Diagnosis of intracranial aneurysms by computed tomography angiography using deep learning-based detection and segmentation.

BACKGROUND: Detecting and segmenting intracranial aneurysms (IAs) from angiographic images is a laborious task. OBJECTIVE: To evaluates a novel deep-learning algorithm, named vessel attention (VA)-Unet, for the efficient detection and segmentation of IAs. METHODS: This retrospective study was conducted using head CT angiography (CTA) examinations depicting IAs from two hospitals in China between 2010 and 2021. Training included cases with subarachnoid hemorrhage (SAH) and arterial stenosis, common accompanying vascular abnormalities. Testing was performed in cohorts with reference-standard digital subtraction angiography (cohort 1), with SAH (cohort 2), acquired outside the time interval of training data (cohort 3), and an external dataset (cohort 4). The algorithm's performance was evaluated using sensitivity, recall, false positives per case (FPs/case), and Dice coefficient, with manual segmentation as the reference standard. RESULTS: The study included 3190 CTA scans with 4124 IAs. Sensitivity, recall, and FPs/case for detection of IAs were, respectively, 98.58%, 96.17%, and 2.08 in cohort 1; 95.00%, 88.8%, and 3.62 in cohort 2; 96.00%, 93.77%, and 2.60 in cohort 3; and, 96.17%, 94.05%, and 3.60 in external cohort 4. The segmentation accuracy, as measured by the Dice coefficient, was 0.78, 0.71, 0.71, and 0.66 for cohorts 1-4, respectively. VA-Unet detection recall and FPs/case and segmentation accuracy were affected by several clinical factors, including aneurysm size, bifurcation aneurysms, and the presence of arterial stenosis and SAH. CONCLUSIONS: VA-Unet accurately detected and segmented IAs in head CTA comparably to expert interpretation. The proposed algorithm has significant potential to assist radiologists in efficiently detecting and segmenting IAs from CTA images.

The incidence and predictors of in-stent stenosis after pipeline flow-diverter stenting for intracranial aneurysm treatment.

Background and purpose: Data on in-stent stenosis (ISS) following the flow diverter (FD) implantation method are scarce and inconsistent. In the present study, we sought to determine the incidence of ISS and identify the factors that predict its severity via the use of ordinal logistic regression. Methods: A retrospective review of our center's electronic database was conducted to identify all patients with intracranial aneurysms (IAs) who received pipeline embolization device (PED) implantation between 2016 and 2020. Patient demographics, aneurysm characteristics, procedural information, and clinical and angiographic outcomes were reviewed. ISS was quantitatively assessed on angiographic follow-ups and graded as mild (<25%), moderate (25-50%), or severe (>50%). Ordinal logistic regression was conducted to determine the predictors of stenosis severity. Results: A total of 240 patients with 252 aneurysms treated in 252 procedures were enrolled in this study. ISS has been detected in 135 (53.6%) lesions, with a mean follow-up time of 6.53 ± 3.26 months. The ISS was mild in 66 (48.9%) cases, moderate in 52 (38.5%) cases, and severe in 17 (12.6%) cases. All patients were asymptomatic, except for two of them with severe stenosis who presented with symptoms of acute cerebral thrombosis. Ordinal logistic regression identified that younger age and a longer procedure duration were independent predictors of a higher likelihood of ISS. Conclusion: ISS is a common angiographic finding after PED implantation for IAs and is presented as a largely benign course through long-term follow-up. Patients who were younger in age and had a longer procedure duration were found to be at a greater risk of developing ISS.

Alcohol flushing syndrome is significantly associated with intracranial aneurysm rupture in the Chinese Han population.

Objective: Although alcohol flushing syndrome (AFS) has been associated with various diseases, its association with intracranial aneurysm rupture (IAR) is unclear. We aimed to examine this association in the Chinese Han population. Methods: We retrospectively reviewed Chinese Han patients with intracranial aneurysms who were evaluated and treated at our institution between January 2020 and December 2021. AFS was determined using a semi-structured telephone interview. Clinical data and aneurysm characteristics were assessed. Univariate and multivariate logistic regression were conducted to determine independent factors associated with aneurysmal rupture. Results: A total of 1,170 patients with 1,059 unruptured and 236 ruptured aneurysms were included. The incidence of aneurysm rupture was significantly higher in patients without AFS (p < 0.001). Meanwhile, there was a significantly difference between the AFS and non-AFS group in habitual alcohol consumption (10.5 vs. 27.2%, p < 0.001). In the univariate analyses, AFS [odds ratio (OR) 0.49; 95% confidence interval (CI), 0.34-0.72] was significantly associated with IAR. In the multivariate analysis, AFS was an independent predictor of IAR (OR 0.50; 95%, CI, 0.35-0.71). Multivariate analysis revealed that AFS was an independent predictor of IAR in both habitual (OR 0.11; 95% CI, 0.03-0.45) and non-habitual drinkers (OR 0.69; 95% CI, 0.49-0.96). Conclusion: Alcohol flushing syndrome may be a novel clinical marker to assess the risk of IAR. The association between AFS and IAR exists independently of alcohol consumption. Further single nucleotide polymorphism testing and molecular biology studies are warranted.

