CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage.

OBJECTIVES: To predict the functional outcome of patients with intracerebral hemorrhage (ICH) using deep learning models based on computed tomography (CT) images. METHODS: A retrospective, bi-center study of ICH patients was conducted. Firstly, a custom 3D convolutional model was built for predicting the functional outcome of ICH patients based on CT scans from randomly selected ICH patients in H training dataset collected from H hospital. Secondly, clinical data and radiological features were collected at admission and the Extreme Gradient Boosting (XGBoost) algorithm was used to establish a second model, named the XGBoost model. Finally, the Convolution model and XGBoost model were fused to build the third "Fusion model." Favorable outcome was defined as modified Rankin Scale score of 0-3 at discharge. The prognostic predictive accuracy of the three models was evaluated using an H test dataset and an external Y dataset, and compared with the performance of ICH score and ICH grading scale (ICH-GS). RESULTS: A total of 604 patients with ICH were included in this study, of which 450 patients were in the H training dataset, 50 patients in the H test dataset, and 104 patients in the Y dataset. In the Y dataset, the areas under the curve (AUCs) of the Convolution model, XGBoost model, and Fusion model were 0.829, 0.871, and 0.905, respectively. The Fusion model prognostic performance exceeded that of ICH score and ICH-GS (p = 0.043 and p = 0.045, respectively). CONCLUSIONS: Deep learning models have good accuracy for predicting functional outcome of patients with spontaneous intracerebral hemorrhage. CLINICAL RELEVANCE STATEMENT: The proposed deep learning Fusion model may assist clinicians in predicting functional outcome and developing treatment strategies, thereby improving the survival and quality of life of patients with spontaneous intracerebral hemorrhage. KEY POINTS: • Integrating clinical presentations, CT images, and radiological features to establish deep learning model for functional outcome prediction of patients with intracerebral hemorrhage. • Deep learning applied to CT images provides great help in prognosing functional outcome of intracerebral hemorrhage patients. • The developed deep learning model performs better than clinical prognostic scores in predicting functional outcome of patients with intracerebral hemorrhage.

Evaluation of Inferior Intercavernous Sinus in Patients With Pituitary Microadenoma by Contrast-Enhanced SPACE Imaging.

OBJECTIVE: Inferior intercavernous sinus (iICS) is a venous channel below the pituitary gland. Inferior intercavernous sinus injury is predisposed to cause venous bleeding during dura incision in transsphenoidal surgery for pituitary adenomas. Therefore, this study aimed to perform a radiological assessment of iICS before transsphenoidal surgery for pituitary microadenoma. METHODS: A retrospective evaluation was performed on 156 patients who underwent magnetic resonance imaging examinations in our hospital before endoscopic transsphenoidal surgery for pituitary microadenoma. Both sagittal reformatted and coronal contrast-enhanced (CE) sampling perfection with application optimized contrast using different flip angle evolutions (SPACE) images were interpreted for the presence, shape, and size of the iICS. RESULTS: In CE SPACE, the iICS was identified in 72 patients (46.15%) with pituitary microadenoma. The iICS was appeared as a filiform-shaped hyperintense structure below the pituitary gland on coronal CE SPACE planes and a crescent-shaped hyperintense structure on sagittal CE SPACE planes. The mean ± SD width, depth, and height of iICS were 11.15 ± 3.47 mm, 5.29 ± 1.24 mm, and 1.41 ± 0.19 mm, respectively. CONCLUSIONS: Contrast-enhanced SPACE may serve as a promising technique in evaluating iICS and individualized preoperative planning before transsphenoidal surgery for pituitary microadenoma.

Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema.

