linear residual fusion into its architecture. Results: Comprehensive experiments were conducted to validate the proposed method using real-world data from 112 patients in two hospitals, comparing it with five well-known baseline methods. The experimental results verify the robustness and accuracy of the proposed HETER, which achieves the maximal improvement of 31.42%, 27.18%, and 34.85% in terms of MAE, MAPE, and RMSE, respectively, over the second-best comparable method. Discussions: HETER integrates global and local temporal information from multi-patient samples to alleviate the impact of heterogeneity and uncertainty. This method can also be extended to other clinical tasks, thereby facilitating efficient and accurate capture of crucial pattern information in structured medical data.

Plasma microRNAs as potential biomarkers in diagnosis of acute venous thromboembolism.

OBJECTIVE: To assess the potential use of plasma microRNAs (miRNAs) in diagnosis of acute venous thromboembolism (VTE). METHODS: Using BGISEQ-500 sequencing technology, we analyzed the miRNA profile of paired plasma samples from the acute and chronic phases of four patients with unprovoked VTE. Using real-time quantitative polymerase chain reaction (RT-qPCR), we verified nine upregulated named miRNAs in the acute phase in the plasma samples of 54 patients with acute VTE and 39 controls. We then compared the relative expression of the 9 candidate miRNAs between the acute VTE and control group, and plotted the receiver operating characteristic (ROC) curves of the differentially expressed miRNAs. We chose the miRNA with the greatest area under curve (AUC) to evaluate the effect of miRNA on coagulation and platelet function in the plasma samples of 5 healthy volunteers. RESULTS: The plasma levels of miR-374b-3p, miR-660-5p, miR-378a-3p, miR-425-5p, miR-3613-5p, miR-130b-3p, miR-183-5p, and miR-103b were higher in patients with acute VTE than in the controls, with AUCs of 0.6776, 0.6614, 0.6648, 0.6885, 0.8048, 0.6871, 0.7298, and 0.7498, respectively, and P values of 0.0036, 0.0081, 0.0069, 0.0020,<0.0001, 0.0022, 0.0002, and < 0.0001, respectively. There were no significant differences in miR-193b-5p level between the acute VTE group and the control group. Fibrinogen (Fib), thrombin- antithrombin complex (TAT), tissue plasminogen activator-inhibitor complex (t-PAIC), and TAT/plasmin-α2-plasmin inhibitor complex (PIC) were decreased in the miR-3613-5p group when compared with the control group (P < 0.05) and the mean platelet aggregation rate was increased in the miR-3613 group (P < 0.05). CONCLUSION: miRNAs can be potential biomarkers for diagnosing acute VTE, and miR-3613-5p may be involved in the formation, coagulation, and platelet functions in acute VTE.

Multi-Physical Field Simulation of Cracking during Crystal Growth by Bridgman Method.

Crystal materials are prone to cracking during growth, which is a key problem leading to slow growth and difficulty in forming large-size crystals. In this study, based on the commercial finite element software COMSOL Multiphysics, the transient finite element simulation of the multi-physical field, including fluid heat transfer-phase transition-solid equilibrium-damage coupling behaviors, is performed. The phase-transition material properties and maximum tensile strain damage variables are customized. Using the re-meshing technique, the crystal growth and damage are captured. The results show the following: The convection channel at the bottom of the Bridgman furnace greatly influences the temperature field inside the furnace, and the temperature gradient field significantly influences the solidification and cracking behaviors during crystal growth. The crystal solidifies faster when it enters the higher-temperature gradient region and is prone to cracking. The temperature field inside the furnace needs to be properly adjusted so that the crystal temperature decreases relatively uniformly and slowly during the growth process to avoid crack formation. In addition, the crystal growth orientation also significantly affects the nucleation and growth direction of cracks. Crystals grown along the a-axis tend to form long cracks starting from the bottom and growing vertically, while crystals grown along the c-axis induce the laminar cracks from the bottom in a horizontal direction. The numerical simulation framework of the damage during crystal growth, which can accurately simulate the process of crystal growth and crack evolution and can be used to optimize the temperature field and crystal growth orientation in the Bridgman furnace cavity, is a reliable method to solve the crystal cracking problem.

