Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma

Assessment of MGMT promoter methylation status in glioblastoma using deep learning features from multi-sequence MRI of intratumoral and peritumoral regions

OBJECTIVE

This study aims to evaluate the effectiveness of deep learning features derived from multi-sequence magnetic resonance imaging (MRI) in determining the O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status among glioblastoma patients.

METHODS

Clinical, pathological, and MRI data of 356 glioblastoma patients (251 methylated, 105 unmethylated) were retrospectively examined from the public dataset The Cancer Imaging Archive. Each patient underwent preoperative multi-sequence brain MRI scans, which included T1-weighted imaging (T1WI) and contrast-enhanced T1-weighted imaging (CE-T1WI). Regions of interest (ROIs) were delineated to identify the necrotic tumor core (NCR), enhancing tumor (ET), and peritumoral edema (PED). The ET and NCR regions were categorized as intratumoral ROIs, whereas the PED region was categorized as peritumoral ROIs. Predictive models were developed using the Transformer algorithm based on intratumoral, peritumoral, and combined MRI features. The area under the receiver operating characteristic curve (AUC) was employed to assess predictive performance.

RESULTS

The ROI-based models of intratumoral and peritumoral regions, utilizing deep learning algorithms on multi-sequence MRI, were capable of predicting MGMT promoter methylation status in glioblastoma patients. The combined model of intratumoral and peritumoral regions exhibited superior diagnostic performance relative to individual models, achieving an AUC of 0.923 (95% confidence interval [CI]: 0.890 - 0.948) in stratified cross-validation, with sensitivity and specificity of 86.45% and 87.62%, respectively.

CONCLUSION

The deep learning model based on MRI data can effectively distinguish between glioblastoma patients with and without MGMT promoter methylation.

Artificial intelligence in fracture detection on radiographs: a literature review

Fractures are one of the most common reasons of admission to emergency department affecting individuals of all ages and regions worldwide that can be misdiagnosed during radiologic examination. Accurate and timely diagnosis of fracture is crucial for patients, and artificial intelligence that uses algorithms to imitate human intelligence to aid or enhance human performs is a promising solution to address this issue. In the last few years, numerous commercially available algorithms have been developed to enhance radiology practice and a large number of studies apply artificial intelligence to fracture detection. Recent contributions in literature have described numerous advantages showing how artificial intelligence performs better than doctors who have less experience in interpreting musculoskeletal X-rays, and assisting radiologists increases diagnostic accuracy and sensitivity, improves efficiency, and reduces interpretation time. Furthermore, algorithms perform better when they are trained with big data on a wide range of fracture patterns and variants and can provide standardized fracture identification across different radiologist, thanks to the structured report. In this review article, we discuss the use of artificial intelligence in fracture identification and its benefits and disadvantages. We also discuss its current potential impact on the field of radiology and radiomics.

Contrast-enhanced ultrasound can differentiate the level of glioma infiltration and correlate it with biological behavior: a study based on local pathology

PURPOSE

The objective of this study is to assess the diagnostic efficacy of contrast-enhanced ultrasound (CEUS) in determining the level of glioma infiltration and to investigate its correlation with pathological markers.

METHODS

A prospective study involving 16 adult glioma patients was conducted. Preoperative US-(Magnetic Resonance)MR fusion imaging was utilized for tumor infiltration localization, while CEUS was employed to assess hemodynamic alterations. Parameters such as peak intensity (PI), rise time (RT), time to peak (TTP), and area under the curve (AUC) were measured. Utilizing contralateral normal brain tissue as the reference standard. The Kruskal-Wallis H-test was conducted to compare CEUS and pathological parameters (significance level, p < 0.05; bonferroni correction) among tumor margins, infiltration zones, and normal tissues, as well as between low-grade glioma (LGG) and high-grade glioma (HGG) within the infiltration zone, based on whole slide pathological images analysis. Spearman correlation analysis was employed to determine the correlation coefficient between hemodynamics and pathology. Receiver operating characteristic (ROC) curves were drawn to evaluate the performance of CEUS in tumor classification.

RESULTS

From tumor margin to normal tissue, PI, AUC, Ki67, EGFR, and 1p/19q showed a significant decreasing trend, while TTP, IDH-1, and MGMT gradually increased. RT was lower at the tumor margin but did not show statistically significant differences. In the infiltration zones, there was a significant increase in parameters such as PI, normalized PI (Nor_PI), AUC, and Ki67 from LGG to HGG, while RT, Nor_RT, TTP, Nor_TTP, IDH-1, and MGMT significantly decreased. Nor_AUC and EGFR increased but were not significant, and 1p/19q decreased but was not significant. RT and Nor_TTP were independent risk factors for distinguishing between LGG and HGG in the infiltration zone, with a combined diagnostic efficacy ROC of 0.891. The sensitivity reached 96.64% and the specificity reached 82.35%. There was a significant correlation between hemodynamic indicators and pathological indicators. CEUS can effectively differentiate levels of infiltration zones, which correlates with their biological behavior, with RT + Nor_TTP showing particularly highest diagnostic efficacy.