OBJECTIVES: To evaluate for the first time the performance of a deep learning method based on no-new-Net for fully automated segmentation and volumetric measurements of intracerebral hemorrhage (ICH), intraventricular extension of intracerebral hemorrhage (IVH), and perihematomal edema (PHE) in primary ICH on CT. METHODS: Three hundred and eighty primary ICH patients who underwent CT at hospital arrival were divided into a training cohort (n = 300) and a validation cohort (n = 80). An independent cohort with 80 patients was used for testing. Ground truth (segmentation masks) was manually generated by radiologists. Model performance on lesion segmentation and volumetric measurement of ICH, IVH, and PHE were evaluated by comparing the model results with the segmentations performed by radiologists. RESULTS: In the test cohort, the Dice scores of lesion segmentation were 0.92, 0.79, and 0.71 for ICH, IVH, and PHE, respectively. The sensitivities were 0.93 for ICH, 0.88 for IVH, and 0.81 for PHE. The positive predictive values were 0.92, 0.76, and 0.69 for ICH, IVH, and PHE, respectively. Excellent concordance (concordance correlation coefficients [CCCs] ≥ 0.98) of ICH and IVH and good concordance of PHE (CCCs ≥ 0.92) were demonstrated between manually and automatically measured volumes. The model took approximately 15 s to provide automatic segmentation and volume analysis for each patient. CONCLUSION: Our model demonstrates good reliability for automatic segmentation and volume measurement of ICH, IVH, and PHE in primary ICH, which can be useful to reduce the effort and time of doctors to calculate volumes of ICH, IVH, and PHE. KEY POINTS: • Deep learning algorithms can provide automatic and reliable assessment of intracerebral hemorrhage, intraventricular hemorrhage, and perihematomal edema on CT. • Non-contrast CT-based deep learning method can be helpful to provide efficient and accurate measurements of ICH, IVH, and PHE in primary ICH patients, thereby reducing the effort and time of doctors to segment and calculate volumes of ICH, IVH, and PHE in primary ICH patients.

Non-contrast MRI for breast screening: preliminary study on detectability of benign and malignant lesions in women with dense breasts.

PURPOSE: The importance of breast cancer screening has long been known. Unfortunately, there is no imaging modality for screening women with dense breasts that is both sensitive and without concerns regarding potential side effects. The purpose of this study is to explore the possibility of combined diffusion-weighted imaging and turbo inversion recovery magnitude MRI (DWI + TIRM) to overcome the difficulty of detection sensitivity and safety. METHODS: One hundred and seventy-six breast lesions from 166 women with dense breasts were retrospectively evaluated. The lesion visibility, area under the curve (AUC), sensitivity and specificity of cancer detection by MG, DWI + TIRM, and clinical MRI were evaluated and compared. MG plus clinical MRI served as the gold standard for lesion detection and pathology served as the gold standard for cancer detection. RESULTS: Lesion visibility of DWI + TIRM (96.6%) was significantly superior to MG (67.6%) in women with dense breasts (p < 0.001). There was no significant difference compared with clinical MRI. DWI + TIRM showed higher accuracy (AUC = 0.935) and sensitivity (93.68%) for breast cancer detection than MG (AUC = 0.783, sensitivity = 46.32%), but was comparable to clinical MRI (AUC = 0.944, sensitivity = 93.68%). The specificity of DWI + TIRM (83.95%) was lower than MG (98.77%), but higher than clinical MRI (77.78%). CONCLUSIONS: DWI combined with TIRM could be a safe, sensitive, and practical alternative for screening women with dense breasts.

Correction to: Non-contrast MRI for breast screening: preliminary study on detectability of benign and malignant lesions in women with dense breasts.

In the original version of the article, the image of Figure 2 was erroneously duplicated as Figure 4. The correct version of Figure 4 is given below. The original article has been corrected.

Heat shock protein 60 affects behavioral improvement in a rat model of Parkinson's disease grafted with human umbilical cord mesenchymal stem cell-derived dopaminergic-like neurons.

