4.6 Article

Estimating the Prognosis of Low-Grade Glioma with Gene Attention Using Multi-Omics and Multi-Modal Schemes

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Chemistry, Analytical

HRGAN: A Generative Adversarial Network Producing Higher-Resolution Images than Training Sets

Minyoung Park et al.

Summary: The traditional GAN framework limits the maximum resolution of generated images. This paper proposes a new GAN framework called HRGAN to address this limitation. HRGAN uses a pre-trained network and additional up-sampling convolutional layers to generate higher resolution images, and introduces an additional target for training to make the generated images more realistic.

SENSORS (2022)

Review Oncology

Machine Learning and Deep Learning Applications in Multiple Myeloma Diagnosis, Prognosis, and Treatment Selection

Alessandro Allegra et al.

Summary: Multiple myeloma is a complex malignant neoplasm of plasma cells. The application of artificial intelligence, particularly machine learning and deep learning algorithms, has significant implications in the diagnosis and treatment of multiple myeloma.

CANCERS (2022)

Article Multidisciplinary Sciences

Clinical measures, radiomics, and genomics offer synergistic value in AI-based prediction of overall survival in patients with glioblastoma

Anahita Fathi Kazerooni et al.

Summary: The study demonstrates the value of integrated diagnostics, using both conventional and deep learning methods, in predicting overall survival in IDH-wildtype GBM patients. Multi-omic data capture multi-faceted tumor characteristics and contribute to a comprehensive risk assessment of patients.

SCIENTIFIC REPORTS (2022)

Article Oncology

A Novel Multi-Omics Analysis Model for Diagnosis and Survival Prediction of Lower-Grade Glioma Patients

Wei Wu et al.

Summary: This study aimed to construct more accurate risk-stratification approaches for lower-grade gliomas (LGGs). By analyzing methylation and transcription sequencing profiles and imaging data, a cluster of 6 genes correlated with IDH mutation/1p19q co-deletion status was identified. Risk score and radiomics score models were developed based on these genes, showing high sensitivity and specificity for survival prediction and therapy response of LGG patients. A predictable nomogram that combined transcriptional signatures and clinical characteristics was established and validated to be preferable to the histopathological classification. A web-based platform was also developed for user-friendly application.

FRONTIERS IN ONCOLOGY (2022)

Review Cardiac & Cardiovascular Systems

Use of Multi-Modal Data and Machine Learning to Improve Cardiovascular Disease Care

Saeed Amal et al.

Summary: Today's digital health revolution aims to improve the efficiency of healthcare delivery and make care more personalized and timely. Data fusion techniques enable the integration of multiple modalities, providing deeper insights specific to the field of cardiovascular medicine and advancing the diagnosis and treatment of cardiovascular diseases.

FRONTIERS IN CARDIOVASCULAR MEDICINE (2022)

Article Biology

An Ensemble Deep Learning Model with a Gene Attention Mechanism for Estimating the Prognosis of Low-Grade Glioma

Minhyeok Lee

Summary: This paper proposes a deep learning model GAENET for prognosis estimation of LGG and discovers HILS1 as a significant prognostic gene through gene attention mechanism.

BIOLOGY-BASEL (2022)

Article Computer Science, Information Systems

Cross validation methods: Analysis based on diagnostics of thyroid cancer metastasis

Mariusz Rafalo

Summary: Much of modern medical research relies on statistics and machine learning techniques. Cross validation is an important tool for measuring the effectiveness of models and comparing them. This paper presents an analysis of cross validation methods using a logistic regression model and finds that high variance in the developed models is a main reason for the lack of a single threshold value. The research also suggests that the choice of validation technique influences both the measurement of model quality and the determination of threshold values.

ICT EXPRESS (2022)

Article Oncology

Brain Functional Connectivity in Low- and High-Grade Gliomas: Differences in Network Dynamics Associated with Tumor Grade and Location

Luca Pasquini et al.

Summary: This study investigates the brain network modifications related to tumor grade and location using resting-state functional magnetic resonance imaging and graph theory. The results show that low-grade gliomas lead to increased efficiency of the surrounding functional network, while high-grade gliomas disrupt brain connectivity in remote areas. Tumor location also influences the pattern of network reorganization. Overall, low-grade gliomas may show more favorable network changes compared to high-grade gliomas.

CANCERS (2022)

Review Oncology

Sexual Dysfunction of Patients with Diffuse Low-Grade Glioma: A Qualitative Review of a Neglected Concern

Arnaud Lombard et al.

