Search

Partial absence of face information challenges the robustness of face recognition algorithms. In order to reduce the effect of partial information loss on face recognition, a Face Recognition Metho...

Decompressive craniectomy is widely used to treat medically refractory intracranial hypertension. There were still few studies focusing on the complications between titanium cranioplasty with non-titanium materials cranioplasty. Our systematic review and meta-analysis aimed to assess the complications following titanium cranioplasty and to make a comparison with nontitanium materials. A systematic review was used to review titanium cranioplasty characters in recent articles. A systematic literature review and meta-analysis were performed by using PubMed/MEDLINE, Scopus, the Cochrane databases and Embase for studies reporting on cranioplasty procedures that compared complication outcomes between titanium with non-titanium materials. The final 15 studies met inclusion criteria and represented 2258 cranioplasty procedures (896 titanium, 1362 nontitanium materials). Overall complications included surgical site infection, hematoma, implant exposure, seizure, cerebrospinal fluid leak, imprecise fitting. Titanium cranioplasty was associated with a significant decrease in overall complications rate (OR, 0.72; P = 0.007), hematoma rate (OR, 0.31; P = 0.0003) and imprecise fitting rate (OR, 0.35; P = 0.04). However, it also suggested that titanium cranioplasty can be greatly increased implant exposure rate (OR, 4.11; P 0.00001). Our results confirmed the advantages of titanium cranioplasty in reducing complications including hematoma, imprecise fitting, and also suggested that clinicians should pay more attention to postoperative implant exposure. With new synthetic materials emerging, it would also be interesting to study the cost-effect and functional outcomes associated with cranioplasty materials.

The disadvantages of poor selectivity, thermal instability and nonlinear output for metal oxide semiconductor (MOS) gas sensors restrict their detection accuracy for flammable and toxic gases. In this paper, a low frequency dynamic temperature modulation detection method using rectangular wave was designed and first proposed herein. The temperature modulation detection mechanism was also provided in detail. The flammable gases CH4 and CO were detected successfully using this method by self-made indirectly Pt/SnO2 sensors. The results show that the response time of the Pt/SnO2 sensors is 9 s and 8 s, and the recovery time is 25 s and 23 s for 100 ppm CH4 and CO, using the rectangular wave temperature modulation with a working temperature of 335-382 °C and an optimized frequency of 100 mHz. The temperature modulation has more advantages than steady-state constant temperature method in power consumption and working temperature. The temperature-modulated response for CH4 and CO, are highly linear with the gas concentration without using the log coordinates. The selectivity of the Pt/SnO2 sensors for 500 ppm CH4 and CO is enhanced from 2.03 using the traditional steady-state constant temperature detection to 2.56 using the temperature modulation method. Compared with the steady-state constant temperature method, both the selectivity and linearity of the response output for the Pt/SnO2 sensors are improved by this method, and an effective detection can be realized for a wide gas concentration range of 0–500 ppm CH4 and CO. It provides a new potential detection pathway for MOS-based gas sensors.

The fault diagnosis of hydrogen sensors is of great significance. However, it is difficult to collect data samples for some modes of hydrogen sensor signals, so the data samples may be unbalanced, which can seriously affect the fault diagnosis results. In this paper, we present a novel convolutional neural network (CNN)-based deep convolutional generative adversarial network (DCG) method (DCG-CNN) for gas sensor fault diagnosis. First, we transform the 1D fault signals of the gas sensor into 2D gray images for end-to-end conversion with no signal data information loss. Second, we use the DCG to enrich the 2D gray images of small fault data samples, which results in balanced sensor fault datasets. Third, we use the CNN method to improve the accuracy of fault diagnosis. In order to understand the internal mechanism of the CNN, we further visualize the learned feature maps of fault data samples in each layer of the CNN and try to analyze the reasons for the method's high performance. The fault diagnosis accuracy of the DCG-CNN is shown to be higher than that of other traditional methods.

ObjectivesPhosphatase and tensin homolog (PTEN) mutation is an indicator of poor prognosis of low-grade and high-grade glioma. This study built a reliable model from multi-parametric magnetic resonance imaging (MRI) for predicting the PTEN mutation status in patients with glioma.MethodsIn this study, a total of 244 patients with glioma were retrospectively collected from our center (n = 77) and The Cancer Imaging Archive (n = 167). All patients were randomly divided into a training set (n = 170) and a validation set (n = 74). Three models were built from preoperative MRI for predicting PTEN status, including a radiomics model, a convolutional neural network (CNN) model, and an integrated model based on both radiomics and CNN features. The performance of each model was evaluated by accuracy and the area under the receiver operating characteristic curve (AUC).ResultsThe CNN model achieved an AUC of 0.84 and an accuracy of 0.81, which performed better than did the radiomics model, with an AUC of 0.83 and an accuracy of 0.66. Combining radiomics with CNN will further benefit the predictive performance (accuracy = 0.86, AUC = 0.91).ConclusionsThe combination of both the CNN and radiomics features achieved significantly higher performance in predicting the mutation status of PTEN in patients with glioma than did the radiomics or the CNN model alone.

Background The biologic meaning of prognostic radiomics phenotypes remains poorly understood, hampered in part by lack of multicenter reproducible evidence. Purpose To uncover the biologic meaning of individual prognostic radiomics phenotypes in glioblastomas using paired MRI and RNA sequencing data and to validate the reproducibility of the identified radiogenomics linkages externally. Materials and Methods This retrospective multicenter study included four data sets gathered between January 2015 and December 2016. From a radiomics analysis set, a 13-feature radiomics signature was built using preoperative MRI for overall survival prediction. Using a radiogenomics training set with both MRI and RNA sequencing, biologic pathways were enriched and correlated with each of the 13 radiomics phenotypes. Radiomics-correlated key genes were identified to derive a prognostic radiomics gene expression (RadGene) score. The reproducibility of identified pathways and genes was validated with an external test set and a public data set (The Cancer Genome Atlas [TCGA]). A log-rank test was performed to assess prognostic significance. Results A total of 435 patients (mean age, 55 years ± 15 [standard deviation]; 263 men) were enrolled. The radiomics signature was associated with overall survival (hazard ratio [HR], 3.68; 95% CI: 2.08, 6.52; P < .001) in the radiomics validation subset. Four types of prognostic radiomics phenotypes were correlated with distinct pathways: immune, proliferative, treatment responsive, and cellular functions (false-discovery rate < 0.10). Thirty radiomics-correlated genes were identified. The prognostic significance of the RadGene score was confirmed in an external test set (HR, 2.02; 95% CI: 1.19, 3.41; P = .01) and a TCGA test set (HR, 1.43; 95% CI: 1.001, 2.04; P = .048). The radiomics-associated pathways and key genes can be replicated in an external test set. Conclusion Individual radiomics phenotypes on MRI scans predictive of overall survival were driven by distinct key pathways involved in immune regulation, tumor proliferation, treatment responses, and cellular functions in glioblastoma, which could be reproduced externally. © RSNA, 2021 Online supplemental material is available for this article.