Incidence and Clinical Features of Venous Thromboembolism in Inpatients with Mental Illness.

AIMS: We investigated the incidence and clinical features of venous thromboembolism (VTE) in inpatients with mental illnesses. METHODS: We retrospectively analyzed records of inpatients with mental illnesses and confirmed VTE at The First Hospital of Hebei Medical University between August 2018 and July 2022. We recorded demographic characteristics, psychosis-related conditions, and thrombus distribution. RESULTS: Among 12939 patients diagnosed with mental illness, 156 (1.21%) presented with VTE at the first visit or during the disease course. Crude VTE incidence varied significantly across mental illnesses, being highest in patients with organic mental disorders (5.20%), followed by emotional disorders (1.10%), and others (P < 0.001). Distal and proximal deep venous thromboses (DVT) occurred in 79.17% and 20.84% of patients, respectively. The Hamilton Depression Scale (HAMD) score was higher in patients with proximal DVT than in those with distal DVT (P < 0.001). On multivariate analysis, the HAMD score (odds ratio [OR] 1.173, confidence interval [CI] 1.100-1.251, P＜0.001) was a risk factor and the Hamilton Anxiety Scale (HAMA) (OR 0.862, CI 0.796-0.934, P＜0.001), a protective factor against DVT progression. CONCLUSION: VTE is not rare in patients with mental illnesses and is most commonly associated with organic mental disorders. Psychosis-related DVT typically shows a significantly high incidence of distal DVT. Prevention and early treatment in patients with severe depression and distal DVT can prevent DVT aggravation.

Uncorrected Preoperative Infection Causing the Death of a Patient with a Thoracic Aortic Aneurysm.

Background: A thoracic aortic aneurysm (TAA) is a known condition seen in cardiovascular practice. A TAA rupture and postoperative infection may result in death. Preoperative infections leading to death are extremely rare. Case Study: A 62-year-old Chinese female was admitted to The First Hospital of Hebei Medical University with a two-day history of abdominal pain. She was diagnosed with a TAA rupture and underwent immediate surgery. The preoperative urine analysis indicated that the positive bacteria and white blood cell count suggested a urinary tract bacterial infection. The patient was administered the empiric antibiotics, cefazolin; however, her blood pressure continued to drop during the perioperative period and she died of uncorrectable acidosis 8 h after the operation. On the second day after death, both the blood and urine cultures were positive for Pseudomonas aeruginosa. Conclusion: Given that this patient with a TAA rupture died of uncorrected acidosis caused by preoperative infection, it is important to evoke the diagnosis in the context of TAA. Routine laboratory indicators are valuable factors for surgeons and physicians in assessing a patient's condition and improving their prognosis.

Midterm Outcomes of Endovascular Therapy for TASC II D Femoropopliteal Lesions with Critical Limb Ischemia: A Retrospective Analysis.

BACKGROUND: This study evaluated the midterm results of endovascular therapy (EVT) for Trans-Atlantic Inter-Society (TASC) II D femoropopliteal lesions in patients with critical limb ischemia (CLI). METHODS: Fifty seven limbs of 54 patients with CLI due to TASC II D femoropopliteal lesions who underwent EVT at the First Hospital of Hebei Medical University were retrospectively analysed in a single-centre, observational study. The patient characteristics, endovascular procedural details, freedom from target lesion revascularization (TLR), patency rates, ulcer healing rate, and limb salvage rate were accessed. RESULTS: The patients' mean age was 68.2 ± 8.2 years. All patients were treated by EVT. The final technical success rate was 98.2% (56/57). There were 23 cases of pain at rest, 18 cases of ulcer, and 15 cases of gangrene. The median length of the treated segment was 286 ± 42 mm (56/56) and the mean number of stents placed per patient was 2.0 ± 0.8 (49/56). The postoperative ankle-brachial index was significantly higher than that of the preoperative ankle-brachial index (P < 0.05). The perioperative complication rate was 10.7% (6/56). The restenosis or occlusion rate was 44.6% (25/56). The estimated rates of freedom from TLR at 1 year, 2 years, and 3 years were 86.8%, 67.0%, and 62.5%, respectively. A univariate analysis showed that predictors of freedom from TLR were the number of runoff vessels, length of the lesion, and complexity of the lesion, while predictors for restenosis or occlusion were the length and the complexity of the lesion. The ulcer healing rate was 93.8%. The limb salvage rates were 76.4%, 74.4%, and 70.9% at 1, 2, and 3 years after treatment, respectively. CONCLUSIONS: The midterm outcomes of EVT for TASC II D femoropopliteal lesions in patients with CLI indicated that this treatment approach is safe and effective and is clinically applicable.

