Abstract
Lung cancer is the world's most lethal type of cancer, being crucial that an early diagnosis is made in order to achieve successful treatments. Computer-aided diagnosis can play an important role in lung nodule detection and on establishing the nodule malignancy likelihood. This paper is a contribution in the design of a learning approach, using computed tomography images. Our methodology involves the measurement of a set of features in the nodular image region, and train classifiers, as K-nearest neighbor or support vector machine (SVM), to compute the malignancy likelihood of lung nodules. For this purpose, the Lung Image Database Consortium and image database resource initiative database is used due to its size and nodule variability, as well as for being publicly available. For training we used both radiologist's labels and annotations and diagnosis data, as biopsy, surgery and follow-up results. We obtained promising results, as an Area Under the Receiver operating characteristic curve value of 0.962 +/- 0.005 and 0.905 +/- 0.04 was achieved for the Radiologists' data and for the Diagnosis data, respectively, using an SVM with an exponential kernel combined with a correlation-based feature selection method.

Abstract
The wireless capsule endoscopy has revolutionized early diagnosis of small bowel diseases. However, a single examination has up to 10 h of video and requires between 30–120 min to read. Computational methods are needed to increase both efficiency and accuracy of the diagnosis. In this paper, an evaluation of deep learning U-Net architecture is presented, to detect and segment red lesions in the small bowel. Its results were compared with those obtained from the literature review. To make the evaluation closer to those used in clinical environments, the U-Net was also evaluated in an annotated sequence by using the Suspected Blood Indicator tool (SBI). Results found that detection and segmentation using U-Net outperformed both the algorithms used in the literature review and the SBI tool. © 2018, Springer International Publishing AG, part of Springer Nature.

Abstract
Vineyard parcels delimitation is a preliminary but important task to support zoning activities, which can be burdensome and time-consuming when manually performed. In spite of being desirable to overcome such issue, the implementation of a semi-/fully automatic delimitation approach can meet serious development challenges when dealing with vineyards like the ones that prevail in Douro Region (north-east of Portugal), mainly due to the great diversity of parcel/row formats and several factors that can hamper detection as, for example, interrupted rows and inter-row vegetation. Thereby, with the aim of addressing vineyard parcels detection and delimitation in Douro Region, a preliminary method based on segmentation and morphological operations upon high-resolution aerial imagery is proposed. This method was tested in a data set collected from vineyards located at the University of Trás-os-Montes and Alto Douro(Vila Real, Portugal). The presence of some of the previously mentioned challenging conditions - namely interrupted rows and inter-row grassing - in a few parcels contributed to lower the overall detection accuracy, pointing out the need for future improvements. Notwithstanding, encouraging preliminary results were achieved.

Abstract
We propose a deep learning-based pipeline that, given a low-dose computed tomography of a patient chest, recommends if a patient should be submitted to further lung cancer assessment. The algorithm is composed of a nodule detection block that uses the object detection framework YOLOv2, followed by a U-Net based segmentation. The found structures of interest are then characterized in terms of diameter and texture to produce a final referral recommendation according to the National Lung Screen Trial (NLST) criteria. Our method is trained using the public LUNA16 and LIDC-IDRI datasets and tested on an independent dataset composed of 500 scans from the Kaggle DSB 2017 challenge. The proposed system achieves a patient-wise recall of 89% while providing an explanation to the referral decision and thus may serve as a second opinion tool to speed-up and improve lung cancer screening.

Abstract
Lung cancer is one of the most common causes of death in the world. The early detection of lung nodules allows an appropriate follow-up, timely treatment and potentially can avoid greater damage in the patient health. The texture is one of the nodule characteristics that is correlated with the malignancy. We developed convolutional neural network architectures to classify automatically the texture of nodules into the non-solid, part-solid and solid classes. The different architectures were tested to determine if the context, the number of slices considered as input and the relation between slices influence on the texture classification performance. The architecture that obtained better performance took into account different scales, different rotations and the context of the nodule, obtaining an accuracy of 0.833 ± 0.041.

Abstract
Endoscopic capsules are vitamin-sized devices that create 8 to 10 hour videos of the digestive tract. They are the leading diagnosing method for the small bowel, a region not easily accessible with traditional endoscopy techniques. However, these capsules do not provide localization information, even though it is crucial for the diagnosis, follow-ups and surgical interventions. Currently, the capsule localization is either estimated based on scarce gastrointestinal tract landmarks or given by additional hardware that causes discomfort to the patient and represents a cost increase. Current software methods show great potential, but still need to improve in order to overcome their limitations. In this work, a visual odometry method for capsule localization inside the small bowel is proposed.