In the mining process of coal, oil, and natural gas, there are often a large number of toxic, hazardous and explosive gases, which pose a greater safety hazard. These gases usually exist in the form of mixtures. Accurately identifying the composition of the mixed gas is of great significance to the prevention of safety accidents. In order to improve the accuracy of the component recognition of the mixed gas, this paper proposes a mixed gas component recognition algorithm based on the combination of principal component analysis (PCA) and k-nearest neighbor algorithm (KNN). PCA is used to extract the characteristics of the sensor array signal to obtain the characteristic value of the gas, and then KNN is used to realize the recognition of the gas type. The results show that the recognition rate of the feature quantity after dimensionality reduction as input is higher than that before dimensionality reduction. Finally, PCA and KNN algorithm and PCA and support vector machine (SVM) algorithm are compared for the recognition rate of mixed gas. Experimental results show that the proposed method has a recognition rate of 96.88% for mixed gas components.

Gases in the real environment always exist in the form of mixtures, and effective identification of gas types to reduce the occurrence of safety incidents has become an important direction in the field of gas analysis research. This paper proposes a mixed gas identification method based on PCA and PSO-LSSVM. This method uses principal component analysis (PCA) to reduce the dimensionality of the sensor array output signal, and uses the Relief algorithm to select data. The particle swarm algorithm is used to iteratively optimize the relevant parameters in the least squares support vector machine model, and the PSO-LSSVM model is constructed to qualitatively analyze the composition of the mixed gas. This article uses a public data set of mixed gases of ethylene, methane and carbon monoxide to conduct experiments. The experimental results show that the method used in this paper can effectively identify the type of mixed gas, and the recognition accuracy rate reaches 91.67%. The method proposed in this paper can provide a research foundation for the follow-up analysis of the mixed gas concentration.

Purpose We aim to investigate the impacts of extent of resection and adjuvant radiotherapy on survival of high-grade meningiomas (WHO grade II–III) according to modern diagnosis and management. Methods Patients with high-grade meningiomas were identified in the Surveillance Epidemiology and End Results (SEER) database between 2000 and 2015 and used for survival analysis. Propensity score matching (PSM) was conducted to reduce selection bias. Another 92 patients from Sun Yat-sen University Cancer Center (SYSUCC) were used for validation. Results 530 patients were enrolled from SEER. Patients with gross total resection (GTR) had no significantly different overall survival (OS) compared with those with subtotal resection (STR), even after performing PSM between these two groups. Multivariable analysis found that age ≥ 65 years (HR 2.22, P 6 cm (HR 1.59, P = 0.004) and grade III tumor (HR 4.31, P

Background and Aim: Approximately 60% of glioblastoma multiforme (GBM) patients possess an unmethylated O-6-methylguanine-DNA methyltransferase (MGMT) gene, which confers a limited response to standard-of-care treatment with temozolomide (TMZ), resulting in a lower survival. Dianhydrogalactitol (VAL-083) is a novel bi-functional DNA-targeting agent that induces interstrand cross-links at N7-guanine, leading to DNA double-strand breaks and ultimately cell death. VAL-083 circumvents MGMT-mediated repair of the O6 guanine alkylator TMZ. A Phase 2 study has been initiated for VAL-083 in newly diagnosed MGMT unmethylated GBM. Subjects and Methods: The study has two parts: part 1 is a dose–escalation and induction format to enroll up to ten patients in which they received VAL-083 at 20, 30, or 40 mg/m2 per day for 3 days every 21 days concurrently with standard radiation treatment and VAL-083 for up to eight additional cycles. Part 2 comprises an expansion phase to enroll up to twenty additional patients. This study was performed with approval by the Institutional Review Board of Sun Yat-sen University Cancer Center (B2016-058-01) on January 13, 2017, and registered with the ClinicalTrials.gov (NCT03050736) on February 13, 2017. Results: After completion of dose escalation, VAL-083, 30 mg/m2 per day, in combination with radiation therapy, was generally safe and well tolerated. At the cutoff date, 23 patients had been enrolled, 14 of whom had been treated in the expansion phase. Consistent with prior studies, myelosuppression was the most common adverse event. Pharmacokinetic assessment indicated that the levels of VAL-083 were as high in the cerebrospinal fluid as in plasma, 2 h postinfusion. Of the 22 patients who had reached their four precycle magnetic resonance imaging assessments, 12 were assessed with disease progression, with a median progression-free survival of 9.9 (95% confidence interval 7.3–12.0) months for all the patients studied. Conclusion: These preliminary data support VAL-083 as a potentially valuable treatment option for newly diagnosed GBM.

Background and Aim: Guidelines recommend adjuvant treatment for patients with high-grade gliomas and low-grade gliomas with high risk of progression. In clinical practice, however, treatments may not conform to these suggested guidelines. In this study, we reviewed the treatments and outcomes in patients with gliomas at Sun Yat-Sen University Cancer Center (SYSUCC), China. Materials and Methods: Medical records and radiologic images of 1215 glioma patients who underwent surgery at the center from 2000 to 2017 were retrospectively reviewed, and their clinicopathological characteristics, treatment method, and overall survival (OS) were analyzed. The study was approved by the Ethics Committee of SYSUCC on February 20, 2019 (approval No. GZR2019-219). Results: A total of 1001 patients diagnosed with glioma (initially World Health Organization 2007 criteria, then 2016 criteria) were enrolled, including 90 patients with Grade I, 307 Grade II, 239 Grade III, and 365 Grade IV gliomas. A total of 331 of 604 patients with high-grade glioma (54.8%) and 159 of 397 with low-grade glioma (40.1%) received postsurgical radiotherapy, and 285 patients with high-grade tumors (47.1%) and 80 with low-grade tumors (20.2%) received adjuvant chemotherapy. The median OS was 17.5 months for Grade IV and 43.1 months for Grade III gliomas. The median OS of patients with low-grade glioma was not reached. The 5-year survival rates of patients with Grades I, II, III, and IV gliomas were 94.7%, 73.7%, 45.7%, and 18.6%, respectively. Multivariate analysis identified onset age, preoperative seizure, tumor location, pathological subtype, resection extent, and postsurgical treatment as independent predictors of OS in patients with high-grade gliomas. Patients with high-grade glioma who received postsurgical treatment had better survival than those without adjuvant therapy (Grade III: 52.6 vs. 20.3 months, P = 0.012; Grade IV: 22.6 vs. 12.1 months, P < 0.001). Among patients with diffuse low-grade gliomas, age, performance status, preoperative seizure, Ki-67 index, tumor subtype, and resection extent were associated with clinical outcomes. Conclusion: Glioma patients are not always treated according to guidelines. Although standard care may lead to favorable prognoses, individualized treatments may be more acceptable and result in better outcomes and should thus be considered in routine clinical practice.