Inherited and acquired causes renal vein thrombosis in an 11-year-old boy who was relieved after piperacillin-tazobactam and rivaroxaban treatment: a case report.

Background: Physiological hypercoagulability is a well-known condition in older populations, whereas thrombosis, especially in renal veins, is a rare occurrence in teenagers. This paper presents a pediatric case of renal venous infarction and thrombosis. Case Description: We report the case of an 11-year-old Chinese boy who presented with low back discomfort and was afraid to walk. Computed tomography (CT) revealed thrombosis in his renal veins and inferior vena cava. He was being treated for severe refractory mycoplasma pneumoniae pneumonia (MPP). He was treated with rivaroxaban and urokinase for thrombosis, and azithromycin for MPP. On day 2 after admission, his symptoms improved. Therefore, the dosage of rivaroxaban was decreased from 10 to 5 mg twice per day. On day 3 after admission, enhanced CT revealed new thromboses in the bilateral pulmonary trunks and arteries, inferior cava, right renal veins, bilateral common iliac veins, and internal iliac vein. The ultrasonography showed a strip hypoecho at the pulmonary artery bifurcation. All the above imaging suggested that antithrombotic therapy was insufficient. His plasma antithrombin (AT) III activity remained consistently low during hospitalization. The family history was re-examined and revealed that both his father and grandfather had experienced spontaneous pulmonary thrombosis around the age of 30. He was diagnosed with acquired and inherited thrombosis and inherited AT III deficiency. Following a medication regimen of piperacillin-tazobactam for 1 week and rivaroxaban (10 mg, twice daily), he was discharged and no thrombosis and other side effects or complications occurred in the following 3 months. Conclusions: This is a rare case of a teenager with inherited and acquired hypercoagulability. For refractory MPP pediatric patients with thrombosis, clinicians should consider whether hereditary factors, such as inherited AT III deficiency, are involved in thrombosis.

Promotion of angiogenesis in vitro by Astragalus polysaccharide via activation of TLR4 signaling pathway.

During the implantation of functional tissue-engineered constructs for treating bone defects, a functional vascular network is critical for the survival of the construct. One strategy to achieve rapid angiogenesis for this application is the co-culture of outgrowth endothelial cells (OECs) and primary human osteoblasts (POBs) within a scaffold prior to implantation. In the present study, we aim to investigate whether Astragalus polysaccharide (APS) promotes angiogenesis or vascularization via the TLR4 signaling pathway in a co-culture of OECs and POBs. The co-cultures were treated with various concentrations of APS for 24 h and, subsequently, another 7 days, followed by CD31 staining and analysis of micro-vessel-formation areas using software. Additionally, APS (0.4 mg/ml for 24 h) was added to monocultures of OECs or POBs for evaluating proliferation, apoptosis, angiogenesis, osteogenesis, TLR4 signaling pathway, and inflammatory cytokine release. We found that APS promoted angiogenesis in the co-culture at the optimal concentration of 0.4 mg/ml. TLR4 activation by APS up-regulated the expression level of TLR4/MyD88 and enhanced angiogenesis and osteogenesis in monocultures of OECs and POBs. The levels of E-selectin adhesion molecules, three cytokines (IL-6, TNF-α, and IFN-γ), and VEGF and PDGF-BB, which can induce angiogenesis, increased significantly (p < .05) following APS treatment. Therefore, APS appears to promote angiogenesis and ossification in the co-culture system via the TLR4 signaling pathway. PRACTICAL APPLICATIONS: This study demonstrates that APS may promote angiogenesis and osteocyte proliferation in OEC and POB co-culture systems through the MyD88-dependent TLR4 signaling pathway. APS might represent a potential therapeutic strategy in tissue-engineered bone implantation for the treatment of large bone defects; additionally, it has the advantage of safety, as it exhibits low or no side effects. In the future, it is expected to be used in vitro for the construction of tissue-engineered bone and in vivo after implantation in patients with bone defects for promoting rapid vascularization and ossification of tissue-engineered bone and early fusion with the recipient's bone. In addition, as a food additive, Astragalus membranaceus can be used as a tonic material in patients recovering from a fracture for promoting blood-vessel formation at the fracture site and fracture recovery. Combining traditional Chinese medicine with tissue engineering can provide further strategies for promoting the development of regenerative medicine.

