A Study on Prognosis of Diffuse Glioma Based on Clinical Factors and Magnetic Resonance Imaging Radiomics.

OBJECTIVE: To construct an optimal prognostic model to assess the prognosis of patients with diffuse glioma. METHODS: Preoperative magnetic resonance imaging and clinical data were retrospectively collected from 266 patients (training cohort: validation cohort=7:3) with pathologically confirmed diffuse gliomas. A radiomics prognostic model (R-model) based on the radiomics features was constructed. A prognostic model based on clinical factors (C-model) and a fusion model (F-model) was also constructed. Based on the optimal model of three models, the nomogram was constructed. Finally, a "Prognosis Calculator for Diffuse Glioma" was constructed based on the nomogram. RESULTS: The c-index of the R-, C-, and F-models in the validation cohort was 0.742, 0.796, and 0.814, respectively. In the validation cohort, the 1-year area under the curve of the R-, C-, and F-models was 0.749, 0.806, and 0.836, respectively; the 3-year area under the curve was 0.896, 0.966, and 0.963, respectively. In the training cohort, validation cohort, all cohorts, and different grades of glioma cohorts, F-model (optimal model) could identify low- and high-risk groups well. The "Prognosis Calculator for Diffuse Glioma" was available at https://github.com/HDCurry/prognosis. CONCLUSIONS: Among the three models, the F-model (radiomics combined with clinical factors) had optimal predictive efficacy and could more accurately assess the prognosis of diffuse glioma. The "Prognosis Calculator for Diffuse Glioma" constructed based on this model could assist clinicians in more easily and accurately assessing the prognosis of patients with diffuse glioma, thus enabling them to make more reasonable treatment strategies.

Establishment of Human Pituitary Neuroendocrine Tumor Derived Organoid and Its Pilot Application for Drug Screening.

CONTEXT: Precision medicine for pituitary neuroendocrine tumors (PitNETs) is limited by the lack of reliable research models. OBJECTIVE: To generate patient-derived organoids (PDOs), which could serve as a platform for personalized drug screening for PitNET patients. DESIGN: From July 2019 to May 2022, a total of 32 human PitNET specimens were collected for the establishment of organoids with an optimized culture protocol. SETTING: This study was conducted at Sun Yat-Sen University Cancer Center. PATIENTS: PitNET patients who were pathologically confirmed were enrolled in this study. INTERVENTIONS: Histological staining and whole-exome sequencing were utilized to confirm the pathologic and genomic features of PDOs. A drug response assay on PDOs was also performed. MAIN OUTCOME MEASURES: PDOs retained key genetic and morphological features of their parental tumors. RESULTS: PDOs were successfully established from various types of PitNET samples with an overall success rate of 87.5%. Clinical nonfunctioning PitNETs-derived organoids (22/23, 95.7%) showed a higher likelihood of successful generation compared to those from functioning PitNETs (6/9, 66.7%). Preservation of cellular structure, subtype-specific neuroendocrine profiles, mutational features, and tumor microenvironment heterogeneity from parental tumors was observed. A distinctive response profile in drug tests was observed among the organoids from patients with different subtypes of PitNETs. With the validation of key characteristics from parental tumors in histological, genomic, and microenvironment heterogeneity consistency assays, we demonstrated the predictive value of the PDOs in testing individual drugs. CONCLUSION: The established PDOs, retaining typical features of parental tumors, indicate a translational significance in innovating personalized treatment for refractory PitNETs.

Retinal vessel segmentation method based on RSP-SA Unet network.