Purpose Accurately predicting outcome (i.e., overall survival (OS) time) for higher grade glioma (HGG) has great clinical value and would provide optimized guidelines for treatment planning. Radiomics focuses on revealing underlying pathophysiological information in biomedical images for disease analysis and demonstrates promising prognostic clinical performance. In this paper, we propose a novel sparse representation-based radiomics framework to predict if HGG patients would have long or short OS time. Methods First, taking advantages of the scale invariant feature transform (SIFT) feature in image characterizing, we developed a sparse representation-based method to convert a local SIFT descriptor into a global tumor feature. Next, because preserving sample structure is beneficial for feature selection, we proposed a locality preserving projection and sparse representation-combined feature selection method to select more discriminative features for tumor classification. Finally, we employed a multifeature collaborative sparse representation classification to combine the information of multimodal images to classify OS time. Results Three experiments were performed on the two datasets provided by different institutions. Specifically, the proposed model was trained and independently tested on dataset 1 (135 subjects), on dataset 2 (86 subjects), and on the combination of dataset 1 and dataset 2, respectively. Experimental results demonstrated that the proposed method achieved encouraging prediction performance, exhibiting a testing accuracy of 93.33% on dataset 1 (one modality), 92.31% on dataset 2 (two modalities), and 87.93% on the combined dataset (one modality). Conclusions The sparse representation theory provides reasonable solutions to feature extraction, feature selection, and classification for radiomics. This study provides a promising tool to enhance the prediction performance of HGG patient's outcome.

Purpose Isocitrate dehydrogenase 1 (IDH1) has been proven as a prognostic and predictive marker in glioblastoma (GBM) patients. The purpose was to preoperatively predict IDH mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI). Methods In this retrospective multicenter study, 225 patients were included. A total of 1614 multiregional features were extracted from enhancement area, non‐enhancement area, necrosis, edema, tumor core, and whole tumor in multiparametric MRI. Three multiregional radiomics models were built from tumor core, whole tumor, and all regions using an all‐relevant feature selection and a random forest classification for predicting IDH1. Four single‐region models and a model combining all‐region features with clinical factors (age, sex, and Karnofsky performance status) were also built. All models were built from a training cohort (118 patients) and tested on an independent validation cohort (107 patients). Results Among the four single‐region radiomics models, the edema model achieved the best accuracy of 96% and the best F1‐score of 0.75 while the non‐enhancement model achieved the best area under the receiver operating characteristic curve (AUC) of 0.88 in the validation cohort. The overall performance of the tumor‐core model (accuracy 0.96, AUC 0.86 and F1‐score 0.75) and the whole‐tumor model (accuracy 0.96, AUC 0.88 and F1‐score 0.75) was slightly better than the single‐regional models. The 8‐feature all‐region radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90, and an F1‐score 0.78. Among all models, the model combining all‐region imaging features with age achieved the best performance of an accuracy 97%, an AUC 0.96, and an F1‐score 0.84. Conclusions The radiomics model built with multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The multiregional model built with all‐region features performed better than the single‐region models, while combining age with all‐region features achieved the best performance.

Background: To develop and validate a deep learning signature (DLS) from diffusion tensor imaging (DTI) for predicting overall survival in patients with infiltrative gliomas, and to investigate the biological pathways underlying the developed DLS. Methods: The DLS was developed based on a deep learning cohort (n = 688). The key pathways underlying the DLS were identified on a radiogenomics cohort with paired DTI and RNA-seq data (n=78), where the prognostic value of the pathway genes was validated in public databases (TCGA, n = 663; CGGA, n = 657). Findings: The DLS was associated with survival (log-rank P < 0.001) and was an independent predictor (P < 0.001). Incorporating the DLS into existing risk system resulted in a deep learning nomogram predicting survival better than either the DLS or the clinicomolecular nomogram alone, with a better calibration and classification accuracy (net reclassification improvement 0.646, P < 0.001). Five kinds of pathways (synaptic transmission, calcium signaling, glutamate secretion, axon guidance, and glioma pathways) were significantly correlated with the DLS. Average expression value of pathway genes showed prognostic significance in our radiogenomics cohort and TCGA/CGGA cohorts (log-rank P < 0.05). Interpretation: DTI-derived DLS can improve glioma stratification by identifying risk groups with dysregulated biological pathways that contributed to survival outcomes. Therapies inhibiting neuron-to-brain tumor synaptic communication may be more effective in high-risk glioma defined by DTI-derived DLS. Funding: A full list of funding bodies that contributed to this study can be found in the Acknowledgements section.

Background: Medulloblastoma (MB) is the most common malignant brain tumor of childhood. Studies have shown that the link between socio-economic status, morbidity and mortality from major cancers has changed significantly over the past 50 years, and therefore the socio-economic variation in cancer incidence is dynamic. Meanwhile, Socio-economic status (SES) characteristics of patients with medulloblastoma and the influence of Socio-economic status on their prognosis have been rarely discussed. Methods: Purpose of our study was aiming to understand ethnic, gender and socioeconomic disparities in medulloblastoma by using the SEER database. Propensity score matching of cases with controls by gender was conducted at the ratio of 1:1. Multivariate cox proportional hazards model was used to assess SES impact and clinically relevant variables of medulloblastoma specific death and overall survival. Independent prognostic factors determined by multivariate analysis were used to construct nomograms. Results: 2660 patients were enrolled after the matching. Study showed unemployed (MBSD, high level vs. low level, HR = 1.334) (OS, high level vs. low level, HR = 1.311) and marital status (OS, married vs unmarried/unknow., HR = 0.706) were important factors affecting the prognosis of medulloblastoma in male. Meanwhile, median household income (MBSD, Quartile 1 vs. Quartile 3, HR = 1.029) (OS, Quartile 1 vs. Quartile 2, HR = 1.809) (OS, Quartile 1 vs. Quartile 3, HR = 1.592), residence (MBSD, urban vs. rural, HR = 0.414) and insurance status (MBSD, insured vs. uninsured/unknow, HR = 0.566) (OS, insured vs. uninsured/unknow, HR = 0.573) were significant factors affecting the prognosis of medulloblastoma in female. Through the calibration plot and C-index test, our nomogram was also of predictive significance. Conclusions: The unique features of medulloblastoma have provided a scenario for the analysis of the impact of racial, ethnic, gender and socioeconomic factors. The current findings have important public health implications for achieving the goal of a healthy population. Given the known morbidity rates and the long-term psychological, financial and medical burdens that these children and their families must bear, it is critical to identify and address these gaps.

Chemical gas sensor array is a common information acquisition device in current machine olfactory systems. However, due to the characteristics of the sensitive materials in the chemical gas sensor, the measurement quality of sensor array decreases in long-term practical application, which gradually affects the analytical results of the machine olfactory system as the time goes on. The self-validating sensor has fault detection and isolation module, fault diagnosis module, fault recovery module and uncertainty analysis module. These functions of self-validating sensor are suitable for monitoring the reliability of the chemical sensor array. In this paper, the self-validating sensor technology is introduced into chemical gas sensor array to improve the measurement quality, so as to improve the overall performance of machine olfactory system. A prototype of self-validating chemical sensor array is designed to illustrate the feasibility of its application in machine olfactory system.

With the development of urbanization, more and more attention has been paid to the problem of urban air pollution. The expansion of city scale results in the dynamic change of pollutant distribution. The monitoring equipment based on optical analysis instrument cannot meet the new demand of spatiotemporal dynamic monitoring of pollution gas distribution in the region. The portable air pollution monitoring equipment can realize the regional monitoring of pollutants and is easy to form a monitoring network. A prototype of a portable air pollution monitoring system based on chemical sensor array is designed in this paper. The monitoring system is mounted in a portable case and can monitor the working state of the system and the process of gas measurement through the touch screen. The instrument can monitor the concentration of environmental pollution gas in real time and display the concentration change curve. It is also equipped with 4G wireless module, which can transmit the pollution gas information remotely. The reliability and effectiveness of the designed monitoring system are proved by testing under laboratory conditions.