Summary: This study reviewed the current knowledge about sexual dysfunction in LGG patients. Despite a high incidence of 44% to 62%, this issue has been largely neglected in research. Therefore, there is a need to systematically assess the occurrence of SD in clinical routine in order to adjust treatment and improve patients' QoL.

CANCERS (2022)

Review Medicine, General & Internal

Convolutional Neural Network Techniques for Brain Tumor Classification (from 2015 to 2022): Review, Challenges, and Future Perspectives

Yuting Xie et al.

Summary: This article provides a comprehensive review of studies using CNN architectures to classify brain tumors. The study found that performance varied widely depending on the classification problem and network choice. Due to inconsistencies in validation methods, performance metrics, and training data reporting, there is currently no clear best method choice. Few studies have focused on clinical usability.

DIAGNOSTICS (2022)

Review Chemistry, Medicinal

Efficacy and Safety of Trametinib in Neurofibromatosis Type 1-Associated Plexiform Neurofibroma and Low-Grade Glioma: A Systematic Review and Meta-Analysis

Dun Wang et al.

Summary: This meta-analysis evaluated the effectiveness and safety of trametinib in treating NF1-related nerve tumors. The results showed that trametinib had a satisfactory ability to stabilize tumor progression but a more limited ability to shrink tumors. The safety profile of trametinib was satisfactory.

PHARMACEUTICALS (2022)

Review Medicine, General & Internal

Depression and Quality of Life in Patients with Gliomas: A Narrative Review

Yue Hu et al.

Summary: Depression is a common complication in patients with gliomas, and it can severely affect their psychological well-being and quality of life. Risk factors for depression in these patients include female sex, unmarried status, low education level, high tumor grade, and a history of mental illness. Antidepressant use can improve the prognosis of patients with gliomas.

JOURNAL OF CLINICAL MEDICINE (2022)

Article Oncology

Identification of Gender- and Subtype-Specific Gene Expression Associated with Patient Survival in Low-Grade and Anaplastic Glioma in Connection with Steroid Signaling

Alex Hirtz et al.

Summary: This study demonstrates a link between the expression of steroid biosynthesis enzymes or hormone receptors and patient survival in low-grade and anaplastic gliomas, which is dependent on gender and molecular subtype. The study also identifies genes associated with these steroid signaling factors and their functions, providing insights into the mechanisms underlying gender-dependent differences. These findings have important implications for refining the classification and personalized management of glioma patients.

CANCERS (2022)

Article Nanoscience & Nanotechnology

SKCV: Stratified K-fold cross-validation on ML classifiers for predicting cervical cancer

Sashikanta Prusty et al.

Summary: This article investigates the use of machine learning techniques to predict cervical cancer and compares different diagnostic tests and machine learning models. The experimental findings demonstrate that utilizing an RF classifier can be a good alternative for assisting clinical specialists in early diagnosis of cervical cancer.

FRONTIERS IN NANOTECHNOLOGY (2022)

Article Biochemistry & Molecular Biology

i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability

Xingxin Pan et al.

Summary: Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. However, a robust framework for integrating multi-omics data types to efficiently and precisely predict survival prognosis is still lacking. Additionally, effective therapeutic targets for treating glioma patients with poor prognoses are urgently needed.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2022)

Article Computer Science, Artificial Intelligence

The ensemble deep learning model for novel COVID-19 on CT images

Zhou Tao et al.

Summary: This study proposes an ensemble deep learning model for rapid detection of COVID-19 from CT images, achieving higher accuracy and sensitivity compared to individual classifiers. This approach can better meet the requirements for rapid detection of the novel coronavirus disease COVID-19.

APPLIED SOFT COMPUTING (2021)

Article Biochemical Research Methods

A deep learning approach for filtering structural variants in short read sequencing data

Yongzhuang Liu et al.

Summary: Short read whole genome sequencing is widely used in human genetic studies and clinical practices for detecting structural variants, but accurate detection is challenging. This study introduces a novel deep learning-based approach, DeepSVFilter, for filtering structural variants in short read whole genome sequencing data.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Chemistry, Analytical

Automatic Lung Segmentation on Chest X-rays Using Self-Attention Deep Neural Network

Minki Kim et al.

Summary: This study introduces a deep learning-based method to segment lung areas in chest X-ray images, utilizing self-attention modules to accurately capture key regions in feature maps. Experimental results demonstrate that adding attention modules in lower layers of U-Net can improve the performance of lung area segmentation.

SENSORS (2021)

Review Green & Sustainable Science & Technology

A Review of Deep-Learning-Based Medical Image Segmentation Methods

Xiangbin Liu et al.

