We retrospectively analyzed the clinical data of 32 patients with medically intractable idiopathic Parkinson＇s disease who had undergone staged bilateral deep brain stimulation of the subtha-lamic nuclei from January...We retrospectively analyzed the clinical data of 32 patients with medically intractable idiopathic Parkinson＇s disease who had undergone staged bilateral deep brain stimulation of the subtha-lamic nuclei from January 2007 to May 2011. The vascularture of the patients who received two deep brain stimulations was detected using double-dose gadolinium-enhanced brain MRI. The dimensions of straight sinus, superior sagittal sinus, ipsilateral internal cerebral vein in the tha- lamic branch and ipsilateral anterior caudate vein were reduced. These findings demonstrate that bilateral deep brain stimulation of the subthalamic nuclei affects cerebral venous blood flow.展开更多
This work presents an efficient method for volume rendering of glioma tumors from segmented 2D MRI Datasets with user interactive control, by replacing manual segmentation required in the state of art methods. The mos...This work presents an efficient method for volume rendering of glioma tumors from segmented 2D MRI Datasets with user interactive control, by replacing manual segmentation required in the state of art methods. The most common primary brain tumors are gliomas, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the preoperative tumor volume is essential. Tumor portions were automatically segmented from 2D MR images using morphological filtering techniques. These segmented tumor slices were propagated and modeled with the software package. The 3D modeled tumor consists of gray level values of the original image with exact tumor boundary. Axial slices of FLAIR and T2 weighted images were used for extracting tumors. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming process and is prone to error. These defects are overcome in this method. Authors verified the performance of our method on several sets of MRI scans. The 3D modeling was also done using segmented 2D slices with the help of medical software package called 3D DOCTOR for verification purposes. The results were validated with the ground truth models by the Radiologist.展开更多
Background: Cognitive impairment (CI) is a common manifestation of multiple sclerosis (MS), which can severely affect patients’ and their families’ life. Early suspicion and detection of CI can improve general medic...Background: Cognitive impairment (CI) is a common manifestation of multiple sclerosis (MS), which can severely affect patients’ and their families’ life. Early suspicion and detection of CI can improve general medical management of MS patients. Objectives: To correlate MS related CI to cortical brain lesions using brain magnetic resonance imaging (MRI). Materials and Methods: Cognitive impairment was detected using mini mental state examination (MMSE);Neurological examination and brain MRI were performed for all patients. Correlation was calculated between disease cortical burden detected by MRI and CI. Results: Fifty-three patients with proven MS were scanned by brain MRI;69.8% of them had cognitive impairment diagnosed with MMSE. The presence and severity of cognitive impairment was correlated to cortical brain lesion. Cognitive impairment was not correlated with non-cortical brain lesions or neurological physical disability measured by Expanded Disability Status Scale (EDSS). Conclusions: Presence of brain frontal cortical lesions detected by MRI in MS patients can predict subsequent development of MS-related CI.展开更多
Objective To explore brain MRI features of methylmalonic acidemia(MMA).Methods This observational study retrospectively analyzed the clinical and imaging data of 123 patients with MMA diagnosed at Shandong Provincial ...Objective To explore brain MRI features of methylmalonic acidemia(MMA).Methods This observational study retrospectively analyzed the clinical and imaging data of 123 patients with MMA diagnosed at Shandong Provincial Hospital Affiliated to Shandong First Medical University and Qilu Hospital of Shandong University from January 2010 to November 2022.The 123 patients were divided into 7 stages according to age of onset,neonatal period(0 to<1 month),infancy(1 month to<1 year),early childhood(1 to<4 years),preschool(4 to<7 years),school age(7 to<13 years),adolescent(13 to 17 years)and adult(>17 years).All patients underwent brain MRI scanning.The imaging performances were evaluated,including the number,location,morphology of the lesions.Results Of the 123 patients,40 were in the neonatal period,29 in infancy,13 in early childhood,9 in preschool,6 in school age,13 in