Segmenting retinal vessels plays a significant role in the diagnosis of fundus disorders. However, there are two problems in the retinal vessel segmentation methods. First, fine-grained features of fine blood vessels are difficult to be extracted. Second, it is easy to lose track of the details of blood vessel edges. To solve the problems above, the Residual SimAM Pyramid-Spatial Attention Unet (RSP-SA Unet) is proposed, in which the encoding, decoding, and upsampling layers of the Unet are mainly improved. Firstly, the RSP structure proposed in this paper approximates a residual structure combined with SimAM and Pyramid Segmentation Attention (PSA), which is applied to the encoding and decoding parts to extract multi-scale spatial information and important features across dimensions at a finer level. Secondly, the spatial attention (SA) is used in the upsampling layer to perform multi-attention mapping on the input feature map, which could enhance the segmentation effect of small blood vessels with low contrast. Finally, the RSP-SA Unet is verified on the CHASE_DB1, DRIVE, and STARE datasets, and the segmentation accuracy (ACC) of the RSP-SA Unet could reach 0.9763, 0.9704, and 0.9724, respectively. Area under the ROC curve (AUC) could reach 0.9896, 0.9858, and 0.9906, respectively. The RSP-SA Unet overall performance is better than the comparison methods.

Improved prediction of hourly PM2.5 concentrations with a long short-term memory and spatio-temporal causal convolutional network deep learning model.

Accurate prediction of particulate matter with aerodynamic diameter ≤ 2.5 µm (PM2.5) is important for environmental management and human health protection. In recent years, many efforts have been devoted to develop air quality predictions using the machine learning and deep learning techniques. In this study, we propose a deep learning model for short-term PM2.5 predictions. The salient feature of the proposed model is that the convolution in the model architecture is causal, where the output of a time step is only convolved with components of the same or earlier time step from the previous layer. The model also weighs the spatial correlation between multiple monitoring stations. Through temporal and spatial correlation analysis, relevant information is screened from the monitoring stations with a strong relationship with the target station. Information from the target and related sites is then taken as input and fed into the model. A case study is conducted in Nanjing, China from January 1, 2020 to December 31, 2020. Using historical air quality and meteorological data from nine monitoring stations, the model predicts PM2.5 concentrations for the next hour. The experimental results show that the predicted PM2.5 concentrations are consistent with observation, with correlation coefficient (R2) and Root Mean Squared Error (RMSE) of our model are 0.92 and 6.75 µg/m3. Additionally, to better understand the factors affecting PM2.5 levels in different seasons, a machine learning algorithm based on Principal Component Analysis (PCA) is used to analyze the correlations between PM2.5 and its influencing factors. By identifying the main factors affecting PM2.5 and optimizing the input of the predictive model, the application of PCA in the model further improves the prediction accuracy, with decrease of up to 17.2 % in RMSE and 38.6 % in mean absolute error (MAE). The deep learning model established in this study provide a valuable tool for air quality management and public health protection.

Refined composite moving average fluctuation dispersion entropy and its application on rolling bearing fault diagnosis.

Vibration signal analysis based on multiscale entropy is one of the important means to realize rotating machinery fault diagnosis. However, the length of the time series will be shortened during the coarse-graining process with the increase of the scale factor, which makes the calculated entropy values unstable. This inherent drawback of the coarse-graining method limits its application in fault feature extraction. This paper presents a novel feature extraction method for vibration signals called refined composite moving average fluctuation dispersion entropy (RCMAFDE). It is verified by simulation experiments that RCMAFDE has high stability of entropy values under different time series lengths as well as different disturbances. The RCMAFDE was applied to the fault diagnosis of rolling bearings, and a new fault diagnosis method of rolling bearings was proposed by combining RCMAFDE and kernel extreme learning machine (KELM) optimized by the chaos sparrow search optimization algorithm (CSSOA). First, the vibration signal is preprocessed to form a sample set, and then, the fault feature vector is calculated by RCMAFDE. Finally, the feature vector set is input into the CSSOA-KELM model for training and testing, and the fault diagnosis result is output. To demonstrate the effectiveness and feasibility of the fault diagnosis method, two publicly available datasets and a self-collected dataset are used for experimental validation. The experimental results show that the proposed fault diagnosis method can extract the nonlinear dynamic complexity information of vibration signals more effectively compared with the comparison methods and obtain the highest fault identification accuracy under different datasets.

The Association Between Socioeconomic Factors at Diagnosis and Survival in Medulloblastoma: A Propensity Score-Matched Analysis and Population-Based Study.

