- Retinal Imaging and Analysis
- Medical Image Segmentation Techniques
- Image and Object Detection Techniques
- Oral microbiology and periodontitis research
- Glaucoma and retinal disorders
- Image Retrieval and Classification Techniques
- Dental Radiography and Imaging
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- COVID-19 diagnosis using AI
- Neural Networks and Applications
- Radiomics and Machine Learning in Medical Imaging
- Digital Imaging for Blood Diseases
- Biometric Identification and Security
- Forensic Anthropology and Bioarchaeology Studies
- Image Processing Techniques and Applications
- Gut microbiota and health
- Medical Imaging and Analysis
- Neural dynamics and brain function
- Cell Image Analysis Techniques
- Genomics and Phylogenetic Studies
- Autopsy Techniques and Outcomes
- Industrial Vision Systems and Defect Detection
- Advanced Vision and Imaging
- Zebrafish Biomedical Research Applications
Universidade de Santiago de Compostela
2011-2024
Instituto de Investigación Sanitaria de Santiago
2020-2024
Center for Research in Molecular Medicine and Chronic Diseases
2017-2024
Weatherford College
2021
Laboratoire d'Informatique de Paris-Nord
2005
Universidad de Santiago de Chile
2003
In this work, the authors have developed a computer-aided diagnosis system, based on two-level artificial neural network (ANN) architecture. This was trained, tested, and evaluated specifically problem of detecting lung cancer nodules found digitized chest radiographs. The first ANN performs detection suspicious regions in low-resolution image. input to second are curvature peaks computed for all pixels each region. comes from fact that small tumors possess identifiable signature...
Chronological age estimation is crucial labour in many clinical procedures, where the teeth have proven to be one of best estimators. Although some methods estimate from tooth measurements orthopantomogram (OPG) images been developed, they rely on time-consuming manual processes whose results are affected by observer subjectivity. Furthermore, all those approaches tested only OPG image sets good radiological quality without any conditioning dental characteristic. In this work, two fully...
Biometrics refer to identity verification of individuals based on some physiologic or behavioural characteristics. The typical authentication process a person consists in extracting biometric pattern him/her and matching it with the stored for authorised user obtaining similarity value between patterns. In this work an efficient method persons is showed. system set feature points representing landmarks retinal vessel tree. extraction described. Also, deep analysis metrics performance...
Zebrafish (Danio rerio) is a model organism that has emerged as tool for cancer research, being the second most common cause of death after cardiovascular disease humans in developed world. useful xenotransplantation human cells and toxicity studies different chemotherapeutic compounds vivo. Compared to murine model, zebrafish faster, can be screened using high-throughput methods lower maintenance cost, making it possible affordable create personalized therapies. While several cell...
This paper presents an improved version of our specific methodology to detect the vessel tree in retinal angiographies. The automatic analysis facilitates computation arteriovenous index, which is essential for diagnosis several eye diseases. developed system inspired classical snake but incorporating domain knowledge, such as blood vessels topological properties. It profits from localization optic disc, creases extraction and, a recent innovation, morphological segmentation, all research...
Abstract Background Sequencing has been widely used to study the composition of oral microbiome present in various health conditions. The extent coverage 16S rRNA gene primers employed for this purpose not, however, evaluated silico using oral-specific databases. This paper analyses these two databases containing sequences from bacteria and archaea found human mouth describes some best each domain. Results A total 369 distinct individual were identified sequencing studies other ecosystems....
Abstract Purpose The shape of the mandible has been analyzed in a variety fields, whether to diagnose conditions like osteoporosis or osteomyelitis, forensics, estimate biological information such as age, gender, and race orthognathic surgery. Although methods employed produce encouraging results, most rely on dry bone analyses complex imaging techniques that, ultimately, hamper sample collection and, consequence, development large-scale studies. Thus, we proposed an objective, repeatable,...
Chronological age and biological sex estimation are two key tasks in a variety of procedures, including human identification migration control. Issues such as these have led to the development both semiautomatic automatic prediction models, but former expensive terms time resources, while latter lack interpretability required be applicable real-life scenarios. This paper therefore proposes new, fully methodology for sex. first applies tooth detection by means modified CNN with objective...
To validate a computer-based method for measuring the calibre of retinal blood vessels, and use it to determine effects ageing arterial hypertension on calibres these vessels their ratio.Digital eye fundus images covering 50 degrees field centred optic disc were obtained using 540 nm filter. The boundaries crossing series circles concentric with located by an image analysis program; perpendicularly determined automatically, average arteriole vein calculated, arteriovenous ratio (AVR) was...
This work describes a computational scheme for automatic detection of suspected lung nodules in chest radiograph. A knowledge‐based system extracts the masks over which we will apply nodule process. First obtain normalized cross‐correlation image. Next detect suspicious regions by assuming threshold. We examine using variable threshold results growth areas and an increase false positives. reduce large number positives applying facet model to An algorithmic classification process gives...
Currently, there is little evidence on the in situ antibacterial activity of essential oils (EO) without alcohol. This study aimed to evaluate substantivity and antiplaque effect plaque-like biofilm (PL-biofilm) two solutions, a traditional formulation that contains EO with alcohol (T-EO) an alcohol-free (Af-EO). Eighteen healthy adults performed single mouthwash of: T-EO, Af-EO, sterile water (WATER) after wearing individualized disk-holding splint for 2 days. The bacterial viability (BV)...
Abstract Background No clinical trials have evaluated the antimicrobial activity and substantivity of gel formulations containing chlorhexidine (CHX) cymenol. Objective To compare in situ effect a new 0.20% CHX + cymenol (test) with current formulation (control) on salivary flora dental plaque biofilm up to seven hours after single application. Methods A randomised-crossover trial was conducted 29 orally healthy volunteers participating development Experiments 1 (saliva) 2 (dental biofilm)....
This study aimed to evaluate the number of 16S rRNA genes in complete genomes bacterial and archaeal species inhabiting human mouth assess how use different primer pairs would affect detection classification redundant amplicons matching (MAs) from taxa. A total 518 oral-bacterial 191 oral-archaeal were downloaded NCBI database, their extracted. The numbers variants per genome calculated. Next, 39 used search for matches obtain amplicons. For each primer, we calculated gene amplicons,...
In this work, the problem of segmenting teeth in panoramic dental images is addressed. The Random Forest Regression Voting Constrained Local Models (RFRV-CLM) are used to perform segmentation two steps. Firstly, a set mandible and keypoints located, then that points initialise each individual tooth model. A method detect missing based on quality fit presented. system evaluated using 346 manually annotated containing adult-stage teeth. Encouraging results detecting achieved. able locate...
Abstract Reliable and effective diagnostic systems are of vital importance for COVID-19, specifically triage screening procedures. In this work, a fully automatic system based on chest X-ray images (CXR) has been proposed. It relies the few-shot paradigm, which allows to work with small databases. Furthermore, three components have added improve diagnosis performance: (1) region proposal network makes focus lungs; (2) novel cost function adds expert knowledge by giving specific penalties...
Although clustering by operational taxonomic units (OTUs) is widely used in the oral microbial literature, no research has specifically evaluated extent of limitations this sequence clustering-based method microbiome. Consequently, our objectives were to: 1) evaluate in-silico coverage a set previously selected primer pairs to detect species having 16S rRNA segments with ≥97% similarity; 2) describe highly similar and determine whether they belong distinct genera or other higher ranks....