Abstract
When designing clinical trials for testing novel cardiovascular therapies, it is highly relevant to understand what a given technology can provide in terms of information on the physiologic status of the heart and vessels. Ultrasound imaging has traditionally been the modality of choice to study the cardiovascular system as it has an excellent temporal resolution; it operates in real-time; it is very widespread and - not unimportant - it is cheap. Although this modality is mostly known clinically as a two-dimensional technology, it has recently matured into a true three-dimensional imaging technique. In this review paper, an overview is given of the available ultrasound technology for cardiac chamber quantification in terms of volume and function and evidence is given why these parameters are of value when testing the effect of new cardiovascular therapies.

Abstract
Chest radiography is one of the most ubiquitous medical imaging modalities. Nevertheless, the interpretation of chest radiography images is time-consuming, complex and subject to observer variability. As such, automated diagnosis systems for pathology detection have been proposed, aiming to reduce the burden on radiologists. The advent of deep learning has fostered the development of solutions for both abnormality detection with promising results. However, these tools suffer from poor explainability as the reasons that led to a decision cannot be easily understood, representing a major hurdle for their adoption in clinical practice. In order to overcome this issue, a method for chest radiography abnormality detection is presented which relies on an object detection framework to detect individual findings and thus separate normal and abnormal CXRs. It is shown that this framework is capable of an excellent performance in abnormality detection (AUC: 0.993), outperforming other state-of-the-art classification methodologies (AUC: 0.976 using the same classes). Furthermore, validation on external datasets shows that the proposed framework has a smaller drop in performance when applied to previously unseen data (21.9% vs 23.4% on average). Several approaches for object detection are compared and it is shown that merging pathology classes to minimize radiologist variability improves the localization of abnormal regions (0.529 vs 0.491 APF when using all pathology classes), resulting in a network which is more explainable and thus more suitable for integration in clinical practice.

Abstract
Two-dimensional echocardiography is the most widely used non-invasive imaging modality due to its fast acquisition time, low cost, and high temporal resolution. Accurate segmentation of the left ventricle in echocardiography is vital for ensuring the accuracy of subsequent diagnosis. Currently, numerous efforts have been made to automatize this task and various public datasets have been released in recent decades to further develop present research. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors, such as operation policies, machine protocols, treatment preference, etc. As a result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using two publicly available echocardiographic datasets. This work validates the efficacy of a supervised deep learning model for left ventricle segmentation and ejection fraction prediction, outside the dataset on which it was trained. The exposure of this model to unseen, but related samples without additional training maintained a good performance. However, a performance decrease from the original results can be observed, while the impact of quality is also noteworthy with lower quality data leading to decreased performance.

Abstract
Chest radiography is one of the most common imaging exams, but its interpretation is often challenging and timeconsuming, which has motivated the development of automated tools for pathology/abnormality detection. Deep learning models trained on large-scale chest X-ray datasets have shown promising results but are highly dependent on the quality of the data. However, these datasets often contain incorrect metadata and non-compliant or corrupted images. These inconsistencies are ultimately incorporated in the training process, impairing the validity of the results. In this study, a novel approach to detect non-compliant images based on deep features extracted from a patient position classification model and a pre-trained VGG16 model are proposed. This method is applied to CheXpert, a widely used public dataset. From a pool of 100 images, it is shown that the deep feature-based methods based on a patient position classification model are able to retrieve a larger number of non-compliant images (up to 81% of non-compliant images), when compared to the same methods but based on a pretrained VGG16 (up to 73%) and the state of the art uncertainty-based method (50%).

Abstract
The importance of X-Ray imaging analysis is paramount for healthcare institutions since it is the main imaging modality for patient diagnosis, and deep learning can be used to aid clinicians in image diagnosis or structure segmentation. In recent years, several articles demonstrate the capability that deep learning models have in classifying and segmenting chest x-ray images if trained in an annotated dataset. Unfortunately, for segmentation tasks, only a few relatively small datasets have annotations, which poses a problem for the training of robust deep learning strategies. In this work, a semi-supervised approach is developed which consists of using available information regarding other anatomical structures to guide the segmentation when the groundtruth segmentation for a given structure is not available. This semi-supervised is compared with a fully-supervised approach for the tasks of lung segmentation and for multi-structure segmentation (lungs, heart and clavicles) in chest x-ray images. The semi-supervised lung predictions are evaluated visually and show relevant improvements, therefore this approach could be used to improve performance in external datasets with missing groundtruth. The multi-structure predictions show an improvement in mean absolute and Hausdorff distances when compared to a fully supervised approach and visual analysis of the segmentations shows that false positive predictions are removed. In conclusion, the developed method results in a new strategy that can help solve the problem of missing annotations and increase the quality of predictions in new datasets.

Abstract