adolescence,and 13 in adulthood.The first symptoms of patients in the neonatal period were mainly digestive system abnormalities,such as difficulty in breastfeeding(37.5%,15/40)and vomiting(25.0%,10/40),with neurological symptoms gradually becoming the main manifestations from infancy.Seventy-three cases(59.3%)showed significant abnormalities on cranial MRI,including 17 cases with 33 foci in the neonatal period,23 cases with 53 foci in infancy,11 cases with 16 foci in early childhood,2 cases with 2 foci in preschool,3 cases with 7 foci in school age,7 cases with 9 foci in adolescence,and 10 cases with 16 foci in adulthood.In neonatal period,the main manifestations were myelin dysplasia(18%,6/33),dilatation of the lateral ventricular system(18%,6/33),and pallidal bulb infarct foci(18%,6/33);in infancy,the main manifestations were hypoplasia or thinning of the corpus callosum(30%,16/53);in early childhood,the main manifestations were pallidal bulb infarct foci(38%,6/16);and the two MRI abnormalities in preschool were pallidum and thalamic infarct foci;in school age,the main manifestations were infarct foci in the chiasmatic nucleus(29%,2/7)and in the caudate nucleus(29%,2/7);in adolescence,the main manifestation was dilatation of the lateral ventricular system(33%,3/9);and in adulthood,the main manifestation was dilatation of the lateral ventricular system(19%,3/16).Conclusion By staging the age of onset,it is found that the imaging manifestations of MMApatients show significant differences with age,suggesting that there is a dynamic nature of MMA damage to brain structures at different developmental stages.展开更多
Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may b...Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may be overlooked during global feature extraction.Therefore,we propose a brain tumor Magnetic Resonance Imaging(MRI)classification model based on a global-local parallel dual-branch structure.The global branch employs ResNet50 with a Multi-Head Self-Attention(MHSA)to capture global contextual information from whole brain images,while the local branch utilizes VGG16 to extract fine-grained features from segmented brain tumor regions.The features from both branches are processed through designed attention-enhanced feature fusion module to filter and integrate important features.Additionally,to address sample imbalance in the dataset,we introduce a category attention block to improve the recognition of minority classes.Experimental results indicate that our method achieved a classification accuracy of 98.04%and a micro-average Area Under the Curve(AUC)of 0.989 in the classification of three types of brain tumors,surpassing several existing pre-trained Convolutional Neural Network(CNN)models.Additionally,feature interpretability analysis validated the effectiveness of the proposed model.This suggests that the method holds significant potential for brain tumor image classification.展开更多
We report two cases of brain metastasis from a lung adenocarcinoma. Magnetic Resonance Imaging (MRI) appearance was closely correlated with the macroscopic and microscopic findings that showed multiples nodules of a &...We report two cases of brain metastasis from a lung adenocarcinoma. Magnetic Resonance Imaging (MRI) appearance was closely correlated with the macroscopic and microscopic findings that showed multiples nodules of a </span><span style="font-family:Verdana;">well-differen</span><span style="font-family:Verdana;">t</span><span style="font-family:Verdana;">iated papillary adenocarcinoma with secreting tubules, surrounded</span><span style="font-family:Verdana;"> by mucoid fluid.展开更多
This paper presents an approach to improve medical image retrieval, particularly for brain tumors, by addressing the gap between low-level visual and high-level perceived contents in MRI, X-ray, and CT scans. Traditio...This paper presents an approach to improve medical image retrieval, particularly for brain tumors, by addressing the gap between low-level visual and high-level perceived contents in MRI, X-ray, and CT scans. Traditional methods based on color, shape, or texture are less effective. The proposed solution uses machine learning to handle high-dimensional image features, reducing computational complexity and mitigating issues caused by artifacts or noise. It employs a genetic algorithm for feature reduction and a hybrid residual UNet(HResUNet) model for Region-of-Interest(ROI) segmentation and classification, with enhanced image preprocessing. The study examines various loss functions, finding that a hybrid loss function yields superior results, and the GA-HResUNet model outperforms the HResUNet. Comparative analysis with state-of-the-art models shows a 4% improvement in retrieval accuracy.展开更多
