Cristián Castillo-Olea

ORCID: 0000-0002-8717-7524
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • AI in cancer detection
  • COVID-19 diagnosis using AI
  • Radiomics and Machine Learning in Medical Imaging
  • Nutrition and Health in Aging
  • Telemedicine and Telehealth Implementation
  • Artificial Intelligence in Healthcare
  • Colorectal Cancer Screening and Detection
  • ECG Monitoring and Analysis
  • Body Composition Measurement Techniques
  • Diabetic Foot Ulcer Assessment and Management
  • Machine Learning in Healthcare
  • Communication and COVID-19 Impact
  • COVID-19 and Mental Health
  • Technology in Education and Healthcare
  • Atrial Fibrillation Management and Outcomes
  • Scientific Research and Technology
  • Antiplatelet Therapy and Cardiovascular Diseases
  • Multiple Sclerosis Research Studies
  • Brain Tumor Detection and Classification
  • Video Analysis and Summarization
  • Knowledge Management in Higher Education
  • Health and Lifestyle Studies
  • Frailty in Older Adults
  • Long-Term Effects of COVID-19
  • TiO2 Photocatalysis and Solar Cells

Universidad La Salle
2024-2025

Universidad Autónoma de Baja California
2013-2024

University of Chile
2023-2024

CETYS Universidad
2023

Universidad de Deusto
2017-2021

Fundación Universitaria de Ciencias de la Salud
2016

Breast cancer analysis implies that radiologists inspect mammograms to detect suspicious breast lesions and identify mass tumors. Artificial intelligence techniques offer automatic systems for segmentation assist in their diagnosis. With the rapid development of deep learning its application medical imaging challenges, UNet variations is one state-of-the-art models image showed promising performance on mammography. In this paper, we propose an architecture, called Connected-UNets, which...

10.1038/s41523-021-00358-x article EN cc-by npj Breast Cancer 2021-12-02

Heart diseases are highly ranked among the leading causes of mortality in world. They have various types including vascular, ischemic, and hypertensive heart disease. A large number medical features reported for patients Electronic Health Records (EHR) that allow physicians to diagnose monitor We collected a dataset from Medica Norte Hospital Mexico includes 800 records 141 indicators such as age, weight, glucose, blood pressure rate, clinical symptoms. Distribution is very unbalanced on...

10.3390/info11040207 article EN cc-by Information 2020-04-14

With recent breakthroughs in artificial intelligence, the use of deep learning models achieved remarkable advances computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous applications provided efficient solutions to assist radiologists for medical imaging analysis. For instance, automatic lesion detection classification mammograms is still considered a crucial task that requires more accurate diagnosis precise analysis abnormal lesions. In this paper, we propose an...

10.32604/cmc.2021.018461 article EN Computers, materials & continua/Computers, materials & continua (Print) 2021-01-01

The large-scale parallel computation that became available on the new generation of graphics processing units (GPUs) and cloud-based services can be exploited for use in healthcare data analysis. Furthermore, workstations suited deep learning are usually equipped with multiple GPUs allowing workload distribution among larger datasets while exploiting parallelism each GPU. In this paper, we utilize distributed techniques to efficiently analyze using techniques. We demonstrate scalability...

10.1109/tii.2019.2919168 article EN IEEE Transactions on Industrial Informatics 2019-05-27

Nailfold Capillaroscopy (NFC) is a simple, non-invasive diagnostic tool used to detect microvascular changes in nailfold. Chronic pathological associated with wide range of systemic diseases, such as diabetes, cardiovascular disorders, and rheumatological conditions like sclerosis, can manifest observable the terminal capillaries nailfolds. The current gold standard relies on experts performing manual evaluations, which an exhaustive time-intensive, subjective process. In this study, we...

10.1038/s41598-025-85277-8 article EN cc-by-nc-nd Scientific Reports 2025-01-15

Colorectal cancer (CRC) is the second leading cause of death in world. This disease could begin as a non-cancerous polyp colon, when not treated timely manner, these polyps induce cancer, and turn, death. We propose deep learning model for classifying colon based on Kudo’s classification schema, using basic colonoscopy equipment. train convolutional with private dataset from University Deusto without VGG feature extractor, compared results. obtained 83% accuracy F1-score after fine tuning...

10.3390/app10020501 article EN cc-by Applied Sciences 2020-01-10

Dementia is the fifth cause of death worldwide with 10 million new cases every year. Healthcare applications using machine learning techniques have almost reached physical limits while more data becoming available resulting from increasing rate diagnosis. Recent research in Quantum Machine Learning (QML) found different approaches that may be useful to accelerate training process existing models and provide an alternative learn complex patterns. This work aims report a real-world application...

10.48550/arxiv.2007.08653 preprint EN other-oa arXiv (Cornell University) 2020-01-01

In this paper, a database generated from the contribution of Urduliz and Biodonostia Hospitals was used, which includes 785 images. The objective is to identify in category Paris classification each image is. 5 ResNet50, ResNet101, Xception, VGG19, Inception V3 models were used. model with best results ResNet50 accuracy 87.1 %, Precision Recall F1-Score % Specificity 93 %. article, we propose frame reference for set neural network models, offers method polypoid or sessile lesions that...

10.1109/isspit47144.2019.9001816 article EN 2019-12-01

The article presents a study based on timeline data analysis of the level sarcopenia in older patients Baja California, Mexico. Information was examined at beginning (first event), three months later (second and six (third event). Sarcopenia is defined as loss muscle mass quality strength. conducted with 166 patients. A total 65% were women 35% men. mean age enrolled 77.24 years. research included 99 variables that consider medical history, pharmacology, psychological tests, comorbidity...