CONCLUSION

These findings contribute to improving the accuracy of diagnosing infiltration zones and provide essential biological insights for subsequent treatments.

Phenotypic approaches for CNS drugs

Central nervous system (CNS) drug development is plagued by high clinical failure rate. Phenotypic assays promote clinical translation of drugs by reducing complex brain diseases to measurable, clinically valid phenotypes. We critique recent platforms integrating patient-derived brain cells, which most accurately recapitulate CNS disease phenotypes, with higher throughput models, including immortalized cells, to balance validity and scalability. These platforms were screened with conventional commercial chemogenomic compound libraries. We explore emerging library curation strategies to improve hit rate and quality, and screening novel fragment libraries as alternatives, for more tractable drug target deconvolution. The clinically relevant models used in these platforms could harbor important, unidentified drug targets, so we review evolving agnostic target deconvolution approaches, including chemical proteomics and artificial intelligence (AI), which aid in phenotypic screening hit mechanism elucidation, thereby facilitating rational hit-to-drug optimization.

Correlation of Edema/Tumor Index With Histopathological Outcomes According to the WHO Classification of Cranial Tumors

BACKGROUND

Metastatic brain tumors are a prevalent challenge in neurosurgery, with vasogenic edema being a significant consequence of these lesions. Despite the critical role of peritumoral edema in prognosis and patient outcomes, few studies have quantified its diagnostic and prognostic implications. This study aims to evaluate the correlation between the edema/tumor index (ETI) and histopathological outcomes according to the 2021 WHO classification of cranial tumors.

METHODOLOGY

We conducted a retrospective analysis of Digital Imaging and Communications in Medicine (DICOM)-format magnetic resonance imaging (MRI) data from May 2023 to May 2024, applying manual 3D volumetric segmentation using Image Tool Kit-SNAP (ITK-SNAP, version 3.8.0, University of Pennsylvania) software. The ETI was calculated by dividing the volume of peritumoral edema by the tumor volume. The study included 60 patients, and statistical analyses were performed to assess the correlation between ETI and tumor histopathology, including Receiver Operating Characteristic (ROC) curve analysis for cutoff points.

RESULTS

A total of 60 patients were included in the study, with 27 males (45%) and 33 females (55%). The average tumor volume measured by 3D segmentation was 46.9 cubic centimeters (cc) (standard deviation [SD] ± 25.6), and the average peritumoral edema volume was 79 cc (SD ± 37.5) for malignant tumors. The ETI was calculated for each case. Malignant tumors (WHO grades 3 and 4) had a mean ETI of 1.6 (SD ± 1.2), while non-malignant tumors (WHO grades 1 and 2) had a mean ETI of 1.2 (SD ± 1.1), but this difference was not statistically significant (P = 0.51). ROC curve analysis for the ETI did not provide a reliable cutoff point for predicting tumor malignancy (area under the curve [AUC] = 0.59, P = 0.20). Despite the larger edema volume observed in malignant tumors, the ETI did not correlate significantly with the histopathological grade.

CONCLUSIONS

This study found no significant correlation between the ETI and the histopathological grade of brain tumors according to the 2021 WHO classification. While malignant tumors were associated with larger volumes of both tumor and peritumoral edema, the ETI did not prove to be a reliable predictor of tumor malignancy. Therefore, the ETI should not be used as a standalone metric for determining tumor aggressiveness or guiding clinical decision-making. Further studies with larger cohorts are required to better understand the potential prognostic value of the ETI in brain tumors.

Spatial transcriptomics analysis identifies therapeutic targets in diffuse high-grade gliomas

Introduction

Diffuse high-grade gliomas are the most common malignant adult neuroepithelial tumors in humans and a leading cause of cancer-related death worldwide. The advancement of high throughput transcriptome sequencing technology enables rapid and comprehensive acquisition of transcriptome data from target cells or tissues. This technology aids researchers in understanding and identifying critical therapeutic targets for the prognosis and treatment of diffuse high-grade glioma.

Methods

Spatial transcriptomics was conducted on two cases of isocitrate dehydrogenase (IDH) wild-type diffuse high-grade glioma (Glio-IDH-wt) and two cases of IDH-mutant diffuse high-grade glioma (Glio-IDH-mut). Gene set enrichment analysis and clustering analysis were employed to pinpoint differentially expressed genes (DEGs) involved in the progression of diffuse high-grade gliomas. The spatial distribution of DEGs in the spatially defined regions of human glioma tissues was overlaid in the t-distributed stochastic neighbor embedding (t-SNE) plots.