Traumatic brain injury is a major cause of death and disability. This is a brief report based on a symposium presentation to the 2014 Chinese Neurotrauma Association Meeting in San Francisco, USA. It covers the work f...Traumatic brain injury is a major cause of death and disability. This is a brief report based on a symposium presentation to the 2014 Chinese Neurotrauma Association Meeting in San Francisco, USA. It covers the work from our laboratory in applying multimodal MRI to study experimental traumatic brain injury in rats with comparisons made to behavioral tests and histology. MRI protocols include structural, perfusion, manganese-enhanced, diffusion-tensor MRI, and MRI of blood-brain barrier integrity and cerebrovascular reactivity.展开更多
We compared the activities of functional regions of the brain in the Deqi versus non-Deqi state, as reported by physicians and subjects cludng acupuncture, Twelve healthy volunteers received sham and true needling at ...We compared the activities of functional regions of the brain in the Deqi versus non-Deqi state, as reported by physicians and subjects cludng acupuncture, Twelve healthy volunteers received sham and true needling at the Waiguan （TE5） acupoint. Real-time cerebral functional MRI showed that compared with non-sensation after sham needling, true needling activated Brodmann areas 3, 6, 8, 9, 10, 11, 13, 20, 21, 37, 39, 40, 43, and 47, the head of the caudate nucleus, the parahippocampal gyrus, thalamus and red nucleus. True needling also deactivated Brodmann areas 1,2, 3, 4, 5, 6, 7, 9. 10. 18.24.31.40 and 46.展开更多
The distinction of radiation-induced brain necrosis (RBN) and recurrent glioblastoma multiform (rGBM) remains a diagnostic challenge due to their similarly on routine follow-up imaging studies and also their clinical ...The distinction of radiation-induced brain necrosis (RBN) and recurrent glioblastoma multiform (rGBM) remains a diagnostic challenge due to their similarly on routine follow-up imaging studies and also their clinical manifestations. Our purpose of this review article is to evaluate the role of advanced MR imaging techniques such as Perfusion-weighted imaging (PWI), Diffusion-weighted imaging (DWI) and Magnetic resonance spectroscopy (MRS) in the differentiation of RBN and rGBM and their complications together with our experience and knowledge gained during our neuroimaging practice.展开更多
We studied the influence of doctor-patient communication skills training on brain functional architecture using resting-state functional MRI（rs-fMRI） with a regional homogeneity（ReHo） method. Ten medical students ...We studied the influence of doctor-patient communication skills training on brain functional architecture using resting-state functional MRI（rs-fMRI） with a regional homogeneity（ReHo） method. Ten medical students participated in the study. A 1-year long doctor-patient communication skills training program was conducted. RsfMRI data were collected at baseline, one month and one year after training. There was a significant increase in the communication skills test average scores between baseline and 1-month duration of training（P〈0.001）. After one month of communication skills training, medical students had decreased ReHo in the right superior temporal gyrus compared with the baseline. After one year of communication skills training, students had increased ReHo in multiple regions and decreased ReHo in several regions（P 〈0.05, Alphasim corrected）. The change of ReHo values in the superior temporal gyrus negatively correlated with the change of communication skills scale score between one month after communication skills training and baseline（r=-0.734, P= 0.036）. The training program we used can be an effective approach of improving doctor-patient communication skills, and the training resulted in functional plasticity of the brain’s architecture toward optimizing locally functional organization.展开更多
The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can dra...The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can draw quicker inferences.The proposed non-invasive diagnostic support system in this study is considered as an image classification system where the given brain image is classified as normal or abnormal.The ability of deep learning allows a single model for feature extraction as well as classification whereas the rational models require separate models.One of the best models for image localization and classification is the Visual Geometric Group(VGG)model.In this study,an efficient modified VGG architecture for brain image classification is developed using transfer learning.The pooling layer is modified to enhance the classification capability of VGG architecture.Results show that the modified VGG architecture outperforms the conventional VGG architecture with a 5%improvement in classification accuracy using 16 layers on MRI images of the REpository of Molecular BRAin Neoplasia DaTa(REMBRANDT)database.展开更多
