Danilo Silva

Danilo Silva, Monika Moir, Cheryl Baxter et al.

Data management can be a complex challenge in fields such as bioinformatics and health sciences, which continuously generate extensive heterogeneous datasets. In the context of collaborative global health initiatives, secure storage and sharing of data are crucial to support impactful research. However, the absence of a unified data management platform complicates efficient data exchange and governance within these initiatives. In this paper, we introduce the design process of OpenHealth Lake, a data management prototype platform based on a data lakehouse architecture, data federation, and the FAIR principles. The platform is designed using open-source tools, guided by system requirements identified in previously published studies and complemented by insights from the existing literature. The current prototype platform comprises a user-friendly website, an open API, Python and R packages, allowing users to interact with the platform in multiple ways. Through a user study that included participants with varying technical backgrounds, we showed that our proposed data management prototype is both usable and useful. Our prototype design showcases the adaptability, scalability, and reproducibility of a lakehouse system that can be used by any organisation. It is designed as a flexible and complementary approach that allows organisations to customise data management systems to their specific requirements and resources, including cloud-based or self-hosted storage choices.

Bruno Machado Pacheco, Guilherme de Souza e Cassia, Danilo Silva

State-of-the-art brain tumor segmentation is based on deep learning models applied to multi-modal MRIs. Currently, these models are trained on images after a preprocessing stage that involves registration, interpolation, brain extraction (BE, also known as skull-stripping) and manual correction by an expert. However, for clinical practice, this last step is tedious and time-consuming and, therefore, not always feasible, resulting in skull-stripping faults that can negatively impact the tumor segmentation quality. Still, the extent of this impact has never been measured for any of the many different BE methods available. In this work, we propose an automatic brain tumor segmentation pipeline and evaluate its performance with multiple BE methods. Our experiments show that the choice of a BE method can compromise up to 15.7% of the tumor segmentation performance. Moreover, we propose training and testing tumor segmentation models on non-skull-stripped images, effectively discarding the BE step from the pipeline. Our results show that this approach leads to a competitive performance at a fraction of the time. We conclude that, in contrast to the current paradigm, training tumor segmentation models on non-skull-stripped images can be the best option when high performance in clinical practice is desired.

Luís Felipe P. Cattelan, Danilo Silva

This paper addresses the problem of selective classification for deep neural networks, where a model is allowed to abstain from low-confidence predictions to avoid potential errors. We focus on so-called post-hoc methods, which replace the confidence estimator of a given classifier without modifying or retraining it, thus being practically appealing. Considering neural networks with softmax outputs, our goal is to identify the best confidence estimator that can be computed directly from the unnormalized logits. This problem is motivated by the intriguing observation in recent work that many classifiers appear to have a "broken" confidence estimator, in the sense that their selective classification performance is much worse than what could be expected by their corresponding accuracies. We perform an extensive experimental study of many existing and proposed confidence estimators applied to 84 pretrained ImageNet classifiers available from popular repositories. Our results show that a simple $p$-norm normalization of the logits, followed by taking the maximum logit as the confidence estimator, can lead to considerable gains in selective classification performance, completely fixing the pathological behavior observed in many classifiers. As a consequence, the selective classification performance of any classifier becomes almost entirely determined by its corresponding accuracy. Moreover, these results are shown to be consistent under distribution shift. Our code is available at https://github.com/lfpc/FixSelectiveClassification.

Bruno Machado Pacheco, Victor Hugo Rocha de Oliveira, Augusto Braga Fernandes Antunes et al.

Brain age prediction using neuroimaging data has shown great potential as an indicator of overall brain health and successful aging, as well as a disease biomarker. Deep learning models have been established as reliable and efficient brain age estimators, being trained to predict the chronological age of healthy subjects. In this paper, we investigate the impact of a pre-training step on deep learning models for brain age prediction. More precisely, instead of the common approach of pre-training on natural imaging classification, we propose pre-training the models on brain-related tasks, which led to state-of-the-art results in our experiments on ADNI data. Furthermore, we validate the resulting brain age biomarker on images of patients with mild cognitive impairment and Alzheimer's disease. Interestingly, our results indicate that better-performing deep learning models in terms of brain age prediction on healthy patients do not result in more reliable biomarkers.

João Gabriel Vinholi, Marco Chini, Anis Amziane et al.

Comparing images captured by disparate sensors is a common challenge in remote sensing. This requires image translation -- converting imagery from one sensor domain to another while preserving the original content. Denoising Diffusion Implicit Models (DDIM) are potential state-of-the-art solutions for such domain translation due to their proven superiority in multiple image-to-image translation tasks in computer vision. However, these models struggle with reproducing radiometric features of large-scale multi-patch imagery, resulting in inconsistencies across the full image. This renders downstream tasks like Heterogeneous Change Detection impractical. To overcome these limitations, we propose a method that leverages denoising diffusion for effective multi-sensor optical image translation over large areas. Our approach super-resolves large-scale low spatial resolution images into high-resolution equivalents from disparate optical sensors, ensuring uniformity across hundreds of patches. Our contributions lie in new forward and reverse diffusion processes that address the challenges of large-scale image translation. Extensive experiments using paired Sentinel-II (10m) and Planet Dove (3m) images demonstrate that our approach provides precise domain adaptation, preserving image content while improving radiometric accuracy and feature representation. A thorough image quality assessment and comparisons with the standard DDIM framework and five other leading methods are presented. We reach a mean Learned Perceptual Image Patch Similarity (mLPIPS) of 0.1884 and a Fréchet Inception Distance (FID) of 45.64, expressively outperforming all compared methods, including DDIM, ShuffleMixer, and SwinIR. The usefulness of our approach is further demonstrated in two Heterogeneous Change Detection tasks.

