Abstract
Lung cancer is the leading cause of cancer death worldwide. Early low-dose computed tomography (CT) screening can decrease its mortality rate and computer-aided diagnoses systems may make these screenings more accessible. Radiomic features and supervised machine learning have traditionally been employed in these systems. Contrary to supervised methods, unsupervised learning techniques do not require large amounts of annotated data which are labor-intensive to gather and long training times. Therefore, recent approaches have used unsupervised methods, such as clustering, to improve the performance of supervised models. However, an analysis of purely unsupervised methods for malignancy prediction of lung nodules from CT images has not been performed. This work studies nodule malignancy in the LIDC-IDRI image collection of chest CT scans using established radiomic features and unsupervised learning methods based on k-Means, Spectral Clustering, and Gaussian Mixture clustering. All tested methods resulted in clusters of high homogeneity malignancy. Results suggest convex feature distributions and well-separated feature subspaces associated with different diagnoses. Furthermore, diagnosis uncertainty may be explained by common characteristics captured by radiomic features. The k-Means and Gaussian Mixture models are able to generalize to unseen data, achieving a balanced accuracy of 87.23% and 86.96% when inference was tested. These results motivate the usage of unsupervised approaches for malignancy prediction of lung nodules, such as cluster-then-label models. Clinical Relevance - Unsupervised clustering of radiomic features of lung nodules in chest CT scans can differentiate between malignant and benign cases and reflects experts' diagnosis uncertainty

Abstract
Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

Abstract
We study the time-dependent behavior of dissipative solitons (DSs) stabilized by nonlinear gradient terms. Two cases are investigated: first, the case of the presence of a Raman term, and second, the simultaneous presence of two nonlinear gradient terms, the Raman term and the dispersion of nonlinear gain. As possible types of time-dependence, we find a number of different possibilities including periodic behavior, quasi-periodic behavior, and also chaos. These different types of time-dependence are found to form quite frequently from a window structure of alternating behavior, for example, of periodic and quasi-periodic behaviors. To analyze the time dependence, we exploit extensively time series and Fourier transforms. We discuss in detail quantitatively the question whether all the DSs found for the cubic complex Ginzburg-Landau equation with nonlinear gradient terms are generic, meaning whether they are stable against structural perturbations, for example, to the additions of a small quintic perturbation as it arises naturally in an envelope equation framework. Finally, we examine to what extent it is possible to have different types of DSs for fixed parameter values in the equation by just varying the initial conditions, for example, by using narrow and high vs broad and low amplitudes. These results indicate an overlapping multi-basin structure in parameter space. Published under an exclusive license by AIP Publishing.

Abstract
Pulp and Paper Companies collaborate to monitor and monetize waste and create value from their by-products. This process of Industrial Symbiosis requires the creation and maintenance of trusted and transparent relationships between all entities participating in these networks, which is a constant challenge. In this context, a blockchain-based system can help in establishing and maintaining these networks, serving as a ground truth between companies operating at a national or a global scale. This paper proposes a scalable and modular blockchain architecture design using smart contracts to enhance the industrial symbiosis process of the Pulp, Paper, and Cardboard Production Sector companies in Portugal. This design comprehends all entities participating in the network. The implementation of this design assumes the use of a permissioned ledger built using Hyperledger Fabric to provide the required trust and transparency between all entities.

Abstract
Messaging services are usually provided within social network platforms and allow these platforms to collect additional information about users, such as what time, for how long, with whom, and where a user communicates. This information allows the identification of users and is available to the messaging service provider even when communication is encrypted end-to-end. Thus, a gap still exists for alternative messaging services that enable anonymous and confidential communication and that are independent of a specific online service. Online services can still be used to support this messaging service, but in a way that enables users to communicate anonymously and without the knowledge and scrutiny of the online services. In this paper, we propose messaging using steganography and online services to support anonymous and confidential communication. In the proposed messaging service, only the sender and the receiver are aware of the existence of the exchanged data, even if the online services used or other third parties have access to the exchanged secret data containers. This work reviews the viability of using existing online services to support the proposed messaging service. Moreover, a proof-of-concept of the proposed message service is implemented and tested using two online services acting as proxies in the exchange of encrypted information disguised within images and links to those images. The obtained results confirm the viability of such a messaging service. © 2022 by the authors.

Abstract
[No abstract available]