Background Medulloblastoma is the common pediatric malignant tumor with poor prognosis in cerebellum. However, MB is always with clinical heterogeneity. To provide patients with more clinically beneficial treatment strategies, there is a pressing need to develop a new prognostic prediction model as a supplement to the prediction outcomes of clinical judgment. Materials and methods Four datasets of mRNA expression and clinical data were downloaded from gene expression omnibus (GEO) database. Differentially expressed genes (DEGs) were identified and functionally enriched among GSE50161, GSE74195, GSE86574. Then we used STRING and Cytoscape to constructed and analyze protein-protein interaction network (PPI) and hub genes. Univariate cox regression analysis was performed to identify overall survival-related hub genes in an unique dataset from GSE85217 as train cohort. Lasso Cox regression model was used to construct the prognostic gene signature. Time-dependent receiver operating characteristic (ROC), Kaplan-Meier curve, univariate and multivariate Cox regression analysis were used to assess the prognostic capacity of the twelve-gene signature. A unique dataset from GSE85217 was downloaded to further validate the results. Finally, we established the nomogram by using the gene signature and validated it with ROC curve. Gene set enrichment analysis (GSEA) was carried out to further investigate its potential molecular mechanism. Besides, the twelve genes expression at the mRNA and protein levels was validated using external database such as Oncomine, cBioportal and HPA, respectively. Results A twelve-gene signature comprising FOXM1, NEK2, CCT2, ACTL6A, EIF4A3, CCND2, ABL1, SYNCRIP, ITGB1, NRXN2, ENAH, and UMPS was established to predict overall survival of medulloblastoma. The ROC curve showed good performance in survival prediction in both the train cohort and the validation cohort. The twelve-gene signature could stratify patients into a high risk and low risk group which had significantly different survival. Univariate and multivariate Cox regression revealed that the twelve-gene signature was an independent prognostic factor in medulloblastoma. Nomogram, which included twelve-gene signatures, was established and showed some clinical benefit. Conclusion Our study identified a twelve-gene signature and established a prognostic nomogram that reliably predicts overall survival in medulloblastoma. The above results will help us to better analyze the pathogenesis and treatment of medulloblastoma in the future.

Background Differentiating glioma recurrence from treatment-related changes can be challenging on conventional imaging. We evaluated the efficacy of quantitative parameters measured by dual-energy spectral computed tomographic (CT) for this differentiation. Methods Twenty-eight patients were examined by dual-energy spectral CT. The effective and normalized atomic number (Zeff and Zeff-N, respectively); spectral Hounsfield unit curve (λHU) slope; and iodine and normalized iodine concentration (IC and ICN, respectively) in the post-treatment enhanced areas were calculated. Pathological results or clinicoradiologic follow-up of ≥2 months were used for final diagnosis. Nonparametric and t-tests were used to compare quantitative parameters between glioma recurrence and treatment-related changes. Sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively), and accuracy were calculated using receiver operating characteristic (ROC) curves. Predictive probabilities were used to generate ROC curves to determine the diagnostic value. Results Examination of pre-contrast λHU, Zeff, Zeff-N, IC, ICN, and venous phase ICN showed no significant differences in quantitative parameters (P > 0.05). Venous phase λHU, Zeff, Zeff-N, and IC in glioma recurrence were higher than in treatment-related changes (P 3, achieving 66.7, 91.7, 83.3, and 91.7% sensitivity; 100.0, 77.8, 88.9, and 77.8% specificity; 100.0, 73.3, 83.3, and 73.3% PPV; 81.8, 93.3, 88.9, and 93.3% NPV; and 86.7, 83.3, 86.7, and 83.3% accuracy, respectively. The respective areas under the curve (AUCs) were 0.912, 0.912, 0.931, and 0.910 in glioma recurrence and treatment-related changes. Conclusions Glioma recurrence could be potentially differentiated from treatment-related changes based on quantitative values measured by dual-energy spectral CT imaging.

Twist is a transcription factor involved in the process of epithelial to mesenchymal transition (EMT) of carcinoma cells, and the promotion of invasion of gliomas through the mesenchymal adjusting process. However, its clinical significance in human glioma has not yet to be understood. To delineate the clinical-pathological significance and prognostic value of Twist, the expression of Twist was evaluated by Immunohistochemistry for 187 glioma samples. We found that Twist demonstrated frequent nuclear expression in the glioma samples and its expression levels were associated with tumor grade (P

Background Vessels with different microcirculation patterns are required for glioblastoma (GBM) growth. However, details of the microcirculation patterns in GBM remain unclear. Here, we examined the microcirculation patterns of GBM and analyzed their roles in patient prognosis together with two well‐known GMB prognosis factors (O6‐methylguanine DNA methyltransferase [MGMT] promoter methylation status and isocitrate dehydrogenase [IDH] mutations). Methods Eighty GBM clinical specimens were collected from patients diagnosed between January 2000 and December 2012. The microcirculation patterns, including endothelium‐dependent vessels (EDVs), extracellular matrix‐dependent vessels (ECMDVs), GBM cell‐derived vessels (GDVs), and mosaic vessels (MVs), were evaluated by immunohistochemistry (IHC) and immunofluorescence (IF) staining in both GBM clinical specimens and xenograft tissues. Vascular density assessments and three‐dimensional reconstruction were performed. MGMT promoter methylation status was determined by methylation‐specific PCR, and IDH1/2 mutations were detected by Sanger sequencing. The relationship between the microcirculation patterns and patient prognosis was analyzed by Kaplan‐Meier method. Results All 4 microcirculation patterns were observed in both GBM clinical specimens and xenograft tissues. EDVs were detected in all tissue samples, while the other three patterns were observed in a small number of tissue samples (ECMDVs in 27.5%, GDVs in 43.8%, and MVs in 52.5% tissue samples). GDV‐positive patients had a median survival of 9.56 months versus 13.60 months for GDV‐negative patients (P = 0.015). In MGMT promoter‐methylated cohort, GDV‐positive patients had a median survival of 6.76 months versus 14.23 months for GDV‐negative patients (P = 0.022). Conclusion GDVs might be a negative predictor for the survival of GBM patients, even in those with MGMT promoter methylation.