BACKGROUND: Medulloblastoma (MB) is the most common malignant brain tumor of childhood. The associations between socioeconomic statuses (SES) and survival outcomes of medulloblastoma remain unclear. The aim of this study was to develop a nomogram to predict medulloblastoma specific death (MBSD) and overall survival (OS) in patients with medulloblastoma, taking into account socioeconomic factors in patients with medulloblastoma. METHODS: We included patients diagnosed with MB between 1975 and 2016 from the Surveillance, Epidemiology, and End Results database. Propensity Score Matching (PSM) was performed to reduce selection bias. 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: A total of 2660 patients were enrolled after matching. Study showed unemployed rate (MBSD, high level vs. low level, P = 0.020) (OS, high level vs. low level, P = 0.017), and marital status (OS, married vs unmarried/unknown, P = 0.029) were important factors affecting prognosis of medulloblastoma in male. Meanwhile, median household income (MBSD, quartile 1 vs. quartile 3, P = 0.047) (OS, quartile 1 vs. quartile 2, P = 0.017) (OS, quartile 1 vs. quartile 3, P = 0.014), residence (MBSD, urban vs. rural, P = 0.041), and insurance status (MBSD, insured vs. uninsured/unknown, P = 0.002)(OS, insured vs. uninsured/unknown, P = 0.001) were significant factors affecting 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 MB have provided a scenario for 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, long-term psychological, financial and medical burdens that these children and their families must bear, it is critical to identify and address these gaps.

Radiomics-based survival risk stratification of glioblastoma is associated with different genome alteration.

BACKGROUND: Glioblastoma (GBM) is a remarkable heterogeneous tumor with few non-invasive, repeatable, and cost-effective prognostic biomarkers reported. In this study, we aim to explore the association between radiomic features and prognosis and genomic alterations in GBM. METHODS: A total of 180 GBM patients (training cohort: n = 119; validation cohort 1: n = 37; validation cohort 2: n = 24) were enrolled and underwent preoperative MRI scans. From the multiparametric (T1, T1-Gd, T2, and T2-FLAIR) MR images, the radscore was developed to predict overall survival (OS) in a multistep postprocessing workflow and validated in two external validation cohorts. The prognostic accuracy of the radscore was assessed with concordance index (C-index) and Brier scores. Furthermore, we used hierarchical clustering and enrichment analysis to explore the association between image features and genomic alterations. RESULTS: The MRI-based radscore was significantly correlated with OS in the training cohort (C-index: 0.70), validation cohort 1 (C-index: 0.66), and validation cohort 2 (C-index: 0.74). Multivariate analysis revealed that the radscore was an independent prognostic factor. Cluster analysis and enrichment analysis revealed that two distinct phenotypic clusters involved in distinct biological processes and pathways, including the VEGFA-VEGFR2 signaling pathway (q-value = 0.033), JAK-STAT signaling pathway (q-value = 0.049), and regulation of MAPK cascade (q-value = 0.0015/0.025). CONCLUSIONS: Radiomic features and radiomics-derived radscores provided important phenotypic and prognostic information with great potential for risk stratification in GBM.

Adjuvant Temozolomide Chemotherapy With or Without Interferon Alfa Among Patients With Newly Diagnosed High-grade Gliomas: A Randomized Clinical Trial.

