Abstract
Capsule endoscopy is becoming the major medical technique for the examination of the gastrointestinal tract, and the detection of small bowel lesions. With the growth of endoscopic capsules and the lack of an appropriate tracking system to allow the localization of lesions, the need to develop software-based techniques for the localisation of the capsule at any given frame is also increasing. With this in mind, and knowing the lack of availability of labelled endoscopic datasets, this work aims to develop a unsupervised method for homography estimation in video capsule endoscopy frames, to later be applied in capsule localisation systems. The pipeline is based on an unsupervised convolutional neural network, with a VGG Net architecture, that estimates the homography between two images. The overall error, using a synthetic dataset, was evaluated through the mean average corner error, which was 34 pixels, showing great promise for the real-life application of this technique, although there is still room for the improvement of its performance. (C) 2019 The Authors. 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/) Peer-review under responsibility of the scientific committee of the CENTERIS -International Conference on ENTERprise Information Systems / ProjMAN - International Conference on Project MANagement / HCist - International Conference on Health and Social Care Information Systems and Technologies.

Abstract
Advances in genomics have driven to the recognition that tumours are populated by different minor subclones of malignant cells that control the way the tumour progresses. However, the spatial and temporal genomic heterogeneity of tumours has been a hurdle in clinical oncology. This is mainly because the standard methodology for genomic analysis is the biopsy, that besides being an invasive technique, it does not capture the entire tumour spatial state in a single exam. Radiographic medical imaging opens new opportunities for genomic analysis by providing full state visualisation of a tumour at a macroscopic level, in a non-invasive way. Having in mind that mutational testing of EGFR and KRAS is a routine in lung cancer treatment, it was studied whether clinical and imaging data are valuable for predicting EGFR and KRAS mutations in a cohort of NSCLC patients. A reliable predictive model was found for EGFR (AUC = 0.96) using both a Multi-layer Perceptron model and a Random Forest model but not for KRAS (AUC = 0.56). A feature importance analysis using Random Forest reported that the presence of emphysema and lung parenchymal features have the highest correlation with EGFR mutation status. This study opens new opportunities for radiogenomics on predicting molecular properties in a more readily available and non-invasive way. © 2019, Springer Nature Switzerland AG.

Abstract
Endoscopic capsules are vitamin-sized devices that leverage from a small wireless camera to create 8 to 10 hour videos of the patients' entire digestive tract, still being the leading tool to diagnose small bowel diseases. The revision of the produced videos is a very time-consuming task, currently conducted manually and frame-by-frame by an expert. Since endoscopic videos usually contain a considerable amount of frames where the mucosa is not clearly visible, the segmentation of the informative regions is a vital component to reduce the necessary time to review each exam. In this work, a CNN encoder-decoder architecture is applied to segment informative regions in small bowel frames of videos of endoscopic capsules. The network was trained and tested with a dataset of 2,929 manually annotated images, achieving a 91.2% Dice coefficient and 83.9% IoU. Furthermore, a video-wise analysis based on the amount of informative pixels in each frame is done.

Abstract
Lung cancer is among the deadliest diseases in the world. The detection and characterization of pulmonary nodules are crucial for an accurate diagnosis, which is of vital importance to increase the patients’ survival rates. The segmentation process contributes to the mentioned characterization, but faces several challenges, due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper proposes two methods for pulmonary nodule segmentation in Computed Tomography (CT) scans. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the center of the nodule, and consequently the filter’s support points, matching the initial border coordinates. This preliminary segmentation is then refined to include mainly the nodular area, and no other regions (e.g. vessels and pleural wall). The second approach is based on Deep Learning, using the U-Net to achieve the same goal. This work compares both performances, and consequently identifies which one is the most promising tool to promote early lung cancer screening and improve nodule characterization. Both methodologies used 2653 nodules from the LIDC database: the SBF based one achieved a Dice score of 0.663, while the U-Net achieved 0.830, yielding more similar results to the ground truth reference annotated by specialists, and thus being a more reliable approach. © Springer Nature Switzerland AG 2019.

Abstract
Wireless capsule endoscopy is a relatively novel technique used for imaging of the gastrointestinal tract. Unlike traditional approaches, it allows painless visualisation of the whole of the gastrointestinal tract, including the small bowel, a region of difficult access. Endoscopic capsules record for about 8h, producing around 60,000 images. These are analysed by an expert that identifies abnormalities present in the frames, a process that is very tedious and prone to errors. Thus there is a clear need to develop systems that automatically analyse this data and detect lesions. Lesion detection achieved a precision of 0.94 and a recall of 0.93 by fmetuning the pre-trained DenseNet-161 model. (C) 2019 The Authors. Published by Elsevier B.V.

Abstract
The offset tracking technique based on synthetic aperture radar (SAR) image intensity information can estimate glacier displacement even when glacier velocities are high and the time interval between images is long, allowing for the broad use of this technique in glacier velocity monitoring. Terrestrial laser scanners, a non-contact measuring system, can measure the velocity of a glacier even if there are no control points arranged on a glacier. In this study, six COSMO-SkyMed images acquired between 31 July and 22 December 2016 were used to obtain the glacial movements of five glaciers on the northern slope of the central Himalayas using the offset tracking approach. During the period of image acquirement, a terrestrial laser scanner was used, and point clouds of two periods in a small area at the terminus of the Pingcuoliesa Glacier were obtained. By selecting three fixed areas of the point clouds that have similar shapes across two periods, the displacements of the centers of gravity of the selected areas were calculated by using contrast analyses of feature points. Although the overall low-density point clouds data indicate that the glacial surfaces have low albedos relative to the wavelength of the terrestrial laser scanner and the effect of its application is therefore influenced in this research, the registration accuracy of 0.0023 m/d in the non-glacial areas of the scanner's measurements is acceptable, considering the magnitude of 0.072 m/d of the minimum glacial velocity measured by the scanner. The displacements from the point clouds broadly agree with the results of the offset tracking technique in the same area, which provides further evidence of the reliability of the measurements of the SAR data in addition to the analyses of the root mean squared error of the velocity residuals in non-glacial areas. The analysis of the movement of five glaciers in the study area revealed the dynamic behavior of these glacial surfaces across five periods. G089972E28213N Glacier, Pingcuoliesa Glacier and Shimo Glacier show increasing surface movement velocities from the terminus end to the upper part with elevations of 1500 m, 4500 m, and 6400 m, respectively. The maximum velocities on the glacial surface profiles were 31.69 cm/d, 62.40 cm/d, and 42.00 cm/d, respectively. In contrast, the maximum velocity of Shie Glacier, 50.60 cm/d, was observed at the glacier's terminus. For each period, G090138E28210N Glacier exhibited similar velocity values across the surface profile, with a maximum velocity of 39.70 cm/d. The maximum velocities of G089972E28213N Glacier, Pingcuoliesa Glacier, and Shie Glacier occur in the areas where the topography is steepest. In general, glacial surface velocities are higher in the summer than in the winter in this region. With the assistance of a terrestrial laser scanner with optimized wavelengths or other proper ground-based remote sensing instruments, the offset tracking technique based on high-resolution satellite SAR data should provide more reliable and detailed information for local and even single glacial surface displacement monitoring.