Long-term outcomes and dynamic changes of in-stent stenosis after Pipeline embolization device treatment of intracranial aneurysms.

BACKGROUND: Flow diverters have revolutionized the treatment of intracranial aneurysms. However, the delayed complications associated with flow diverter use are unknown. OBJECTIVE: To evaluate the incidence, severity, clinical outcomes, risk factors, and dynamic changes associated with in-stent stenosis (ISS) after treatment with a Pipeline embolization device (PED). METHODS: Patients who underwent PED treatment between 2015 and 2020 were enrolled. The angiographic, clinical, and follow-up data of 459 patients were independently reviewed by four neuroradiologists to identify ISS. Binary logistic regression was conducted to determine ISS risk factors, and an ISS-time curve was established to demonstrate dynamic changes in ISS after PED implantation. RESULTS: Of the 459 treated patients, 69 (15.0%) developed ISS. At follow-up, nine patients (2.0%) with ISS demonstrated reversal, while 18 (3.9%) developed parental artery occlusion. A total of 380 patients (82.8%) achieved complete aneurysm occlusion (O'Kelly-Marotta grade D). Patients with posterior-circulation aneurysm (OR=2.895, 95% CI (1.732 to 4.838; P<0.001) or balloon angioplasty (OR=1.992, 95% CI 1.162 to 3.414; P=0.037) were more likely to develop ISS. Patients aged >54 years (OR=0.464, 95% CI 0.274 to 0.785; P=0.006) or with a body mass index of >28 kg/m2 (OR=0.427, 95% CI 0.184 to 0.991; P=0.026) had a lower ISS risk. Intimal hyperplasia initiated by PED placement peaked within 1 year after the procedure, rarely progressed after 12 months, and tended to reverse within 24 months. CONCLUSIONS: ISS is a common, benign, and self-limiting complication of PED implantation in the Chinese population.

Machine learning to predict in-stent stenosis after Pipeline embolization device placement.

Background: The Pipeline embolization device (PED) is a flow diverter used to treat intracranial aneurysms. In-stent stenosis (ISS) is a common complication of PED placement that can affect long-term outcome. This study aimed to establish a feasible, effective, and reliable model to predict ISS using machine learning methodology. Methods: We retrospectively examined clinical, laboratory, and imaging data obtained from 435 patients with intracranial aneurysms who underwent PED placement in our center. Aneurysm morphological measurements were manually measured on pre- and posttreatment imaging studies by three experienced neurointerventionalists. ISS was defined as stenosis rate >50% within the PED. We compared the performance of five machine learning algorithms (elastic net (ENT), support vector machine, Xgboost, Gaussian Naïve Bayes, and random forest) in predicting ISS. Shapley additive explanation was applied to provide an explanation for the predictions. Results: A total of 69 ISS cases (15.2%) were identified. Six predictors of ISS (age, obesity, balloon angioplasty, internal carotid artery location, neck ratio, and coefficient of variation of red cell volume distribution width) were identified. The ENT model had the best predictive performance with a mean area under the receiver operating characteristic curve of 0.709 (95% confidence interval [CI], 0.697-0.721), mean sensitivity of 77.9% (95% CI, 75.1-80.6%), and mean specificity of 63.4% (95% CI, 60.8-65.9%) in Monte Carlo cross-validation. Shapley additive explanation analysis showed that internal carotid artery location was the most important predictor of ISS. Conclusion: Our machine learning model can predict ISS after PED placement for treatment of intracranial aneurysms and has the potential to improve patient outcomes.

Protocol and Preliminary Results of the Establishment of Intracranial Aneurysm Database for Artificial Intelligence Application Based on CTA Images.

