Danilo Silva

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.

Matteus Vargas Simão da Silva, Rodrigo Reis Arrais, Jhessica Victoria Santos da Silva et al.

Over the last few years, the number of works about deep learning applied to the medical field has increased enormously. The necessity of a rigorous assessment of these models is required to explain these results to all people involved in medical exams. A recent field in the machine learning area is explainable artificial intelligence, also known as XAI, which targets to explain the results of such black box models to permit the desired assessment. This survey analyses several recent studies in the XAI field applied to medical diagnosis research, allowing some explainability of the machine learning results in several different diseases, such as cancers and COVID-19.

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.