
Segmentation services
MRI preprocessing and quality improvement in combination with automated segmentation of enhancing tumor, necrotic core and peritumoral edema based on Deep Learning state-of-the-art Convolutional Neural Networks.
Multiparametric Tissue Signatures
Heterogeneity assessment of the glioblastoma by means of the detection of functional habitats within the lesion through state-of-the-art unsupervised machine learning analysis. Includes all the modules of the Anatomical service
Biomarker quantification services
Functional assessment of biological imaging markers from perfusion and diffusion magnetic resonance sequences for the quantitative evaluation of tumor physiological features.
ONCOhabitats technology
Open-access services for tumor heterogeneity assessment, implementing consolidated state-of-the-art techniques.
PROCESSED CASES
USERS
INSTITUTIONS
Biomedical Data Science Lab
The Biomedical Data Science Lab is an interdisciplinary research line of the ITACA institute at Universitat Politècnica de València (UPV) committed to biomedical computer science since its creation in 2000. With more than 13 years of experience, the BDSLab focuses its research on real problems in the field of biomedical data mining by means of advanced pattern recognition and machine learning techniques, computational prediction and development of tools to support health care professionals and their patients.
More infoSupported by






CLINICAL TRIAL |
|
![]() | Multicentre Validation of How Vascular Biomarkers From Tumor Can Predict the Survival of the Patient With Glioblastoma (ONCOhabitats)Juan M. García-Gómez, BDSLab |
PUBLICATION |
|
![]() | Glioblastoma: Vascular Habitats Detected at Preoperative Dynamic Susceptibility-weighted Contrast-enhanced Perfusion MR Imaging Predict SurvivalJavier Juan-Albarracín, Elies Fuster-Garcia, Alexandre Pérez-Girbés, Fernando Aparici-Robles, Ángel Alberich-Bayarri, Antonio Revert-Ventura, Luis Martí-Bonmatí, Juan M. García-Gómez |
PUBLICATION |
|
![]() | Automated Glioblastoma Segmentation Based on a Multiparametric Structured Unsupervised ClassificationJavier Juan-Albarracín, Elies Fuster-Garcia, José V. Manjón, Montserrat Robles, F. Aparici, L. Martí-Bonmatí, Juan M. García-Gómez |