Advanced MRI and molecular markers have been raised as crucial to improve prognostic models for patients having glioblastoma (GBM) lesions. In particular, different MR perfusion based markers describing vascular intrapatient heterogeneity have been correlated with tumor aggressiveness, and represent key information to understand tumor resistance against effective therapies of these neoplasms. Recently, hemodynamic tissue signature (HTS) markers based on MR perfusion images have been demonstrated to be useful for describing the heterogeneity of GBM at the voxel level, as well as demonstrating significant correlations with the patient's overall survival. In this work, we analyze the abilities of these markers to improve the conventional prognostic models based on clinical, morphological, and demographic features. Our results, in both the regression and classification tests, show that inclusion of the HTS markers improves the reliability of prognostic models. The HTS method is fully automatic and it is available for research use at http://www.oncohabitats.upv.es.

The objectives of this study are to describe the radiologic abnormalities detected on chest computed tomography (CT) of children suffering from tuberculosis and identify in which asymptomatic children, with positive tuberculin skin test and normal chest radiography, CT has the highest diagnostic yield using a low radiation dose protocol. The most common finding on CT in cases of tuberculosis is lymphadenopathy with necrotic appearance. In asymptomatic children with positive tuberculin skin test and normal chest radiography, CT had higher diagnostic yield in children younger than 5 years, modifying the therapeutic approach in a high percentage of cases. Reduction kilovoltage (kV) and milliamperage (mA) protocols significantly decrease the radiation dose, keeping sufficient diagnostic quality.

The purpose of this project is to develop and validate a Deep Learning (DL) FDG PET imaging algorithm able to identify patients with any neurodegenerative diseases (Alzheimer's Disease (AD), Frontotemporal Degeneration (FTD) or Dementia with Lewy Bodies (DLB)) among patients with Mild Cognitive Impairment (MCI). A 3D Convolutional neural network was trained using images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The ADNI dataset used for the model training and testing consisted of 822 subjects (472 AD and 350 MCI). The validation was performed on an independent dataset from La Fe University and Polytechnic Hospital. This dataset contained 90 subjects with MCI, 71 of them developed a neurodegenerative disease (64 AD, 4 FTD and 3 DLB) while 19 did not associate any neurodegenerative disease. The model had 79% accuracy, 88% sensitivity and 71% specificity in the identification of patients with neurodegenerative diseases tested on the 10% ADNI dataset, achieving an area under the receiver operating characteristic curve (AUC) of 0.90. On the external validation, the model preserved 80% balanced accuracy, 75% sensitivity, 84% specificity and 0.86 AUC. This binary classifier model based on FDG PET images allows the early prediction of neurodegenerative diseases in MCI patients in standard clinical settings with an overall 80% classification balanced accuracy.

No abstract

No abstract