Results

We identified a total of 10,693 DEGs, with 5,677 upregulated and 5,016 downregulated, in spatially defined regions of diffuse high-grade gliomas. Specifically, SPP1, IGFBP2, CALD1, and TMSB4X exhibited high expression in carcinoma regions of both Glio-IDH-wt and Glio-IDH-mut, and 3 upregulated DEGs (SMOC1, APOE, and HIPK2) and 4 upregulated DEGs (PPP1CB, UBA52, S100A6, and CTSB) were only identified in tumor regions of Glio-IDH-wt and Glio-IDH-mut, respectively. Moreover, Kyoto Encyclopedia of Genes and Genomes (KEGG) and gene ontology (GO) enrichment analyses revealed that upregulated DEGs were closely related to PI3K/Akt signaling pathway, virus infection, and cytokine-cytokine receptor interaction. Importantly, the expression of these DEGs was validated using GEPIA databases. Furthermore, the study identified spatial expression patterns of key regulatory genes, including those involved in protein post-translational modification and RNA binding protein-encoding genes, with spatially defined regions of diffuse high-grade glioma.

Discussion

Spatial transcriptome analysis is one of the breakthroughs in the field of medical biotechnology as this can map the analytes such as RNA information in their physical location in tissue sections. Our findings illuminate previously unexplored spatial expression profiles of key biomarkers in diffuse high-grade glioma, offering novel insight for the development of therapeutic strategies in glioma.

Development of a prognostic model related to homologous recombination deficiency in glioma based on multiple machine learning

Background

Despite advances in neuro-oncology, treatments of glioma and tools for predicting the outcome of patients remain limited. The objective of this research is to construct a prognostic model for glioma using the Homologous Recombination Deficiency (HRD) score and validate its predictive capability for glioma.

Methods

We consolidated glioma datasets from TCGA, various cancer types for pan-cancer HRD analysis, and two additional glioma RNAseq datasets from GEO and CGGA databases. HRD scores, mutation data, and other genomic indices were calculated. Using machine learning algorithms, we identified signature genes and constructed an HRD-related prognostic risk model. The model's performance was validated across multiple cohorts. We also assessed immune infiltration and conducted molecular docking to identify potential therapeutic agents.

Results

Our analysis established a correlation between higher HRD scores and genomic instability in gliomas. The model, based on machine learning algorithms, identified seven key genes, significantly predicting patient prognosis. Moreover, the HRD score prognostic model surpassed other models in terms of prediction efficacy across different cancers. Differential immune cell infiltration patterns were observed between HRD risk groups, with potential implications for immunotherapy. Molecular docking highlighted several compounds, notably Panobinostat, as promising for high-risk patients.

Conclusions

The prognostic model based on the HRD score threshold and associated genes in glioma offers new insights into the genomic and immunological landscapes, potentially guiding therapeutic strategies. The differential immune profiles associated with HRD-risk groups could inform immunotherapeutic interventions, with our findings paving the way for personalized medicine in glioma treatment.

Construction and validation of a machine learning-based immune-related prognostic model for glioma

BACKGROUND

Glioma stands as the most prevalent primary brain tumor found within the central nervous system, characterized by high invasiveness and treatment resistance. Although immunotherapy has shown potential in various tumors, it still faces challenges in gliomas. This study seeks to develop and validate a prognostic model for glioma based on immune-related genes, to provide new tools for precision medicine.

METHODS

Glioma samples were obtained from a database that includes the ImmPort database. Additionally, we incorporated ten machine learning algorithms to assess the model's performance using evaluation metrics like the Harrell concordance index (C-index). The model genes were further studied using GSCA, TISCH2, and HPA databases to understand their role in glioma pathology at the genomic, molecular, and single-cell levels, and validate the biological function of IKBKE in vitro experiments.

RESULTS

In this study, a total of 199 genes associated with prognosis were identified using univariate Cox analysis. Subsequently, a consensus prognostic model was developed through the application of machine learning algorithms. In which the Lasso + plsRcox algorithm demonstrated the best predictive performance. The model showed a good ability to distinguish two groups in both the training and test sets. Additionally, the model genes were closely related to immunity (oligodendrocytes and macrophages), and mutation burden. The results of in vitro experiments showed that the expression level of the IKBKE gene had a significant effect on the apoptosis and migration of GL261 glioma cells. Western blot analysis showed that down-regulation of IKBKE resulted in increased expression of pro-apoptotic protein Bax and decreased expression of anti-apoptotic protein Bcl-2, which was consistent with increased apoptosis rate. On the contrary, IKBKE overexpression caused a decrease in Bax expression an increase in Bcl-2 expression, and a decrease in apoptosis rate. Tunel results further confirmed that down-regulation of IKBKE promoted apoptosis, while overexpression of IKBKE reduced apoptosis. In addition, cells with down-regulated IKBKE had reduced migration in scratch experiments, while cells with overexpression of IKBKE had increased migration.