Henrique Pickler, Jorge K. S. Kamassury, Danilo Silva

Label noise is a common problem in real-world datasets, affecting both model training and validation. Clean data are essential for achieving strong performance and ensuring reliable evaluation. While various techniques have been proposed to detect noisy labels, there is no clear consensus on optimal approaches. We perform a comprehensive benchmark of detection methods by decomposing them into three fundamental components: label agreement function, aggregation method, and information gathering approach (in-sample vs out-of-sample). This decomposition can be applied to many existing detection methods, and enables systematic comparison across diverse approaches. To fairly compare methods, we propose a unified benchmark task, detecting a fraction of training samples equal to the dataset's noise rate. We also introduce a novel metric: the false negative rate at this fixed operating point. Our evaluation spans vision and tabular datasets under both synthetic and real-world noise conditions. We identify that in-sample information gathering using average probability aggregation combined with the logit margin as the label agreement function achieves the best results across most scenarios. Our findings provide practical guidance for designing new detection methods and selecting techniques for specific applications.

João Paulo Vieira, Victor Afonso Bauler, Rodrigo Kobashikawa Rosa et al.

Reliable detection of bearing faults is essential for maintaining the safety and operational efficiency of rotating machinery. While recent advances in machine learning (ML), particularly deep learning, have shown strong performance in controlled settings, many studies fail to generalize to real-world applications due to methodological flaws, most notably data leakage. This paper investigates the issue of data leakage in vibration-based bearing fault diagnosis and its impact on model evaluation. We demonstrate that common dataset partitioning strategies, such as segment-wise and condition-wise splits, introduce spurious correlations that inflate performance metrics. To address this, we propose a rigorous, leakage-free evaluation methodology centered on bearing-wise data partitioning, ensuring no overlap between the physical components used for training and testing. Additionally, we reformulate the classification task as a multi-label problem, enabling the detection of co-occurring fault types and the use of prevalence-independent metrics such as Macro AUROC. Beyond preventing leakage, we also examine the effect of dataset diversity on generalization, showing that the number of unique training bearings is a decisive factor for achieving robust performance. We evaluate our methodology on three widely adopted datasets: CWRU, Paderborn University (PU), and University of Ottawa (UORED-VAFCLS). This study highlights the importance of leakage-aware evaluation protocols and provides practical guidelines for dataset partitioning, model selection, and validation, fostering the development of more trustworthy ML systems for industrial fault diagnosis applications.

Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva

In semantic segmentation, even state-of-the-art deep learning models fall short of the performance required in certain high-stakes applications such as medical image analysis. In these cases, performance can be improved by allowing a model to abstain from making predictions when confidence is low, an approach known as selective prediction. While well-known in the classification literature, selective prediction has been underexplored in the context of semantic segmentation. This paper tackles the problem by focusing on image-level abstention, which involves producing a single confidence estimate for the entire image, in contrast to previous approaches that focus on pixel-level uncertainty. Assuming the Dice coefficient as the evaluation metric for segmentation, two main contributions are provided in this paper: (i) In the case of known marginal posterior probabilities, we derive the optimal confidence estimator, which is observed to be intractable for typical image sizes. Then, an approximation computable in linear time, named Soft Dice Confidence (SDC), is proposed and proven to be tightly bounded to the optimal estimator. (ii) When only an estimate of the marginal posterior probabilities are known, we propose a plug-in version of the SDC and show it outperforms all previous methods, including those requiring additional tuning data. These findings are supported by experimental results on both synthetic data and real-world data from six medical imaging tasks, including out-of-distribution scenarios, positioning the SDC as a reliable and efficient tool for selective prediction in semantic segmentation.

Henrique P. Silva, Arthur D. Reys, Daniel S. Severo et al.

Pressure ulcers have high prevalence in ICU patients but are preventable if identified in initial stages. In practice, the Braden scale is used to classify high-risk patients. This paper investigates the use of machine learning in electronic health records data for this task, by using data available in MIMIC-III v1.4. Two main contributions are made: a new approach for evaluating models that considers all predictions made during a stay, and a new training method for the machine learning models. The results show a superior performance in comparison to the state of the art; moreover, all models surpass the Braden scale in every operating point in the precision-recall curve. -- -- Lesões por pressão possuem alta prevalência em pacientes de UTI e são preveníveis ao serem identificadas em estágios iniciais. Na prática utiliza-se a escala de Braden para classificação de pacientes em risco. Este artigo investiga o uso de aprendizado de máquina em dados de registros eletrônicos para este fim, a partir da base de dados MIMIC-III v1.4. São feitas duas contribuições principais: uma nova abordagem para a avaliação dos modelos e da escala de Braden levando em conta todas as predições feitas ao longo das internações, e um novo método de treinamento para os modelos de aprendizado de máquina. Os resultados obtidos superam o estado da arte e verifica-se que os modelos superam significativamente a escala de Braden em todos os pontos de operação da curva de precisão por sensibilidade.

