Gustavo Carneiro
YOU?
Author Swipe
View article: Learning To Defer To A Population With Limited Demonstrations
Learning To Defer To A Population With Limited Demonstrations Open
This paper addresses the critical data scarcity that hinders the practical deployment of learning to defer (L2D) systems to the population. We introduce a context-aware, semi-supervised framework that uses meta-learning to generate expert-…
View article: Ethical Challenges in Advanced Dementia: Role of Enteral Feeding Devices
Ethical Challenges in Advanced Dementia: Role of Enteral Feeding Devices Open
View article: EndoCompass project: artificial intelligence in endocrinology
EndoCompass project: artificial intelligence in endocrinology Open
Background Endocrine science remains underrepresented in European Union research programs despite the fundamental role of hormone health in human wellbeing. Analysis of the CORDIS database reveals a persistent gap between the societal impa…
View article: PRIMEIRO MAPA GENÔMICO COMPLETO DE LINFOMAS DE CÉLULAS T NO BRASIL: ASSINATURAS MUTACIONAIS EXCLUSIVAS E NOVOS ALVOS TERAPÊUTICOS
PRIMEIRO MAPA GENÔMICO COMPLETO DE LINFOMAS DE CÉLULAS T NO BRASIL: ASSINATURAS MUTACIONAIS EXCLUSIVAS E NOVOS ALVOS TERAPÊUTICOS Open
View article: Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model using X-ray Images
Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model using X-ray Images Open
Medical imaging plays a crucial role in assessing knee osteoarthritis (OA) risk by enabling early detection and disease monitoring. Recent machine learning methods have improved risk estimation (i.e., predicting the likelihood of disease p…
View article: AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting
AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting Open
Segment Anything Model 2 (SAM2) exhibits strong generalisation for promptable segmentation in video clips; however, its integration with the audio modality remains underexplored. Existing approaches mainly follow two directions: (1) inject…
View article: AVANÇOS NO TRATAMENTO DA HIPERTENSÃO ARTERIAL: NOVAS TERAPIAS E ESTRATÉGIAS DE PREVENÇÃO
AVANÇOS NO TRATAMENTO DA HIPERTENSÃO ARTERIAL: NOVAS TERAPIAS E ESTRATÉGIAS DE PREVENÇÃO Open
Introdução: A hipertensão arterial continua sendo um dos principais fatores de risco para doenças cardiovasculares, afetando milhões de pessoas em todo o mundo. Nas últimas décadas, houve avanços significativos no entendimento da fisiopato…
View article: NOVAS FRONTEIRAS NO TRATAMENTO DA DEPRESSÃO: TERAPIAS FARMACOLÓGICAS E NÃO FARMACOLÓGICAS
NOVAS FRONTEIRAS NO TRATAMENTO DA DEPRESSÃO: TERAPIAS FARMACOLÓGICAS E NÃO FARMACOLÓGICAS Open
Introdução: A depressão é uma das condições psiquiátricas mais prevalentes no mundo, afetando milhões de pessoas em todas as faixas etárias. Apesar dos avanços no entendimento da patogênese da depressão, o tratamento ainda representa um de…
View article: MANEJO CLÍNICO DA ASMA EM ADULTOS: TERAPIAS INOVADORAS E ABORDAGENS PERSONALIZADAS
MANEJO CLÍNICO DA ASMA EM ADULTOS: TERAPIAS INOVADORAS E ABORDAGENS PERSONALIZADAS Open
Introdução: A asma é uma condição inflamatória crônica das vias aéreas que afeta milhões de pessoas em todo o mundo, impactando significativamente a qualidade de vida dos pacientes. O entendimento da fisiopatologia da asma tem evoluído sub…
View article: IMPACTO PSICOLÓGICO DO LÚPUS ERITEMATOSO SISTÊMICO: ABORDAGENS CLÍNICAS NO MANEJO DE PACIENTES
IMPACTO PSICOLÓGICO DO LÚPUS ERITEMATOSO SISTÊMICO: ABORDAGENS CLÍNICAS NO MANEJO DE PACIENTES Open
Introdução: O Lúpus Eritematoso Sistêmico (LES) é uma doença autoimune crônica de natureza inflamatória, que pode acometer múltiplos órgãos e sistemas. Afetando predominantemente mulheres em idade fértil, o LES apresenta manifestações clín…
View article: MANEJO DA DOENÇA ARTERIAL PERIFÉRICA: ABORDAGENS TERAPÊUTICAS E INTERVENÇÕES CIRÚRGICAS
MANEJO DA DOENÇA ARTERIAL PERIFÉRICA: ABORDAGENS TERAPÊUTICAS E INTERVENÇÕES CIRÚRGICAS Open
Introdução: A Doença Arterial Periférica (DAP) é uma condição crônica e progressiva caracterizada pela obstrução parcial ou total das artérias periféricas, geralmente dos membros inferiores, devido ao acúmulo de placas ateroscleróticas. O …
View article: DESAFIOS NO DIAGNÓSTICO E TRATAMENTO DA DIABETES TIPO 1 EM CRIANÇAS: AVANÇOS E DESAFIOS CLÍNICOS
DESAFIOS NO DIAGNÓSTICO E TRATAMENTO DA DIABETES TIPO 1 EM CRIANÇAS: AVANÇOS E DESAFIOS CLÍNICOS Open
Introdução: A Diabetes Mellitus Tipo 1 (DM1) é uma condição autoimune crônica que geralmente se manifesta na infância ou adolescência. O diagnóstico precoce é essencial para reduzir complicações agudas e proporcionar uma melhor qualidade d…
View article: Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home
Remote Monitoring in Dementia Care - Lightweight, Explainable AI Validated for Early Warning of Health Events in the Home Open
Sensor-based remote health monitoring for people living with dementia (PLwD) enables early detection of adverse health events, reducing hospitalization risk. Identifying anomalies in real-world home activity data poses significant challeng…
View article: Toward a Human-Centered AI-assisted Colonoscopy System in Australia
Toward a Human-Centered AI-assisted Colonoscopy System in Australia Open
While AI-assisted colonoscopy promises improved colorectal cancer screening, its success relies on effective integration into clinical practice, not just algorithmic accuracy. This paper, based on an Australian field study (observations an…
View article: Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning Open
