Development and validation of a multi-modality fusion deep learning model for differentiating glioblastoma from solitary brain metastases. / åŒºåˆ†èƒ¶è´¨æ¯ç»†èƒžç˜¤å’Œå•å‘æ€§è„‘è½¬ç§»ç˜¤çš„å¤šæ¨¡æ€èžåˆæ·±åº¦å­¦ä¹ æ¨¡åž‹çš„å¼€å‘å’ŒéªŒè¯.

OBJECTIVES: Glioblastoma (GBM) and brain metastases (BMs) are the two most common malignant brain tumors in adults. Magnetic resonance imaging (MRI) is a commonly used method for screening and evaluating the prognosis of brain tumors, but the specificity and sensitivity of conventional MRI sequences in differential diagnosis of GBM and BMs are limited. In recent years, deep neural network has shown great potential in the realization of diagnostic classification and the establishment of clinical decision support system. This study aims to apply the radiomics features extracted by deep learning techniques to explore the feasibility of accurate preoperative classification for newly diagnosed GBM and solitary brain metastases (SBMs), and to further explore the impact of multimodality data fusion on classification tasks. METHODS: Standard protocol cranial MRI sequence data from 135 newly diagnosed GBM patients and 73 patients with SBMs confirmed by histopathologic or clinical diagnosis were retrospectively analyzed. First, structural T1-weight, T1C-weight, and T2-weight were selected as 3 inputs to the entire model, regions of interest (ROIs) were manually delineated on the registered three modal MR images, and multimodality radiomics features were obtained, dimensions were reduced using a random forest (RF)-based feature selection method, and the importance of each feature was further analyzed. Secondly, we used the method of contrast disentangled to find the shared features and complementary features between different modal features. Finally, the response of each sample to GBM and SBMs was predicted by fusing 2 features from different modalities. RESULTS: The radiomics features using machine learning and the multi-modal fusion method had a good discriminatory ability for GBM and SBMs. Furthermore, compared with single-modal data, the multimodal fusion models using machine learning algorithms such as support vector machine (SVM), Logistic regression, RF, adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT) achieved significant improvements, with area under the curve (AUC) values of 0.974, 0.978, 0.943, 0.938, and 0.947, respectively; our comparative disentangled multi-modal MR fusion method performs well, and the results of AUC, accuracy (ACC), sensitivity (SEN) and specificity(SPE) in the test set were 0.985, 0.984, 0.900, and 0.990, respectively. Compared with other multi-modal fusion methods, AUC, ACC, and SEN in this study all achieved the best performance. In the ablation experiment to verify the effects of each module component in this study, AUC, ACC, and SEN increased by 1.6%, 10.9% and 15.0%, respectively after 3 loss functions were used simultaneously. CONCLUSIONS: A deep learning-based contrast disentangled multi-modal MR radiomics feature fusion technique helps to improve GBM and SBMs classification accuracy.

Usability of serum inter-α-trypsin inhibitor heavy chain 4 as a biomarker for assessing severity and predicting functional outcome after human aneurysmal subarachnoid hemorrhage: A prospective observational cohort study at a single institution.

BACKGROUND: Inter-α-trypsin inhibitor heavy chain 4 (ITIH4) may harbor anti-inflammatory activities. We sought to discern the predictive significance of serum ITIH4 for delayed cerebral ischemia (DCI) and clinical outcomes of human aneurysmal subarachnoid hemorrhage (aSAH). METHODS: At a single institution, we performed a prospective and observational cohort study of 148 patients with aSAH and 52 healthy controls. Poststroke six-month extended Glasgow Outcome Scale (GOSE) score of 1-4 was designated as a poor prognosis. Prognosis associations were verified using multivariate analysis. RESULTS: As compared to controls, patients had significantly declined serum ITIH4 concentrations from admission until day 10, with the lowest concentrations at days 1-3 after stroke. Serum ITIH4 concentrations, which were substantially decreased with the increasing Hunt-Hess scores or modified Fisher scores, were independently correlated with the two scores. Moreover, serum ITIH4 concentrations, which were markedly elevated in the order of GOSE scores from 1 to 8, together with Hunt-Hess scores and modified Fisher scores were independently related to GOSE scores and poor prognosis. However, serum ITIH4 concentrations were not independently predictive of DCI. Prediction model of poor prognosis integrating the preceding three variables were delineated using the nomogram, were verified under the calibration curve, and displayed high discriminatory efficiencies under the receiver operating characteristic curve. CONCLUSIONS: A significant decline of serum ITIH4 concentrations during the early phase after aSAH was closely related to severity and poor prognosis, assuming that serum ITIH4 may represent a promising prognostic biomarker of aSAH.