10.3390/ijerph17061917 article EN International Journal of Environmental Research and Public Health 2020-03-15

The past decade has witnessed an explosive growth in the development and use of artificial intelligence (AI) across diverse fields [...]

10.3390/info15020090 article EN cc-by Information 2024-02-06

This paper presents a study based on data analysis of the sarcopenia level in older adults. Sarcopenia is prevalent pathology adults around 50 years age, whereby muscle mass decreases by 1 to 2% year, and strength experiences an annual decrease 1.5% between 60 subsequently increasing 3% each year. The World Health Organisation estimates that 5–13% individuals 70 age 11–50% persons 80 or over have sarcopenia. was conducted with 166 patients 99 variables. Demographic compiled including gender,...

10.3390/ijerph16183275 article EN International Journal of Environmental Research and Public Health 2019-09-06

A new benzotrithiophene-based small molecule, namely 2,5,8-Tris[5-(2,2-dicyanovinyl)-2-thienyl]-benzo[1,2-b:3,4-b′:6,5-b″]-trithiophene (DCVT-BTT), was successfully synthesized and subsequently characterized. This compound found to present an intense absorption band at a wavelength position of ∼544 nm displayed potentially relevant optoelectronic properties for photovoltaic devices. Theoretical studies demonstrated interesting behavior charge transport as electron donor (hole-transporting)...

10.3390/ma16103759 article EN Materials 2023-05-16

Cumulative evidence has established that Interferon (IFN)-γ both pathogenic and protective roles in Multiple Sclerosis the animal model, Experimental Autoimmune Encephalomyelitis (EAE). However, underlying mechanisms to beneficial effects of IFN-γ are not well understood. In this study, we found exerts therapeutic on chronic, relapsing-remitting, chronic progressive EAE models. The frequency regulatory T (Treg) cells spinal cords from mice treated with was significantly increased no effect...

10.1186/s12974-024-03126-3 article EN cc-by Journal of Neuroinflammation 2024-05-31

Thoracic pain is a shared symptom among gastrointestinal diseases, muscle pain, emotional disorders, and the most deadly: Cardiovascular diseases. Due to limited space in emergency department, it important identify when thoracic of cardiac origin, since being CVD (Cardiovascular Disease), attention patient must be immediate prevent irreversible injuries or even death. Artificial intelligence contributes early detection pathologies, such as chest pain. In this study, machine learning...

10.3390/ijerph18042155 article EN International Journal of Environmental Research and Public Health 2021-02-23

Convolutional neural networks and deep learning models represent the gold standard in medical image classification. Their innovative architectures have led to notable breakthroughs classification feature extraction performance. However, these advancements often remain underutilized imaging field due scarcity of sufficient labeled data which are needed leverage new features fully. While many methodologies exhibit stellar performance on benchmark sets like DDSM or Minimias, their efficacy...

10.3390/app13179639 article EN cc-by Applied Sciences 2023-08-25

As colon cancer is among the top causes of death, there a growing interest in developing improved techniques for early detection polyps. Given close relation between polyps and cancer, their helps avoid cases. The increment availability colorectal screening tests number colonoscopies have increased burden on medical personnel. In this article, application deep learning segmentation presented. Four were implemented evaluated: Mask-RCNN, PANet, Cascade R-CNN Hybrid Task (HTC). These trained...

10.32604/cmc.2021.013618 article EN Computers, materials & continua/Computers, materials & continua (Print) 2021-01-01

Background: The current pandemic caused by SARS-CoV-2 is an acute illness of global concern. infectious disease a recently discovered coronavirus. Most people who get sick from COVID-19 experience either mild, moderate, or severe symptoms. In order to help make quick decisions regarding treatment and isolation needs, it useful determine which significant variables indicate infection cases in the population served Tijuana General Hospital (Hospital de Tijuana). An Artificial Intelligence...

10.3390/info12120490 article EN cc-by Information 2021-11-24

The emergence of digital convergence and the explosive growth wireless communications in conjunction with learning experiences regarding provision Internet services rural communities all over world make necessary to rethinking strategies methods employed by governments, development agencies private sectors detonate socioeconomic through adoption Information Communication Technologies (ICT) communities. We start our analysis from participation inclusion projects as well reports research...

10.1145/2517899.2517909 article EN 2013-12-07

Introducción: producto de la investigación “Innovación, complejidad y gestión en sistemas sociotécnicos”, desarrollada entre 2014-2017 el Centro Investigación Científica Educación Superior Ensenada, Baja California, México. Los procesamiento, distribución transporte información digital tienen hoy gran impacto operación del sector salud, creando oportunidades para mejorar sus servicios, cobertura los procesos sanitaria carácter administrativo, clínico operativo. Una perspectiva salud...

10.16925/in.v23i13.1982 article ES cc-by-nc-nd Ingenieria Solidaria 2017-09-01

Acute myocardial infarction is the main cause of death worldwide, it part acute coronary syndromes (ACS) which are characterized by an obstruction blood flow in arteries heart. ACS diagnosis poses a highly complex problem where use intelligent systems represents opportunity for optimization diagnosis. The objective present work to perform cross validation federation collaborative rational agents population with high probability exhibiting chest pain. A study diagnostic tests was performed,...

10.1109/icmla.2016.0125 article EN 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) 2016-12-01
Coming Soon ...