Publications

@article{porto-alvarez_ct-based_2023,

title = {CT-based radiomics to predict KRAS mutation in CRC patients using a machine learning algorithm: a retrospective study},

author = {Jacobo Porto-Álvarez and Eva Cernadas and Rebeca Aldaz-Martínez and Manuel Fernández-Delgado and Emilio Huelga and Víctor González-Castro and Sandra Baleato-González and Roberto García-Figueiras and José Ramón Antúnez-López and Miguel Souto-Bayarri},

url = {https://www.mdpi.com/2227-9059/11/8/2144},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

journal = {Biomedicines},

volume = {11},

number = {8},

pages = {2144},

abstract = {This study examines the use of CT-based radiomics to predict KRAS mutations in colorectal cancer (CRC) patients. Several classifiers were tested, with AdaBoost on clinical data achieving the highest accuracy (76.8%). Texture descriptors also showed a correlation with KRAS mutations. Radiomics could reduce the need for invasive diagnostic methods for CRC in the future.},

note = {Publisher: MDPI},

keywords = {colorectal cancer, KRAS Mutation, Radiogenomics, Radiomics, texture analysis},

pubstate = {published},

tppubtype = {article}

}

@article{gonzalez-castro_ct_2020,

title = {CT radiomics in colorectal cancer: Detection of KRAS mutation using texture analysis and machine learning},

author = {Víctor González-Castro and Eva Cernadas and Emilio Huelga and Manuel Fernández-Delgado and Jacobo Porto-Álvarez and José Ramón Antúnez-López and Miguel Souto-Bayarri},

url = {https://www.mdpi.com/2076-3417/10/18/6214},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Applied Sciences},

volume = {10},

number = {18},

pages = {6214},

abstract = {This study analyzes CT image textures to classify colorectal cancer patients as KRAS+ or KRAS- using machine learning classifiers (SVM, GBM, NNET, RF). Texture analysis quantifies tumor heterogeneity, supporting the use of radiomics to predict KRAS mutations. A retrospective study with 47 patients achieved the highest accuracy (83%) and kappa (64.7%) using NNET with wavelet transform and Haralick features. This non-invasive approach could eliminate the need for biopsies, reducing risks and enabling more personalized treatment.},

note = {Publisher: MDPI},

keywords = {colorectal cancer, KRAS Mutation, machine learning, Non-invasive Diagnosis, Radiomics},

pubstate = {published},

tppubtype = {article}

}

@article{ortiz-ramon_identification_2019,

title = {Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images},

author = {Rafael Ortiz-Ramón and Maria del Carmen Valdés-Hernández and Victor González-Castro and Stephen Makin and Paul A Armitage and Benjamin S Aribisala and Mark E Bastin and Ian J Deary and Joanna M Wardlaw and David Moratal},

url = {https://www.sciencedirect.com/science/article/pii/S0895611119300278},

year  = {2019},

date = {2019-01-01},

journal = {Computerized Medical Imaging and Graphics},

volume = {74},

pages = {12–24},

abstract = {This study investigates using radiomics to detect stroke lesions in brain MRI scans, which are often missed by automated methods. Analyzing 1800 MRI scans, the research found that radiomic features could identify stroke lesions with accuracy between 0.7 and 0.83 AUC. Age was the clinical factor most correlated with accurate detection. The study suggests that incorporating texture features into deep learning models could improve stroke lesion detection in MRI scans.},

note = {Publisher: Pergamon},

keywords = {Radiomics, small vessel disease, Stroke, texture analysis, white matter hyperintensities},

pubstate = {published},

tppubtype = {article}

}