Diffuse gliomas are currently challenging to classify in the field of brain tumours due to their clinical and imaging characteristics. This study aims to develop and train a patient classification system based on the study of various parameters to support personalized treatment planning. The use of MATLAB allows us to analyse, segment, and process all data to extract relevant features associated with glioma characteristics. Classification was performed by considering Radiomics (such as texture and shape), biomolecular makers, and clinical information from the patient, in order to predict therapeutic response. Experimental results show that the system is able to distinguish subgroups of patients with moderate but consistent accuracy, demonstrating the feasibility of applying computational image analysis in combination with clinical and molecular variables. The integration of radiomics, biomolecular, and clinical information underscores the potential of such an approach as a decision-support tool in neuro-oncology. Overall, the findings suggest that multimodal classification systems represent a promising pathway toward improving the accuracy of glioma diagnosis and advancing personalized treatment planning, ultimately contributing to better patient outcomes.
Diffuse gliomas are currently challenging to classify in the field of brain tumours due to their clinical and imaging characteristics. This study aims to develop and train a patient classification system based on the study of various parameters to support personalized treatment planning. The use of MATLAB allows us to analyse, segment, and process all data to extract relevant features associated with glioma characteristics. Classification was performed by considering Radiomics (such as texture and shape), biomolecular makers, and clinical information from the patient, in order to predict therapeutic response. Experimental results show that the system is able to distinguish subgroups of patients with moderate but consistent accuracy, demonstrating the feasibility of applying computational image analysis in combination with clinical and molecular variables. The integration of radiomics, biomolecular, and clinical information underscores the potential of such an approach as a decision-support tool in neuro-oncology. Overall, the findings suggest that multimodal classification systems represent a promising pathway toward improving the accuracy of glioma diagnosis and advancing personalized treatment planning, ultimately contributing to better patient outcomes. Read More
Related posts:
Machine learning models for predicting cure or relapse in post kala azar dermal leishmaniasis (PKDL)
Design and Implementation of Artificial Intelligence Algorithms for Prognostic Stratification in Acute Myeloid Leukemia
Activity recognition in patients with tremor: integrating time–length windows for enhanced detection
Integration of personalized healthcare pathways in an ICT platform for diabetes managements: a small-scale exploratory study
Radiomic-based biomarkers for the evaluation of prosthetic heart valve infective endocarditis in non-attenuation correction [18F]FDG PET/CT images
Developing Ontology-Driven Knowledge Graphs to Link Genomic Variants and Clinical Phenotypes in the Prenatal Context