It is significantly important to define brain death with greater precision in terms of timing and accuracy. While in the past determination of brain death is simply based on conventional angiography, now with major te...It is significantly important to define brain death with greater precision in terms of timing and accuracy. While in the past determination of brain death is simply based on conventional angiography, now with major technological advances the Diffusion-weighted MRI is a new method sensitive to cerebral ischemia which gives on the molecular level the deeply ischemic nature of the changes. Its value in brain death has been shown in various studies. In our study, we did a comparative overview of diffusion-weighted imaging (DWI) with and magnetic resonance angiography (MRA) considering the contribution of ADC measurements from brain parenchyma, in the patients diagnosed with brain death by clinical criteria. We studied 16 brain deaths in serial studies, in which there is a prominent difference between the white and gray matter ADC values on diffusion MRI. In the postmortem brains, ADC values comparing with the normal brain parenchyma, were reduced 65% in white matter and 42% in gray matter. Also, the patients’ ADC values of gray and white matter were significantly lower than those of irreversible brain-ischemia patients’ in ADC values. In comparison to most of the other studies, in our study population studied is large, in which is a comprehensive study that results consistent with the literature. As a result we propose that in the definition of brain death Diffusion MRI and ADC measurements are reliable to show diffuse ishemic changes of brain parenchyma.展开更多
目的:探讨抑郁症患者脑部MRI参数变化及与认知和情感症状的关系。方法:选取2020年1月至2023年12月本院收治的228例抑郁症患者纳入抑郁症组,另于同期本院健康体检人群中随机选取114例纳入对照组,均接受MRI检查。比较两组重复性成套神经...目的:探讨抑郁症患者脑部MRI参数变化及与认知和情感症状的关系。方法:选取2020年1月至2023年12月本院收治的228例抑郁症患者纳入抑郁症组,另于同期本院健康体检人群中随机选取114例纳入对照组,均接受MRI检查。比较两组重复性成套神经心理状态测验(repeatable battery for the assessment of neuropsychologicals status,RBANS)、汉密尔顿抑郁量表(Hamilton depression scale,HAMD)总分及各维度评分;比较前扣带回、颞中回、前额叶、丘脑的脑灰质体积和内侧眶额叶、中央前回的大脑皮层厚度;Pearson相关性分析差异脑区灰质体积、大脑皮层厚度与RBANS评分、HAMD评分的相关性。结果:抑郁症组RBANS评分总分及各维度评分均低于对照组,HAMD评分总分及各维度评分均高于对照组(P<0.05);抑郁症组前扣带回、颞中回、前额叶、丘脑的脑灰质体积和内侧眶额叶大脑皮层厚度低于对照组(P<0.05);抑郁症患者前额叶、颞中回的脑灰质体积和内侧眶额叶大脑皮层厚度与RBANS评分呈中等正相关(P<0.05);抑郁症患者前扣带回、前额叶的脑灰质体积和内侧眶额叶大脑皮层厚度与HAMD评分负相关(P<0.05)。结论:抑郁症患者脑部MRI检查多个认知、情感相关脑区脑灰质体积和大脑皮层厚度异常降低,前额叶、颞中回灰质体积和内侧眶额叶大脑皮层厚度与认知功能正相关,前扣带回、前额叶灰质体积和内侧眶额叶大脑皮层厚度与情感症状负相关。展开更多
文摘We retrospectively analyzed the clinical data of 32 patients with medically intractable idiopathic Parkinson＇s disease who had undergone staged bilateral deep brain stimulation of the subtha-lamic nuclei from January 2007 to May 2011. The vascularture of the patients who received two deep brain stimulations was detected using double-dose gadolinium-enhanced brain MRI. The dimensions of straight sinus, superior sagittal sinus, ipsilateral internal cerebral vein in the tha- lamic branch and ipsilateral anterior caudate vein were reduced. These findings demonstrate that bilateral deep brain stimulation of the subthalamic nuclei affects cerebral venous blood flow.
文摘This work presents an efficient method for volume rendering of glioma tumors from segmented 2D MRI Datasets with user interactive control, by replacing manual segmentation required in the state of art methods. The most common primary brain tumors are gliomas, evolving from the cerebral supportive cells. For clinical follow-up, the evaluation of the preoperative tumor volume is essential. Tumor portions were automatically segmented from 2D MR images using morphological filtering techniques. These segmented tumor slices were propagated and modeled with the software package. The 3D modeled tumor consists of gray level values of the original image with exact tumor boundary. Axial slices of FLAIR and T2 weighted images were used for extracting tumors. Volumetric assessment of tumor volume with manual segmentation of its outlines is a time-consuming process and is prone to error. These defects are overcome in this method. Authors verified the performance of our method on several sets of MRI scans. The 3D modeling was also done using segmented 2D slices with the help of medical software package called 3D DOCTOR for verification purposes. The results were validated with the ground truth models by the Radiologist.