Parkinson's disease (PD) is a neurodegenerative disorder that is caused by a loss of dopaminergic (DAergic) neurons in mesencephalic substantia nigra (SN). Human umbilical cord mesenchymal stem cells (hUC-MSCs) are capable of self-renewal and differentiation into multiple cell lineages, including DAergic neurons. Thus, hUC-MSCs could be a promising alternative to compensate for the loss of DAergic neurons in PD. In the current study, hUC-MSCs and hUC-MSCs-derived DAergic-like neurons were transplanted into the striatum and SN of a rat model of PD that is induced by 6-hydroxydopamine (6-OHDA). We evaluated their therapeutic effects on improving rotation behavior in the rat and on modulating the level of heat shock protein 60 (Hsp60) expression in the brain. After transplantation, an amelioration of rotation behavior was observed in rats that underwent cell grafting, and hUC-MSCs-derived DAergic-like neurons were superior to hUC-MSCs at inducing behavioral improvement. Western blot and immunohistochemistry analysis indicated significantly elevated levels of Hsp60 in cell-grafted rats compared to 6-OHDA-lesioned (PD) rats. These results demonstrate that hUC-MSCs-based cell transplantation is potential therapeutic treatment for PD, and hUC-MSCs-derived DAergic-like neurons appear to be favorable candidates for cell replacement therapy in PD. Finally, Hsp60 could be involved in a mechanism of behavioral recovery.

Association between FGF20 rs12720208 gene polymorphism and Parkinson's disease: a meta-analysis.

Previous studies have claimed the association of rs12720208 polymorphism in the fibroblast growth factor 20 (FGF20) gene with the increased risk of Parkinson's disease (PD), but results from the published data were controversial. The aim of our present meta-analysis was to estimate the overall association between FGF20 rs12720208 polymorphism and the risk of PD. Case-control studies with sufficient data evaluating the association between rs12720208 C/T polymorphism and PD susceptibility were systematically identified in PubMed, OVID, SinoMed, Chinese National Knowledge Infrastructure (CNKI) up to July 10, 2015. A total of 3402 PD patients and 3739 controls from seven case-control studies were collected for this meta-analysis. The pooled odds ratio (OR) with its 95 % confidence interval (CI) was calculated to assess the genetic association between FGF20 rs12720208 polymorphism and the risk of PD. In this study, no enough proof was found to prove the association in any genetic models with random-effects model (CT+TT vs. CC: OR = 1.147, 95 % CI: 0.883-1.489, P = 0.304; TT vs. CC+CT: OR = 1.754, 95 % CI: 0.878-3.505, P = 0.112; T vs. C: OR = 1.169, 95 % CI = 0.919-1.487, P = 0.204; TT+CC vs. CT: OR = 0.906, 95 % CI = 0.694-1.182, P = 0.466). Our results suggest that there is no sufficient evidence to support the association between rs12720208 polymorphism and PD risk. Studies with larger sample size across diverse populations and subgroup analyses are necessary in the future.

Inhibition of Notch 1 signaling in the subacute stage after stroke promotes striatal astrocyte-derived neurogenesis.

Inhibition of Notch1 signaling has been shown to promote astrocyte-derived neurogenesis after stroke. To investigate the regulatory role of Notch1 signaling in this process, in this study, we used a rat model of stroke based on middle cerebral artery occlusion and assessed the behavior of reactive astrocytes post-stroke. We used the γ-secretase inhibitor N-[N-(3,5-diuorophenacetyl)-1-alanyl]-S-phenylglycine t-butylester (DAPT) to block Notch1 signaling at 1, 4, and 7 days after injury. Our results showed that only administration of DAPT at 4 days after stroke promoted astrocyte-derived neurogenesis, as manifested by recovery of white matter fiber bundle integrity on magnetic resonance imaging, which is consistent with recovery of neurologic function. These findings suggest that inhibition of Notch1 signaling at the subacute stage post-stroke mediates neural repair by promoting astrocyte-derived neurogenesis.

Intensive Versus Standard Glucose Control in Patients with Ischemic Stroke: A Meta-Analysis of Randomized Controlled Trials.

