A5014631198- Gastrointestinal Bleeding Diagnosis and Treatment
- Colorectal Cancer Screening and Detection
- Gastric Cancer Management and Outcomes
- Pancreatic and Hepatic Oncology Research
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Gallbladder and Bile Duct Disorders
- Gastrointestinal disorders and treatments
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Esophageal Cancer Research and Treatment
- Cervical Cancer and HPV Research
- Esophageal and GI Pathology
- Colorectal and Anal Carcinomas
- COVID-19 diagnosis using AI
- Inflammatory Bowel Disease
- Diverticular Disease and Complications
- Liver Disease Diagnosis and Treatment
- Surgical Simulation and Training
- Myofascial pain diagnosis and treatment
- Trace Elements in Health
- Clinical practice guidelines implementation
- Neonatal Health and Biochemistry
- Liver Diseases and Immunity
- Hepatitis C virus research
Hospital de São João
2023-2025
Universidade do Porto
2024-2025
Centro Hospitalar do Porto
2023
Centro Hospitalar do Baixo Vouga
2023
The role of capsule endoscopy and enteroscopy in managing various small-bowel pathologies is well-established. However, their broader application has been hampered mainly by lengthy reading times. As a result, there growing interest employing artificial intelligence (AI) these diagnostic therapeutic procedures, driven the prospect overcoming some major limitations enhancing healthcare efficiency, while maintaining high accuracy levels. In past two decades, applicability AI to...
Background: Capsule endoscopy (CE) improved the digestive tract assessment; yet, its reading burden is substantial. Deep-learning (DL) algorithms were developed for detection of enteric and gastric lesions. Nonetheless, their application in esophagus lacks evidence. The study aim was to develop a DL model esophageal pleomorphic lesion (PL) detection. Methods: A bicentric retrospective conducted using 598 CE exams. Three different devices provided 7982 frames, including 2942 PL data divided...
High-resolution anorectal manometry (HR-ARM) is the gold standard for functional disorders' evaluation, despite being limited by its accessibility and complex data analysis. The London Protocol Classification were developed to standardize motility patterns classification. This proof-of-concept study aims develop validate an artificial intelligence model identification differentiation of disorders anal tone contractility in HR-ARM. A dataset 701 HR-ARM exams from a tertiary center, classified...
Background: Several artificial intelligence systems based on large language models (LLMs) have been commercially developed, with recent interest in integrating them for clinical questions. Recent versions now include image analysis capacity, but their performance gastroenterology remains untested. This study assesses ChatGPT-4's interpreting images. Methods: A total of 740 images from five procedures-capsule endoscopy (CE), device-assisted enteroscopy (DAE), endoscopic ultrasound (EUS),...
Capsule endoscopy (CE) is a minimally invasive examination for evaluating the gastrointestinal tract. However, its diagnostic yield detecting gastric lesions suboptimal. Convolutional neural networks (CNNs) are artificial intelligence models with great performance image analysis. Nonetheless, their role in evaluation by wireless CE (WCE) has not been explored.Our group developed CNN-based algorithm automatic classification of pleomorphic lesions, including vascular (angiectasia, varices, and...
Digital single-operator cholangioscopy (D-SOC) has enhanced the ability to diagnose indeterminate biliary strictures (BSs). Pilot studies using artificial intelligence (AI) models in D-SOC demonstrated promising results. Our group aimed develop a convolutional neural network (CNN) for identification and morphological characterization of malignant BSs D-SOC. A total 84,994 images from 129 exams two centers (Portugal Spain) were used developing CNN. Each image was categorized as either...
Capsule endoscopy (CE) is commonly used as the initial exam for suspected mid-gastrointestinal bleeding after normal upper and lower endoscopy. Although assessment of small bowel primary focus CE, detecting upstream or downstream vascular lesions may also be clinically significant. This study aimed to develop test a convolutional neural network (CNN)-based model panendoscopic automatic detection during CE.