Importance: High-grade gliomas (HGGs) constitute the most common and aggressive primary brain tumor, with 5-year survival rates of 30.9% for grade 3 gliomas and 6.6% for grade 4 gliomas. The add-on efficacy of interferon alfa is unclear for the treatment of HGG. Objectives: To compare the therapeutic efficacy and toxic effects of the combination of temozolomide and interferon alfa and temozolomide alone in patients with newly diagnosed HGG. Design, Setting, and Participants: This multicenter, randomized, phase 3 clinical trial enrolled 199 patients with newly diagnosed HGG from May 1, 2012, to March 30, 2016, at 15 Chinese medical centers. Follow-up was completed July 31, 2021, and data were analyzed from September 13 to November 24, 2021. Eligible patients were aged 18 to 75 years with newly diagnosed and histologically confirmed HGG and had received no prior chemotherapy, radiotherapy, or immunotherapy for their HGG. Interventions: All patients received standard radiotherapy concurrent with temozolomide. After a 4-week break, patients in the temozolomide with interferon alfa group received standard temozolomide combined with interferon alfa every 28 days. Patients in the temozolomide group received standard temozolomide. Main Outcomes and Measures: The primary end point was 2-year overall survival (OS). Secondary end points were 2-year progression-free survival (PFS) and treatment tolerability. Results: A total of 199 patients with HGG were enrolled, with a median follow-up time of 66.0 (95% CI, 59.1-72.9) months. Seventy-nine patients (39.7%) were women and 120 (60.3%) were men, with ages ranging from 18 to 75 years and a median age of 46.9 (95% CI, 45.3-48.7) years. The median OS of patients in the temozolomide plus interferon alfa group (26.7 [95% CI, 21.6-31.7] months) was significantly longer than that in the standard group (18.8 [95% CI, 16.9-20.7] months; hazard ratio [HR], 0.64 [95% CI, 0.47-0.88]; P = .005). Temozolomide plus interferon alfa also significantly improved median OS in patients with O6-methylguanine-DNA methyltransferase (MGMT) unmethylation (24.7 [95% CI, 20.5-28.8] months) compared with temozolomide (17.4 [95% CI, 14.1-20.7] months; HR, 0.57 [95% CI, 0.37-0.87]; P = .008). Seizure and influenzalike symptoms were more common in the temozolomide plus interferon alfa group, with 2 of 100 (2.0%) and 5 of 100 (5.0%) patients with grades 1 and 2 toxic effects, respectively (P = .02). Finally, results suggested that methylation level at the IFNAR1/2 promoter was a marker of sensitivity to temozolomide plus interferon alfa. Conclusions and Relevance: Compared with the standard regimen, temozolomide plus interferon alfa treatment could prolong the survival time of patients with HGG, especially the MGMT promoter unmethylation variant, and the toxic effects remained tolerable. Trial Registration: ClinicalTrials.gov Identifier: NCT01765088.

Imaging phenotypes from MRI for the prediction of glioma immune subtypes from RNA sequencing: A multicenter study.

Tumor subtyping based on its immune landscape may guide precision immunotherapy. The aims of this study were to identify immune subtypes of adult diffuse gliomas with RNA sequencing data, and to noninvasively predict this subtype using a biologically interpretable radiomic signature from MRI. A subtype discovery dataset (n = 210) from a public database and two radiogenomic datasets (n = 130 and 55, respectively) from two local hospitals were included. Brain tumor microenvironment-specific signatures were constructed from RNA sequencing to identify the immune types. A radiomic signature was built from MRI to predict the identified immune subtypes. The pathways underlying the radiomic signature were identified to annotate their biological meanings. The reproducibility of the findings was verified externally in multicenter datasets. Three distinctive immune subtypes were identified, including an inflamed subtype marked by elevated hypoxia-induced immunosuppression, a "cold" subtype that exhibited scarce immune infiltration with downregulated antigen presentation, and an intermediate subtype that showed medium immune infiltration. A 10-feature radiomic signature was developed to predict immune subtypes, achieving an AUC of 0.924 in the validation dataset. The radiomic features correlated with biological functions underpinning immune suppression, which substantiated the hypothesis that molecular changes can be reflected by radiomic features. The immune subtypes, predictive radiomic signature, and radiomics-correlated biological pathways were validated externally. Our data suggest that adult-type diffuse gliomas harbor three distinctive immune subtypes that can be predicted by MRI radiomic features with clear biological significance. The immune subtypes, radiomic signature, and radiogenomic links can be replicated externally.

Predicting glioblastoma molecular subtypes and prognosis with a multimodal model integrating convolutional neural network, radiomics, and semantics.