Development and validation of a feature extraction-based logical anthropomorphic diagnostic system for early gastric cancer: A case-control study.

Background: Prompt diagnosis of early gastric cancer (EGC) is crucial for improving patient survival. However, most previous computer-aided-diagnosis (CAD) systems did not concretize or explain diagnostic theories. We aimed to develop a logical anthropomorphic artificial intelligence (AI) diagnostic system named ENDOANGEL-LA (logical anthropomorphic) for EGCs under magnifying image enhanced endoscopy (M-IEE). Methods: We retrospectively collected data for 692 patients and 1897 images from Renmin Hospital of Wuhan University, Wuhan, China between Nov 15, 2016 and May 7, 2019. The images were randomly assigned to the training set and test set by patient with a ratio of about 4:1. ENDOANGEL-LA was developed based on feature extraction combining quantitative analysis, deep learning (DL), and machine learning (ML). 11 diagnostic feature indexes were integrated into seven ML models, and an optimal model was selected. The performance of ENDOANGEL-LA was evaluated and compared with endoscopists and sole DL models. The satisfaction of endoscopists on ENDOANGEL-LA and sole DL model was also compared. Findings: Random forest showed the best performance, and demarcation line and microstructures density were the most important feature indexes. The accuracy of ENDOANGEL-LA in images (88.76%) was significantly higher than that of sole DL model (82.77%, p = 0.034) and the novices (71.63%, p<0.001), and comparable to that of the experts (88.95%). The accuracy of ENDOANGEL-LA in videos (87.00%) was significantly higher than that of the sole DL model (68.00%, p<0.001), and comparable to that of the endoscopists (89.00%). The accuracy (87.45%, p<0.001) of novices with the assistance of ENDOANGEL-LA was significantly improved. The satisfaction of endoscopists on ENDOANGEL-LA was significantly higher than that of sole DL model. Interpretation: We established a logical anthropomorphic system (ENDOANGEL-LA) that can diagnose EGC under M-IEE with diagnostic theory concretization, high accuracy, and good explainability. It has the potential to increase interactivity between endoscopists and CADs, and improve trust and acceptability of endoscopists for CADs. Funding: This work was partly supported by a grant from the Hubei Province Major Science and Technology Innovation Project (2018-916-000-008) and the Fundamental Research Funds for the Central Universities (2042021kf0084).

A deep learning-based system for real-time image reporting during esophagogastroduodenoscopy: a multicenter study.

