A5045090259- Remote-Sensing Image Classification
- Optical Imaging and Spectroscopy Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Brain Tumor Detection and Classification
- Spectroscopy and Chemometric Analyses
- Infrared Thermography in Medicine
- Photoacoustic and Ultrasonic Imaging
- Advanced Image Fusion Techniques
- AI in cancer detection
- Advanced Chemical Sensor Technologies
- Artificial Intelligence in Healthcare
- Cell Image Analysis Techniques
- Cutaneous Melanoma Detection and Management
- Machine Learning in Healthcare
- Image and Signal Denoising Methods
- Phonocardiography and Auscultation Techniques
- ECG Monitoring and Analysis
- Skin Protection and Aging
- Remote Sensing and Land Use
- Imbalanced Data Classification Techniques
- Optical Coherence Tomography Applications
- Diabetes Management and Research
- Medical and Biological Ozone Research
- Digital Imaging for Blood Diseases
- Experimental Learning in Engineering
Fundación Canaria de Investigación Sanitaria
2022-2025
Universidad de Las Palmas de Gran Canaria
2016-2025
Hospital Universitario de Gran Canaria Doctor Negrín
2023-2025
Tokyo University of Science
2023
Hospital Universitario Insular de Gran Canaria
2023
Microelectronica (Romania)
2022
Institute of Microelectronics
2021
The University of Texas at Dallas
2019
Universidad Politécnica de Madrid
2016-2018
Software (Spain)
2018
The main goal of brain cancer surgery is to perform an accurate resection the tumor, preserving as much normal tissue possible for patient. development a non-contact and label-free method provide reliable support tumor in real-time during neurosurgical procedures current clinical need. Hyperspectral imaging non-contact, non-ionizing, modality that can assist surgeons this challenging task without using any contrast agent. In work, we present deep learning-based framework processing...
Surgery for brain cancer is a major problem in neurosurgery. The diffuse infiltration into the surrounding normal by these tumors makes their accurate identification naked eye difficult. Since surgery common treatment cancer, an radical resection of tumor leads to improved survival rates patients. However, boundaries during challenging. Hyperspectral imaging non-contact, non-ionizing and non-invasive technique suitable medical diagnosis. This study presents development novel classification...
Hyperspectral imaging (HSI) allows for the acquisition of large numbers spectral bands throughout electromagnetic spectrum (within and beyond visual range) with respect to surface scenes captured by sensors. Using this information a set complex classification algorithms, it is possible determine which material or substance located in each pixel. The work presented paper aims exploit characteristics HSI develop demonstrator capable delineating tumor tissue from brain during neurosurgical...
The use of hyperspectral imaging for medical applications is becoming more common in recent years. One the main obstacles that researchers find when developing algorithms lack specific, publicly available, and data. work described this paper was developed within framework European project HELICoiD (HypErspectraL Imaging Cancer Detection), which had as a goal application to delineation brain tumors real-time during neurosurgical operations. In paper, methodology followed generate first...
Hyperspectral imaging (HSI) is an emerging technology for medical diagnosis.This research work presents a proof-of-concept on the use of HSI data to automatically detect human brain tumor tissue in pathological slides.The samples, consisting hyperspectral cubes collected from 400 nm 1000 nm, were acquired ten different patients diagnosed with high-grade glioma.Based diagnosis provided by pathologists, spectral library normal and tissues was created processed using three supervised...
Skin cancer is one of the most common forms worldwide and its early detection key to achieve an effective treatment lesion. Commonly, skin diagnosis based on dermatologist expertise pathological assessment biopsies. Although there are aid systems morphological processing algorithms using conventional imaging, currently, these have reached their limit not able outperform dermatologists. In this sense, hyperspectral (HS) imaging (HSI) arises as a new non-invasive technology facilitate...
Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have ability automatic feature extraction from data for successful classification. In this study, we exploit HSI DL differentiation glioblastoma (GB) non-tumor on hematoxylin eosin (H&E) stained histological slides human brain tissue. GB detection is challenging...
Recent advances in hyperspectral imaging have made it a promising solution for intra-operative tissue characterization, with the advantages of being non-contact, non-ionizing, and non-invasive. Working images vivo, however, is not straightforward as high dimensionality data makes real-time processing challenging. In this paper, novel reduction scheme new pipeline are introduced to obtain detailed tumor classification map margin definition during brain surgery. However, existing approaches...