Background and Purpose: Unruptured intracranial aneurysms (UIAs) are increasingly being detected in clinical practice. Artificial intelligence (AI) has been increasingly used to assist diagnostic techniques and shows encouraging prospects. In this study, we reported the protocol and preliminary results of the establishment of an intracranial aneurysm database for AI application based on computed tomography angiography (CTA) images. Methods: Through a review of picture archiving and communication systems, we collected CTA images of patients with aneurysms between January 2010 and March 2021. The radiologists performed manual segmentation of all diagnosed aneurysms on subtraction CTA as the basis for automatic aneurysm segmentation. Then, AI will be applied to two stages of aneurysm treatment, namely, automatic aneurysm detection and segmentation model based on the CTA image and the aneurysm risk prediction model. Results: Three medical centers have been included in this study so far. A total of 3,190 cases of CTA examinations with 4,124 aneurysms were included in the database. All identified aneurysms from CTA images that enrolled in this study were manually segmented on subtraction CTA by six readers. We developed a structure of 3D-Unet for aneurysm detection and segmentation in CTA images. The algorithm was developed and tested using a total of 2,272 head CTAs with 2,938 intracranial aneurysms. The recall and false positives per case (FP/case) of this model for detecting aneurysms were 0.964 and 2.01, and the Dice values for aneurysm segmentation were 0.783. Conclusion: This study introduces the protocol and preliminary results of the establishment of the intracranial aneurysm database for AI applications based on CTA images. The establishment of a multicenter database based on CTA images of intracranial aneurysms is the basis for the application of AI in the diagnosis and treatment of aneurysms. In addition to segmentation, AI should have great potential for aneurysm treatment and management in the future.

Electroacupuncture at Zusanli (ST36), Guanyuan (CV4), and Qihai (CV6) Acupoints Regulates Immune Function in Patients with Sepsis via the PD-1 Pathway.

Objective: The present study is aimed at investigating the biochemical and clinical effects of electroacupuncture in patients with sepsis. Methods: Patients with sepsis treated at Guangdong Provincial Hospital of Chinese Medicine from July 2019 to December 2020 were included. Patients were randomly assigned to treatment with routine Western medicine (WM group) or treatment with Western medicine plus electroacupuncture based on Western medicine (EA group). Indices associated with immune function and clinical efficacy were determined before and at 3 and 5 days after treatment. Indicators of immune function included the percentage of T lymphocyte subsets, natural killer (NK) cells, and soluble programmed death protein 1 (sPD-1) levels. Indicators of clinical efficacy included infection-related indicators in whole blood; levels of tumor necrosis factor-α (TNF-α), C-reactive protein (CRP), and interferon-γ (INF-γ); and assessments using acute physiology and chronic health evaluation-II (APACHE-II) and sequential organ failure assessment (SOFA) scores. Results: Baseline data were not different between WM (N = 30) and EA groups (N = 30). At day 5 following treatment, the level of sPD-1 in the EA group was lower than that in the WM group. Proportions of CD3 + T lymphocytes, CD4 + T lymphocytes, and NK cells, the percentage of lymphocytes, and INF-γ levels in the EA group were significantly higher than those in the WM group. Compared with the WM group, the white blood cell count (WBC), percentage and count of neutrophils, ratio of neutrophils to lymphocytes, and levels of CRP and TNF-α were significantly decreased in the EA group 5 days after treatment. The APACHE-II score of the EA group was significantly lower than that of the WM group 5 days after treatment. Conclusion: Electroacupuncture may regulate the immune function of patients with sepsis through the PD-1 pathway to achieve an anti-inflammatory state and improve clinical symptoms.

Evaluation of the Efficacy and Safety of Chinese Herbal Injection Combined With Trimetazidine for Viral Myocarditis: A Network Meta-Analysis.

