Pedro Fagundes

Mr. Pedro Fagundes


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2026 in Cancers
Verified
Journal Article
Open access
PDF file
FMFERNANDO MALHEIROS
FERNANDO MALHEIROS
ESEvelyn Rocha Silva
Evelyn Rocha Silva
PFPedro Fagundes
Pedro Fagundes
JFJose Jeronimo Rabelo Faria
Jose Jeronimo Rabelo Faria
RLRaquel Descie Veraldi Leite
Raquel Descie Veraldi Leite
VVVinicius vazquez
Vinicius vazquez
Background: Infrared thermography has emerged as a non-invasive imaging modality capable of capturing physiological alterations associated with skin cancer; however, its diagnostic utility remains insufficiently characterized. This study aimed to compare the diagnostic performance of active (cooling-induced) and passive infrared thermography in distinguishing benign from malignant skin lesions. Methods: In this clinical study conducted at Barretos Cancer Hospital, 64 individuals contributed 100 skin lesions, of which 68 (56 malignant, 12 benign) met criteria for diagnostic accuracy analysis. Long-wave infrared images were acquired under steady-state conditions (passive thermography) and after standardized cooling (active thermography). Diagnostic performance was assessed using thermal contrast patterns and temperature differentials (ΔT), with histopathology as the reference standard. Results: Active thermography markedly outperformed passive imaging. Active thermography achieved a sensitivity of 91.1% and specificity of 75.0%, whereas passive thermography demonstrated low sensitivity (17.9%) despite perfect specificity (100%). Malignant lesions displayed substantially higher ΔT values, particularly during active thermal recovery. ROC analysis confirmed the superiority of the active technique (AUC = 0.871) over passive imaging (AUC = 0.650), with an optimal ΔT cutoff of 0.70 °C yielding high discriminative accuracy. Conclusions: Active infrared thermography enhances thermal contrast and provides significantly improved diagnostic sensitivity compared with passive imaging. As a low-cost, non-invasive technique, active thermography shows promise as a complementary tool for skin cancer triage, particularly in settings with limited access to dermatologic evaluation.

17 January 2025 in Journal of the Brazilian Computer Society
Verified
Journal Article
Open access
PDF file
PFPedro Fagundes
Pedro Fagundes
PSPaulo Vitor Costa Silva
Paulo Vitor Costa Silva
JGJanina de Sales Guilarducci
Janina de Sales Guilarducci
LPLaura Cristina Jardim Porto Pimenta
Laura Cristina Jardim Porto Pimenta
LMLuis David Solis Murgas
Luis David Solis Murgas
FMFERNANDO MALHEIROS
FERNANDO MALHEIROS
In recent years, the term Artificial Intelligence (AI) has gained recognition across various fields, such as healthcare, finance, agriculture, and many other sectors due to its versatility and capacity to improve outcome. Within the applications of AI, classification stands out as one of the most prevalent, aiding in optimizing decision-making and efficiently organizing data. In recent years, there has been an increase in the use of zebrafish (Danio rerio) in studies related to human dermatological diseases, such as vitiligo, which involves the autoimmune-mediated destruction of the melanocytes in the epidermal layer. Despite the current interest in studies related to this disease, no papers were found applying Machine Learning (ML) or Deep Learning (DL) models to classify the effects of the disease and its treatments. In this context, this paper uses the challenge of evaluating the effects of vitiligo in zebrafish to compare the performance of different AI approaches. The methodology employed in this paper includes image acquisition, dataset creation, preprocessing, model testing, and evaluation. The ML models applied in this study were Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost), while the DL models included Visual Geometry Group 16 (VGG16) and GoogLeNet. Following the evaluation, SVM and GoogLeNet achieved the best results, correctly classifying 80% and 71% of the data, respectively. Moreover, the former accurately identified all samples in the healthy and treated classes, with misclassifications occurring only within the sick class. The models performed satisfactorily in relation to the objectives of this study and the results exhibited potential for future applications in treating vitiligo in humans.