Summary: Medical image segmentation based on deep learning has made significant contributions to sustainable medical care, but still faces challenges such as low segmentation accuracy and limited dataset size. Further research is needed to address these issues and improve the technology.

SUSTAINABILITY (2021)

Article Chemistry, Analytical

COVID-19 Detection from Chest X-ray Images Using Feature Fusion and Deep Learning

Nur-A-Alam et al.

Summary: This study proposed a machine vision approach for detecting COVID-19 by fusing features extracted from HOG and CNN, then training CNN (VGGNet) for classification with high accuracy. Various techniques were used for processing X-ray images, including MADF and watershed segmentation, with overfitting problems addressed through cross-validation analysis.

SENSORS (2021)

Article Multidisciplinary Sciences

Prioritizing non-coding regions based on human genomic constraint and sequence context with deep learning

Dimitrios Vitsios et al.

Summary: The study integrates intolerance to variation, functional genomic annotations, and primary genomic sequences to build a comprehensive deep learning model JARVIS and genome-wide residual variation intolerance score (gwRVIS) for prioritizing non-coding regions. Both JARVIS and gwRVIS capture previously inaccessible human-lineage constraint information and enhance understanding of the non-coding genome.

NATURE COMMUNICATIONS (2021)

Article Environmental Sciences

Vision Transformers for Remote Sensing Image Classification

Yakoub Bazi et al.

Summary: This paper proposes a remote-sensing scene-classification method based on vision transformers, which utilize multihead attention mechanisms to establish long-range contextual relationships between pixels in images. The approach involves dividing images into patches, converting them into sequences, and applying data augmentation techniques for improved classification performance. The study also demonstrates the efficacy of compressing the network by pruning half of the layers while maintaining competitive classification accuracies.

REMOTE SENSING (2021)

Review Oncology

MYB oncoproteins: emerging players and potential therapeutic targets in human cancer

Ylenia Ciciro et al.

Summary: MYB transcription factors are highly conserved from plants to vertebrates, and their aberrant activation in humans may lead to cancer. Recent detection of MYB gene rearrangements and mutations in human cancer provides smoking gun evidence of the involvement of MYB family members in human malignancies. Studies linking the activity of MYB family members to human cancers and experimental therapeutic interventions tailored for MYB-expressing cancers are highlighted in this review.

ONCOGENESIS (2021)

Article Biochemistry & Molecular Biology

Multi-Omics Analysis of Key microRNA-mRNA Metabolic Regulatory Networks in Skeletal Muscle of Obese Rabbits

Yanhong Li et al.

Summary: Through experiments, it was found that in rabbits induced to be obese by a high-fat diet, there were significant differences in the expression of certain miRNAs and core genes, with the miRNAs being able to regulate transcription factors that impact lipid metabolism. These results contribute to a better understanding of the molecular mechanisms of skeletal muscle metabolism in rabbits.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2021)

Article Cell Biology

miR-30d suppresses proliferation and invasiveness of pancreatic cancer by targeting the SOX4/PI3K-AKT axis and predicts poor outcome

Xiaodong Xu et al.

Summary: Aberrant expression of miR-30d in pancreatic cancer is associated with poor prognosis and early relapse of patients. The tumor suppressive effect of miR-30d is mediated through direct targeting of SOX4, leading to inhibition of the PI3K-AKT signaling pathway and repression of pancreatic cancer cell growth and metastasis.

CELL DEATH & DISEASE (2021)

Article Computer Science, Artificial Intelligence

Multi-modal advanced deep learning architectures for breast cancer survival prediction

Nikhilanand Arya et al.

Summary: Breast cancer is a common cancer among women, with manual prognosis and diagnosis taking a long time. A deep learning model using multi-modal data has been proposed to enhance the accuracy of breast cancer prognosis prediction.

KNOWLEDGE-BASED SYSTEMS (2021)

Review Computer Science, Artificial Intelligence

Deep learning in ECG diagnosis: A review

Xinwen Liu et al.

Summary: Cardiovascular disease is a leading cause of death globally, and early detection of heart abnormalities can reduce the severity of the consequences. While electrocardiogram is an important tool for diagnosing CVDs, its complex nature requires computer-aided methods to alleviate the burden on humans.

KNOWLEDGE-BASED SYSTEMS (2021)

Article Chemistry, Analytical

Estimation with Uncertainty via Conditional Generative Adversarial Networks

Minhyeok Lee et al.

Summary: The study proposes a new predictive probabilistic neural network model, which reverses the input and output of ordinary conditional Generative Adversarial Network (cGAN) to be used as a predictive model. The model can estimate the uncertainty of predictions accurately and demonstrates superior estimation performance in stock market data and image classification tasks.