BACKGROUND AND STUDY AIMS: Endoscopic reports are essential for the diagnosis and follow-up of gastrointestinal diseases. This study aimed to construct an intelligent system for automatic photo documentation during esophagogastroduodenoscopy (EGD) and test its utility in clinical practice. PATIENTS AND METHODS: Seven convolutional neural networks trained and tested using 210,198 images were integrated to construct the endoscopic automatic image reporting system (EAIRS). We tested its performance through man-machine comparison at three levels: internal, external, and prospective test. Between May 2021 and June 2021, patients undergoing EGD at Renmin Hospital of Wuhan University were recruited. The primary outcomes were accuracy for capturing anatomical landmarks, completeness for capturing anatomical landmarks, and detected lesions. RESULTS: The EAIRS outperformed endoscopists in retrospective internal and external test. A total of 161 consecutive patients were enrolled in the prospective test. The EAIRS achieved an accuracy of 95.2% in capturing anatomical landmarks in the prospective test. It also achieved higher completeness on capturing anatomical landmarks compared with endoscopists: (93.1% vs. 88.8%), and was comparable to endoscopists on capturing detected lesions: (99.0% vs. 98.0%). CONCLUSIONS: The EAIRS can generate qualified image reports and could be a powerful tool for generating endoscopic reports in clinical practice.

Crocin ameliorates atherosclerosis by promoting the reverse cholesterol transport and inhibiting the foam cell formation via regulating PPARγ/LXR-α.

Crocin (CRO) is feasible in alleviating atherosclerosis (AS), the mechanism of which was therefore explored in the study. High-fat diet (HFD)-induced apolipoprotein E-deficient (ApoE-/-) mice and lysophosphatidic acid (LPA)-treated macrophages received CRO treatment. Treated macrophage viability was determined via MTT assay. In both murine and macrophage, the lipid level and total Cholesterol/Cholesteryl l Ester (TC/CE) levels were quantified by oil-red-O staining and ELISA, respectively. Lipid droplet, aortic plaque formation and collagen deposition were detected via Oil-red-O staining, hematoxylin-eosin staining and Masson staining, respectively. Liver X Receptor-α (LXR-α), Peroxisome Proliferator-Activated Receptor γ (PPARγ), CD68, PCSK9, CD36, ATP Binding Cassette Subfamily A Member 1 (ABCA1), phosphorylated (p)-AKT, and AKT expressions were detected via Western blot, the former three also being detected using Immunohistochemistry and the first being measured by qRT-PCR. CRO decreased HFD-induced weight gain, ameliorated the abnormal serum lipid levels of HFD-treated mice, and inhibited aortic plaque formation and lipid deposition, and increased collagen fibers, with upregulated high-density lipoprotein-cholesterol (HDL-C) and downregulated TC and low-density lipoprotein-cholesterol (LDL-C). CRO alleviated the HFD-induced upregulations of CD68, PCSK9 and CD36 as well as downregulations of PPARγ/LXR-α, ABCA1 and AKT phosphorylation. In LPA-treated macrophages, CRO alone exerted no effect on the viability yet inhibited the lipid droplets formation and downregulated TC/CE levels. Silent LXR-α reversed the effect of CRO on the lipid droplets formation and levels of lipid metabolism-related factors. CRO ameliorated AS by inhibiting foam cells formation and promoting reverse cholesterol transport via PPARγ/LXR-α.

Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos).

BACKGROUND AND AIMS: White-light endoscopy (WLE) is the most pivotal tool to detect gastric cancer in an early stage. However, the skill among endoscopists varies greatly. Here, we aim to develop a deep learning-based system named ENDOANGEL-LD (lesion detection) to assist in detecting all focal gastric lesions and predicting neoplasms by WLE. METHODS: Endoscopic images were retrospectively obtained from Renmin Hospital of Wuhan University (RHWU) for the development, validation, and internal test of the system. Additional external tests were conducted in 5 other hospitals to evaluate the robustness. Stored videos from RHWU were used for assessing and comparing the performance of ENDOANGEL-LD with that of experts. Prospective consecutive patients undergoing upper endoscopy were enrolled from May 6, 2021 to August 2, 2021 in RHWU to assess clinical practice applicability. RESULTS: Over 10,000 patients undergoing upper endoscopy were enrolled in this study. The sensitivities were 96.9% and 95.6% for detecting gastric lesions and 92.9% and 91.7% for diagnosing neoplasms in internal and external patients, respectively. In 100 videos, ENDOANGEL-LD achieved superior sensitivity and negative predictive value for detecting gastric neoplasms from that of experts (100% vs 85.5% ± 3.4% [P = .003] and 100% vs 86.4% ± 2.8% [P = .002], respectively). In 2010 prospective consecutive patients, ENDOANGEL-LD achieved a sensitivity of 92.8% for detecting gastric lesions with 3.04 ± 3.04 false positives per gastroscopy and a sensitivity of 91.8% and specificity of 92.4% for diagnosing neoplasms. CONCLUSIONS: Our results show that ENDOANGEL-LD has great potential for assisting endoscopists in screening gastric lesions and suspicious neoplasms in clinical work. (Clinical trial registration number: ChiCTR2100045963.).