OBJECTIVE: The aim of this study was to build a convolutional neural network (CNN)-based prediction model of glioblastoma (GBM) molecular subtype diagnosis and prognosis with multimodal features. METHODS: In total, 222 GBM patients were included in the training set from Sun Yat-sen University Cancer Center (SYSUCC) and 107 GBM patients were included in the validation set from SYSUCC, Xuanwu Hospital Capital Medical University, and the First Hospital of Jilin University. The multimodal model was trained with MR images (pre- and postcontrast T1-weighted images and T2-weighted images), corresponding MRI impression, and clinical patient information. First, the original images were segmented using the Multimodal Brain Tumor Image Segmentation Benchmark toolkit. Convolutional features were extracted using 3D residual deep neural network (ResNet50) and convolutional 3D (C3D). Radiomic features were extracted using pyradiomics. Report texts were converted to word embedding using word2vec. These three types of features were then integrated to train neural networks. Accuracy, precision, recall, and F1-score were used to evaluate the model performance. RESULTS: The C3D-based model yielded the highest accuracy of 91.11% in the prediction of IDH1 mutation status. Importantly, the addition of semantics improved precision by 11.21% and recall in MGMT promoter methylation status prediction by 14.28%. The areas under the receiver operating characteristic curves of the C3D-based model in the IDH1, ATRX, MGMT, and 1-year prognosis groups were 0.976, 0.953, 0.955, and 0.976, respectively. In external validation, the C3D-based model showed significant improvement in accuracy in the IDH1, ATRX, MGMT, and 1-year prognosis groups, which were 88.30%, 76.67%, 85.71%, and 85.71%, respectively (compared with 3D ResNet50: 83.51%, 66.67%, 82.14%, and 70.79%, respectively). CONCLUSIONS: The authors propose a novel multimodal model integrating C3D, radiomics, and semantics, which had a great performance in predicting IDH1, ATRX, and MGMT molecular subtypes and the 1-year prognosis of GBM.

Longest survival with primary intracranial malignant melanoma: A case report and literature review.

BACKGROUND: Primary intracranial malignant melanoma (PIMM) is rare, and its prognosis is very poor. It is not clear what systematic treatment strategy can achieve long-term survival. This case study attempted to identify the optimal strategy for long-term survival outcomes by reviewing the PIMM patient with the longest survival following comprehensive treatment and by reviewing the related literature. CASE SUMMARY: The patient is a 47-year-old Chinese man who suffered from dizziness and gait disturbance. He underwent surgery for right cerebellum melanoma and was subsequently diagnosed by pathology in June 2000. After the surgery, the patient received three cycles of chemotherapy but relapsed locally within 4 mo. Following the second surgery for total tumor resection, the patient received an injection of Newcastle disease virus-modified tumor vaccine, interferon, and ß-elemene treatment. The patient was tumor-free with a normal life for 21 years before the onset of the recurrence of melanoma without any symptoms in July 2021. A third gross-total resection with adjuvant radiotherapy and temozolomide therapy was performed. Brain magnetic resonance imaging showed no residual tumor or recurrence 3 mo after the 3rd operation, and the patient recovered well without neurological dysfunction until the last follow-up in June 2022, which was 22 years following the initial treatment. CONCLUSION: It is important for patients with PIMM to receive comprehensive treatment to enable the application of the most appropriate treatment strategies. Long-term survival is not impossible in patients with these malignancies.

A Novel Fault Diagnosis Method for Rolling Bearing Based on Hierarchical Refined Composite Multiscale Fluctuation-Based Dispersion Entropy and PSO-ELM.

This paper proposes a novel fault diagnosis method for rolling bearing based on hierarchical refined composite multiscale fluctuation-based dispersion entropy (HRCMFDE) and particle swarm optimization-based extreme learning machine (PSO-ELM). First, HRCMFDE is used to extract fault features in the vibration signal at different time scales. By introducing the hierarchical theory algorithm into the vibration signal decomposition process, the problem of missing high-frequency signals in the coarse-grained process is solved. Fluctuation-based dispersion entropy (FDE) has the characteristics of insensitivity to noise interference and high computational efficiency based on the consideration of nonlinear time series fluctuations, which makes the extracted feature vectors more effective in describing the fault information embedded in each frequency band of the vibration signal. Then, PSO is used to optimize the input weights and hidden layer neuron thresholds of the ELM model to improve the fault identification capability of the ELM classifier. Finally, the performance of the proposed rolling bearing fault diagnosis method is verified and analyzed by using the CWRU dataset and MFPT dataset as experimental cases, respectively. The results show that the proposed method has high identification accuracy for the fault diagnosis of rolling bearings with varying loads and has a good load migration effect.

