Abstract
Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model's attention are within expert annotations, whereas 36.03% of the two dimensional model's attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.

Abstract
The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Abstract
Statistics have demonstrated that one of the main factors responsible for the high mortality rate related to lung cancer is the late diagnosis. Precision medicine practices have shown advances in the individualized treatment according to the genetic profile of each patient, providing better control on cancer response. Medical imaging offers valuable information with an extensive perspective of the cancer, opening opportunities to explore the imaging manifestations associated with the tumor genotype in a non-invasive way. This work aims to study the relevance of physiological features captured from Computed Tomography images, using three different 2D regions of interest to assess the Epidermal growth factor receptor (EGFR) mutation status: nodule, lung containing the main nodule, and both lungs. A Convolutional Autoencoder was developed for the reconstruction of the input image. Thereafter, the encoder block was used as a feature extractor, stacking a classifier on top to assess the EGFR mutation status. Results showed that extending the analysis beyond the local nodule allowed the capture of more relevant information, suggesting the presence of useful biomarkers using the lung with nodule region of interest, which allowed to obtain the best prediction ability. This comparative study represents an innovative approach for gene mutations status assessment, contributing to the discussion on the extent of pathological phenomena associated with cancer development, and its contribution to more accurate Artificial Intelligence-based solutions, and constituting, to the best of our knowledge, the first deep learning approach that explores a comprehensive analysis for the EGFR mutation status classification.

Abstract
Liquid biopsy is an emerging technology with a potential role in the screening and early detection of lung cancer. Several liquid biopsy-derived biomarkers have been identified and are currently under ongoing investigation. In this article, we review the available data on the use of circulating biomarkers for the early detection of lung cancer, focusing on the circulating tumor cells, circulating cell-free DNA, circulating micro-RNAs, tumor-derived exosomes, and tumor-educated platelets, providing an overview of future potential applicability in the clinical practice. While several biomarkers have shown exciting results, diagnostic performance and clinical applicability is still limited. The combination of different biomarkers, as well as their combination with other diagnostic tools show great promise, although further research is still required to define and validate the role of liquid biopsies in clinical practice.

Abstract
Artificial intelligence (AI)-based solutions have revolutionized our world, using extensive datasets and computational resources to create automatic tools for complex tasks that, until now, have been performed by humans. Massive data is a fundamental aspect of the most powerful AI-based algorithms. However, for AI-based healthcare solutions, there are several socioeconomic, technical/infrastructural, and most importantly, legal restrictions, which limit the large collection and access of biomedical data, especially medical imaging. To overcome this important limitation, several alternative solutions have been suggested, including transfer learning approaches, generation of artificial data, adoption of blockchain technology, and creation of an infrastructure composed of anonymous and abstract data. However, none of these strategies is currently able to completely solve this challenge. The need to build large datasets that can be used to develop healthcare solutions deserves special attention from the scientific community, clinicians, all the healthcare players, engineers, ethicists, legislators, and society in general. This paper offers an overview of the data limitation in medical predictive models; its impact on the development of healthcare solutions; benefits and barriers of sharing data; and finally, suggests future directions to overcome data limitations in the medical field and enable AI to enhance healthcare. This perspective is dedicated to the technical requirements of the learning models, and it explains the limitation that comes from poor and small datasets in the medical domain and the technical options that try or can solve the problem related to the lack of massive healthcare data.

Abstract
Lung segmentation represents a fundamental step in the development of computer-aided decision systems for the investigation of interstitial lung diseases. In a holistic lung analysis, eliminating background areas from Computed Tomography (CT) images is essential to avoid the inclusion of noise information and spend unnecessary computational resources on non-relevant data. However, the major challenge in this segmentation task relies on the ability of the models to deal with imaging manifestations associated with severe disease. Based on U-net, a general biomedical image segmentation architecture, we proposed a light-weight and faster architecture. In this 2D approach, experiments were conducted with a combination of two publicly available databases to improve the heterogeneity of the training data. Results showed that, when compared to the original U-net, the proposed architecture maintained performance levels, achieving 0.894 +/- 0.060, 4.493 +/- 0.633 and 4.457 +/- 0.628 for DSC, HD and HD-95 metrics, respectively, when using all patients from the ILD database for testing only, while allowing a more efficient computational usage. Quantitative and qualitative evaluations on the ability to cope with high-density lung patterns associated with severe disease were conducted, supporting the idea that more representative and diverse data is necessary to build robust and reliable segmentation tools.