Deep learning system compared with expert endoscopists in predicting early gastric cancer and its invasion depth and differentiation status (with videos).

BACKGROUND AND AIMS: We aimed to develop and validate a deep learning-based system that covers various aspects of early gastric cancer (EGC) diagnosis, including detecting gastric neoplasm, identifying EGC, and predicting EGC invasion depth and differentiation status. Herein, we provide a state-of-the-art comparison of the system with endoscopists using real-time videos in a nationwide human-machine competition. METHODS: This multicenter, prospective, real-time, competitive comparative, diagnostic study enrolled consecutive patients who received magnifying narrow-band imaging endoscopy at the Peking University Cancer Hospital from June 9, 2020 to November 17, 2020. The offline competition was conducted in Wuhan, China, and the endoscopists and the system simultaneously read patients' videos and made diagnoses. The primary outcomes were sensitivity in detecting neoplasms and diagnosing EGCs. RESULTS: One hundred videos, including 37 EGCs and 63 noncancerous lesions, were enrolled; 46 endoscopists from 44 hospitals in 19 provinces in China participated in the competition. The sensitivity rates of the system for detecting neoplasms and diagnosing EGCs were 87.81% and 100%, respectively, significantly higher than those of endoscopists (83.51% [95% confidence interval [CI], 81.23-85.79] and 87.13% [95% CI, 83.75-90.51], respectively). Accuracy rates of the system for predicting EGC invasion depth and differentiation status were 78.57% and 71.43%, respectively, slightly higher than those of endoscopists (63.75% [95% CI, 61.12-66.39] and 64.41% [95% CI, 60.65-68.16], respectively). CONCLUSIONS: The system outperformed endoscopists in identifying EGCs and was comparable with endoscopists in predicting EGC invasion depth and differentiation status in videos. This deep learning-based system could be a powerful tool to assist endoscopists in EGC diagnosis in clinical practice.

Real-time use of artificial intelligence for diagnosing early gastric cancer by magnifying image-enhanced endoscopy: a multicenter diagnostic study (with videos).

BACKGROUND AND AIMS: Endoscopy is a pivotal method for detecting early gastric cancer (EGC). However, skill among endoscopists varies greatly. Here, we proposed a deep learning-based system named ENDOANGEL-ME to diagnose EGC in magnifying image-enhanced endoscopy (M-IEE). METHODS: M-IEE images were retrospectively obtained from 6 hospitals in China, including 4667 images for training and validation, 1324 images for internal tests, and 4702 images for external tests. One hundred eighty-seven stored videos from 2 hospitals were used to evaluate the performance of ENDOANGEL-ME and endoscopists and to assess the effect of ENDOANGEL-ME on improving the performance of endoscopists. Prospective consecutive patients undergoing M-IEE were enrolled from August 17, 2020 to August 2, 2021 in Renmin Hospital of Wuhan University to assess the applicability of ENDOANGEL-ME in clinical practice. RESULTS: A total of 3099 patients undergoing M-IEE were enrolled in this study. The diagnostic accuracy of ENDOANGEL-ME for diagnosing EGC was 88.44% and 90.49% in internal and external images, respectively. In 93 internal videos, ENDOANGEL-ME achieved an accuracy of 90.32% for diagnosing EGC, significantly superior to that of senior endoscopists (70.16% ± 8.78%). In 94 external videos, with the assistance of ENDOANGEL-ME, endoscopists showed improved accuracy and sensitivity (85.64% vs 80.32% and 82.03% vs 67.19%, respectively). In 194 prospective consecutive patients with 251 lesions, ENDOANGEL-ME achieved a sensitivity of 92.59% (25/27) and an accuracy of 83.67% (210/251) in real clinical practice. CONCLUSIONS: This multicenter diagnostic study showed that ENDOANGEL-ME can be well applied in the clinical setting. (Clinical trial registration number: ChiCTR2000035116.).