BACKGROUND: The present study explored the predictive value of systemic inflammatory indexes in diagnosing grade III gliomas of oligodendroglial origin. METHODS: A retrospective study of 154 patients with grade III gliomas was conducted. Systemic inflammatory indexes, including neutrophil-to-lymphocyte ratio (NLR), albumin-to-gamma-glutamyl transferase ratio (AGR), platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, prognostic nutritional index, and fibrinogen-to-albumin ratio, were reviewed. The resulting predictive model was externally validated using a demographic-matched cohort of 49 grade III glioma patients. RESULTS: In the training set, gliomas of oligodendroglial origin tended to have a lower NLR (P=0.018) and a higher AGR (P=0.036) than those with tumors of astrocytic origin. Moreover, both NLR and AGR had predictive value for oligodendroglial tumors, when compared with astrocytic tumors. The best diagnostic value was obtained using NLR + AGR (AUC =64.9%, 95% CI: 55.5–74.3%, P=0.005). In the validation set, NLR + AGR satisfactorily predicted the presence of oligodendroglial tumors (AUC =66.5%, 95% CI: 50.6–82.4%, P

The intraoperative tumor-free principles refer to the operation techniques that must be carried out to prevent the exfoliation and planting of tumor cells during the operation, so as to prevent local recurrence and distant metastasis. Following the intraoperative tumor-free principles has been valued in resection of extracranial solid tumors. However, the significance of intraoperative tumor-free principles for brain tumors is still unclear. We retrospectively analyzed 106 patients with primary glioblastoma who underwent resection following the intraoperative tumor-free principles from 2010 to 2016. By February 28, 2019, 11 (10.4%) patients were lost to follow-up. The median overall survival (OS) was 20.2 months, and the 1-, 3-, and 5-year survival rates were 71%, 30%, and 26%, respectively. For patients with complete tumor resection, the median OS was 24.8 months, and the 1-, 3-, and 5-year survival rates were 80%, 38%, and 36%, respectively. Patients who received postoperative Stupp regimen had a median OS of 74.1 months, and the 1-, 3-, and 5-year survival rates were 82%, 51%, and 51%, respectively. A total of 36 patients had complete tumor resection followed by Stupp regimen. Their 1-, 3-, and 5-year survival rates were 94%, 68%, and 68%, respectively. Median OS was not reached. The patient with the longest OS had survived for 108 months and was still alive. In summary, the OS of patients in this study was relatively longer than that reported in most previous literatures, which suggests that following the intraoperative tumor-free principles in resection of GBM can benefit patient survival.

e14019 Background: High-grade glioma (HGG) is the most common malignant brain tumor and lacks effective treatment regimen. Anlotinib is a multikinase inhibitor blocking angiogenesis and tumor cell proliferation simultaneously. This study was performed to evaluate the efficacy and safety of anlotinib alone or in combination with temozolomide (TMZ) in the treatment of recurrent HGG. Methods: This is a single-center, retrospective study. Eligible patients (pts) were diagnosed with pathologically confirmed high grades (WHO III/IV) glioma and had recurrent or progressive disease on or after prior treatment. Other key eligibility criteria included Karnofsky Performance Status (KPS) ≥ 40, aged 16 ̃75 years and having at least one measurable lesion (RANO criteria). Pts were administrated with anlotinib once daily for 14 days every 3 weeks till disease progression, intolerable toxicities or death. The initial dose was 12mg for younger pts ( < 40 years old) with KPS ≥ 60 and 10 mg for others. Combination treatment was allowed if previous TMZ was effective and tolerable. TMZ was administered on dose-dense schedule (150mg/m2, QD, d1-d7 and d15-d21 every 28 days) or metronomic schedule (25-50mg/m2 QD). The primary endpoint was progression-free survival at 6 months (PFS6m) accessed according to RANO criteria. The second endpoints included overall survival (OS), objective response rate (ORR) and disease control rate (DCR). Results: Between August 2019 and June 2020, 23 pts with HGG (15 grade IV; 8 grade III; 12 males, 11 females) were enrolled. The median age and median KPS was 42 years and 60. 16 pts have multifocal or disseminated disease. 18 pts received ≥2 lines previous treatment. At the data cutoff date on September 2020, the median duration of treatment was 9 weeks (range: 3-33). The PFS6m was 39.1% and the median PFS was 4.2 months (95% CI: 2.8, 5.6). The median OS was not reached (95% CI: NE, NE) and the OS at 12 months (OS12m) was 54.8%. 8 pts observed tumor response and 9 pts had stable disease. The ORR and DCR were 34.8% and 73.9% respectively. The results of survival analysis for subgroups were summarized in table below. Grade 1 or 2 treatment-related adverse events (TRAEs) occurred in 65.2% pts. No ≥ grade 3 TRAE was found. All hematological TRAEs occurred in patients received combination regimen. No TRAE-induced treatment termination occurred. The lower incidence of TRAE may partly attributed to that most pts (18/23) received lower initial dose (10mg) of anlotinib and the relatively shorter treatment duration. Conclusions: This study showed treatment with anlotinib alone or in combination with TMZ had promising efficacy and favorable tolerability in patients with recurrent HGG.[Table: see text]

To enhance the reliability of multifunctional sensors, a novel data validation strategy is presented by handling independent and related variables separately. The maximal information coefficient (MIC), which can measure the strength of the correlation between two variables, is applied to divide all variables of multifunctional sensors into related and independent. For one thing, the k-nearest neighbor (kNN) rule is introduced to accomplish fault detection and isolation of independent variables, and the grey predictive model GM(1,1), which has the advantages of low computation burden and high accuracy, is adopted to achieve data recovery of faulty independent variables. For another, the kernel principal component analysis (KPCA), which can handle possible non-linearity of data, is employed to realize fault detection of related variables. An iterative reconstruction-based contribution (IRBC) method is developed to isolate all faulty related variables, and data recovery of them are implemented using a fuzzy similarity (FS)-based reconstruction method based on the spatial correlations among related variables. An experimental system for multifunctional sensors is built to evaluate the proposed strategy, and the performance comparisons with its counterparts are also conducted.

Purpose This paper aims to enhance the reliability of self-validating multifunctional sensors. Design/methodology/approach An effective fault detection, isolation and data recovery (FDIR) strategy by using kernel principal component analysis (KPCA) coupled with gray bootstrap and fault reconstruction methods. Findings The proposed FDIR strategy is able to the address fault detection, isolation and data recovery problem of self-validating multifunctional sensors efficiently. Originality/value A KPCA-based model which can overcome the limitation of existing linear-based models is used to achieve the fault detection task. By using gray bootstrap method, the position of all faulty sensitive units can be calculated even under the multiple faults situation. A reconstruction-based contribution method is adopted to evaluate the amplitudes of the fault signals, and the fault-free output of the faulty sensitive units can be used to replace the fault output.

A novel fault detection, isolation, and data recovery (FDIR) approach for self-validating multifunctional sensors is presented in this paper. To improve the fault detection accuracy under multiple steady conditions for multifunctional sensors, a sparse non-negative matrix factorization (SNMF)-based model is employed to accomplish fault detection through a combination of newly proposed $C^{2}$ and squared prediction error ( SPE ) statistics. Furthermore, a self-adaptive multiple-variable reconstruction strategy (SMVR) is proposed to achieve high accuracy on multiple-fault isolation and data recovery for faulty sensitive units. The performance of the proposed approach is fully verified in a real experimental system for self-validating multifunctional sensors, and it is compared with those of other fault detection models, such as principal component analysis (PCA), non-negative matrix factorization (NMF), and fault isolation algorithms, such as PCA-based contribution plots and SNMF-based contribution plots. The experimental results demonstrate that the proposed approach provides an excellent solution to the FDIR of self-validating multifunctional sensors.

