Abstract
Chest X-ray scans are frequently requested to detect the presence of abnormalities, due to their low-cost and non-invasive nature. The interpretation of these images can be automated to prioritize more urgent exams through deep learning models, but the presence of image artifacts, e.g. lettering, often generates a harmful bias in the classifiers and an increase of false positive results. Consequently, healthcare would benefit from a system that selects the thoracic region of interest prior to deciding whether an image is possibly pathologic. The current work tackles this binary classification exercise, in which an image is either normal or abnormal, using an attention-driven and spatially unsupervised Spatial Transformer Network (STERN), that takes advantage of a novel domain-specific loss to better frame the region of interest. Unlike the state of the art, in which this type of networks is usually employed for image alignment, this work proposes a spatial transformer module that is used specifically for attention, as an alternative to the standard object detection models that typically precede the classifier to crop out the region of interest. In sum, the proposed end-to-end architecture dynamically scales and aligns the input images to maximize the classifier's performance, by selecting the thorax with translation and non-isotropic scaling transformations, and thus eliminating artifacts. Additionally, this paper provides an extensive and objective analysis of the selected regions of interest, by proposing a set of mathematical evaluation metrics. The results indicate that the STERN achieves similar results to using YOLO-cropped images, with reduced computational cost and without the need for localization labels. More specifically, the system is able to distinguish abnormal frontal images from the CheXpert dataset, with a mean AUC of 85.67% -a 2.55% improvement vs. the 0.98% improvement achieved by the YOLO-based counterpart in comparison to a standard baseline classifier. At the same time, the STERN approach requires less than 2/3 of the training parameters, while increasing the inference time per batch in less than 2 ms. Code available via GitHub.

Abstract
Chest radiography has been widely used for automatic analysis through deep learning (DL) techniques. However, in the manual analysis of these scans, comparison with images at previous time points is commonly done, in order to establish a longitudinal reference. The usage of longitudinal information in automatic analysis is not a common practice, but it might provide relevant information for desired output. In this work, the application of longitudinal information for the detection of cardiomegaly and change in pairs of CXR images was studied. Multiple experiments were performed, where the inclusion of longitudinal information was done at the features level and at the input level. The impact of the alignment of the image pairs (through a developed method) was also studied. The usage of aligned images was revealed to improve the final mcs for both the detection of pathology and change, in comparison to a standard multi-label classifier baseline. The model that uses concatenated image features outperformed the remaining, with an Area Under the Receiver Operating Characteristics Curve (AUC) of 0.858 for change detection, and presenting an AUC of 0.897 for the detection of pathology, showing that pathology features can be used to predict more efficiently the comparison between images. In order to further improve the developed methods, data augmentation techniques were studied. These proved that increasing the representation of minority classes leads to higher noise in the dataset. It also showed that neglecting the temporal order of the images can be an advantageous augmentation technique in longitudinal change studies.

Abstract
Although the classification of chest radiographs has long been an extensively researched topic, interest increased significantly with the onset of the COVID-19 pandemic. Existing results are promising; however, the radiological similarities between COVID-19 and other types of respiratory diseases limit the success of conventional image classification approaches that focus on single instances. This study proposes a novel perspective that conceptualizes COVID-19 pneumonia as a deviation from a normative distribution of typical pneumonia patterns. Using a population- based approach, our approach utilizes distributional anomaly detection. This method diverges from traditional instance-wise approaches by focusing on sets of scans instead of individual images. Using an autoencoder to extract feature representations, we present instance-based and distribution-based assessments of the separability between COVID-positive and COVIDnegative pneumonia radiographs. The results demonstrate that the proposed distribution-based methodology outperforms conventional instance-based techniques in identifying radiographic changes associated with COVID-positive cases. This underscores its potential as an early warning system capable of detecting significant distributional shifts in radiographic data. By continuously monitoring these changes, this approach offers a mechanism for early identification of emerging health trends, potentially signaling the onset of new pandemics and enabling prompt public health responses.

Abstract
Large-scale datasets are essential for training deep learning models in medical imaging. However, many of these datasets contain poor-quality images that can compromise model performance and clinical reliability. In this study, we propose a framework to detect non-compliant images, such as corrupted scans, incomplete thorax X-rays, and images of non-thoracic body parts, by leveraging contrastive learning for feature extraction and parametric or non-parametric scoring methods for out-of-distribution ranking. Our approach was developed and tested on the CheXpert dataset, achieving an AUC of 0.75 in a manually labeled subset of 1,000 images, and further qualitatively and visually validated on the external PadChest dataset, where it also performed effectively. Our results demonstrate the potential of contrastive learning to detect non-compliant images in large-scale medical datasets, laying the foundation for future work on reducing dataset pollution and improving the robustness of deep learning models in clinical practice. © 2024 IEEE.

Abstract
Chest X-Ray (CXR), plays a vital role in diagnosing lung and heart conditions, but the high demand for CXR examinations poses challenges for radiologists. Automatic support systems can ease this burden by assisting radiologists in the image analysis process. While Deep Learning models have shown promise in this task, concerns persist regarding their complexity and decision-making opacity. To address this, various visual explanation techniques have been developed to elucidate the model reasoning, some of which have received significant attention in literature and are widely used such as GradCAM. However, it is unclear how different explanations methods perform and how to quantitatively measure their performance, as well as how that performance may be dependent on the model architecture used and the dataset characteristics. In this work, two widely used deep classification networks - DenseNet121 and ResNet50 - are trained for multi-pathology classification on CXR and visual explanations are then generated using GradCAM, GradCAM++, EigenGrad-CAM, Saliency maps, LRP and DeepLift. These explanations methods are then compared with radiologist annotations using previously proposed explainability evaluations metrics - intersection over union and hit rate. Furthermore, a novel method to convey visual explanations in the form of radiological written reports is proposed, allowing for a clinically-oriented explainability evaluation metric - zones score. It is shown that Grad-CAM++ and Saliency methods offer the most accurate explanations and that the effectiveness of visual explanations is found to vary based on the model and corresponding input size. Additionally, the explainability performance across different CXR datasets is evaluated, highlighting that the explanation quality depends on the dataset's characteristics and annotations.