CONCLUSION

This study successfully constructed a glioma prognosis model based on immune-related genes. These findings provide new perspectives for glioma prognosis assessment and immunotherapy.

Study on risk factors of impaired fasting glucose and development of a prediction model based on Extreme Gradient Boosting algorithm

Objective

The aim of this study was to develop and validate a machine learning-based model to predict the development of impaired fasting glucose (IFG) in middle-aged and older elderly people over a 5-year period using data from a cohort study.

Methods

This study was a retrospective cohort study. The study population was 1855 participants who underwent consecutive physical examinations at the First Affiliated Hospital of Soochow University between 2018 and 2022.The dataset included medical history, physical examination, and biochemical index test results. The cohort was randomly divided into a training dataset and a validation dataset in a ratio of 8:2. The machine learning algorithms used in this study include Extreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), Naive Bayes, Decision Trees (DT), and traditional Logistic Regression (LR). Feature selection, parameter optimization, and model construction were performed in the training set, while the validation set was used to evaluate the predictive performance of the models. The performance of these models is evaluated by an area under the receiver operating characteristic (ROC) curves (AUC), calibration curves and decision curve analysis (DCA). To interpret the best-performing model, the Shapley Additive exPlanation (SHAP) Plots was used in this study.

Results

The training/validation dataset consists of 1,855 individuals from the First Affiliated Hospital of Soochow University, yielded significant variables following selection by the Boruta algorithm and logistic multivariate regression analysis. These significant variables included systolic blood pressure (SBP), fatty liver, waist circumference (WC) and serum creatinine (Scr). The XGBoost model outperformed the other models, demonstrating an AUC of 0.7391 in the validation set.

Conclusions

The XGBoost model was composed of SBP, fatty liver, WC and Scr may assist doctors with the early identification of IFG in middle-aged and elderly people.

Biologically interpretable multi-task deep learning pipeline predicts molecular alterations, grade, and prognosis in glioma patients

Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep learning (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well as prognosis (primary task) in gliomas. Further, we aimed to provide the biological mechanisms underlying the model's predictions. We collected multiscale data including baseline MRI images from 2776 glioma patients across two private (FAHZU and HPPH, n = 1931) and three public datasets (TCGA, n = 213; UCSF, n = 410; and EGD, n = 222). We trained and internally validated the MDL model using our private datasets, and externally validated it using the three public datasets. We used the model-predicted deep prognosis score (DPS) to stratify patients into low-DPS and high-DPS subtypes. Additionally, a radio-multiomics analysis was conducted to elucidate the biological basis of the DPS. In the external validation cohorts, the MDL model achieved average areas under the curve of 0.892-0.903, 0.710-0.894, and 0.850-0.879 for predicting IDH mutation status, 1p/19q co-deletion status, and tumor grade, respectively. Moreover, the MDL model yielded a C-index of 0.723 in the TCGA and 0.671 in the UCSF for the prediction of overall survival. The DPS exhibits significant correlations with activated oncogenic pathways, immune infiltration patterns, specific protein expression, DNA methylation, tumor mutation burden, and tumor-stroma ratio. Accordingly, our work presents an accurate and biologically meaningful tool for predicting molecular subtypes, tumor grade, and survival outcomes in gliomas, which provides personalized clinical decision-making in a global and non-invasive manner.

A novel deep learning framework for rolling bearing fault diagnosis enhancement using VAE-augmented CNN model

In the context of burgeoning industrial advancement, there is an increasing trend towards the integration of intelligence and precision in mechanical equipment. Central to the functionality of such equipment is the rolling bearing, whose operational integrity significantly impacts the overall performance of the machinery. This underscores the imperative for reliable fault diagnosis mechanisms in the continuous monitoring of rolling bearing conditions within industrial production environments. Vibration signals are primarily used for fault diagnosis in mechanical equipment because they provide comprehensive information about the equipment's condition. However, fault data often contain high noise levels, high-frequency variations, and irregularities, along with a significant amount of redundant information, like duplication, overlap, and unnecessary information during signal transmission. These characteristics present considerable challenges for effective fault feature extraction and diagnosis, reducing the accuracy and reliability of traditional fault detection methods. This research introduces an innovative fault diagnosis methodology for rolling bearings using deep convolutional neural networks (CNNs) enhanced with variational autoencoders (VAEs). This deep learning approach aims to precisely identify and classify faults by extracting detailed vibration signal features. The VAE enhances noise robustness, while the CNN improves signal data expressiveness, addressing issues like gradient vanishing and explosion. The model employs the reparameterization trick for unsupervised learning of latent features and further trains with the CNN. The system incorporates adaptive threshold methods, the "3/5" strategy, and Dropout methods. The diagnosis accuracy of the VAE-CNN model for different fault types at different rotational speeds typically reaches more than 90 %, and it achieves a generally acceptable diagnosis result. Meanwhile, the VAE-CNN augmented fault diagnosis model, after experimental validation in various dimensions, can achieve more satisfactory diagnosis results for various fault types compared to several representative deep neural network models without VAE augmentation, significantly improving the accuracy and robustness of rolling bearing fault diagnosis.

