Gastric Intestinal Metaplasia (GIM) is a precancerous gastric lesion and its early detection facilitates patient followup, thus lowering significantly the risk of death by gastric cancer. However, ...effective screening of this condition is a very challenging task, resulting low intra and inter-observer concordance. Computer assisted diagnosis systems leveraging deep neural networks (DNNs) have emerged as a way to mitigate these ailments. Notwithstanding, these approaches typically require large datasets in order to learn invariance to the extreme variations typically present in Esophagogastroduodenoscopy (EGD) still frames, such as perspective, illumination, and scale. Hence, we propose to combine a priori information regarding texture characteristics of GIM with data-driven DNN solutions. In particular, we define two different models that treat pre-trained DNNs as general features extractors, whose pairwise interactions with a collection of highly invariant local texture descriptors grounded on fractal geometry are computed by means of an outer product in the embedding space. Our experiments show that these models outperform a baseline DNN by a significant margin over several metrics (e.g., area under the curve (AUC) 0.792 vs. 0.705) in a dataset comprised of EGD narrow-band images. Our best model measures double the positive likelihood ratio when compared to a baseline GIM detector.
INTRODUCTIONEndoscopic retrograde cholangiopancreatography is the method of choice for biliary drainage, although in some cases standard biliary access is difficult or even impossible. Endoscopic ...ultrasound (EUS)-guided endoluminal procedures are an alternative in these cases, although experience with these techniques is still limited. CLINICAL CASEWe present two cases of successful EUS-guided biliary drainage. In the first case, a hepaticogastrostomy was performed in a patient with stage IV gastric adenocarcinoma with obstructive jaundice due to compression of the hilum, where malignant gastric stenosis and previous palliative gastrojejunostomy precluded access to the second part of the duodenum. In the second case, a patient with a pancreatic head adenocarcinoma with duodenal invasion that precluded major papillae identification was submitted to a choledochoduodenostomy. Both procedures occurred without immediate or delayed adverse events, with technical and clinical success. DISCUSSIONAlthough experience with EUS-guided biliary drainage is still limited, its efficacy and safety is favorable when compared with percutaneous and surgical drainage, and should be considered an alternative to these techniques where sufficient expertise exists.
Lake Paranoá is an eutrophic reservoir situated in the urban region of Brasília. This study was carried out in a fixed collection station located in the Riacho Fundo branch of the reservoir. ...Zooplankton samples were collected at intervals of 3-5 d at 9:00 a.m. during two months in the dry and rainy seasons for two years (dry-1996, rainy-1997, dry-1997 and rainy-1998), using a 64 microns-mesh plankton net. The most predominant species was Thermocyclops decipiens (about 50% of the total zooplankton community), which during the whole period had a high reproductive rate. The highest densities were found in the dry-1996 season (1700 ind/l for nauplii), and also fluctuated widely overtime. Nauplii stages dominated during the four periods, comprising 50-75% of the total population density. Ovigerous females peaked in the dry-1996 and rainy-1997 seasons, with 20-30% of the total females. The largest peak in egg production occurred during the dry-1996 season, and the total egg production was 2.0 x 10(3) eggs/l. Mesocyclops longisetus is a first record for Lake Paranoá. The ecological factors that determine the success of T. decipiens in eutrophic systems are related to omnivorous feeding habits and prey-predator interactions.
This study aimed to build convolutional neural network (CNN) models capable of classifying upper endoscopy images, to determine the stage of infection in the development of a gastric cancer. Two ...different problems were covered. A first one with a smaller number of categorical classes and a lower degree of detail. A second one, consisting of a larger number of classes, corresponding to each stage of precancerous conditions in the Correa's cascade. Three public datasets were used to build the dataset that served as input for the classification tasks. The CNN models built for this study are capable of identifying the stage of precancerous conditions/lesions in the moment of an upper endoscopy. A model based on the DenseNet169 architecture achieved an average accuracy of 0.72 in discriminating among the different stages of infection. The trade-off between detail in the definition of lesion classes and classification performance has been explored. Results from the application of Grad CAMs to the trained models show that the proposed CNN architectures base their classification output on the extraction of physiologically relevant image features. Clinical relevance- This research could improve the accuracy of upper endoscopy exams, which have margin for improvement, by assisting doctors when analysing the lesions seen in patient's images.