ABSTRACT
Objective: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. Conclusion:A deep learning-based contrast disentangled multi-modal MR radiomics feature fusion technique helps to improve GBM and SBMs classification accuracy.
ABSTRACT
Objective To analyze the correlation between the concentration of serum and cerebrospinal fluid clusterin(CLU)and the severity of acute traumatic brain injury(TBI).Methods A total of 102 patients with acute moderate and severe TBI admitted to the Second Hospital of Jiaxing from September 2019 to October 2020 were included in the study,and were divided into two batches in chronological order.The first batch of 20 cases were tested for serum CLU content and its time expression map for 4 consecutive days after injury by Western blot;The second batch of 82 cases were divided into groups according to Glasgow coma score(GCS),Rotterdam-CT score and brain contusion and laceration volume,the CLU concentration in serum and cerebrospinal fluid was detected by enzyme linked immunosorbent assay(ELISA)at peak time according to the serum CLU time expression map,and the differences of CLU concentrations between the groups were compared;The correlation between CLU concentration and patients'general data,GCS score,Rotterdam CT score and brain contusion and laceration volume was analyzed by Spearman correlation coefficient;The factors affecting CLU concentration were analyzed by multiple linear regression.Results The serum CLU concentration gradually increases in patients after TBI,and reached the peak at 3 days after injury;There was no statistical difference in serum CLU concentration in two GCS groups,three Rotterdam-CT score groups and two brain contusion and laceration volume groups(P>0.05),but there was a statistical difference in cerebrospinal fluid CLU concentration(P<0.05);Cerebrospinal fluid CLU concentration was negatively correlated with GCS score(r=-0.542,P<0.05),and positively correlated with Rotterdam-CT score and brain contusion and laceration volume(r=0.414,0.738,P<0.05);There was statistical difference in the influence of brain contusion and laceration volume on cerebrospinal fluid CLU concentration(β=8.074,P<0.001).Conclusion The concentration of CLU in cerebrospinal fluid can reflect the severity of TBI,which is mainly related to the volume of brain contusion and laceration.
ABSTRACT
Objective To explore the effect of hypertonic saline combined with magnesium sulfate on severe craniocerebral injury.Methods Patients with severe craniocerebral injury admitted to our hospital from September 2017 to February 2019 were selected prospectively.With the informed consent of the patients' families,the patients were divided into control group and experimental group according to the random number table.Patients in the two groups accepted intracranial pressure monitoring;patients in the experimental group additionally accepted magnesium sulfate combined with hypertonic saline for a continuous use of 7 d.Incidences of high intracranial pressure,epilepsy,low intracranial perfusion,cerebral vasospasm,cerebral infarction,and intracranial pressure rebound,total mannitol dosages one week after injury,serum neuron specific enolase (NSE) level,and Glasgow outcome scale (GOS) scores and mortality rate 3 months after injury were analyzed and compared between the two groups.Results A total of 93 patients were enrolled;47 were into the control group and 46 into the experimental group.There were no significant differences in age,gender,Glasgow coma scale (GCS) scores and NSE levels at admission,and percentages of patients accepted craniotomy evacuation of hematoma or bone flap decompression between the two groups (P＞0.05).As compared with those in the control group,the total mannitol dosage one week after injury and serum NSE concentration were significantly lower,and GOS scores 3 months after injury in the experimental group were significantly higher(P＜0.05).Patients in the experimental group had significantly lower incidences of high intracranial pressure,cerebral vasospasm and intracranial pressure rebound as compared with patients in the control group (P＜0.05).Conclusion Hypertonic saline combined with magnesium sulfate can improve the prognoses of severe craniocerebral injury;it has few side effects and is cheap;it might be an effective cerebral protective agent.
ABSTRACT
Objective To investigate the correlation between serum S100B, IL-6 and intracranial pressure in patients with severe craniocerebral injury.Methods 81 cases of patients with severe brain injury in our hospital from August 2012 to April 2016 were selected,intracranial pressure was monitored immediately after admission to calculate the average daily ICP level ,and venous blood were collected after craniocerebral injury 6,12,24,48, 72 hours.Detection of serum S100B protein and IL-6 levels,and the correlation analysis with the level of intracranial pressure.Results Patients with severe craniocerebral injury S100B levels increased gradually after injury, reached the peak at 24 hours, then decreased gradually; while patients with IL-6 and intracranial pressure after injury gradually increased, the difference was statistically significant in different time points among the S100B,IL-6 and intracranial pressure levels (P<0.05).Conclusion The changes of intracranial pressure after severe craniocerebral injury were proportional to the levels of serum S100B and IL-6,S100B and IL-6 can reflect the changes of intracranial pressure,intracranial pressure changes predicted by S100B plasma concentration in 48 hours were more sensitive than those in the same concentration of IL-6.