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification ta…
View article: Groundwater Quality in The Region That Hosted the Largest Open Dump in Latin America: Ten Years of Analysis
Groundwater Quality in The Region That Hosted the Largest Open Dump in Latin America: Ten Years of Analysis Open
Objective: The objective of this study is to investigate the quality of groundwater in the Estrutural Administrative Region, located in the Central region of the Federal District, Brazil, before and after the closure of the largest open-ai…
View article: AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning
AEON: Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise for Robust Learning Open
Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets often contain a mix of in-distribution (ID) and out-of-distrib…
View article: Leveraging labelled data knowledge: A cooperative rectification learning network for semi-supervised 3D medical image segmentation
Leveraging labelled data knowledge: A cooperative rectification learning network for semi-supervised 3D medical image segmentation Open
View article: Haemorrhagic Retroperitoneal Paraganglioma: A Report of a Rare Case
Haemorrhagic Retroperitoneal Paraganglioma: A Report of a Rare Case Open
Catecholamine-producing tumours are rare entities that, even though their clinical diagnostic might be a challenge due to the non-specificity of the symptoms, have had a growing incidence due to the continuous improvement of medical imagin…
View article: Treatment of Energy from Waste Plant fly-ash for blast furnace slag substitution as a Supplementary Cementitious Material
Treatment of Energy from Waste Plant fly-ash for blast furnace slag substitution as a Supplementary Cementitious Material Open
View article: Deep Learning for Photoacoustic Imaging of Reversibly Photoswitchable Chromophores: Training and Performance Testing Using Simulated Msot Images
Deep Learning for Photoacoustic Imaging of Reversibly Photoswitchable Chromophores: Training and Performance Testing Using Simulated Msot Images Open
View article: Fair Distillation: Teaching Fairness from Biased Teachers in Medical Imaging
Fair Distillation: Teaching Fairness from Biased Teachers in Medical Imaging Open
Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportionately affect demographic groups defined by sensitive attribu…
View article: Coverage-Constrained Human-AI Cooperation with Multiple Experts
Coverage-Constrained Human-AI Cooperation with Multiple Experts Open
Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabilities. Current HAI-…
View article: Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation
Cross- and Intra-image Prototypical Learning for Multi-label Disease Diagnosis and Interpretation Open
Recent advances in prototypical learning have shown remarkable potential to provide useful decision interpretations associating activation maps and predictions with class-specific training prototypes. Such prototypical learning has been we…
View article: ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels
ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels Open
An important stage of most state-of-the-art (SOTA) noisy-label learning methods consists of a sample selection procedure that classifies samples from the noisy-label training set into noisy-label or clean-label subsets. The process of samp…
View article: REVEALING HIDDEN PATTERNS: HOW UNSUPERVISED MACHINE LEARNING AND MCA PREDICT SURVIVAL IN NODAL PERIPHERAL T-CELL LYMPHOMA PATIENTS
REVEALING HIDDEN PATTERNS: HOW UNSUPERVISED MACHINE LEARNING AND MCA PREDICT SURVIVAL IN NODAL PERIPHERAL T-CELL LYMPHOMA PATIENTS Open
Unsupervised machine learning techniques are employed to understand patterns and behaviors of variables in databases. Multiple Correspondence Analysis (MCA), an extension of correspondence analysis, can be used to verify the association of…
View article: A Novel Perspective for Multi-modal Multi-label Skin Lesion Classification
A Novel Perspective for Multi-modal Multi-label Skin Lesion Classification Open
The efficacy of deep learning-based Computer-Aided Diagnosis (CAD) methods for skin diseases relies on analyzing multiple data modalities (i.e., clinical+dermoscopic images, and patient metadata) and addressing the challenges of multi-labe…
View article: Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis
Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis Open
Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs of the disease using either laparoscopic surgery or the ana…
View article: Exploring vision transformers for classifying early Barrett's dysplasia in endoscopic images: A pilot study on white‐light and narrow‐band imaging
Exploring vision transformers for classifying early Barrett's dysplasia in endoscopic images: A pilot study on white‐light and narrow‐band imaging Open
Background and Aim Various deep learning models, based on convolutional neural network (CNN), have been shown to improve the detection of early esophageal neoplasia in Barrett's esophagus. Vision transformer (ViT), derived from natural lan…
View article: Comparison of AI-integrated pathways with human-AI interaction in population mammographic screening for breast cancer
Comparison of AI-integrated pathways with human-AI interaction in population mammographic screening for breast cancer Open
Artificial intelligence (AI) readers of mammograms compare favourably to individual radiologists in detecting breast cancer. However, AI readers cannot perform at the level of multi-reader systems used by screening programs in countries su…