Thesis

chee_sing_lee

Former ViBOT student Chee Sing Lee defends his PhD Thesis

This thesis focuses on the problem of SLAM, in particular feature-based SLAM, where a mobile autonomous vehicle explores an unknown environment, navigating by observing landmarks. As the environment is previously unexplored, SLAM algorithms must estimate the location of the landmarks in addition to the location of the vehicle. The majority of research in feature-based SLAM builds on the legacy of foundational work using the Extended Kalman Filter (EKF), a single-object estimation technique. Because feature-based SLAM is an inherently multi-object problem, this has led to a number of suboptimalities in popular solutions. We hypothesize that a feature based SLAM algorithm derived…

Christian Mata defends his PhD thesis “Web-based Application for Medical Imaging Management”

The rapid growth of digital technology in medical fields during the last few years has increased the need for applications able to manage patient medical records, imaging tests, and chart information. Technologies related with digital database architectures, storage and transmission protocols, management of large volumes of data, and security are being improved every day, allowing the possibility of reading, analyzing, and even diagnosing a case far from the medical center where the information was acquired. Furthermore, the inclusion of web-based applications applied to the medical imaging field has growing demand over the last few years in the medical community. The…

Automated Analysis of Magnetic Resonance Imaging of the Breast

Albert Gubern defends his PhD thesis “Automated Analysis of Magnetic Resonance Imaging of the Breast”

Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) of the breast is employed for breast cancer screening in women with cumulative lifetime breast cancer risk of more than 20-25% (US and EU guideline). Other indications include, but are not limited to, preoperative staging, evaluation of women treated with neoadjuvant chemotherapy and problem solving in case of inconclusive findings from other modalities. Compared to mammography, which is the image modality commonly used in regular screening, breast DCE-MRI presents higher sensitivity, especially in women with dense breasts. However, the analysis of breast MRI requires interpretation of four-dimensional DCE data, as well as correlation to…

Tali Hurtós

Tali Hurtós defends her PhD thesis: “Forward-Looking Sonar Mosaicing for Underwater Environments”

Vehicle operations in underwater environments are frequently compromised by poor visibility conditions. The perception range of optical devices is heavily constrained in turbid waters, thus often complicating navigation and mapping tasks in environments such as harbors, bays, or rivers. A new generation of high-frequency forward-looking sonars that provide acoustic imagery at near-video frame rates have recently emerged as a promising alternative for working under these challenging conditions. In this thesis, we propose an end-to-end mosaicing framework tailored to the characteristics of forward-looking sonar imagery in order to build consistent overviews of planar underwater areas regardless of water visibility. Our solution…

Onur Ganiler defends his PhD thesis: “Automated detection of new Multiple Sclerosis lesions in longitudinal brain magnetic resonance imaging”

  This thesis deals with the detection of new multiple sclerosis (MS) lesions in longitudinal brain magnetic resonance (MR) imaging. This disease is characterized by the presence of lesions in the brain, predominantly in the white matter (WM) tissue of the brain. The detection and quantification of new lesions are crucial to follow-up MS patients. Moreover, the manual detection of these new lesions is not only time-consuming, but is also prone to intra- and inter-observer variability. Therefore, the development of automated techniques for the detection MS lesions is a major challenge. After a thorough analysis of the state-of-the art in…

PhD Vicorob

MARC MASIAS defends his PhD thesis: “Automatic source detection in astronomical images”

This thesis is focused on the automatic detection of sources (objects) in astronomical images. These sources are something that suggests the presence of an astronomical object such as stars, galaxies, gas, dust or cosmic rays. The use of automatic algorithms to perform such a task becomes of great importance in the astronomical field because of the increasing amount of data and the inefficiency and inaccuracy of manual inspection.   In the first place, we exhaustively analyze the state of the art on this topic, presenting a new classification of techniques and pointing out their main strengths and weaknesses. A complementary…

image analysis

Konstantin Korotkov defends his PhD thesis “Automatic change detection in multiple pigmented skin lesions”

Malignant melanoma is the rarest and deadliest of skin cancers causing three times more deaths than all other skin-related malignancies combined. Fortunately, in its early stages, it is completely curable, making a total body skin examination (TBSE) a fundamental procedure for many patients. During TBSE, dermatologists look for pigmented skin lesions (PSLs) exhibiting typical melanoma signs as well as PSLs undergoing the rapid changes characteristic of cancer. Accompanied by clinical and dermoscopic baseline photography, a TBSE can be very tedious and time-consuming, especially for patients with numerous lesions. In addition, establishing correct body-to-image and image-to-image lesion correspondences can be extremely…

3D mapping

Ricard Campos defends his PhD thesis “Surface Reconstruction Methods for Seafloor Modelling”

Underwater maps are an important source of information for the scientific community, since mapping the seafloor is the starting point for underwater exploration. The advance of range scanning methodologies, both using acoustic and optical techniques, enables the mapping of the seabed to attain increasingly larger resolutions. However, all these techniques sample the surface to reconstruct in the form of a point cloud. For the case of areas containing non-trivial 3D relief, achieving a continuous representation from this discrete sampling is a complex task.   Surface reconstruction methods try to tackle this problem by recovering a continuous surface representing the object…