Victor H. R. Oliveira, Augusto Antunes, Alexandre S. Soares et al.

In this work, deep learning techniques for brain age prediction from magnetic resonance images are investigated, aiming to assist in the identification of biomarkers of the natural aging process. The identification of biomarkers is useful for detecting an early-stage neurodegenerative process, as well as for predicting age-related or non-age-related cognitive decline. Two techniques are implemented and compared in this work: a 3D Convolutional Neural Network applied to the volumetric image and a 2D Convolutional Neural Network applied to slices from the axial plane, with subsequent fusion of individual predictions. The best result was obtained by the 2D model, which achieved a mean absolute error of 3.83 years. -- Neste trabalho são investigadas técnicas de aprendizado profundo para a predição da idade cerebral a partir de imagens de ressonância magnética, visando auxiliar na identificação de biomarcadores do processo natural de envelhecimento. A identificação de biomarcadores é útil para a detecção de um processo neurodegenerativo em estágio inicial, além de possibilitar prever um declínio cognitivo relacionado ou não à idade. Duas técnicas são implementadas e comparadas neste trabalho: uma Rede Neural Convolucional 3D aplicada na imagem volumétrica e uma Rede Neural Convolucional 2D aplicada a fatias do plano axial, com posterior fusão das predições individuais. O melhor resultado foi obtido pelo modelo 2D, que alcançou um erro médio absoluto de 3.83 anos.

Arthur D. Reys, Danilo Silva, Daniel Severo et al.

ICD coding from electronic clinical records is a manual, time-consuming and expensive process. Code assignment is, however, an important task for billing purposes and database organization. While many works have studied the problem of automated ICD coding from free text using machine learning techniques, most use records in the English language, especially from the MIMIC-III public dataset. This work presents results for a dataset with Brazilian Portuguese clinical notes. We develop and optimize a Logistic Regression model, a Convolutional Neural Network (CNN), a Gated Recurrent Unit Neural Network and a CNN with Attention (CNN-Att) for prediction of diagnosis ICD codes. We also report our results for the MIMIC-III dataset, which outperform previous work among models of the same families, as well as the state of the art. Compared to MIMIC-III, the Brazilian Portuguese dataset contains far fewer words per document, when only discharge summaries are used. We experiment concatenating additional documents available in this dataset, achieving a great boost in performance. The CNN-Att model achieves the best results on both datasets, with micro-averaged F1 score of 0.537 on MIMIC-III and 0.485 on our dataset with additional documents.

Danilo Silva, Marco Tulio Valente

Refactoring is a well-known technique that is widely adopted by software engineers to improve the design and enable the evolution of a system. Knowing which refactoring operations were applied in a code change is a valuable information to understand software evolution, adapt software components, merge code changes, and other applications. In this paper, we present RefDiff, an automated approach that identifies refactorings performed between two code revisions in a git repository. RefDiff employs a combination of heuristics based on static analysis and code similarity to detect 13 well-known refactoring types. In an evaluation using an oracle of 448 known refactoring operations, distributed across seven Java projects, our approach achieved precision of 100% and recall of 88%. Moreover, our evaluation suggests that RefDiff has superior precision and recall than existing state-of-the-art approaches.

Danilo Silva, Nikolaos Tsantalis, Marco Tulio Valente

Refactoring is a widespread practice that helps developers to improve the maintainability and readability of their code. However, there is a limited number of studies empirically investigating the actual motivations behind specific refactoring operations applied by developers. To fill this gap, we monitored Java projects hosted on GitHub to detect recently applied refactorings, and asked the developers to ex- plain the reasons behind their decision to refactor the code. By applying thematic analysis on the collected responses, we compiled a catalogue of 44 distinct motivations for 12 well-known refactoring types. We found that refactoring activity is mainly driven by changes in the requirements and much less by code smells. Extract Method is the most versatile refactoring operation serving 11 different purposes. Finally, we found evidence that the IDE used by the developers affects the adoption of automated refactoring tools.

Danilo Silva, Ricardo Terra, Marco Tulio Valente

Although Extract Method is a key refactoring for improving program comprehension, refactoring tools for such purpose are often underused. To address this shortcoming, we present JExtract, a recommendation system based on structural similarity that identifies Extract Method refactoring opportunities that are directly automated by IDE-based refactoring tools. Our evaluation suggests that JExtract is far more effective (w.r.t. recall and precision) to identify misplaced code in methods than JDeodorant, a state-of-the-art tool