A data-centric machine learning approach to improve prediction of glioma grades using low-imbalance TCGA data

Accurate prediction and grading of gliomas play a crucial role in evaluating brain tumor progression, assessing overall prognosis, and treatment planning. In addition to neuroimaging techniques, identifying molecular biomarkers that can guide the diagnosis, prognosis and prediction of the response to therapy has aroused the interest of researchers in their use together with machine learning and deep learning models. Most of the research in this field has been model-centric, meaning it has been based on finding better performing algorithms. However, in practice, improving data quality can result in a better model. This study investigates a data-centric machine learning approach to determine their potential benefits in predicting glioma grades. We report six performance metrics to provide a complete picture of model performance. Experimental results indicate that standardization and oversizing the minority class increase the prediction performance of four popular machine learning models and two classifier ensembles applied on a low-imbalanced data set consisting of clinical factors and molecular biomarkers. The experiments also show that the two classifier ensembles significantly outperform three of the four standard prediction models. Furthermore, we conduct a comprehensive descriptive analysis of the glioma data set to identify relevant statistical characteristics and discover the most informative attributes using four feature ranking algorithms.

Generation of B7-H3 isoform regulated by ANXA2/NSUN2/YBX1 axis in human glioma

In recent years, in the development of emerging immunotherapy, B7-H3 is also termed as CD276 and has become a novel chimeric antigen receptor (CAR)-T target against glioma and other tumours, and aroused extensive attention. However, B7-H3 has three isoforms (2, 3 and 4Ig) with the controversial expression and elusive function in tumour especially glioma. The current study mainly focuses on the regulatory factors and related mechanisms of generation of different B7-H3 isoforms. First, we have determined that 2Ig is dominant in glioma with high malignancy, and 4Ig is widely expressed, whereas 3Ig shows negative expression in all glioma. Next, we have further found that RNA binding protein annexin A2 (ANXA2) is essential for B7-H3 isoform maintenance, but fail to determine the choice of 4Ig or 2Ig. RNA methyltransferase NOP2/Sun RNA methyltransferase 2 (NSUN2) and 5-methylcytosine reader Y-box binding protein 1 (YBX1) facilitate the production of 2Ig. Our findings have uncovered a series of factors (ANXA2/NSUN2/YBX1) that can determine the alternative generation of different isoforms of B7-H3 in glioma. Our result aims to help peers gain a clearer understanding of the expression and regulatory mechanisms of B7H3 in tumour patients, and to provide better strategies for designing B7H3 as a target in immunotherapy.

Identification of potential shared gene signatures between gastric cancer and type 2 diabetes: a data-driven analysis

Background

Gastric cancer (GC) and type 2 diabetes (T2D) contribute to each other, but the interaction mechanisms remain undiscovered. The goal of this research was to explore shared genes as well as crosstalk mechanisms between GC and T2D.

Methods

The Gene Expression Omnibus (GEO) database served as the source of the GC and T2D datasets. The differentially expressed genes (DEGs) and weighted gene co-expression network analysis (WGCNA) were utilized to identify representative genes. In addition, overlapping genes between the representative genes of the two diseases were used for functional enrichment analysis and protein-protein interaction (PPI) network. Next, hub genes were filtered through two machine learning algorithms. Finally, external validation was undertaken with data from the Cancer Genome Atlas (TCGA) database.

Results

A total of 292 and 541 DEGs were obtained from the GC (GSE29272) and T2D (GSE164416) datasets, respectively. In addition, 2,704 and 336 module genes were identified in GC and T2D. Following their intersection, 104 crosstalk genes were identified. Enrichment analysis indicated that "ECM-receptor interaction," "AGE-RAGE signaling pathway in diabetic complications," "aging," and "cellular response to copper ion" were mutual pathways. Through the PPI network, 10 genes were identified as candidate hub genes. Machine learning further selected BGN, VCAN, FN1, FBLN1, COL4A5, COL1A1, and COL6A3 as hub genes.

