Search

Abstract Background Coil embolization is a common method for treating unruptured intracranial aneurysms (UIAs). To effectively perform coil embolization for UIAs, clinicians must undergo extensive training with the assistance of senior physicians over an extended period. This study aimed to establish a deep-learning system for measuring the morphological features of UIAs and help the surgical planning of coil embolization for UIAs. Methods Preoperative computational tomography angiography (CTA) data and surgical data from UIA patients receiving coil embolization in our medical institution were retrospectively reviewed. A convolutional neural network (CNN) model was trained on the preoperative CTA data, and the morphological features of UIAs were measured automatically using this CNN model. The intraclass correlation coefficient (ICC) was utilized to examine the similarity between the morphologies measured by the CNN model and those determined by experienced clinicians. A deep neural network model to determine the diameter of first coil was further established based on the CNN model within the derivation set (75% of all patients) using neural factorization machines (NFM) model and was validated using a validation set (25% of all patients). The general match ratio (the difference was within ± 1 mm) between the predicted diameter of first coil by model and that used in practical scenario was calculated. Results One-hundred fifty-three UIA patients were enrolled in this study. The CNN model could diagnose UIAs with an accuracy of 0.97. The performance of this CNN model in measuring the morphological features of UIAs (i.e., size, height, neck diameter, dome diameter, and volume) was comparable to the accuracy of senior clinicians (all ICC > 0.85). The diameter of first coil predicted by the model established based on CNN model and the diameter of first coil used actually exhibited a high general match ratio (0.90) within the derivation set. Moreover, the model performed well in recommending the diameter of first coil within the validation set (general match ratio as 0.91). Conclusion This study presents a deep-learning system which can help to improve surgical planning of coil embolization for UIAs.

Background and PurposeAneurysm wall enhancement (AWE) is correlated with the rupture and growth risk of unruptured intracranial aneurysms (UIAs). Pyroptosis is a proinflammation mode of lytic cell death, mediated by pyroptosis-related proteins, i.e., gasdermin D and interleukin 1 β (IL-1β). Integrating serum cytokines and histology, this study aimed to investigate the correlation between AWE and pyroptosis in UIAs.MethodsUIA patients receiving microsurgical clipping were prospectively enrolled from January 2017 and June 2020. UIA samples were collected, as well as the corresponding blood samples. In this study, high-resolution magnetic resonance was employed to identify the AWE. The serum 46-cytokines examination and the histological analysis were conducted to determine pyroptosis, CD68 and MMP2. The IL-1 ra/beta ratio was determined by complying with the serum IL-1β and IL-1.ra. A comparison was drawn in the differences between UIAs with and without AWE. Lastly, the correlation between inflammation in UIA samples and serums was investigated.ResultsThis study included 34 UIA patients. The serum proinflammatory cytokines [IL-1β (P < 0.001) and TNF-α (P < 0.001)] were up-regulated, and serum anti-inflammatory cytokine (IL-1.ra, P = 0.042) were down-regulated in patients with AWE UIAs. The patients with AWE UIAs achieved a higher IL-1.ra/beta ratio (P < 0.001). The multivariate logistic analysis demonstrated IL-1β [odds ratio (OR), 1.15; 95% confidence interval (CI), 1.02–1.30; P = 0.028] and IL-1.ra (OR, 0.998; 95% CI, 0.997–1.000; P = 0.017) as the risk factors correlated with the AWE. IL-1.ra/beta ratio achieved the highest predictive accuracy [area under the curve (AUC), 0.96] for AWE, followed by IL-1.ra (AUC, 0.90), IL-1β (AUC, 0.88) and TNF-α (AUC, 0.85). As compared with the UIAs without AWE, the AWE UIAs were manifested as a severer wall remodeling, with higher relative levels of pyroptosis-related proteins, CD68 and MMP2. The serum IL-1β, IL-1.ra and IL-1.ra/beta ratio had a positive correlation with the relative levels of pyroptosis-related proteins, CD68 and MMP2 in UIA tissues.ConclusionThe serum IL-1β and IL-1.ra were correlated with the AWE. More pyroptosis-related proteins were identified in UIAs with AWE. The serum IL-1β and IL-1.ra were correlated with the pyroptosis-related proteins in aneurysm tissues.

Asiatic acid (AA) has been demonstrated to exhibit anti-diabetic activity. However, the mechanisms and underlying signaling pathways remain to be elucidated. The present study was performed to confirm the protective effect of AA and demonstrate its ability to regulate the phosphatidylinositol 3-kinase (PI3K)/protein kinase B (AKT)/glycogen synthase kinase-3β (GSK-3β) signaling pathway in db/db mice. Db/db mice fed on a high-fat diet were used to model diabetes mellitus. Modeled mice were divided randomly into the model control, pioglitazone hydrochloride tablet (PH) and AA groups. Age-matched C57 BL/6J mice served as normal controls. Lipid and glucose levels, and glycogen synthesis rates were assessed following treatment. Pathological changes were detected using hematoxylin and eosin staining. Expression of the PI3K/AKT/GSK-3β signaling pathway at the mRNA level was measured using quantitative polymerase chain reaction analysis. The model control group revealed typical characteristics of obesity and diabetes, including high glucose and lipid levels, and decreased glycogen synthesis. Four weeks of treatment with AA or PH ameliorated these abnormalities. AA and PH treatments mitigated the upregulation of PI3K, AKT, insulin receptor, and insulin receptor substrate-1 mRNA expression in modeled mice. Furthermore, AA and PH treatments decreased GSK-3β and glucose-6-phosphatase mRNA expression compared with the normal control group. The results of the present study confirmed that AA possesses anti-diabetic activity in db/db mice. The PI3K/AKT/GSK-3β signaling pathway may mediate this protective effect. [ABSTRACT FROM AUTHOR]