Existing deep convolutional neural network-based survival analysis neither consider the modern attention mechanism nor use 3D tomographic medical images such as magnetic resonance images (MRI). This paper for the first time presents a 3D deep convolutional neural network using attention mechanism for survival prediction from multiparametric MRI in glioblastoma (GBM) patients. The attention module is incorporated into the residual network to enhance the representation power of meaningful features while suppress unimportant ones. The proposed model achieves an C-index of 0.71 in the training dataset and 0.68 in an independent test dataset, which outperforms both the traditional Cox model (0.60,0.54) and the non-attentive model (0.63,0.61). It indicates that the proposed 3D attention network has the potential of offering better performance in predicting survival using MRI than traditional survival analysis.

Air pollution is one of the major threats to human health. The monitoring of toxic NO2 gas in urban air emission pollution is becoming increasingly important. Thus, the development of an NO2 sensor with low power consumption, low cost, and high performance is urgent. In this paper, a planar structural micro hotplate gas sensor based on an AlN ceramic substrate with an annular Pt film heater was designed and prepared by micro-electro-mechanical system (MEMS) technology, in which Pt/Nb/In2O3 composite semiconductor oxide was used as the sensitive material with a molar ratio of In:Nb = 9:1. The annular thermal isolation groove was designed around the heater to reduce the power consumption and improve the thermal response rate. Furthermore, the finite element simulation analysis of the thermal isolation structure of the sensor was carried out by using ANSYS software. The results show that a low temperature of 94 &deg, C, low power consumption of 150 mW, and low concentration detection of 1 to 10 ppm NO2 were simultaneously realized for the Nb-doped In2O3-based gas sensor. Our findings provide a promising strategy for the application of In2O3-based sensors in highly effective and low concentration NO2 detection.

Background Ependymal tumors are pathologically defined intrinsic neoplasms originating in the intracranial compartments or the spinal cord that affect both children and adults. The recently integrated classification of ependymomas based on both histological and molecular characteristics is capable of subgrouping patients with various prognoses. However, the application of histological and molecular markers in Chinese patients with ependymomas has rarely been reported. We aimed to demonstrate the significance of histological characteristics, the v-relavian reticuloendotheliosis viral oncogene homolog A (RELA) fusions and other molecular features in ependymal tumors. Methods We reviewed the histological characteristics of ependymal tumors using conventional pathological slides and investigate the RELA fusions and Cylclin D1 (CCND1) amplification by Fluorescence in situ hybridization (FISH) and trimethylation of histone 3 lysine 27 (H3K27me3) expression by immunohistochemistry (IHC) methods. SPSS software was used to analyze the data. Results We demonstrated that hypercellularity, atypia, microvascular proliferation, necrosis, mitosis, and an elevated Ki-67 index, were tightly associated with an advanced tumor grade. Tumor location, necrosis, mitosis and the Ki-67 index were related to the survival of the ependymomas, but Ki67 was the only independent prognostic factor. Additionally, RELA fusions, mostly presented in pediatric grade III intracranial ependymomas, indicated decreased survival times of patients, and closely related to the patients’ age, tumor grade, cellularity, cellular atypia, necrosis and Ki67 index in the intracranial ependymal tumors, whereas reduction of H3K27me3 predicted the worse prognosis in ependymal tumors. Conclusions Histological and molecular features facilitate tumor grading and prognostic predictions for ependymal tumors in Chinese patients.

To improve the fault identification accuracy of rolling bearing and effectively analyze the fault severity, a novel rolling bearing fault diagnosis and severity analysis method based on the fast sample entropy, the wavelet packet energy entropy, and a multiclass relevance vector machine is proposed in this paper. A fast sample entropy calculation method based on a kd tree is adopted to improve the real-time performance of fault detection in this paper. In view of the non-linearity and non-stationarity of the vibration signals, the vibration signal of the rolling bearing is decomposed into several sub-signals containing fault information by using a wavelet packet. Then, the energy entropy values of the sub-signals decomposed by the wavelet packet are calculated to generate the feature vectors for describing different fault types and severity levels of rolling bearings. The multiclass relevance vector machine modeled by the feature vectors of different fault types and severity levels is used to realize fault type identification and a fault severity analysis of the bearings. The proposed fault diagnosis and severity analysis method is fully evaluated by experiments. The experimental results demonstrate that the fault detection method based on the sample entropy can effectively detect rolling bearing failure. The fault feature extraction method based on the wavelet packet energy entropy can effectively extract the fault features of vibration signals and a multiclass relevance vector machine can identify the fault type and severity by means of the fault features contained in these signals. Compared with some existing bearing rolling fault diagnosis methods, the proposed method is excellent for fault diagnosis and severity analysis and improves the fault identification rate reaching as high as 99.47%.

The reliability monitoring of sensor arrays is a challenging and critical issue that directly influences the performance of a measurement and control system. In this paper, a novel strategy based on gray forecasting model GM(1,1) coupled with the bootstrap method is proposed for status self-validation of sensor arrays. The proposed strategy focuses on fault detection, isolation, and recovery (FDIR), data validation and dynamic measurement uncertainty estimation of the sensor arrays. The FDIR scheme can effectively detect and isolate sensor abrupt faults and simultaneously accomplish fault recovery with high accuracy and good timeliness. Furthermore, the proposed FDIR scheme has the advantage of discriminating between fault-free signals with sudden changes and undoubted abrupt faults through the trust mechanism. The model GM(1,1) is updated continuously by a metabolism method to improve the adaptivity of the strategy for reliability monitoring. After signal reconstruction, the data validation and dynamic measurement uncertainty can be evaluated by the bootstrap method without any prior information about measurands. A real metal-oxide gas sensor array experimental system is designed to verify the excellent performance of the proposed strategy. The experimental results demonstrate that the proposed approach is capable of conducting the status self-validation of sensor arrays effectively and improving the reliability of sensor arrays in engineering applications.

BACKGROUND: Glioblastoma Multiforme (GBM) patients with isocitrate dehydrogenase 1 (IDH1) mutations have significantly improved prognosis than those without such mutations. We aimed to preoperatively predict IDH1 mutation status in GBM using multiregional radiomics features from multiparametric magnetic resonance imaging (MRI). MATERIAL AND METHODS: In total 225 patients were recruited in this retrospective multicenter study. 1614 quantitative features were extracted from multiple tumor subregions (including enhancement area, non-enhancement area, necrosis and edema) in multiparametric MRI. After intensitynormalization, tumor subregion segmentation, resampling-based data balancing and relevant feature selection, a multiregional radiomics model was built using a machine-learning method for prediction of IDH1 mutation from a primary cohort (118 patients) and tested on an independent validation cohort (107 patients). Four single-region radiomics models with features from each tumor subregion, and a model combining multiregional features with clinical factors (age, sex, and Karnofsky performance status) were also built and tested. RESULTS: Among four single-region radiomics models, the model built from edema region achieved the best accuracy of 96% and the best F1-score of 0.75 in the independent validation cohort. The 8-feature multiregional radiomics model achieved an improved overall performance of an accuracy 96%, an AUC 0.90 and an F1-score 0.78 in the validation cohort, which significantly outperformed the single-region models. Among all predictive models, the model combining multiregional imaging features with patient age achieved the best performance of an accuracy 97%, an AUC 0.96 and an F1-score 0.84 in the validation cohort. CONCLUSION: The radiomics-based model built with a minimal set of multiregional features from multiparametric MRI has the potential to preoperatively detect the IDH1 mutation status in GBM patients. The proposed predictor may serve as a potential noninvasive biomarker to guide preoperative GBM patient care.

