Bernardo Brás Gonçalves

Mr. Bernardo Brás Gonçalves

NOVA School of Science and Technology
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
17 January 2022 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
RVRui Varandas
Rui Varandas
BGBernardo Brás Gonçalves
Bernardo Brás Gonçalves
Hugo GamboaHugo Gamboa
Hugo Gamboa
PVPedro M. Vieira
Pedro M. Vieira
In clinical practice, every decision should be reliable and explained to the stakeholders. The high accuracy of deep learning (DL) models pose a great advantage, but the fact that they function as black-boxes hinders their clinical applications. Hence, explainability methods became important as they provide explanation to DL models. In this study, two datasets with electrocardiogram (ECG) image representations of six heartbeats were built, one given the label of the last heartbeat and the other given the label of the first heartbeat. Each dataset was used to train one neural network. Finally, we applied well-known explainability methods to the resulting networks to explain their classifications. Explainability methods produced attribution maps where pixels intensities are proportional to their importance to the classification task. Then, we developed a metric to quantify the focus of the models in the heartbeat of interest. The classification models achieved testing accuracy scores of around 93.66% and 91.72%. The models focused around the heartbeat of interest, with values of the focus metric ranging between 8.8% and 32.4%. Future work will investigate the importance of regions outside the region of interest, besides the contribution of specific ECG waves to the classification.

7 June 2024 in BioMedInformatics
Verified
Journal Article
Open access
PDF file
BGBernardo Brás Gonçalves
Bernardo Brás Gonçalves
MSMariana Silva
Mariana Silva
AVAna Luísa Vieira
Ana Luísa Vieira
PVPedro M. Vieira
Pedro M. Vieira
Current computer vision models require a significant amount of annotated data to improve their performance in a particular task. However, obtaining the required annotated data is challenging, especially in medicine. Hence, data augmentation techniques play a crucial role. In recent years, generative models have been used to create artificial medical images, which have shown promising results. This study aimed to use a state-of-the-art generative model, StyleGAN3, to generate realistic synthetic abdominal magnetic resonance images. These images will be evaluated using quantitative metrics and qualitative assessments by medical professionals. For this purpose, an abdominal MRI dataset acquired at Garcia da Horta Hospital in Almada, Portugal, was used. A subset containing only axial gadolinium-enhanced slices was used to train the model. The obtained Fréchet inception distance value (12.89) aligned with the state of the art, and a medical expert confirmed the significant realism and quality of the images. However, specific issues were identified in the generated images, such as texture variations, visual artefacts and anatomical inconsistencies. Despite these, this work demonstrated that StyleGAN3 is a viable solution to synthesise realistic medical imaging data, particularly in abdominal imaging.

7 July 2021 in Research Square
Verified
Preprint
Open access
PDF file
RVRui Varandas
Rui Varandas
BGBernardo Brás Gonçalves
Bernardo Brás Gonçalves
HGHugo Gamboa
Hugo Gamboa
PVPedro Vieira
Pedro Vieira
Background: Deep Learning (DL) models are able to produce accurate results in various areas. However, the medical field is specially sensitive, because every decision should be reliable and explained to the stakeholders. Thus, the high accuracy of DL models pose a great advantage, but the fact that they function as a black-box hinders their application to sensitive fields, given that they are not explainable per se. Hence, the application of explainability methods became important to provide explaination DL models in various problems. In this work, we trained different classifiers and generated explanation of their classification of electrocardiograms (ECG) by applying well-known methods. Finally, we extract quantifiable information to evaluate the explanation of our classifiers. Methods: In this study two datasets were built consisting of image representation of ECG that were labelled given one specific heartbeat: 1. labelled given the last heartbeat and 2. labelled given the first heartbeat. DL models were trained with each dataset. Three different explainability methods were applied to the DL models to explain their classification. These methods produce attribution maps in which the intensity of the pixels are proportional to their importance to the classification task. Thus, we developed a metric to quantify the focus of the models in the region of interest (ROI) of the ECG representation. Results: The developed classification models achieved accuracy scores of around 93.66% and 91.72% in the testing set. The explainability methods were successfully applied to these models. The quantification metric developed in this work demonstrated that, in most cases, the models did have a focus around the heartbeat of interest. The results ranged from around 8.8% in the worst case, until 32.4%, where the random focus would mean a value of approximately 10%. Conclusions: The classification models performed accurately in the two datasets, however, even though their focus is higher in the ROI of the figures compared with the random case, the results allow the interpretation that other regions of the figures might also be important for classification. In the future, it should be investigated the importance of regions outside the ROI and also if specific waves of the ECG signal contribute to the classification.

8 April 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
BGBernardo Brás Gonçalves
Bernardo Brás Gonçalves
GSGoncalo Saldanha
Goncalo Saldanha
MRMiguel Ramalho
Miguel Ramalho
AVAna Luísa Vieira
Ana Luísa Vieira
PVPedro M. Vieira
Pedro M. Vieira
Adrenal lesions are common findings in abdominal imaging, with adrenal adenomas being the most frequent type. Accurate detection of adrenal adenomas is essential to avoid unnecessary diagnostic procedures and treatments. However, conventional imaging-based evaluation relies heavily on the expertise of radiologists and can be complicated by pseudo-lesions, overlapping imaging features, and suboptimal imaging techniques. To address these challenges, we propose an end-to-end machine learning pipeline that integrates deep learning-based lesion detection (FCOS) with an ensemble classifier for adrenal lesion classification in MRI. Our pipeline operates directly on broader regions of interest, eliminating the need for manual lesion segmentation. Our method was evaluated on a multi-sequence MRI dataset comprising 206 adenomas and 45 non-adenomas. The pipeline achieved 87.45% accuracy, 87.33% specificity, and 87.63% recall for adenoma classification, demonstrating competitive performance compared to prior studies. The results highlight strong non-adenoma identification while maintaining robust adenoma detection. Future research should focus on dataset expansion, external validation, and comparison with radiologist performance to further validate clinical applicability.