文摘Background: Cognitive impairment (CI) is a common manifestation of multiple sclerosis (MS), which can severely affect patients’ and their families’ life. Early suspicion and detection of CI can improve general medical management of MS patients. Objectives: To correlate MS related CI to cortical brain lesions using brain magnetic resonance imaging (MRI). Materials and Methods: Cognitive impairment was detected using mini mental state examination (MMSE);Neurological examination and brain MRI were performed for all patients. Correlation was calculated between disease cortical burden detected by MRI and CI. Results: Fifty-three patients with proven MS were scanned by brain MRI;69.8% of them had cognitive impairment diagnosed with MMSE. The presence and severity of cognitive impairment was correlated to cortical brain lesion. Cognitive impairment was not correlated with non-cortical brain lesions or neurological physical disability measured by Expanded Disability Status Scale (EDSS). Conclusions: Presence of brain frontal cortical lesions detected by MRI in MS patients can predict subsequent development of MS-related CI.
文摘Objective To explore brain MRI features of methylmalonic acidemia(MMA).Methods This observational study retrospectively analyzed the clinical and imaging data of 123 patients with MMA diagnosed at Shandong Provincial Hospital Affiliated to Shandong First Medical University and Qilu Hospital of Shandong University from January 2010 to November 2022.The 123 patients were divided into 7 stages according to age of onset,neonatal period(0 to<1 month),infancy(1 month to<1 year),early childhood(1 to<4 years),preschool(4 to<7 years),school age(7 to<13 years),adolescent(13 to 17 years)and adult(>17 years).All patients underwent brain MRI scanning.The imaging performances were evaluated,including the number,location,morphology of the lesions.Results Of the 123 patients,40 were in the neonatal period,29 in infancy,13 in early childhood,9 in preschool,6 in school age,13 in adolescence,and 13 in adulthood.The first symptoms of patients in the neonatal period were mainly digestive system abnormalities,such as difficulty in breastfeeding(37.5%,15/40)and vomiting(25.0%,10/40),with neurological symptoms gradually becoming the main manifestations from infancy.Seventy-three cases(59.3%)showed significant abnormalities on cranial MRI,including 17 cases with 33 foci in the neonatal period,23 cases with 53 foci in infancy,11 cases with 16 foci in early childhood,2 cases with 2 foci in preschool,3 cases with 7 foci in school age,7 cases with 9 foci in adolescence,and 10 cases with 16 foci in adulthood.In neonatal period,the main manifestations were myelin dysplasia(18%,6/33),dilatation of the lateral ventricular system(18%,6/33),and pallidal bulb infarct foci(18%,6/33);in infancy,the main manifestations were hypoplasia or thinning of the corpus callosum(30%,16/53);in early childhood,the main manifestations were pallidal bulb infarct foci(38%,6/16);and the two MRI abnormalities in preschool were pallidum and thalamic infarct foci;in school age,the main manifestations were infarct foci in the chiasmatic nucleus(29%,2/7)and in the caudate nucleus(29%,2/7);in adolescence,the main manifestation was dilatation of the lateral ventricular system(33%,3/9);and in adulthood,the main manifestation was dilatation of the lateral ventricular system(19%,3/16).Conclusion By staging the age of onset,it is found that the imaging manifestations of MMApatients show significant differences with age,suggesting that there is a dynamic nature of MMA damage to brain structures at different developmental stages.