This study aimed to build a reliable radiomics model from magnetic resonance imaging (MRI) for pretreatment prediction of MGMT methylation status in Glioblastoma. High-throughput radiomics features were automatically extracted from multiparametric MRI, including location features, geometry features, intensity features and texture features. A machine learning method was used to select a minimal set of all-relevant features. Based on these selected features, a radiomics model were built by using a random forest classifier for MGMT methylation prediction from a primary cohort (133 patients) and tested on an independent validation cohort (60 patients). Predictive models combing radiomics features and clinical factors were built and evaluated. The radiomics model with 6 all-relevant features allowed pretreatment prediction of MGMT methylation (AUC = 0.88, accuracy = 80%). Combing clinical factors with radiomics features did not benefit the prediction performance. The proposed radiomics model could provide a tool to guide preoperative patient care and made a step forward radiomics-based precision medicine for GBM patients.

Brain tumors are the most common malignant neurologic tumors with the highest mortality and disability rate. Because of the delicate structure of the brain, the clinical use of several commonly used biopsy diagnosis is limited for brain tumors. Radiomics is an emerging technique for noninvasive diagnosis based on quantitative medical image analyses. However, current radiomics techniques are not standardized regarding feature extraction, feature selection, and decision making. In this paper, we propose a sparse representation-based radiomics (SRR) system for the diagnosis of brain tumors. First, we developed a dictionary learning- and sparse representation-based feature extraction method that exploits the statistical characteristics of the lesion area, leading to fine and more effective feature extraction compared with the traditional explicitly calculation-based methods. Then, we set up an iterative sparse representation method to solve the redundancy problem of the extracted features. Finally, we proposed a novel multi-feature collaborative sparse representation classification framework that introduces a new coefficient of regularization term to combine features from multi-modal images at the sparse representation coefficient level. Two clinical problems were used to validate the performance and usefulness of the proposed SRR system. One was the differential diagnosis between primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM), and the other was isocitrate dehydrogenase 1 estimation for gliomas. The SRR system had superior PCNSL and GBM differentiation performance compared with some advanced imaging techniques and yielded 11% better performance for estimating IDH1 compared with the traditional radiomics methods.

Background The pineal gland has been demonstrated to be involved in the development of mood and psychotic disorders. However, few studies have looked at the relationship between pineal region tumors and psychiatric disorders. Intracranial epidermoid cysts usually arise in the cerebellopontine angle area and are extremely rare in the pineal region. The case of pineal epidermoid cyst presenting as schizophrenia has never been reported before. Case Presentation We described the case of a 23-year-old man who presented to the hospital with symptoms suggestive of schizophrenia. During work-up, he was found to have a pineal lesion on brain magnetic resonance imaging. Total resection of the tumor was subsequently performed, and pathology confirmed an epidermoid cyst. One month after surgery, the patient's psychotic symptoms significantly improved free of drug and fully returned to work 3 months postoperatively. Conclusions This case highlights the importance of including mass lesions of the pineal region in the differential diagnosis of psychotic disorders. It also provides further support that the pineal region may play a role in the pathophysiology of psychiatric diseases, although more studies will be needed to elucidate this interesting connection.

Due to the totally different therapeutic regimens needed for primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM), accurate differentiation of the two diseases by noninvasive imaging techniques is important for clinical decision-making.Thirty cases of PCNSL and 66 cases of GBM with conventional T1-contrast magnetic resonance imaging (MRI) were analyzed in this study. Convolutional neural networks was used to segment tumor automatically. A modified scale invariant feature transform (SIFT) method was utilized to extract three-dimensional local voxel arrangement information from segmented tumors. Fisher vector was proposed to normalize the dimension of SIFT features. An improved genetic algorithm (GA) was used to extract SIFT features with PCNSL and GBM discrimination ability. The data-set was divided into a cross-validation cohort and an independent validation cohort by the ratio of 2:1. Support vector machine with the leave-one-out cross-validation based on 20 cases of PCNSL and 44 cases of GBM was employed to build and validate the differentiation model.Among 16,384 high-throughput features, 1356 features show significant differences between PCNSL and GBM with p0.05 and 420 features with p0.001. A total of 496 features were finally chosen by improved GA algorithm. The proposed method produces PCNSL vs. GBM differentiation with an area under the curve (AUC) curve of 99.1% (98.2%), accuracy 95.3% (90.6%), sensitivity 85.0% (80.0%) and specificity 100% (95.5%) on the cross-validation cohort (and independent validation cohort).Since the local voxel arrangement characterization provided by SIFT features, proposed method produced more competitive PCNSL and GBM differentiation performance by using conventional MRI than methods based on advanced MRI.

To build a reliable radiomics model from multiregional and multiparametric magnetic resonance imaging (MRI) for pretreatment prediction of O6-methylguanine-DNA methyltransferase (MGMT) promotor methylation status in glioblastoma multiforme (GBM). In this retrospective multicentre study, 1,705 multiregional radiomics features were automatically extracted from multiparametric MRI. A radiomics model with a minimal set of all-relevant features and a radiomics model with univariately-predictive and non-redundant features were built for MGMT methylation prediction from a primary cohort (133 patients) and tested on an independent validation cohort (60 patients). Predictive models combing clinical factors were built and evaluated. Both radiomics models were assessed on subgroups stratified by clinical factors. The radiomics model with six all-relevant features allowed pretreatment prediction of MGMT methylation (AUC=0.88, accuracy=80 %), which significantly outperformed the model with eight univariately-predictive and non-redundant features (AUC=0.76, accuracy=70 %). Combing clinical factors with radiomics features did not benefit the prediction performance. The all-relevant model achieved significantly better performance in stratified analysis. Radiomics model built from multiregional and multiparameter MRI may serve as a potential imaging biomarker for pretreatment prediction of MGMT methylation in GBM. The all-relevant features have the potential of offering better predictive power than the univariately-predictive and non-redundant features. • Multiregional and multiparametric MRI features reliably predicted MGMT methylation in multicentre cohorts. • All-relevant imaging features predicted MGMT methylation better than univariately-predictive and non-redundant features. • Combing clinical factors with radiomics features did not benefit the prediction performance.

In fully-automatic radiomics model for predicting overall survival (OS) of glioblastoma multiforme (GBM) patients, the effect of image standardization parameters such as voxel size, quantization method and gray level on model reproducibility and prognostic performance are still unclear. In this study, 45792 multiregional radiomics features were automatically extracted from multi-modality MR images with different voxel sizes, quantization methods, and gray levels. The feature reproducibility and prognostic performance were assessed. Multiparametric and fixed-parameter radiomics signatures were constructed based on a training cohort (60 patients). In an independent validation cohort (32 patients), the multiparametric signature achieved better performance for OS prediction (C-Index = 0.705, 95% CI: 0.672, 0.738) and significant stratification of patients into high- and low-risk groups (P = 0.0040, HR = 3.29, 95% CI: 1.40, 7.70), which outperformed the fixed-parameter signatures and conventional factors such as age, Karnofsky Performance Score and tumor volume. This study demonstrated that voxel size, quantization method and gray level had influence on reproducibility and prognosis of radiomics features for GBM OS prediction. An automatic method to determine the optimal parameter settings was provided. It indicated that multiparametric radiomics signature had the potential of offering better prognostic performance than fixed-parameter signatures.