Conclusion

"ECM-receptor interaction," "AGE-RAGE signaling pathway in diabetic complications," "aging," and "cellular response to copper ion" were revealed as possible crosstalk mechanisms. BGN, VCAN, FN1, FBLN1, COL4A5, COL1A1, and COL6A3 were identified as shared genes and potential therapeutic targets for people suffering from GC and T2D.

GNB4 Silencing Promotes Pyroptosis to Inhibit the Development of Glioma by Activating cGAS-STING Pathway

The induction of immunogenic cell death is a promising therapeutic option for gliomas. Pyroptosis is a type of programmed immunogenic cell death and its role in gliomas remains unclear. Differentially expressed genes (DEGs) were obtained from GSE4290 and GSE31262 datasets. Hub genes were screened from protein-protein interaction networks and assessed using principal component analysis and receiver operating characteristic curves. Quantitative real-time polymerase chain reaction (qRT-PCR) was used to measure the mRNA expression of hub genes. Pyroptosis and pathway-related proteins were assessed using western blotting. Inflammatory factor levels were determined using enzyme-linked immunosorbent assay. The effect of guanine nucleotide-binding protein-4 (GNB4) on proliferation, migration, and invasion was evaluated using a cell viability test kit and wound-healing and transwell assays. In total, 202 DEGs were identified. Among them, F2R, GNG4, GNG3, PRKCB, and GNB4 were identified as hub genes in gliomas after comprehensive bioinformatics analysis. GNB4 was significantly upregulated in glioma cells compared to normal brain glial cells. Silencing GNB4 significantly inhibited proliferation, invasion, and migration of glioma cells. The expression of pyroptosis-related proteins increased after GNB4 silencing, with elevated levels of inflammatory factors. Pyroptosis inhibitors reversed the inhibitory effects of GNB4 silencing on cell proliferation, migration, and invasion. Additionally, GNB4 silencing activated the cGAS-STING pathway. Treatment with a cGAS-STING pathway inhibitor reversed the inhibition of proliferation, migration, and invasion while downregulating the expression of pyroptosis-related proteins. Silencing GNB4 promotes pyroptosis and thus inhibits the proliferation, migration, and invasion of glioma cells by activating the cGAS-STING pathway, which is a promising biomarker and therapeutic target for glioma.

Practical Application of Deep Learning in Diagnostic Neuropathology-Reimagining a Histological Asset in the Era of Precision Medicine

In the past few decades, neuropathology has experienced several paradigm shifts with the introduction of new technologies. Deep learning, a rapidly progressing subfield of machine learning, seems to be the next innovation to alter the diagnostic workflow. In this review, we will explore the recent changes in the field of neuropathology and how this has led to an increased focus on molecular features in diagnosis and prognosis. Then, we will examine the work carried out to train deep learning models for various diagnostic tasks in neuropathology, as well as the machine learning frameworks they used. Focus will be given to both the challenges and successes highlighted therein, as well as what these trends may tell us about future roadblocks in the widespread adoption of this new technology. Finally, we will touch on recent trends in deep learning, as applied to digital pathology more generally, and what this may tell us about the future of deep learning applications in neuropathology.

Advancements in Image-Based Models for High-Grade Gliomas Might Be Accelerated

The first half of 2022 saw the publication of several major research advances in image-based models and artificial intelligence applications to optimize treatment strategies for high-grade gliomas, the deadliest brain tumors. We review them and discuss the barriers that delay their entry into clinical practice; particularly, the small sample size and the heterogeneity of the study designs and methodologies used. We will also write about the poor and late palliation that patients suffering from high-grade glioma can count on at the end of life, as well as the current legislative instruments, with particular reference to Italy. We suggest measures to accelerate the gradual progress in image-based models and end of life care for patients with high-grade glioma.

Revolutionizing lymph node metastasis imaging: the role of drug delivery systems and future perspectives

The deployment of imaging examinations has evolved into a robust approach for the diagnosis of lymph node metastasis (LNM). The advancement of technology, coupled with the introduction of innovative imaging drugs, has led to the incorporation of an increasingly diverse array of imaging techniques into clinical practice. Nonetheless, conventional methods of administering imaging agents persist in presenting certain drawbacks and side effects. The employment of controlled drug delivery systems (DDSs) as a conduit for transporting imaging agents offers a promising solution to ameliorate these limitations intrinsic to metastatic lymph node (LN) imaging, thereby augmenting diagnostic precision. Within the scope of this review, we elucidate the historical context of LN imaging and encapsulate the frequently employed DDSs in conjunction with a variety of imaging techniques, specifically for metastatic LN imaging. Moreover, we engage in a discourse on the conceptualization and practical application of fusing diagnosis and treatment by employing DDSs. Finally, we venture into prospective applications of DDSs in the realm of LNM imaging and share our perspective on the potential trajectory of DDS development.

