A5032922184- Gastrointestinal Bleeding Diagnosis and Treatment
- Remote-Sensing Image Classification
- Colorectal Cancer Screening and Detection
- Image Retrieval and Classification Techniques
- Gastric Cancer Management and Outcomes
- Geochemistry and Geologic Mapping
- Hearing Loss and Rehabilitation
- Acoustic Wave Phenomena Research
- Speech and Audio Processing
- Neural Networks and Applications
- Advanced Image Fusion Techniques
- Noise Effects and Management
- Phonocardiography and Auscultation Techniques
- Advanced Data Compression Techniques
- Wireless Body Area Networks
- Neural Networks and Reservoir Computing
- Medical Image Segmentation Techniques
- Air Quality Monitoring and Forecasting
- Seismology and Earthquake Studies
- Molecular Communication and Nanonetworks
- Advanced X-ray and CT Imaging
i2CAT
2024
Universitat Politècnica de Catalunya
2024
Deleted Institution
2023
Universitat de Barcelona
2016-2022
State-of-the-art machine learning models, and especially deep ones, are significantly data-hungry; they require vast amounts of manually labeled samples to function correctly. However, in most medical imaging fields, obtaining said data can be challenging. Not only the volume is a problem, but also imbalances within its classes; it common have many more images healthy patients than those with pathology. Computer-aided diagnostic systems suffer from these issues, usually over-designing their...
Contemporary research advances in nanotechnology and material science are rooted the emergence of nanodevices as a versatile tool that harmonizes sensing, computing, wireless communication, data storage, energy harvesting. These devices hold promise precision medicine, offering novel pathways for disease diagnostics, treatment, monitoring within bloodstreams. Ensuring precise localization events diagnostic interest, which underpins concept flow-guided in-body nanoscale localization, would...
The production of thematic maps depicting land cover is one the most common applications remote sensing. To this end, several semantic segmentation approaches, based on deep learning, have been proposed in literature, but still considered an open problem due to some specific problems related sensing imaging. In paper we propose a novel approach deal with modelling multiscale contexts surrounding pixels different categories. leverages computation heteroscedastic measure uncertainty when...
Wireless Capsule Endoscopy (WCE) is a procedure to examine the human digestive system for potential mucosal polyps, tumours, or bleedings using an encapsulated camera. This work focuses on polyp detection within WCE videos through Machine Learning. When Learning in medical field, scarce and unbalanced datasets often make it hard receive satisfying performance. We claim that Sequential Models order take temporal nature of data into account improves performance previous approaches. Thus, we...
The interpretation and analysis of the wireless capsule endoscopy recording is a complex task which requires sophisticated computer aided decision (CAD) systems in order to help physicians with video screening and, finally, diagnosis. Most CAD share common system design, but use very different image representations. As result, each time new clinical application WCE appears, has be designed from scratch. This characteristic makes design consuming. Therefore, this paper we introduce for small...
Advancements in nanotechnology and material science are paving the way toward nanoscale devices that combine sensing, computing, data energy storage, wireless communication. In precision medicine, these nanodevices show promise for disease diagnostics, treatment, monitoring from within patients' bloodstreams. Assigning location of a sensed biological event with itself, which is main proposition flow-guided in-body localization, would be immensely beneficial perspective medicine. The nature...
The production of thematic maps depicting land cover is one the most common applications remote sensing. To this end, several semantic segmentation approaches, based on deep learning, have been proposed in literature, but still considered an open problem due to some specific problems related sensing imaging. In paper we propose a novel approach deal with modelling multiscale contexts surrounding pixels different categories. leverages computation heteroscedastic measure uncertainty when...
Deep learning models thrive with high amounts of data where the classes are, usually, appropriately balanced. In medical imaging, however, we often encounter opposite case. Wireless Capsule Endoscopy is not an exception; even if huge could be obtained, labeling each frame a video take up to twelve hours for expert physician. Those videos would show no pathologies most patients, while minority have few frames associated pathology. Overall, there low and great unbalance. Self-supervised...