Having dense and regularly sampled data is becoming increasingly important in seismic processing. However, due to physical or financial constraints, seismic data sets can be often undersampled. Occasionally, these data sets may also present bad or dead traces the geoscientist must deal with. Many works have tackled this problem using prestack data and can be classified in three main categories: wave-equation, domain transform, and prediction-error-filter methods. In this letter, we assess the performance of a conditional generative adversarial network for the interpolation problem in poststack seismic data sets. To the best of our knowledge, this is the first work to evaluate a deep learning approach in this context. Quantitative and qualitative evaluations of our experiments indicate that deep networks may present an interesting alternative to classical methods.

Optical imagery is often affected by the presence of clouds. Aiming to reduce their effects, different reconstruction techniques have been proposed in the last years. A common alternative is to extract data from active sensors, like Synthetic Aperture Radar (SAR), because they are almost independent on the atmospheric conditions and solar illumination. On the other hand, SAR images are more complex to interpret than optical images requiring particular handling. Recently, Conditional Generative Adversarial Networks (cGANs) have been widely used in different image generation tasks presenting state-of-the-art results. One application of cGANs is learning a nonlinear mapping function from two images of different domains. In this work, we combine the fact that SAR images are hardly affected by clouds with the ability of cGANS for image translation in order to map optical images from SAR ones so as to recover regions that are covered by clouds. Experimental results indicate that the proposed solution achieves better classification accuracy than SAR based classification.

Cancer treatments are complex and involve different actions, which include many times a surgical procedure. Medical imaging provides important information for surgical planning, and it usually demands a proper segmentation, i.e., the identification of meaningful objects, such as organs and lesions. This study proposes a methodology to segment the liver, its vessels and nodules from computer tomography images for surgical planning. The proposed methodology consists of four steps executed sequentially: segmentation of liver, segmentation of vessels and nodules, identification of hepatic and portal veins, and segmentation of Couinaud anatomical segments. Firstly, the liver is segmented by a method based on a deformable model implemented through level sets, of which parameters are adjusted by using a supervised optimization procedure. Secondly, a mixture model is used to segment nodules and vessels through a region growing process. Then, the identification of hepatic and portal veins is performed using liver anatomical knowledge and a vein tracking algorithm. Finally, the Couinaud anatomical segments are identified according to the anatomical liver model proposed by Couinaud. Experiments were conducted using data and metrics brought from the liver segmentation competition held in the Sliver07 conference. A subset of five exams was used for estimation of segmentation parameter values, while 15 exams were used for evaluation. The method attained a good performance in 17 of the 20 exams, being ranked as the 6^th best semi-automatic method when comparing to the methods described on the Sliver07 website (2008). It attained visual consistent results for nodules and veins segmentation, and we compiled the results, showing the best, worst, and mean results for all dataset. The method for liver segmentation performed well, according to the results of the numerical evaluation implemented, and the segmentation of liver internal structures were consistent with the anatomy of the liver, as confirmed by a specialist. The analysis provided evidences that the method to segment the liver may be applied to segment other organs, especially to those whose distribution of voxel intensities is nearly Gaussian shaped.

In recent years, black-box machine learning approaches have become a dominant modeling paradigm for knowledge extraction in remote sensing. Despite the potential benefits of uncovering the inner workings of these models with explainable AI, a comprehensive overview summarizing the used explainable AI methods and their objectives, findings, and challenges in remote sensing applications is still missing. In this paper, we address these issues by performing a systematic review to identify the key trends of how explainable AI is used in remote sensing and shed light on novel explainable AI approaches and emerging directions that tackle specific remote sensing challenges. We also reveal the common patterns of explanation interpretation, discuss the extracted scientific insights in remote sensing, and reflect on the approaches used for explainable AI methods evaluation. As such, our review provides a complete summary of the state-of-the-art of explainable AI in remote sensing. Further, we give a detailed outlook on the challenges and promising research directions, representing a basis for novel methodological development and a useful starting point for new researchers in the field.

Automatic document layout analysis is a crucial step in cognitive computing and processes that extract information out of document images, such as specific-domain knowledge database creation, graphs and images understanding, extraction of structured data from tables, and others. Even with the progress observed in this field in the last years, challenges are still open and range from accurately detecting content boxes to classifying them into semantically meaningful classes. With the popularization of mobile devices and cloud-based services, the need for approaches that are both fast and economic in data usage is a reality. In this paper we propose a fast one-dimensional approach for automatic document layout analysis considering text, figures and tables based on convolutional neural networks (CNN). We take advantage of the inherently one-dimensional pattern observed in text and table blocks to reduce the dimension analysis from bi-dimensional documents images to 1D signatures, improving significantly the overall performance: we present considerably faster execution times and more compact data usage with no loss in overall accuracy if compared with a classical bidimensional CNN approach.