A5027168396- Medical Image Segmentation Techniques
- AI in cancer detection
- Brain Tumor Detection and Classification
- Digital Radiography and Breast Imaging
- Image Retrieval and Classification Techniques
- Medical Imaging and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Multiple Sclerosis Research Studies
- Image Processing Techniques and Applications
- Ultrasound Imaging and Elastography
- Prostate Cancer Diagnosis and Treatment
- Acute Ischemic Stroke Management
- Medical Imaging Techniques and Applications
- Digital Imaging for Blood Diseases
- Advanced Neural Network Applications
- Cell Image Analysis Techniques
- Gene expression and cancer classification
- Advanced Image and Video Retrieval Techniques
- Cerebrovascular and Carotid Artery Diseases
- Infrared Thermography in Medicine
- 3D Shape Modeling and Analysis
- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Image and Object Detection Techniques
- Advanced Vision and Imaging
Universitat de Girona
2016-2025
Spanish Multiple Sclerosis Network
2021
Wansbeck General Hospital
2012
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> It has been shown that the accuracy of mammographic abnormality detection methods is strongly dependent on breast tissue characteristics, where a dense drastically reduces sensitivity. In addition, density widely accepted to be an important risk indicator for development cancer. Here, we describe automatic classification methodology, which can summarized in number distinct steps: 1) segmentation...
In recent years, several convolutional neural network (CNN) methods have been proposed for the automated white matter lesion segmentation of multiple sclerosis (MS) patient images, due to their superior performance compared with those other state-of-the-art methods. However, accuracies CNN tend decrease significantly when evaluated on different image domains used training, which demonstrates lack adaptability CNNs unseen imaging data. this study, we analyzed effect intensity domain...
Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of research community for a long time as morphological changes these structures are related to different neurodegenerative disorders. However, manual can be tedious and prone variability, highlighting need robust automated methods. In this paper, we present novel convolutional neural network based approach accurate sub-cortical that combines both prior spatial features improving accuracy....
Autism Spectrum Disorder (ASD) is a brain disorder that typically characterized by deficits in social communication and interaction, as well restrictive repetitive behaviors interests. During the last years, there has been an increase use of magnetic resonance imaging (MRI) to help detection common patterns autism subjects versus typical controls for classification purposes. In this work, we propose method ASD patients control using both functional structural MRI information. Functional...
The use of Computed Tomography (CT) imaging for patients with stroke symptoms is an essential step triaging and diagnosis in many hospitals. However, the subtle expression ischemia acute CT images has made it hard automated methods to extract potentially quantifiable information. In this work, we present evaluate deep learning tool lesion core segmentation from perfusion images. For evaluation, Ischemic Stroke Lesion Segmentation (ISLES) 2018 challenge dataset used that includes 94 cases...
Purpose Ground‐truth annotations from the well‐known Internet Brain Segmentation Repository (IBSR) datasets consider Sulcal cerebrospinal fluid (SCSF) voxels as gray matter. This can lead to bias when evaluating performance of tissue segmentation methods. In this work we compare accuracy 10 brain methods analyzing effects SCSF ground‐truth on estimations. Materials and Methods The set is composed by FAST, SPM5, SPM8, GAMIXTURE, ANN, FCM, KNN, SVPASEG, FANTASM, PVC. are evaluated using...
The presence of microcalcification clusters is a primary sign breast cancer; however, it difficult and time consuming for radiologists to classify microcalcifications as malignant or benign. In this paper, novel method the classification in mammograms proposed.The topology/connectivity individual analyzed within cluster using multiscale morphology. This distinct from existing approaches that tend concentrate on morphology and/or global (statistical) features. A set graphs are generated...
Magnetic resonance imaging (MRI) synthesis has attracted attention due to its various applications in the medical domain. In this paper, we propose generating synthetic multiple sclerosis (MS) lesions on MRI images with final aim improve performance of supervised machine learning algorithms, therefore, avoiding problem lack available ground truth. We a two-input two-output fully convolutional neural network model for MS lesion images. The information is encoded as discrete binary intensity...
Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new T2-w lesions on brain MR scans is considered a predictive biomarker for disease. In this study, we propose fully convolutional neural network (FCNN) to detect longitudinal images.One year apart, multichannel (T1-w, T2-w, PD-w, FLAIR) were obtained 60 patients, 36 them with lesions. Modalities from both temporal points preprocessed linearly...
Hemorrhagic stroke is the condition involving rupture of a vessel inside brain and characterized by high mortality rates. Even if patient survives, can cause temporary or permanent disability depending on how long blood flow has been interrupted. Therefore, it crucial to act fast prevent irreversible damage. In this work, deep learning-based approach automatically segment hemorrhagic lesions in CT scans proposed. Our based 3D U-Net architecture which incorporates recently proposed...