Abstract
Background: Gene expression studies are an important tool in biological and biomedical research. The signal carried in expression profiles helps derive signatures for the prediction, diagnosis and prognosis of different diseases. Data science and specifically machine learning have many applications in gene expression analysis. However, as the dimensionality of genomics datasets grows, scalable solutions become necessary. Methods: In this paper we review the main steps and bottlenecks in machine learning pipelines, as well as the main concepts behind scalable data science including those of concurrent and parallel programming. We discuss the benefits of the Dask framework and how it can be integrated with the Python scientific environment to perform data analysis in computational biology and bioinformatics. Results: This review illustrates the role of Dask for boosting data science applications in different case studies. Detailed documentation and code on these procedures is made available at https:// github. com/martaccmoreno/gexp-ml-dask. Conclusion: By showing when and how Dask can be used in transcriptomics analysis, this review will serve as an entry point to help genomic data scientists develop more scalable data analysis procedures.

Abstract
Morphing attacks are one of the many threats that are constantly affecting deep face recognition systems. It consists of selecting two faces from different individuals and fusing them into a final image that contains the identity information of both. In this work, we propose a novel regularisation term that takes into account the existent identity information in both and promotes the creation of two orthogonal latent vectors. We evaluate our proposed method (OrthoMAD) in five different types of morphing in the FRLL dataset and evaluate the performance of our model when trained on five distinct datasets. With a small ResNet-18 as the backbone, we achieve state-of-the-art results in the majority of the experiments, and competitive results in the others.

Abstract
Chest radiography is one of the most common medical imaging modalites. However, chest radiography interpretation is a complex task that requires significant expertise. As such, the development of automatic systems for pathology detection has been proposed in literature, particularly using deep learning. However, these techniques suffer from a lack of explainability, which hinders their adoption in clinical scenarios. One technique commonly used by radiologists to support and explain decisions is to search for cases with similar findings for direct comparison. However, this process is extremely time-consuming and can be prone to confirmation bias. Automatic image retrieval methods have been proposed in literature but typically extract features from the whole image, failing to focus on the lesion in which the radiologist is interested. In order to overcome these issues, a novel framework LXIR for lesion-based image retrieval is proposed in this study, based on a state of the art object detection framework (YOLOv5) for the detection of relevant lesions as well as feature representation of those lesions. It is shown that the proposed method can successfully identify lesions and extract features which accurately describe high-order characteristics of each lesion, allowing to retrieve lesions of the same pathological class. Furthermore, it is show that in comparison to SSIM-based retrieval, a classical perceptual metric, and random retrieval of lesions, the proposed method retrieves the most relevant lesions 81% of times, according to the evaluation of two independent radiologists, in comparison to 42% of times by SSIM.

Abstract

Abstract
Objective: Supervised exercise therapy is recommended as first line in the management of intermittent claudication. Its use is often limited by accessibility, compliance and cost. Home-based exercise therapy (HBET) programs emerged as an alternative solution, but have shown inferior results. The use of structured monitoring with the use of external wearable activity monitors (WAM) has been shown to improve outcomes. Mobile applications (apps) can make use of built-in accelerometers of modern smartphones and become an alternative solution for monitoring patients during HBET, potentially providing wider accessibility. This review aims to assess current use of smartphone technology (ie, mobile apps) for monitoring or tracking patients' activity in exercise therapy for peripheral arterial disease (PAD). Methods: The PubMed database was searched from January 2011 to September 2021. Eligible articles had to include a population of patients with PAD, conduct a mobile-health exercise intervention and use smartphone technology for monitoring or tracking patients' activity. Randomized controlled trials, prospective studies, and study protocols were included. Results: A total of seven artic les met the selection criteria. These articles described six different studies and five different mobile apps. Three were fitness apps (FitBit, Nike+ FuelBand, and Garmin Connect) that synchronized with commercially available WAMs to provide users with feedback. Two were PAD-specific apps (TrackPAD and Movn) developed specifically to assess patients' activity during exercise therapy. PAD-specific apps also incorporated coaching and educational elements such as weekly goal setting, claudication reminders, messaging, gamification, training advice, and PAD education. Conclusions: Current HBET programs use smartphone apps mainly via commercially available fitness apps that synchronize with WAM devices to register and access data. PAD-specific apps are scarce, but show promising features that can be used to monitor, train, coach, and educate patients during HBET programs. Larger studies combining these elements into HBET programs should provide future direction.

Abstract
Artificial Intelligence-based tools have shown promising results to help clinicians in diagnosis tasks. Radio-genomics would aid in the genotype characterization using information from radiologic images. The prediction of the mutations status of main oncogenes associated with lung cancer will help the clinicians to have a more accurate diagnosis and a personalized treatment plan, decreasing the need to use the biopsy. In this work, novel and objective features were extracted from the lung that contained the nodule, and several machine learning methods were combined with feature selection techniques to select the best approach to predict the EGFR mutation status in lung cancer CT images. An AUC of 0.756 ± 0.055 was obtained using a logistic regression and independent component analysis as feature selector, supporting the hypothesis that CT images can capture pathophysiological information with great value for clinical assessment and personalized medicine of lung cancer. Clinical Relevance-Radiogenomic approaches could be an interesting help for lung cancer characterization. This work represents a preliminary study for the development of computer-aided decision systems to provide a more accurate and fast characterization of lung cancer which is fundamental for an adequate treatment plan for lung cancer patients.