A Novel Reconstruction Method for Temperature Distribution Measurement Based on Ultrasonic Tomography.

The precise temperature distribution measurement is crucial in many industrial fields, where ultrasonic tomography (UT) has broad application prospects and significance. In order to improve the resolution of reconstructed temperature distribution images and maintain high accuracy, a novel two-step reconstruction method is proposed in this article. First, the problem of solving the temperature distribution is converted to an optimization problem and then solved by an improved version of the equilibrium optimizer (IEO), in which a new nonlinear time strategy and novel population update rules are deployed. Then, based on the low-resolution and high-precision images reconstructed by IEO, Gaussian process regression (GPR) is adopted to enhance image resolution and keep the reconstruction errors low. After that, the number of divided grids and the parameters of IEO are also further studied to improve the reconstruction quality. The results of numerical simulations and experiments indicate that high-resolution images with low reconstruction errors can be reconstructed effectively by the proposed IEO-GPR method, and it also shows excellent robust performance. For a complex three-peak temperature distribution, a competitive accuracy with 3.10% and 2.37% error at root-mean-square error and average relative error is achieved, respectively. In practical experiment, the root-mean-square error of IEO-GPR is 0.72%, which is at least 0.89% lower than that of conventional algorithms.

Glioma survival prediction from whole-brain MRI without tumor segmentation using deep attention network: a multicenter study.

OBJECTIVES: To develop and validate a deep learning model for predicting overall survival from whole-brain MRI without tumor segmentation in patients with diffuse gliomas. METHODS: In this multicenter retrospective study, two deep learning models were built for survival prediction from MRI, including a DeepRisk model built from whole-brain MRI, and an original ResNet model built from expert-segmented tumor images. Both models were developed using a training dataset (n = 935) and an internal tuning dataset (n = 156) and tested on two external test datasets (n = 194 and 150) and a TCIA dataset (n = 121). C-index, integrated Brier score (IBS), prediction error curves, and calibration curves were used to assess the model performance. RESULTS: In total, 1556 patients were enrolled (age, 49.0 ± 13.1 years; 830 male). The DeepRisk score was an independent predictor and can stratify patients in each test dataset into three risk subgroups. The IBS and C-index for DeepRisk were 0.14 and 0.83 in external test dataset 1, 0.15 and 0.80 in external dataset 2, and 0.16 and 0.77 in TCIA dataset, respectively, which were comparable with those for original ResNet. The AUCs at 6, 12, 24, 26, and 48 months for DeepRisk ranged between 0.77 and 0.94. Combining DeepRisk score with clinicomolecular factors resulted in a nomogram with a better calibration and classification accuracy (net reclassification improvement 0.69, p < 0.001) than the clinical nomogram. CONCLUSIONS: DeepRisk that obviated the need of tumor segmentation can predict glioma survival from whole-brain MRI and offers incremental prognostic value. KEY POINTS: • DeepRisk can predict overall survival directly from whole-brain MRI without tumor segmentation. • DeepRisk achieves comparable accuracy in survival prediction with deep learning model built using expert-segmented tumor images. • DeepRisk has independent and incremental prognostic value over existing clinical parameters and IDH mutation status.

Deep Learning Radiomics to Predict PTEN Mutation Status From Magnetic Resonance Imaging in Patients With Glioma.

OBJECTIVES: Phosphatase 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. METHODS: In 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). RESULTS: The 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). CONCLUSIONS: The 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.

Imbalanced data fault diagnosis of hydrogen sensors using deep convolutional generative adversarial network with convolutional neural network.

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.

Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities.

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.

Biologic Pathways Underlying Prognostic Radiomics Phenotypes from Paired MRI and RNA Sequencing in Glioblastoma.

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.

Complications following titanium cranioplasty compared with nontitanium implants cranioplasty: A systematic review and meta-analysis.

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.