VICOROB

DOCTORAL THESIS: Automatic segmentation of brain structures in magnetic resonance images using deep learning techniques

By Kaisar Kushibar Supervised by Dr. Sergi Valverde / Dr. Arnau Oliver / Dr. Xavier Lladó   Abstract The sub-cortical brain structures are located beneath the cerebral cortex and in- clude the thalamus, caudate, putamen, pallidum, hippocampus, amygdala, and ac- cumbens structures. These bilateral structures – symmetrically located within the left and right hemispheres – are involved in systematic activities such as emotion, pleasure, memory and hormone production. Their deviations in…

TWIN roBOTs for cooperative underwater intervention missions

TWINBOT is a project that aims to develop a new kind of I-AUVs able to work autonomously in a cooperative way.   The underwater inspection, maintenance and repair operations are becoming the main focus of the research in underwater robotics. Due to the desire of using small, autonomous vehicles instead of heavy work-class remotely operated vehicles, these tasks need a new definition and approach, to overcome the limits of the…

ViCOROB presented Artificial Intelligence in Breast Cancer Diagnosis

Profound improvements have been introduced by artificial intelligence techniques in general, and deep learning in specific, to the medical image processing and analysis field in the last decade. That was due to the surge of data availability derived from internet spread and social media. One aspect of AI is referred to as Artificial Neural Networks (ANN), which in turn has several kinds including Generative Adversarial Neural Networks (GAN). Based on…

Featured Video Play Icon

Deepfield project: Short-term scientific mission

From the 13th of February until the 12th of March, Eduardo Soarez, an INES TEC pre doc researcher, has carried out a shot term scientific mission at CIRS facilities within the framework of Deepfield project.   The main focus of the short-term scientific missions is to engage INESC TEC young researchers in a assignment of a deep learning topic related to the previous thematic workshop, in which our case was…

TNA experiments in the VICOROB’s infrastructures

From the 2nd to the 6th of March, a team of researchers and students of the Université de Toulon have been carrying out experiments at the facilities of the CIRS.   These tests allowed them to collect real data regarding the dynamic behaviour of SPARUS AUV which will be compared with the data from the simulator they are developing in order to improve their predictions.   This action has been possible…

Deep learning, AI, and Machine Learning

From the 15th to 20th of February, the Medical Imaging Congress took place in Huston, Texas. It is one of the leading congresses in the field of the medical imaging in the world, organized by SPIE, the International Society for Optics and Photonics).   It is a conference where the latest advances in image processing, physics, computed-aided diagnosis, perception, radiology and digital pathology, among other medical imaging fields is presented,…

DEEPFIELD Thematic Workshop: Autonomous Underwater Intervention

The first Thematic Workshop called “Autonomous Underwater Intervention” took place on February 11th and 12th within the framework of the European project Deepfiled.   Pere Ridao, Patryk Cieslak and Guillem Vallicrosa run the training in the Girona’s Science and Technology Park. During the event, both INESC TEC and UdG students expanded their knowledge about the intervention and manipulation of an autonomous underwater vehicle. This training was conducted with a simulation,…

DOCTORAL THESIS: Deep learning methods for automated detection of new multiple sclerosis lesions in longitudinal magnetic resonance images

By Mostafa Salem Supervised by Prof. Joaquim Salvi / Prof. Xavier Lladó   Abstract Multiple sclerosis (MS) is an inflammatory disease of the central nervous system, which is characterized by the presence of lesions in the brain and the spinal cord. Magnetic resonance imaging (MRI) has become a core para-clinical tool for diagnosing and predicting long-term disability and treatment response in MS patients. It has been accepted that dissemination in time…