Two New Methods of Supine Venographically Guided Popliteal Vein Puncture: A Retrospective Study.

OBJECTIVE: Presently, the prone position is necessary for popliteal vein puncture access, but it makes the patients uncomfortable and does not allow traditional femoral or jugular access. To address these deficiencies, this study introduces two new methods, anterior and medial access carried out in the supine position. METHODS: Venous interventions with punctures in the popliteal vein of 120 limbs in 97 patients were performed during the period from February 2017 to April 2019. After puncture, venographic guidance was achieved by dorsal vein injection of contrast medium. Interventional therapy was performed after puncture and insertion of the introducer sheath. RESULTS: In all, 120 limbs were punctured in the popliteal vein, with technical success in 118 (98.3% in total) cases: 100%, 96.1%, and 100% successful punctures in, respectively, 32 anterior, 49 medial, and 37 posterior access cases. A comparison of the three groups revealed that the fluoroscopy time and duration of puncture were longer in the medial and anterior access groups than in the posterior access group. The rate of intra-operative and post-operative complications was 7.5% (9/120), with no statistically significant difference between the three access groups. Compared with the pre-operative median score of 2.5, the post-operative SVS (Society of Vascular Surgery) score of the popliteal vein was reduced to 1.5 in the anterior and 0.5 in the medial groups. CONCLUSION: Medial and anterior puncture of the popliteal vein in the supine position can be used as a safe alternative in venous endovascular therapy. The two new methods can mitigate frailty or respiratory problems resulting from the prone position and facilitate traditional femoral and jugular access.

Effect of a deep learning-based system on the miss rate of gastric neoplasms during upper gastrointestinal endoscopy: a single-centre, tandem, randomised controlled trial.

BACKGROUND: White light endoscopy is a pivotal first-line tool for the detection of gastric neoplasms. However, gastric neoplasms can be missed during upper gastrointestinal endoscopy due to the subtle nature of these lesions and varying skill among endoscopists. Here, we aimed to evaluate the effect of an artificial intelligence (AI) system designed to detect focal lesions and diagnose gastric neoplasms on reducing the miss rate of gastric neoplasms in clinical practice. METHODS: This single-centre, randomised controlled, tandem trial was done at Renmin Hospital of Wuhan University, China. We recruited consecutive patients (≥18 years old) undergoing routine upper gastrointestinal endoscopy for screening, surveillance, or investigation of symptoms. Same-day tandem upper gastrointestinal endoscopy was done where patients first underwent either AI-assisted (AI-first) or routine (routine-first) white light endoscopy, followed immediately by the other procedure, with targeted biopsies for all detected lesions taken at the end of the second examination. Patients were randomly assigned (1:1) to the AI-first or routine-first group using a computer-generated random numerical series and block randomisation (block size of four). Endoscopists were not blinded to randomisation status, whereas patients and pathologists were. The primary endpoint was the miss rate of gastric neoplasms and the analysis was done per protocol. This trial is registered with the Chinese Clinical Trial Registry, ChiCTR2000034453, and has been completed. FINDINGS: Between July 6, 2020, and Dec 11, 2020, 907 patients were randomly assigned to the AI-first group and 905 to the routine-first group. The gastric neoplasm miss rate was significantly lower in the AI-first group than in the routine-first group (6·1%, 95% CI 1·6-17·9 [3/49] vs 27·3%, 15·5-43·0 [12/44]; relative risk 0·224, 95% CI 0·068-0·744; p=0·015). The only reported adverse event was bleeding from a target lesion after biopsy. INTERPRETATION: The use of an AI system during upper gastrointestinal endoscopy significantly reduced the gastric neoplasm miss rate. AI-assisted endoscopy has the potential to improve the yield of gastric neoplasms by endoscopists. FUNDING: The Project of Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision and the Hubei Province Major Science and Technology Innovation Project.