High-resolution anoscopy (HRA) plays a central role in the detection and treatment of precursors anal squamous cell carcinoma (ASCC). Artificial intelligence (AI) algorithms have shown high levels efficiency detecting differentiating HSIL from low-grade intraepithelial lesions (LSIL) HRA images. Our aim was to develop deep learning system for automatic differentiation versus LSIL using images both conventional digital proctoscopes. A convolutional neural network (CNN) developed based on 151...
Background/Objectives: Proficient colposcopy is crucial for the adequate management of cervical cancer precursor lesions; nonetheless its limitations may impact cost-effectiveness. The development artificial intelligence models experiencing an exponential growth, particularly in image-based specialties. aim this study to develop and validate a Convolutional Neural Network (CNN) automatic differentiation high-grade (HSIL) from low-grade dysplasia (LSIL) colposcopy. Methods: A unicentric...
Background and Objectives: Device-assisted enteroscopy (DAE) has a significant role in approaching enteric lesions. Endoscopic observation of ulcers or erosions is frequent can be associated with many nosological entities, namely Crohn's disease. Although the application artificial intelligence (AI) growing exponentially various imaged-based gastroenterology procedures, there still lack evidence AI technical feasibility clinical applicability DAE. This study aimed to develop test multi-brand...
Background and objectives: Capsule endoscopy (CE) is a non-invasive method to inspect the small bowel that, like other enteroscopy methods, requires adequate small-bowel cleansing obtain conclusive results. Artificial intelligence (AI) algorithms have been seen offer important benefits in field of medical imaging over recent years, particularly through adaptation convolutional neural networks (CNNs) achieve more efficient image analysis. Here, we aimed develop deep learning model that uses...
In the early 2000s, introduction of single-camera wireless capsule endoscopy (CE) redefined small bowel study. Progress continued with development double-camera devices, first for colon and rectum, then, panenteric assessment. Advancements magnetic (MCE), particularly when assisted by a robotic arm, designed to enhance gastric evaluation. Indeed, as CE provides full visualization entire gastrointestinal (GI) tract, minimally invasive panendoscopy (CPE) could be feasible alternative, despite...
Gastroenterology is increasingly moving towards minimally invasive diagnostic modalities. The exploration of the colon via capsule endoscopy, both in specific protocols for endoscopy and during panendoscopic evaluations, regarded as an appropriate first-line approach. Adequate colonic preparation essential conclusive examinations as, contrary to a conventional colonoscopy, moves passively does not have capacity clean debris. Several scales been developed classification bowel endoscopy....
The surge in the implementation of artificial intelligence (AI) recent years has permeated many aspects our life, and health care is no exception. Whereas this technology can offer clear benefits, some problems associated with its use have also been recognised brought into question, for example, environmental impact. In a similar fashion, significant impact, it requires considerable source greenhouse gases. efforts are being made to reduce footprint AI tools, here, we were specifically...
Device-assisted enteroscopy (DAE) is capable of evaluating the entire gastrointestinal tract, identifying multiple lesions. Nevertheless, DAE’s diagnostic yield suboptimal. Convolutional neural networks (CNN) are multi-layer architecture artificial intelligence models suitable for image analysis, but there a lack studies about their application in DAE. Our group aimed to develop multidevice CNN panendoscopic detection clinically relevant lesions during In total, 338 exams performed two...
Background: Capsule endoscopy (CE) is a valuable tool for assessing inflammation in patients with Crohn’s disease (CD). The current standard evaluating are validated scores (and clinical laboratory values) like Lewis score (LS), Endoscopy Disease Activity Index (CECDAI), and ELIAKIM. Recent advances artificial intelligence (AI) have made it possible to automatically select the most relevant frames CE. Objectives: In this proof-of-concept study, our objective was develop an automated scoring...
Introduction: Capsule endoscopy (CE) is a minimally invasive exam suitable of panendoscopic evaluation the gastrointestinal (GI) tract. Nevertheless, CE time-consuming with suboptimal diagnostic yield in upper GI Convolutional neural networks (CNN) are human brain architecture-based models for image analysis. However, there no study about their role capsule panendoscopy. Methods: Our group developed an artificial intelligence (AI) model automatic detection pleomorphic lesions (namely...