Coronary artery disease (CAD) remains a leading cause of morbidity and mortality worldwide, underscoring the need for accurate and reliable diagnostic tools. While AI-driven models have shown significant promise in identifying CAD through imaging techniques, their 'black box' nature often hinders clinical adoption due to a lack of interpretability. In response, this paper proposes a novel approach to image captioning specifically tailored for CAD diagnosis, aimed at enhancing the transparency and usability of AI systems. Utilizing the COCA dataset, which comprises gated coronary CT images along with Ground Truth (GT) segmentation annotations, we introduce a hybrid model architecture that combines a Vision Transformer (ViT) for feature extraction with a Generative Pretrained Transformer (GPT) for generating clinically relevant textual descriptions. This work builds on a previously developed 3D Convolutional Neural Network (CNN) for coronary artery segmentation, leveraging its accurate delineations of calcified regions as critical inputs to the captioning process. By incorporating these segmentation outputs, our approach not only focuses on accurately identifying and describing calcified regions within the coronary arteries but also ensures that the generated captions are clinically meaningful and reflective of key diagnostic features such as location, severity, and artery involvement. This methodology provides medical practitioners with clear, context-rich explanations of AI-generated findings, thereby bridging the gap between advanced AI technologies and practical clinical applications. Furthermore, our work underscores the critical role of Explainable AI (XAI) in fostering trust, improving decision-making, and enhancing the efficacy of AI-driven diagnostics, paving the way for future advancements in the field.

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.

The importance of X-Ray imaging analysis is paramount for health care 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.

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.

Backed by more powerful computational resources and optimized training routines, deep learning models have attained unprecedented performance in extracting information from chest X-ray data. Preceding other tasks, an automated abnormality detection stage can be useful to prioritize certain exams and enable a more efficient clinical workflow. However, the presence of image artifacts such as lettering often generates a harmful bias in the classifier, leading to an increase of false positive results. Consequently, health care would benefit from a system that selects the thoracic region of interest prior to deciding whether an image is possibly pathologic. The current work tack-les this binary classification exercise using an attention-driven and spatially unsupervised Spatial Transformer Network (STN). The results indicate that the STN achieves similar results to using YOLO-cropped images, with fewer computational expenses and without the need for localization labels. More specifically, the system is able to distinguish between normal and abnormal CheXpert Images with a mean AUC of 84.22%.

Chest radiography is one of the most ubiquitous imaging modalities, playing an essential role in screening, diagnosis and disease management. However, chest radiography interpretation is a time-consuming and complex task, requiring the availability of experienced radiologists. As such, automated diagnosis systems for pathology detection have been proposed aiming to reduce the burden on radiologists and reduce variability in image interpretation. While promising results have been obtained, particularly since the advent of deep learning, there are significant limitations in the developed solutions, namely the lack of representative data for less frequent pathologies and the learning of biases from the training data, such as patient position, medical devices and other markers as proxies for certain pathologies. The lack of explainability is also a challenge for the adoption of these solutions in clinical practice.Generative adversarial networks could play a significant role as a solution for these challenges as they allow to artificially create new realistic images. This way, new synthetic chest radiography images could be used to increase the prevalence of less represented pathology classes and decrease model biases as well as improving the explainability of automatic decisions by generating samples that serve as examples or counter-examples to the image being analysed, ensuring patient privacy.In this study, a few-shot generative adversarial network is used to generate synthetic chest radiography images. A minimum Fréchet Inception Distance score of 17.83 was obtained, allowing to generate convincing synthetic images. Perceptual validation was then performed by asking multiple readers to classify a mixed set of synthetic and real images. An average accuracy of 83.5% was obtained but a strong dependency on reader experience level was observed. While synthetic images showed structural irregularities, the overall image sharpness was a major factor in the decision of readers. The synthetic images were then validated using a MobileNet abnormality classifier and it was shown that over 99% of images were classified correctly, indicating that the generated images were correctly interpreted by the classifier. Finally, the use of the synthetic images during training of a YOLOv5 pathology detector showed that the addition of the synthetic images led to an improvement of mean average precision of 0.05 across 14 pathologies.In conclusion, the usage of few-shot generative adversarial networks for chest radiography image generation was shown and tested in multiple scenarios, establishing a baseline for future experiments to increase the applicability of generative models in clinical scenarios of automatic CXR screening and diagnosis tools.

Early diagnosis of lung cancer via computed tomography can significantly reduce the morbidity and mortality rates associated with the pathology. However, searching lung nodules is a high complexity task, which affects the success of screening programs. Whilst computer-aided detection systems can be used as second observers, they may bias radiologists and introduce significant time overheads. With this in mind, this study assesses the potential of using gaze information for integrating automatic detection systems in the clinical practice. For that purpose, 4 radiologists were asked to annotate 20 scans from a public dataset while being monitored by an eye tracker device, and an automatic lung nodule detection system was developed. Our results show that radiologists follow a similar search routine and tend to have lower fixation periods in regions where finding errors occur. The overall detection sensitivity of the specialists was 0.67±0.07, whereas the system achieved 0.69. Combining the annotations of one radiologist with the automatic system significantly improves the detection performance to similar levels of two annotators. Filtering automatic detection candidates only for low fixation regions still significantly improves the detection sensitivity without increasing the number of false-positives.

Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing 2D echocardiographic images, i.e., segmenting cardiac structures and estimating clinical indices, on a dataset, especially, designed to answer this objective. We, therefore, introduce the cardiac acquisitions for multi-structure ultrasound segmentation dataset, the largest publicly-available and fully-annotated dataset for the purpose of echocardiographic assessment. The dataset contains two and four-chamber acquisitions from 500 patients with reference measurements from one cardiologist on the full dataset and from three cardiologists on a fold of 50 patients. Results show that encoder-decoder-based architectures outperform state-of-the-art non-deep learning methods and faithfully reproduce the expert analysis for the end-diastolic and end-systolic left ventricular volumes, with a mean correlation of 0.95 and an absolute mean error of 9.5 ml. Concerning the ejection fraction of the left ventricle, results are more contrasted with a mean correlation coefficient of 0.80 and an absolute mean error of 5.6%. Although these results are below the inter-observer scores, they remain slightly worse than the intra-observer's ones. Based on this observation, areas for improvement are defined, which open the door for accurate and fully-automatic analysis of 2D echocardiographic images.

Cardiac volume/function assessment remains a critical step in daily cardiology, and 3-D ultrasound plays an increasingly important role. Fully automatic left ventricular segmentation is, however, a challenging task due to the artifacts and low contrast-to-noise ratio of ultrasound imaging. In this paper, a fast and fully automatic framework for the full-cycle endocardial left ventricle segmentation is proposed. This approach couples the advantages of the B-spline explicit active surfaces framework, a purely image information approach, to those of statistical shape models to give prior information about the expected shape for an accurate segmentation. The segmentation is propagated throughout the heart cycle using a localized anatomical affine optical flow. It is shown that this approach not only outperforms other state-of-the-art methods in terms of distance metrics with a mean average distances of 1.81±0.59 and 1.98±0.66 mm at end-diastole and end-systole, respectively, but is computationally efficient (in average 11 s per 4-D image) and fully automatic.