Abstract
Chest radiography is increasingly used worldwide to diagnose a series of illnesses targeting the lungs and heart. The high amount of examinations leads to a severe burden on radiologists, which benefit from the introduction of artificial intelligence tools in clinical practice, such as deep learning classification models. Nevertheless, these models are undergoing limited implementation due to the lack of trustworthy explanations that provide insights about their reasoning. In an attempt to increase the level of explainability, the deep learning approaches developed in this work incorporate in their decision process eye-tracking data collected from experts. More specifically, eye-tracking data is used in the form of heatmaps to change the input to the selected classifier, an EfficientNet-b0, and to guide its focus towards relevant parts of the images. Prior to the classification task, UNet-based models are used to perform heatmap reconstruction, making this framework independent of eye-tracking data during inference. The two proposed approaches are applied to all existing public eye-tracking datasets, to our knowledge, regarding chest X-ray screening, namely EGD, REFLACX and CXR-P. For these datasets, the reconstructed heatmaps highlight important anatomical/pathological regions and the area under the curve results are comparable to the state-of-the-art and to the considered baseline. Furthermore, the quality of the explanations derived from the classifier is superior for one of the approaches, which can be attributed to the use of eye-tracking data.

Abstract
Background and Objective: Convolutional neural networks are widely used to detect radiological findings in chest radiographs. Standard architectures are optimized for images of relatively small size (for exam-ple, 224 x 224 pixels), which suffices for most application domains. However, in medical imaging, larger inputs are often necessary to analyze disease patterns. A single scan can display multiple types of radi-ological findings varying greatly in size, and most models do not explicitly account for this. For a given network, whose layers have fixed-size receptive fields, smaller input images result in coarser features, which better characterize larger objects in an image. In contrast, larger inputs result in finer grained features, beneficial for the analysis of smaller objects. By compromising to a single resolution, existing frameworks fail to acknowledge that the ideal input size will not necessarily be the same for classifying every pathology of a scan. The goal of our work is to address this shortcoming by proposing a lightweight framework for multi-scale classification of chest radiographs, where finer and coarser features are com-bined in a parameter-efficient fashion. Methods: We experiment on CheXpert, a large chest X-ray database. A lightweight multi-resolution (224 x 224, 4 48 x 4 48 and 896 x 896 pixels) network is developed based on a Densenet-121 model where batch normalization layers are replaced with the proposed size-specific batch normalization. Each input size undergoes batch normalization with dedicated scale and shift parameters, while the remaining parameters are shared across sizes. Additional external validation of the proposed approach is performed on the VinDr-CXR data set. Results: The proposed approach (AUC 83 . 27 +/- 0 . 17 , 7.1M parameters) outperforms standard single-scale models (AUC 81 . 76 +/- 0 . 18 , 82 . 62 +/- 0 . 11 and 82 . 39 +/- 0 . 13 for input sizes 224 x 224, 4 48 x 4 48 and 896 x 896, respectively, 6.9M parameters). It also achieves a performance similar to an ensemble of one individual model per scale (AUC 83 . 27 +/- 0 . 11 , 20.9M parameters), while relying on significantly fewer parameters. The model leverages features of different granularities, resulting in a more accurate classifi-cation of all findings, regardless of their size, highlighting the advantages of this approach. Conclusions: Different chest X-ray findings are better classified at different scales. Our study shows that multi-scale features can be obtained with nearly no additional parameters, boosting performance. (c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )

Abstract
Purpose: The development of accurate methods for retinal layer and fluid segmentation in optical coherence tomography images can help the ophthalmologists in the diagnosis and follow-up of retinal diseases. Recent works based on joint segmentation presented good results for the segmentation of most retinal layers, but the fluid segmentation results are still not satisfactory. We report a hierarchical framework that starts by distinguishing the retinal zone from the background, then separates the fluid-filled regions from the rest, and finally, discriminates the several retinal layers.Approach: Three fully convolutional networks were trained sequentially. The weighting scheme used for computing the loss function during training is derived from the outputs of the networks trained previously. To reinforce the relative position between retinal layers, the mutex Dice loss (included for optimizing the last network) was further modified so that errors between more distant layers are more penalized. The method's performance was evaluated using a public dataset.Results: The proposed hierarchical approach outperforms previous works in the segmentation of the inner segment ellipsoid layer and fluid (Dice coefficient = 0.95 and 0.82, respectively). The results achieved for the remaining layers are at a state-of-the-art level.Conclusions: The proposed framework led to significant improvements in fluid segmentation, without compromising the results in the retinal layers. Thus, its output can be used by ophthalmologists as a second opinion or as input for automatic extraction of relevant quantitative biomarkers.

Abstract

Abstract
In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.