The primary treatment for malignant brain tumors is surgical resection. While gross total resection improves the prognosis, a supratotal may result in neurological deficits. On other hand, accurate intraoperative identification of tumor boundaries be very difficult, resulting subtotal resections. Histological examination biopsies can used repeatedly to help achieve but this not practically feasible due turn-around time tissue analysis. Therefore, techniques recognize types are investigated...
In recent years, hyperspectral imaging (HSI) has been shown as a promising modality to assist pathologists in the diagnosis of histological samples. this work, we present use HSI for discriminating between normal and tumor breast cancer cells. Our customized system includes (HS) push-broom camera, which is attached standard microscope, home-made software control image acquisition. HS microscopic works visible near-infrared (VNIR) spectral range (400 - 1000 nm). Using system, 112 images were...
Machine Learning (ML) methods have become important for enhancing the performance of decision-support predictive models. However, class imbalance is one main challenges developing ML models, because it may bias learning process and model generalization ability. In this paper, we consider oversampling generating synthetic categorical clinical data aiming to improve in identification risk factors cardiovascular diseases (CVDs). We performed a comparative study several generation methods,...
Hyperspectral imaging (HSI) is a non-ionizing and non-contact technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic surgical guidance purposes. However, large amount provided by normally contains redundant or non-relevant information, it extremely important identify most relevant wavelengths certain application in order improve accuracy predictions...
Several causes make brain cancer identification a challenging task for neurosurgeons during the surgical procedure. The surgeons' naked eye sometimes is not enough to accurately delineate tumor location and extension due its diffuse nature that infiltrates in surrounding healthy tissue. For this reason, support system provides accurate delimitation essential order improve surgery outcomes hence patient's quality of life. detection developed as part "HypErspectraL Imaging Cancer Detection"...
Currently, intraoperative guidance tools used for brain tumor resection assistance during surgery have several limitations. Hyperspectral (HS) imaging is arising as a novel technique that could offer new capabilities to delineate tissue in surgical-time. However, the HS acquisition systems some limitations regarding spatial and spectral resolution depending on range be captured. Image fusion techniques combine information from different sensors obtain an cube with improved resolution. This...
The increasing prevalence of chronic non-communicable diseases makes it a priority to develop tools for enhancing their management. On this matter, Artificial Intelligence algorithms have proven be successful in early diagnosis, prediction and analysis the medical field. Nonetheless, two main issues arise when dealing with data: lack high-fidelity datasets maintenance patient's privacy. To face these problems, different techniques synthetic data generation emerged as possible solution. In...
In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived serve role diagnostic tool surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, label-free...
Abstract Brain surgery is one of the most common and effective treatments for brain tumour. However, neurosurgeons face challenge determining boundaries tumour to achieve maximum resection, while avoiding damage normal tissue that may cause neurological sequelae patients. Hyperspectral (HS) imaging (HSI) has shown remarkable results as a diagnostic tool detection in different medical applications. In this work, we demonstrate, with robust k-fold cross-validation approach, HSI combined...
The development of real-time, reliable, low-cost automatic Phonocardiogram (PCG) analysis systems is critical for early detection Cardiovascular Diseases (CVDs), especially in countries with limited access to primary health care programs. Once the raw PCG acquired by stethoscope has been preprocessed, first key task its segmentation into fundamental heart sounds. For this purpose, an optimized hardware implementation algorithm essential attain a computer-aided diagnostic system based on...
Cervical cancer remains a major global health concern, with specially alarming incidence in younger women. Traditional detection techniques such as the Pap smear and colposcopy often lack sensitivity specificity are highly dependent on experience of gynaecologist. In response, this study proposes use Hyperspectral Imaging, pioneering technology that combines traditional imaging spectroscopy to provide detailed spatial spectral information. Over period six-months, our custom-designed...
Background: Numbness and tingling secondary to chemotherapy-induced peripheral neuropathy (CIPN) are frequent side effects that limit chemotherapy treatment quality of life. Successful treatments for CIPN limited. This preliminary report shows the potential long-term ozone in management persistent numbness CIPN. Methods: Ozone was administered by rectal insufflation 15 patients (female/male: 8/7, age: 66 years old) suffering from grade-2 or grade-3 Planned consisted 40 sessions over 4...