文摘Brain tumor classification is crucial for personalized treatment planning.Although deep learning-based Artificial Intelligence(AI)models can automatically analyze tumor images,fine details of small tumor regions may be overlooked during global feature extraction.Therefore,we propose a brain tumor Magnetic Resonance Imaging(MRI)classification model based on a global-local parallel dual-branch structure.The global branch employs ResNet50 with a Multi-Head Self-Attention(MHSA)to capture global contextual information from whole brain images,while the local branch utilizes VGG16 to extract fine-grained features from segmented brain tumor regions.The features from both branches are processed through designed attention-enhanced feature fusion module to filter and integrate important features.Additionally,to address sample imbalance in the dataset,we introduce a category attention block to improve the recognition of minority classes.Experimental results indicate that our method achieved a classification accuracy of 98.04%and a micro-average Area Under the Curve(AUC)of 0.989 in the classification of three types of brain tumors,surpassing several existing pre-trained Convolutional Neural Network(CNN)models.Additionally,feature interpretability analysis validated the effectiveness of the proposed model.This suggests that the method holds significant potential for brain tumor image classification.
文摘We report two cases of brain metastasis from a lung adenocarcinoma. Magnetic Resonance Imaging (MRI) appearance was closely correlated with the macroscopic and microscopic findings that showed multiples nodules of a </span><span style="font-family:Verdana;">well-differen</span><span style="font-family:Verdana;">t</span><span style="font-family:Verdana;">iated papillary adenocarcinoma with secreting tubules, surrounded</span><span style="font-family:Verdana;"> by mucoid fluid.
文摘This paper presents an approach to improve medical image retrieval, particularly for brain tumors, by addressing the gap between low-level visual and high-level perceived contents in MRI, X-ray, and CT scans. Traditional methods based on color, shape, or texture are less effective. The proposed solution uses machine learning to handle high-dimensional image features, reducing computational complexity and mitigating issues caused by artifacts or noise. It employs a genetic algorithm for feature reduction and a hybrid residual UNet(HResUNet) model for Region-of-Interest(ROI) segmentation and classification, with enhanced image preprocessing. The study examines various loss functions, finding that a hybrid loss function yields superior results, and the GA-HResUNet model outperforms the HResUNet. Comparative analysis with state-of-the-art models shows a 4% improvement in retrieval accuracy.
文摘Traumatic brain injury is a major cause of death and disability. This is a brief report based on a symposium presentation to the 2014 Chinese Neurotrauma Association Meeting in San Francisco, USA. It covers the work from our laboratory in applying multimodal MRI to study experimental traumatic brain injury in rats with comparisons made to behavioral tests and histology. MRI protocols include structural, perfusion, manganese-enhanced, diffusion-tensor MRI, and MRI of blood-brain barrier integrity and cerebrovascular reactivity.
基金supported by the National Basic Research Program of China (973 Program), No. 2006CB504505,2012CB518504the Third Key Construction Program of"211 Project" of Guangdong Province
文摘We compared the activities of functional regions of the brain in the Deqi versus non-Deqi state, as reported by physicians and subjects cludng acupuncture, Twelve healthy volunteers received sham and true needling at the Waiguan （TE5） acupoint. Real-time cerebral functional MRI showed that compared with non-sensation after sham needling, true needling activated Brodmann areas 3, 6, 8, 9, 10, 11, 13, 20, 21, 37, 39, 40, 43, and 47, the head of the caudate nucleus, the parahippocampal gyrus, thalamus and red nucleus. True needling also deactivated Brodmann areas 1,2, 3, 4, 5, 6, 7, 9. 10. 18.24.31.40 and 46.
文摘The distinction of radiation-induced brain necrosis (RBN) and recurrent glioblastoma multiform (rGBM) remains a diagnostic challenge due to their similarly on routine follow-up imaging studies and also their clinical manifestations. Our purpose of this review article is to evaluate the role of advanced MR imaging techniques such as Perfusion-weighted imaging (PWI), Diffusion-weighted imaging (DWI) and Magnetic resonance spectroscopy (MRS) in the differentiation of RBN and rGBM and their complications together with our experience and knowledge gained during our neuroimaging practice.
文摘We studied the influence of doctor-patient communication skills training on brain functional architecture using resting-state functional MRI（rs-fMRI） with a regional homogeneity（ReHo） method. Ten medical students participated in the study. A 1-year long doctor-patient communication skills training program was conducted. RsfMRI data were collected at baseline, one month and one year after training. There was a significant increase in the communication skills test average scores between baseline and 1-month duration of training（P〈0.001）. After one month of communication skills training, medical students had decreased ReHo in the right superior temporal gyrus compared with the baseline. After one year of communication skills training, students had increased ReHo in multiple regions and decreased ReHo in several regions（P 〈0.05, Alphasim corrected）. The change of ReHo values in the superior temporal gyrus negatively correlated with the change of communication skills scale score between one month after communication skills training and baseline（r=-0.734, P= 0.036）. The training program we used can be an effective approach of improving doctor-patient communication skills, and the training resulted in functional plasticity of the brain’s architecture toward optimizing locally functional organization.
