Abstract
In this work a fully automatic system to identify the extensor tendon on ultrasound images of the metacarpophalangeal joint is proposed. These images are used to diagnose rheumatic diseases which are one of the main causes of impairment and pain in developed countries. The early diagnosis of these conditions is crucial to a proper treatment and follow-up and so, a system such as the one proposed here, could be useful to automatically extract relevant information from the resulting images. This work is an extension of a previous published work which uses manual annotations of the skin line, metacarpus and phalange to guide the extensor tendon segmentation. By introducing automatic segmentations of all structures, we expect to create a fully automatic system, which is more interesting to the possible end-users. Results show that, despite an expected loss in the performance, it is still possible to correctly identify the extensor tendon with a Confidence of 88% considering a maximum allowed Modified Hausdorff Distance of 0.5mm. © 2018 IEEE.

Abstract
Gastroenterology imaging is a diagnostic procedure that incorporates various computer vision challenges for the design of assisted diagnostic systems. The most typical challenge is the design of more adequate visual descriptors that can assist the classification algorithms in getting good diagnostic results. Literature shows that most of the texture descriptors for feature extraction from gastric lesions are based on Gabor filters or local binary patterns (LBP). Although good results are obtained, these techniques have their shortcomings. In this paper, we aim to explore the use of fusion of Gabor filters and LBPs for characterizing gastric lesions. The images are first subjected to Gabor filtering using isotropic Gabor filters, followed by extracting LBPs from the filtered images. We validate the performance of the descriptor on a novel gastroenterology dataset: the Post-MAPS dataset. Our results show that the proposed feature set outperforms the other methods that have been considered in this paper.

Abstract
Gastric cancer is a serious disease that most people usually do not know they have until they start to get symptoms. Gastroenterology imaging is an essential tool for this battle, since an early diagnosis typically leads to a good prognosis. However, this is a rapidly evolving technological area with novel imaging devices such as capsule, narrow-band imaging or high-definition endoscopy. Adapting to these technologies has a high time-price cost, even for experienced clinicians, motivating the appearance of interactive environments that can accelerate these training processes. The GEMINI (Gastroenterology Made Interactive) project aims to create an interactive clinical decision support system (CDSS) that can be used to help with the diagnosis within a gastroenterology room during real endoscopic examinations. We used human computer interaction (HCI) support methodologies in order to identify interaction opportunities. As a final conclusion, the most promising avenue for interactions with CDSS is probably using mobile devices such as tablets, controlled by a nurse at the physician's request. As future work, we will prototype and evaluate such a system in a real hospital environment. © 2015 European Federation for Medical Informatics (EFMI).

Abstract
In this work we study the impact of a set of bag-of-features strategies for the recognition of cancer in gastroenterology images. By using the SIFT descriptor, we analyzed the importance and performance impact of term weighting functions for the construction of visual vocabularies. Further analyzes were conducted in order to ascertain the robustness of multiclass decomposition rules for Support Vector Machines with different kernels. Our study was extended by tailoring a decomposition rule that explores prior knowledge according the four grades of the Singh taxonomy (SDR). We found that SDR coupled with a frequency term weight function attained the best overall results (80%) when trained with an intersection kernel. It also outperformed standard decomposition rules when using a chi(2) kernel and attained competitive performances with a linear kernel.

Abstract
Gastroenterology imaging is an essential tool to detect gastrointestinal cancer in patients. Computer-assisted diagnosis is desirable to help us improve the reliability of this detection. However, traditional computer vision methodologies, mainly segmentation, do not translate well to the specific visual characteristics of a gastroenterology imaging scenario. In this paper, we propose a novel method for the segmentation of gastroenterology images from two distinct imaging modalities and organs: chromoendoscopy (CH) and narrow-band imaging (NBI) from stomach and esophagus, respectively. We have used various visual features individually and their combinations (edgemaps, creaseness, and color) in normalized cuts image segmentation framework to segment ground truth datasets of 142 CH and 224 NBI images. Experiments show that an integration of edgemaps and creaseness in normalized cuts gives the best segmentation performance resulting in high-quality segmentations of the gastroenterology images.

Abstract
The introduction of various novel imaging technologies such as narrow-band imaging have posed novel image processing challenges to the design of computer assisted decision systems. In this paper, we propose an image descriptor refered to as integrated scale histogram local binary patterns. We propagate an aggregated histogram of local binary patterns of an image at various resolutions. This results in low dimensional feature vectors for the images while incorporating their multiresolution analysis. The descriptor was used to classify gastroenterology images into four distinct groups. Results produced by the proposed descriptor exhibit around 92% accuracy for classification of gastroenteroloy images outperforming other state-of-the-art methods, endorsing the effectiveness of the proposed descriptor.