A Novel Model Based on Deep Convolutional Neural Network Improves Diagnostic Accuracy of Intramucosal Gastric Cancer (With Video).

BACKGROUND AND AIMS: Prediction of intramucosal gastric cancer (GC) is a big challenge. It is not clear whether artificial intelligence could assist endoscopists in the diagnosis. METHODS: A deep convolutional neural networks (DCNN) model was developed via retrospectively collected 3407 endoscopic images from 666 gastric cancer patients from two Endoscopy Centers (training dataset). The DCNN model's performance was tested with 228 images from 62 independent patients (testing dataset). The endoscopists evaluated the image and video testing dataset with or without the DCNN model's assistance, respectively. Endoscopists' diagnostic performance was compared with or without the DCNN model's assistance and investigated the effects of assistance using correlations and linear regression analyses. RESULTS: The DCNN model discriminated intramucosal GC from advanced GC with an AUC of 0.942 (95% CI, 0.915-0.970), a sensitivity of 90.5% (95% CI, 84.1%-95.4%), and a specificity of 85.3% (95% CI, 77.1%-90.9%) in the testing dataset. The diagnostic performance of novice endoscopists was comparable to those of expert endoscopists with the DCNN model's assistance (accuracy: 84.6% vs. 85.5%, sensitivity: 85.7% vs. 87.4%, specificity: 83.3% vs. 83.0%). The mean pairwise kappa value of endoscopists was increased significantly with the DCNN model's assistance (0.430-0.629 vs. 0.660-0.861). The diagnostic duration reduced considerably with the assistance of the DCNN model from 4.35s to 3.01s. The correlation between the perseverance of effort and diagnostic accuracy of endoscopists was diminished using the DCNN model (r: 0.470 vs. 0.076). CONCLUSIONS: An AI-assisted system was established and found useful for novice endoscopists to achieve comparable diagnostic performance with experts.

Evaluation of the effects of an artificial intelligence system on endoscopy quality and preliminary testing of its performance in detecting early gastric cancer: a randomized controlled trial.

BACKGROUND: Esophagogastroduodenoscopy (EGD) is a prerequisite for detecting upper gastrointestinal lesions especially early gastric cancer (EGC). An artificial intelligence system has been shown to monitor blind spots during EGD. In this study, we updated the system (ENDOANGEL), verified its effectiveness in improving endoscopy quality, and pretested its performance in detecting EGC in a multicenter randomized controlled trial. METHODS: ENDOANGEL was developed using deep convolutional neural networks and deep reinforcement learning. Patients undergoing EGD in five hospitals were randomly assigned to the ENDOANGEL-assisted group or to a control group without use of ENDOANGEL. The primary outcome was the number of blind spots. Secondary outcomes included performance of ENDOANGEL in predicting EGC in a clinical setting. RESULTS: 1050 patients were randomized, and 498 and 504 patients in the ENDOANGEL and control groups, respectively, were analyzed. Compared with the control group, the ENDOANGEL group had fewer blind spots (mean 5.38 [standard deviation (SD) 4.32] vs. 9.82 [SD 4.98]; P < 0.001) and longer inspection time (5.40 [SD 3.82] vs. 4.38 [SD 3.91] minutes; P < 0.001). In the ENDOANGEL group, 196 gastric lesions with pathological results were identified. ENDOANGEL correctly predicted all three EGCs (one mucosal carcinoma and two high grade neoplasias) and two advanced gastric cancers, with a per-lesion accuracy of 84.7 %, sensitivity of 100 %, and specificity of 84.3 % for detecting gastric cancer. CONCLUSIONS: In this multicenter study, ENDOANGEL was an effective and robust system to improve the quality of EGD and has the potential to detect EGC in real time.