Artificial intelligence-based MRI radiomics and radiogenomics in glioma

The specific genetic subtypes that gliomas exhibit result in variable clinical courses and the need to involve multidisciplinary teams of neurologists, epileptologists, neurooncologists and neurosurgeons. Currently, the diagnosis of gliomas pivots mainly around the preliminary radiological findings and the subsequent definitive surgical diagnosis (via surgical sampling). Radiomics and radiogenomics present a potential to precisely diagnose and predict survival and treatment responses, via morphological, textural, and functional features derived from MRI data, as well as genomic data. In spite of their advantages, it is still lacking standardized processes of feature extraction and analysis methodology among different research groups, which have made external validations infeasible. Radiomics and radiogenomics can be used to better understand the genomic basis of gliomas, such as tumor spatial heterogeneity, treatment response, molecular classifications and tumor microenvironment immune infiltration. These novel techniques have also been used to predict histological features, grade or even overall survival in gliomas. In this review, workflows of radiomics and radiogenomics are elucidated, with recent research on machine learning or artificial intelligence in glioma.

Systems Biology in Cancer Diagnosis Integrating Omics Technologies and Artificial Intelligence to Support Physician Decision Making

Cancer is the second major cause of disease-related death worldwide, and its accurate early diagnosis and therapeutic intervention are fundamental for saving the patient's life. Cancer, as a complex and heterogeneous disorder, results from the disruption and alteration of a wide variety of biological entities, including genes, proteins, mRNAs, miRNAs, and metabolites, that eventually emerge as clinical symptoms. Traditionally, diagnosis is based on clinical examination, blood tests for biomarkers, the histopathology of a biopsy, and imaging (MRI, CT, PET, and US). Additionally, omics biotechnologies help to further characterize the genome, metabolome, microbiome traits of the patient that could have an impact on the prognosis and patient's response to the therapy. The integration of all these data relies on gathering of several experts and may require considerable time, and, unfortunately, it is not without the risk of error in the interpretation and therefore in the decision. Systems biology algorithms exploit Artificial Intelligence (AI) combined with omics technologies to perform a rapid and accurate analysis and integration of patient's big data, and support the physician in making diagnosis and tailoring the most appropriate therapeutic intervention. However, AI is not free from possible diagnostic and prognostic errors in the interpretation of images or biochemical-clinical data. Here, we first describe the methods used by systems biology for combining AI with omics and then discuss the potential, challenges, limitations, and critical issues in using AI in cancer research.

Risk factors for surgical compliance and impact on the survival of patients with glioma: a population-based propensity score-matched study

PURPOSE

To comprehensively analyze the impact of surgical compliance on the survival of patients with glioma and to explore the factors that influence surgical compliance.

METHODS

Clinical data of patients with glioma between 2004 and 2018 were collected from the Surveillance, Epidemiology, and End Results (SEER) database. Kaplan-Meier curves and Cox regression were used to analyze the effect of surgical compliance on overall survival (OS) and disease-specific survival (DSS). Multivariate Cox regression was used to select the prediction variables and construct the nomograms. The predictive power of these models was assessed using Harell's consistency index (C-index), decision curve analysis (DCA), receiver operating characteristic (ROC) curves, and calibration curves. Multivariate logistic regression was performed to analyze the related variables of surgical compliance, and 1:1 propensity score matching (PSM) was applied to evaluate the validity of the results of patients with favorable and poor surgical compliance.

RESULTS

Among the 47,573 eligible glioma patients recommended for surgery, 46,380 (97.5%) were in the surgical compliance group, while 1193 (2.5%) were in the noncompliance group. Surgical compliance was an independent prognostic factor for glioma patients, as indicated by multivariate Cox regression analysis that patients with surgical compliance had worse OS (hazard ratio [HR] 1.924; 95% confidence interval [CI] 1.800-2.056, p < 0.001) and DSS (HR 1.718; 95% CI 1.592-1.853, p < 0.001) in comparison to those without surgical compliance. A nomogram was developed and internally validated to be able to predict glioma prognosis. The nomogram can well predict patients' OS (C-index: 0.745) and DSS (C-index: 0.744). ROC curve, DCA curve, and calibration curve were applied to further assess the accuracy of the nomogram. Poor surgical compliance was found to be related to older age, female gender, tumor diameter, grade II or higher, poor grading, tumor location in the cerebellum and brainstem, and low household income.

CONCLUSION

Surgical compliance is an independent prognostic factor for predicting the OS and DSS of patients with glioma, and good surgical compliance was significantly related to good survival.