Prediction of submitochondrial proteins localization based on Gene Ontology.

Mitochondria, which are double-membrane bound organelles commonly found in eukaryotic cells, play a fundamental role as sites for cellular energy production. Within the mitochondria, there exist substructures called submitochondria, and specific proteins associated with submitochondria have been implicated in various human diseases. Therefore, comprehending the precise localization of these submitochondrial proteins is of utmost importance. Such knowledge not only aids in unraveling their role in the pathogenesis of diseases but also facilitates the development of therapeutic drugs and diagnostic methods. In this study, we proposed a novel method based on Gene Ontology (GO) to predict the localization of the submitochondrial proteins, called GO-Submito. More specifically, the GO-Submito fine-tuned pre-training Bidirectional Encoder Representations from Transformers models to encode GO annotations into vectors. Subsequently, the Multi-head Attention Mechanism was employed to fuse these encoded vectors of GO annotations, enabling precise localization prediction. Through comprehensive evaluation, our results demonstrated that GO-Submito outperforms existing methods, offering a reliable and efficient tool for precisely localizing submitochondrial proteins.

Traumatic pseudoaneurysms of external carotid artery branch: Case series and treatment considerations.

PURPOSE: To explore the diagnosis and treatment of traumatic external carotid branch pseudoaneurysms. METHODS: Eleven cases of traumatic external carotid artery branch pseudoaneurysms were admitted in our hospital. Digital subtraction angiography was performed in all patients. It revealed that the pseudoaneurysms originated from the internal maxillary artery in 5 cases, superficial temporal artery in 5 cases and occipital artery in 1 case. Five cases of internal maxillary artery pseudoaneurysms and 2 cases of superficial temporal artery pseudoaneurysms were treated by embolization; the other 3 cases were surgically resected. RESULTS: Complete cessation of nasal bleeding was achieved in all the 5 pseudoaneurysms of internal maxillary artery after the endovascular therapies. Scalp bleeding stopped and scalp defect healed up in 2 patients with superficial temporal artery pseudoaneurysms treated by interventional therapy. All patients were followed up for 0.5-2.0 years without recurrence of nosebleed and scalp lump. CONCLUSION: For patients with repeated severe epistaxis after craniocerebral injury, digital subtraction angiography should be performed as soon as possible to confirm traumatic pseudoaneurysm. Endovascular therapy is an effective method for traumatic internal maxillary artery pseudoaneurysms. For patients with scalp injuries and pulsatile lumps, further examinations including digital subtraction angiography should be performed to confirm the diagnosis. Surgical treatment or endovascular therapy for scalp traumatic pseudoaneurysm is effective.

Efficacy of Statins in Cerebral Vasospasm, Mortality, and Delayed Cerebral Ischemia in Patients with Aneurysmal Subarachnoid Hemorrhage: A Systematic Review and Meta-Analysis of Randomized Controlled Trials.

BACKGROUND: Aneurysmal subarachnoid hemorrhage (aSAH) is an acute cerebrovascular disease with frequent cerebral vasospasm and delayed cerebral ischemia (DCI). The use of statins for patients with aSAH is controversial. The present study evaluated the efficacy of statins in aSAH-induced vasospasm, DCI, delayed ischemic neurological deficit (DIND), mortality, and other outcomes. METHODS: A literature search was performed in PubMed, EMBASE, and the Cochrane Library. English reports of patients with aSAH who had been treated with statins without combination were included. The outcomes, including cerebral vasospasm, DIND, DCI, mortality, disability, and creatine kinase/alanine aminotransferase/aspartic transaminase elevation, were extracted for meta-analysis. RESULTS: A total of 13 studies, with 776 versus 821 patients treated with statins versus placebo, were retained for the statistical meta-analysis. The results showed that statin administration significantly reduced the frequency of vasospasm (relative risk [RR], 0.76; 95% confidence interval [CI], 0.63-0.91; P = 0.003), DIND (RR, 0.76; 95% CI, 0.63-0.91; P = 0.003), vasospasm-DCI (RR, 0.49; 95% CI, 0.32-0.74; P = 0.0008), and mortality (RR, 0.73; 95% CI, 0.54-0.98; P = 0.03). Statins showed insignificant efficacy in the prevention of disability (RR, 0.92; 95% CI, 0.71-1.20), a neurological poor prognosis (RR, 0.75; 95% CI, 0.45-1.27), and creatine kinase/alanine aminotransferase/aspartic transaminase elevation (RR, 1.90; 95% CI, 0.55-6.50). CONCLUSIONS: Statins significantly reduced the incidence of vasospasm, DIND, DCI, and mortality in individuals with aSAH, suggesting its efficacy in aSAH.