Traditional radiomics models mainly rely on explicitly-designed handcrafted features from medical images. This paper aimed to investigate if deep features extracted via transfer learning can generate radiomics signatures for prediction of overall survival (OS) in patients with Glioblastoma Multiforme (GBM). This study comprised a discovery data set of 75 patients and an independent validation data set of 37 patients. A total of 1403 handcrafted features and 98304 deep features were extracted from preoperative multi-modality MR images. After feature selection, a six-deep-feature signature was constructed by using the least absolute shrinkage and selection operator (LASSO) Cox regression model. A radiomics nomogram was further presented by combining the signature and clinical risk factors such as age and Karnofsky Performance Score. Compared with traditional risk factors, the proposed signature achieved better performance for prediction of OS (C-index = 0.710, 95% CI: 0.588, 0.932) and significant stratification of patients into prognostically distinct groups (P

This paper identifies a MR imaging radiomics signature for prediction of overall survival (OS) in patients with glioblastoma multiforme (GBM). A fully-automatic radiomics model is presented, including automatic tumor segmentation, high-throughput features extraction, features selection, and multi-feature signature identification. The automatic GBM segmentation method employs a random forest classifier with a CRF spatial regulation where the importances of the multi-modality features are considered. After feature selection, a 4-feature radiomics signature is identified based on training data and further confirmed on independent validation data. The proposed signature succeeds to stratify patients into prognostically high-risk and low-risk groups, indicating the potential to facilitate the preoperative patient care of GBM patients.

This paper proposes a fully-automatic method for extraction of high-throughput MRI radiomics features in Glioblastoma Multiforme (GBM). First, the tumor subregions are automatically segmented from multi- modality MR images using a proposed random forest classifier with a conditional random field spatial regulation, where the importances of the multi-modality features are considered. Within the segmented subregions, 44928 high-order texture features are extracted at different voxel sizes by using different quantization methods with varying gray levels. The DICE score, sensitivity and specificity of the proposed automatic segmentation algorithm are calculated. The reproducibility of the extracted features against the changes in voxel sizes, quantization methods and gray levels are assessed quantitatively. The proposed radiomics method can be used for exploring of imaging biomarker and facilitate the pre-treatment care of GBM patients.

Machine Olfaction is a bionic detection technique that adopts electronic device to simulate biological olfactory system. As an information acquisition device, MOS gas sensor array is an important component of machine olfactory system. In this paper, a novel gas concentration estimation method based on multivariate relevance vector machine (MVRVM) is proposed for mixed gas detection by using MOS gas sensor array. The proposed method utilizes the excellent multivariate regression analysis performance of MVRVM to estimate any one analyte concentration in the mixed gas. To demonstrate the performance of proposed gas concentration estimation method, a machine olfactory system is designed and implemented. Gas concentration experiments with methane and carbon monoxide gas mixture as the research object were performed in the above machine olfactory system. Experimental results show that the proposed method can provide a good solution for mixed gas concentration estimation in the aspects of estimated accuracy and computational complexity.

The vibration signals of rolling bearing have the characteristics of nonlinearity and nonstationarity, in which a large number of working condition informations on rolling bearing are contained. By using vibration signals of rolling bearing, a novel rolling bearing fault diagnosis method based on ensemble empirical mode decomposition and permutation entropy (EEMD-PE) coupled with multiclass relevance vector machines (M-RVM) is proposed in this paper. The proposed method can decompose the vibration signals of rolling bearing to a series of intrinsic mode functions (IMFs) that contain different fault features of rolling bearing by using the self-adaptive decomposition ability of EEMD. Permutation entropy (PE) is used to extract the feature of each IMF and the fault feature vector of vibration singal is constituted by the PE values of IMFs. The M-RVM classifier is built by the feature vectors extracted from rolling bearing vibration samples in different fault modes. Moreover, the multiple faults identification result can be implemented by the MRVM classifier in the form of probability output. The experimental results demonstrate that the proposed fault diagnosis method is capable of effectively extracting fault features in vibration signal and improving the fault identification accuracy compared with the existing bearing fault diagnosis methods.

The traditional gas sensor array has been viewed as a simple apparatus for information acquisition in chemosensory systems. Gas sensor arrays frequently undergo impairments in the form of sensor failures that cause significant deterioration of the performance of previously trained pattern recognition models. Reliability monitoring of gas sensor arrays is a challenging and critical issue in the chemosensory system. Because of its importance, we design and implement a status self-validating gas sensor array prototype to enhance the reliability of its measurements. A novel fault detection, isolation, and diagnosis (FDID) strategy is presented in this paper. The principal component analysis-based multivariate statistical process monitoring model can effectively perform fault detection by using the squared prediction error statistic and can locate the faulty sensor in the gas sensor array by using the variables contribution plot. The signal features of gas sensor arrays for different fault modes are extracted by using ensemble empirical mode decomposition (EEMD) coupled with sample entropy (SampEn). The EEMD is applied to adaptively decompose the original gas sensor signals into a finite number of intrinsic mode functions (IMFs) and a residual. The SampEn values of each IMF and the residual are calculated to reveal the multi-scale intrinsic characteristics of the faulty sensor signals. Sparse representation-based classification is introduced to identify the sensor fault type for the purpose of diagnosing deterioration in the gas sensor array. The performance of the proposed strategy is compared with other different diagnostic approaches, and it is fully evaluated in a real status self-validating gas sensor array experimental system. The experimental results demonstrate that the proposed strategy provides an excellent solution to the FDID of status self-validating gas sensor arrays.

This paper proposed a radiomics model from magnetic resonance imaging (MRI) for Glioblastoma Multiforme (GBM) patients. One challenge of radiomics study is to reduce the redundancy of the features. Totally 466 radiomics features were extracted from automatically segmented tumors from T1, T1 contrast, T2, and FLAIR MRIs. The consensus clustering method was used and 10 feature clusters were obtained. All clusters had a prognostic association with survival, where three clusters had a mean C-index \(\ge \)0.60. The medoid features in each clusters with highest C-index were selected as radiomics signature candidates. The maximum and mean C-indices of the medoids are 0.75 and 0.68. The results demonstrated that the clusters reduced the data redundancy as well as generated clinical relevant radiomics features.

A novel self-validating strategy using grey bootstrap method (GBM) is proposed for data validation and dynamic uncertainty estimation of self-validating sensor. The failure detection, isolation, and recovery (FDIR) of self-validating sensor based on GM(1,1) predictor can simultaneously detect and isolate fault and accomplish failure recovery with high accuracy and good timeliness. Furthermore, the proposed FDIR scheme has good effectiveness of discriminating between fault-free signals with sudden changes and undoubted faults. In dynamic measurement process, because of unknown prior information about probability density functions (PDFs) of uncertainty sources, the uncertainty cannot be estimated by Guide to the Expression of Uncertainty in Measurement (GUM). The GBM can evaluate the measurement uncertainty by poor information and small sample. Experiment results show that the GBM strategy provides a good solution to data validation and dynamic uncertainty estimation of self-validating sensor.