SENSORS (2021)

Article Cell Biology

Genome-wide CRISPR/Cas9 screening identifies CARHSP1 responsible for radiation resistance in glioblastoma

Guo-dong Zhu et al.

Summary: CARHSP1 is identified as a critical driver for radioresistance in glioblastomas, potentially mediating radioresistance by activating the inflammatory signaling pathway. Patients with high levels of CARHSP1 have poorer survival when treated with radiotherapy.

CELL DEATH & DISEASE (2021)

Article Multidisciplinary Sciences

A deep learning model for predicting next-generation sequencing depth from DNA sequence

Jinny X. Zhang et al.

Summary: A deep learning model is developed to predict NGS depth using DNA probe sequences, applied to both human and non-human sequencing panels. The model shows high accuracy in cross-validation for different panels.

NATURE COMMUNICATIONS (2021)

Article Multidisciplinary Sciences

Long-term cancer survival prediction using multimodal deep learning

Luis A. Vale-Silva et al.

Summary: MultiSurv is a multimodal deep learning method for long-term pan-cancer survival prediction that can handle missing data and achieve accurate results, as well as provide insights on cancer characteristics and heterogeneity through visualizations of learned multimodal representations.

SCIENTIFIC REPORTS (2021)

Article Genetics & Heredity

Identifying miRNA-mRNA Integration Set Associated With Survival Time

Yongkang Kim et al.

Summary: A miRNA-mRNA integration model called mimi-surv was proposed to more effectively identify integrated markers associated with survival and progression in PDAC patients. Through simulation and application to real datasets, mimi-surv was shown to better identify PDAC-related miRNAs and have higher statistical power compared to other methods.

FRONTIERS IN GENETICS (2021)

Article Computer Science, Information Systems

Improved recurrent generative adversarial networks with regularization techniques and a controllable framework

Minhyeok Lee et al.

INFORMATION SCIENCES (2020)

Article Medicine, General & Internal

Upregulation of miR-421 predicts poor prognosis and promotes proliferation, migration, and invasion of papillary thyroid cancer cells

Anbing Dong et al.

JOURNAL OF THE CHINESE MEDICAL ASSOCIATION (2020)

Article Genetics & Heredity

SALMON: Survival Analysis Learning With Multi-Omics Neural Networks on Breast Cancer

Zhi Huang et al.

FRONTIERS IN GENETICS (2019)

Article Medicine, Research & Experimental

miR-885-5p Negatively Regulates Warburg Effect by Silencing Hexokinase 2 in Liver Cancer

Fei Xu et al.

MOLECULAR THERAPY-NUCLEIC ACIDS (2019)

Review Computer Science, Artificial Intelligence

Ensemble learning: A survey

Omer Sagi et al.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2018)

Review Endocrinology & Metabolism

Overview of MicroRNA Biogenesis, Mechanisms of Actions, and Circulation

Jacob O'Brien et al.

FRONTIERS IN ENDOCRINOLOGY (2018)

Article Oncology

Deep Learning-Based Multi-Omics Integration Robustly Predicts Survival in Liver Cancer

Kumardeep Chaudharyl et al.

CLINICAL CANCER RESEARCH (2018)

Article Medicine, Research & Experimental

Downregulation of microRNA-30d promotes cell proliferation and invasion by targeting LRH-1 in colorectal carcinoma

Likun Yan et al.

INTERNATIONAL JOURNAL OF MOLECULAR MEDICINE (2017)

Article Statistics & Probability

Regularization Paths for Cox's Proportional Hazards Model via Coordinate Descent

Noah Simon et al.

Journal of Statistical Software (2015)

Article Oncology

Low-Grade Gliomas

Deborah A. Forst et al.

ONCOLOGIST (2014)

Article Clinical Neurology

CIC and FUBP1 mutations in oligodendrogliomas, oligoastrocytomas and astrocytomas

Felix Sahm et al.

ACTA NEUROPATHOLOGICA (2012)

Article Multidisciplinary Sciences

miR-495 is a tumor-suppressor microRNA down-regulated in MLL-rearranged leukemia

Xi Jiang et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2012)

Article Multidisciplinary Sciences

Mutations in CIC and FUBP1 Contribute to Human Oligodendroglioma

Chetan Bettegowda et al.

SCIENCE (2011)

Article Statistics & Probability

RANDOM SURVIVAL FORESTS

Hemant Ishwaran et al.

ANNALS OF APPLIED STATISTICS (2008)

Review Clinical Neurology

The 2007 WHO classification of tumours of the central nervous system

David N. Louis et al.

ACTA NEUROPATHOLOGICA (2007)