文摘The advancement of automated medical diagnosis in biomedical engineering has become an important area of research.Image classification is one of the diagnostic approaches that do not require segmentation which can draw quicker inferences.The proposed non-invasive diagnostic support system in this study is considered as an image classification system where the given brain image is classified as normal or abnormal.The ability of deep learning allows a single model for feature extraction as well as classification whereas the rational models require separate models.One of the best models for image localization and classification is the Visual Geometric Group(VGG)model.In this study,an efficient modified VGG architecture for brain image classification is developed using transfer learning.The pooling layer is modified to enhance the classification capability of VGG architecture.Results show that the modified VGG architecture outperforms the conventional VGG architecture with a 5%improvement in classification accuracy using 16 layers on MRI images of the REpository of Molecular BRAin Neoplasia DaTa(REMBRANDT)database.
文摘It is significantly important to define brain death with greater precision in terms of timing and accuracy. While in the past determination of brain death is simply based on conventional angiography, now with major technological advances the Diffusion-weighted MRI is a new method sensitive to cerebral ischemia which gives on the molecular level the deeply ischemic nature of the changes. Its value in brain death has been shown in various studies. In our study, we did a comparative overview of diffusion-weighted imaging (DWI) with and magnetic resonance angiography (MRA) considering the contribution of ADC measurements from brain parenchyma, in the patients diagnosed with brain death by clinical criteria. We studied 16 brain deaths in serial studies, in which there is a prominent difference between the white and gray matter ADC values on diffusion MRI. In the postmortem brains, ADC values comparing with the normal brain parenchyma, were reduced 65% in white matter and 42% in gray matter. Also, the patients’ ADC values of gray and white matter were significantly lower than those of irreversible brain-ischemia patients’ in ADC values. In comparison to most of the other studies, in our study population studied is large, in which is a comprehensive study that results consistent with the literature. As a result we propose that in the definition of brain death Diffusion MRI and ADC measurements are reliable to show diffuse ishemic changes of brain parenchyma.
文摘目的:探讨抑郁症患者脑部MRI参数变化及与认知和情感症状的关系。方法:选取2020年1月至2023年12月本院收治的228例抑郁症患者纳入抑郁症组,另于同期本院健康体检人群中随机选取114例纳入对照组,均接受MRI检查。比较两组重复性成套神经心理状态测验(repeatable battery for the assessment of neuropsychologicals status,RBANS)、汉密尔顿抑郁量表(Hamilton depression scale,HAMD)总分及各维度评分;比较前扣带回、颞中回、前额叶、丘脑的脑灰质体积和内侧眶额叶、中央前回的大脑皮层厚度;Pearson相关性分析差异脑区灰质体积、大脑皮层厚度与RBANS评分、HAMD评分的相关性。结果:抑郁症组RBANS评分总分及各维度评分均低于对照组,HAMD评分总分及各维度评分均高于对照组(P<0.05);抑郁症组前扣带回、颞中回、前额叶、丘脑的脑灰质体积和内侧眶额叶大脑皮层厚度低于对照组(P<0.05);抑郁症患者前额叶、颞中回的脑灰质体积和内侧眶额叶大脑皮层厚度与RBANS评分呈中等正相关(P<0.05);抑郁症患者前扣带回、前额叶的脑灰质体积和内侧眶额叶大脑皮层厚度与HAMD评分负相关(P<0.05)。结论:抑郁症患者脑部MRI检查多个认知、情感相关脑区脑灰质体积和大脑皮层厚度异常降低,前额叶、颞中回灰质体积和内侧眶额叶大脑皮层厚度与认知功能正相关,前扣带回、前额叶灰质体积和内侧眶额叶大脑皮层厚度与情感症状负相关。