BACKGROUND: Hyperglycemia is common in patients with ischemic stroke (IS) and has been proven to be associated with worse clinical outcomes. However, it is controversial whether intensive glucose control (IGC) is superior to standard glucose control (SGC). Therefore, we carried out this meta-analysis based on randomized controlled trials (RCTs). METHODS: We systematically searched databases for RCTs that evaluated the efficacy of IGC versus SGC in patients with IS. The retrieval time was limited from the establishment of the database to October 2019. The retrieval databases included PubMed, Medline, Embase, OVID, Web of Science, Google Scholar, and a Chinese literature database. Two researchers independently screened and evaluated the quality of literature. We used Stata 11.0 software for data analysis. Odds ratios (ORs) and 95% confidence intervals (CIs) were used to compare the results. RESULTS: Finally, 7 RCTs including 1691 participants were included in this study. Among the patients, 857 patients were in the IGC group and 834 were in the SGC group. Our results show that IGC significantly increased the risk of hypoglycemia compared with SGC (OR, 4.76; 95% CI, 1.17-19.45). No significant differences were observed in modified Rankin scale score ≤2 (OR, 0.97; 95% CI, 0.75-1.25), National Institutes of Health Stroke Scale score ≤2 (OR, 1.48; 95% CI, 0.54-4.06), and death (OR, 0.74; 95% CI, 0.53-1.02) between the 2 groups within 3 months. CONCLUSIONS: Our results suggest there is no evidence that IGC is superior to SGC in patients with IS, but IGC increases the risk of hypoglycemia.

Quantitative measurements of facets on the ulnar coronoid process from reformatted CT images.

BACKGROUND: To quantify the size and angle of the medial and lateral facets of the ulnar coronoid process by reformatted computed tomography (CT) imaging. METHODS: Elbow CT images were retrospectively selected from the picture archiving and communication system in our hospital over a 5-year period (January 2011 to December 2015). The widths, heights, gradient and tilt angles of both the medial and lateral facet of the ulnar coronoid process were measured using two-dimensional (2D) reformations of CT images. RESULTS: Our database research yielded 120 elbow joints (53 right, 67 left) of 120 patients (54 males, 66 females) which fulfilled our criteria. The average width of the two facets of the ulnar coronoid process were 13.34±1.85 mm for the medial facet and 8.39±1.29 mm for the lateral facet. The average height of the medial facet was 18.45±3.38 mm and the lateral facet was 17.55±3.81 mm. The average tilt angles of medial and lateral facet were 80.34°±7.71° and 98.78°±5.71° respectively. The average gradient angles of the medial and lateral facet ridge were 60.02°±8.78° and 36.97°±4.99° respectively. The length of the lateral facet ridge was longer than the medial facet ridge. CONCLUSIONS: Reformatted CT images allow for multiple, accurate measurements of facets on the ulnar coronoid process. These measurements can be applied to guiding appropriate surgical interventions for fractures in this area.

Neurochemical changes in patients with chronic low back pain detected by proton magnetic resonance spectroscopy: A systematic review.

BACKGROUND: Low back pain is a highly prevalent health problem around the world, affecting 50% to 85% of people at some point in life. The purpose of this systematic review is to summarize the previous proton magnetic resonance spectroscopy studies on brain chemical changes in patients with chronic low back pain (CLBP). METHODS: We identified relevant studies from a literature search of PubMed and EMBASE from 1980 to March 2016. Data extraction was performed on the subjects' characteristics, MRS methods, spectral analyses, cerebral metabolites and perceptual measurements. RESULTS: The review identified 9 studies that met the inclusion criteria, comprised of data on 135 CLBP subjects and 137 healthy controls. Seven of these studies reported statistically different neurochemical alterations in patients with CLBP. The results showed that compared to controls, CLBP patients showed reductions of 1) N-acetyl-aspartate (NAA) in the dorsolateral prefrontal cortex (DLPFC), right primary motor cortex, left somatosensory cortex (SSC), left anterior insula and anterior cingulate cortex (ACC); 2) glutamate in the ACC; 3) myo-inositol in the ACC and thalamus; 4) choline in the right SSC; and 5) glucose in the DLPFC. CONCLUSION: This review provides evidence for alterations in the biochemical profile of the brain in patients with CLBP, which suggests that biochemical changes may play a significant role in the development and pathophysiology of CLBP and shed light on the development of new treatments for CLBP.