Background: Viral myocarditis (VMC) is a common emergency of cardiovascular disease. Current treatment for VMC includes the prohibition of exercise plus supportive and symptomatic treatment, given the lack of specific antiviral therapeutic options and insufficient evidence for the use of novel immunosuppressive therapies. Trimetazidine, a drug used to improve myocardial energy metabolism, is frequently used for the treatment of viral myocarditis. In China, Chinese herbal injections (CHIs) are often used in combination with trimetazidine. Therefore, we evaluate the efficacy and safety of CHI combined with trimetazidine in the treatment of VMC through the method of network meta-analysis. Methods: We searched PubMed, the Cochrane Library, Embase, China National Knowledge Infrastructure (CNKI), Wanfang Database, Chinese Scientific Journals Full-text Database (VIP), and China Biology Medicine Database (CBM) databases from inception to September 1, 2020, to identify eligible randomized controlled trials. The Cochrane risk of bias tool was used to assess the risk of bias among selected studies and the Stata 16.0 software was used to perform the network meta-analysis. Results: A total of 29 studies were included, representing data from 2,687 patients. The effectiveness rate, level of myocardial injury marker, and the adverse reaction rate were evaluated. Compared with conventional treatment or conventional treatment combined with trimetazidine, CHIs combined with trimetazidine appeared to have a better therapeutic effect, with higher effectiveness rate and better reduction of the levels of creatine kinase, creatine kinase-MB, and lactate dehydrogenase. Based on surface under the cumulative ranking, Shenmai injection combined with trimetazidine appeared to be superior in terms of effective rate, while Astragalus injection or Salviae miltiorrhizae and ligustrazine hydrochloride injection combined with trimetazidine appeared most effective in reducing myocardial injury markers. There was no significant difference in safety between the interventions. However, a lack of safety monitoring in some selected studies meant that the safety of some interventions could not be fully evaluated. Conclusion: CHIs combined with trimetazidine may have therapeutic value in the treatment of viral myocarditis, and Shenmai injection, Astragalus injection, and Salviae miltiorrhizae and ligustrazine hydrochloride injection may represent the most effective CHIs. Further clinical investigation is required to confirm these results.

Case report on a 32-year-old female with elevated serum creatinine levels and primary Sjögren's syndrome-chronic interstitial nephritis.

Primary Sjögren's syndrome (PSS) is a chronic autoimmune disease characterized by lymphoplasmacytic infiltration of the exocrine glands, which results in multiple organs damage. Renal injury affects 0.3-27.0% of PSS patients, and tubulointerstitial nephritis is the most frequent form of nephropathy in PSS. The present study reports on the case of a 32-year-old female with a 1-year history of elevated serum creatinine levels, and a 6-month history of mild pain in the waist and leg. Blood biochemistry tests indicated a creatinine level of 221.3 µmol/l and estimated glomerular filtration rate of 24.6 ml/min/1.73 m2 [Chronic Kidney Disease Epidemiology (CKD-EPI) formula]. Accordingly, the patient was diagnosed with stage IV chronic kidney disease. To clarify the underlying cause of the disease, a kidney biopsy was performed, which revealed tubular epithelial cells with multiple focal and lamellar atrophy (~60%), as well as extensive renal interstitial fibrosis with scattered inflammatory cell infiltration. Based on these results, the patient was finally diagnosed with severe chronic interstitial nephritis, chronic kidney disease stage IV, PSS and anemia due to chronic kidney disease. The patient was treated with half-dose glucocorticoid (prednisone, 25 mg oral qd maintained up to 12 months). The patient's serum creatinine levels had decreased to 172.4 µmol/l after 1 month and to 178.7 µmol/l after 12 months. The present case concluded that young patients with chronic renal failure should first be assessed for rheumatic immune system diseases. PSS may involve several organs and the clinical manifestations may be varied. Although chronic renal failure is frequently the first manifestation of renal disorder due to PSS, it may be overlooked by clinicians. The present results suggest that further attention should be paid to determine the association between symptoms in the clinical setting.

Wenxin Keli for atrial fibrillation: Protocol for a systematic review and meta-analysis.

BACKGROUND: Atrial fibrillation (AF) is a most common cardiac arrhythmia in clinical practice. In China, Wenxin Keli (WXKL) therapy is a common treatment for AF, but its effects and safety remain uncertain. This protocol is to provide the methods used to assess the effectiveness and safety of WXKL for the treatment of patients with AF. METHODS: We will search comprehensively the 4 English databases EMBASE, the Cochrane Central Register of Controlled Trials (Cochrane Library), PubMed, and Medline and 3 Chinese databases China National Knowledge Infrastructure (CNKI), Chinese Biomedical Literature Database (CBM), and Chinese Science and Technology Periodical database (VIP) on computer on March 2018 for the randomized controlled trials (RCTs) regarding WXKL for AF. The therapeutic effects according to the sinus rhythm and p-wave dispersion (Pwd) will be accepted as the primary outcomes. We will use RevMan V.5.3 software as well to compute the data synthesis carefully when a meta-analysis is allowed. RESULTS: This study will provide a high-quality synthesis of current evidence of WXKL for AF. CONCLUSION: The conclusion of our systematic review will provide evidence to judge whether WXKL is an effective intervention for patient with AF. PROSPERO REGISTRATION NUMBER: PROSPERO CRD 42018082045.