Radiomics and Machine Learning in Medical Imaging

This study uses computational perturbation on AI-generated MRI data to identify pathway-specific radiogenomic signatures in breast cancer.

This study evaluates fractal measures for distinguishing malignant from normal breast mammograms and assessing molecular subtype differentiation, finding moderate discriminatory performance.

This study uses radiomic features from thalamic nuclei to identify associations with cognitive performance in multiple sclerosis patients, finding radiomic features outperform volumetric measures.

This study integrates MRI radiomics and germline genetics to predict IDH mutation status in gliomas, improving classification accuracy and prognostic risk assessment.

The paper uses radioproteomics to stratify molecular response to antifibrotic treatment in pulmonary fibrosis by analyzing radiomic and proteomic profiles in mice and patients.

This study develops machine learning models using CT radiomics and clinical data to predict survival in metastatic NSCLC patients on durvalumab, showing improved accuracy compared to PD-L1 status.

This study develops a 2YS logistic regression model using radiogenomics analysis to predict GBM patient survival based on MRI features and gene associations.

This paper introduces a dual adversarial deconfounding autoencoder to remove batch effects from multi-center radiomics data, improving prognostic model performance for Hodgkin Lymphoma.

ImaGene is a web-based platform for radiogenomic analysis that correlates tumor imaging and omics data, identifies gene-imaging feature associations, and generates diagnostic reports.

The paper develops radiomic signatures from FDG-PET imaging to predict response to neoadjuvant chemotherapy in triple-negative breast cancer using machine learning in a co-clinical trial setting.

This paper develops a radiomic signature from T2-FLAIR MRI images to predict white matter hyperintensities burden and links it to clinical phenotypes.

This study develops a clinical-radiomics model to predict immunotherapy response in NSCLC patients, identifying a radiomic feature linked to hypoxia and poor outcomes.

This paper introduces a machine learning method for analyzing radiomics data with right-censored survival outcomes, showing it outperforms existing methods in identifying prognostic markers.

The paper develops a machine learning model using radiomic features from MRI to predict survival and tumor subtype in pancreatic ductal adenocarcinoma with high accuracy.

This paper develops a machine learning model to predict molecular subtypes of PDAC from radiomic features, showing differential chemotherapy response based on subtype.

The paper uses machine learning to connect proteomics data with histopathology images in kidney cancer, finding correlations between proteins and imaging-based predictions.

The paper introduces a framework combining deep learning and radiomics for cancer prognosis using CT and PET imaging, showing improved accuracy over single-method approaches.