A Machine Learning Approach Using [18F]FDG PET-Based Radiomics for Prediction of Tumor Grade and Prognosis in Pancreatic Neuroendocrine Tumor

PURPOSE

We sought to develop and validate machine learning (ML) models for predicting tumor grade and prognosis using 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) positron emission tomography (PET)-based radiomics and clinical features in patients with pancreatic neuroendocrine tumors (PNETs).

PROCEDURES

A total of 58 patients with PNETs who underwent pretherapeutic [18F]FDG PET/computed tomography (CT) were retrospectively enrolled. PET-based radiomics extracted from segmented tumor and clinical features were selected to develop prediction models by the least absolute shrinkage and selection operator feature selection method. The predictive performances of ML models using neural network (NN) and random forest algorithms were compared by the areas under the receiver operating characteristic curves (AUROCs) and validated by stratified five-fold cross validation.

RESULTS

We developed two separate ML models for predicting high-grade tumors (Grade 3) and tumors with poor prognosis (disease progression within two years). The integrated models consisting of clinical and radiomic features with NN algorithm showed the best performances than the other models (stand-alone clinical or radiomics models). The performance metrics of the integrated model by NN algorithm were AUROC of 0.864 in the tumor grade prediction model and AUROC of 0.830 in the prognosis prediction model. In addition, AUROC of the integrated clinico-radiomics model with NN was significantly higher than that of tumor maximum standardized uptake model in predicting prognosis (P < 0.001).

CONCLUSIONS

Integration of clinical features and [18F]FDG PET-based radiomics using ML algorithms improved the prediction of high-grade PNET and poor prognosis in a non-invasive manner.

The role of long non-coding RNAs in breast cancer microenvironment

The tumor microenvironment (TME), which includes tumor cells, fibroblasts, endothelial cells, immune cells, and blood vessels, can affect tumor growth and metastasis. Studies have shown that tumor cells, fibroblasts, and macrophages can promote the development of tumors, while T and B cells can inhibit tumor progression. The crosstalk among different cells within the TME needs further study. Long non-coding RNAs (lncRNAs) are involved in biological processes, including cell proliferation, migration, and differentiation. The abnormal expression of certain lncRNAs is correlated with the progression of breast cancer and has been proven as diagnostic markers in various cancers, including breast cancer. In breast cancer, recent studies have shown that tumor cell- and non-tumor cell-derived lncRNAs can affect various facets of tumor progression, including growth, proliferation, and migration of tumor cells. Interestingly, in addition to being regulated by lncRNAs derived from tumor and non-tumor cells, the TME can regulate the expression of lncRNAs in tumor cells, fibroblasts, and macrophages, influencing their phenotype and function. However, the detailed molecular mechanisms of these phenomena remain unclear in the breast cancer microenvironment. Currently, many studies have shown that TME-associated lncRNAs are potential diagnostic and therapeutic targets for breast cancer. Considering that TME and lncRNAs can regulate each other, we summarize the role of lncRNAs in the breast cancer microenvironment and the potential of lncRNAs as valuable diagnostic markers.

Eukaryotic initiation factor 4 A-3 promotes glioblastoma growth and invasion through the Notch1-dependent pathway

BACKGROUND

As an adult tumor with the most invasion and the highest mortality rate, the inherent heterogeneity of glioblastoma (GBM) is the main factor that causes treatment failure. Therefore, it is important to have a deeper understanding of the pathology of GBM. Some studies have shown that Eukaryotic Initiation Factor 4A-3 (EIF4A3) can promote the growth of many people's tumors, and the role of specific molecules in GBM remains unclear.

METHODS

The correlation between the expression of EIF4A3 gene and its prognosis was studied in 94 GBM patients using survival analysis. Further in vitro and in vivo experiments, the effect of EIF4A3 on GBM cells proliferation, migration, and the mechanism of EIF4A3 on GBM was explored. In addition, combined with bioinformatics analysis, we further confirmed that EIF4A3 contributes to the progress of GBM.

RESULTS

The expression of EIF4A3 was upregulated in GBM tissues, and high expression of EIF4A3 is associated with poor prognosis in GBM. In vitro, knockdown of EIF4A3 significantly reduced the proliferation, migration, and invasion abilities of GBM cells, whereas overexpression of EIF4A3 led to the opposite effect. The analysis of differentially expressed genes related to EIF4A3 indicates that it is involved in many cancer-related pathways, such as Notch and JAK-STAT3 signal pathway. In Besides, we demonstrated the interaction between EIF4A3 and Notch1 by RNA immunoprecipitation. Finally, the biological function of EIF4A3-promoted GBM was confirmed in living organisms.

CONCLUSION

The results of this study suggest that EIF4A3 may be a potential prognostic factor, and Notch1 participates in the proliferation and metastasis of GBM cells mediated by EIF4A3.