Search

As an emerging technology that uses a pill‐sized camera to visualize images of the digestive tract. Wireless capsule endoscopy (WCE) presents several advantages, since it is far less invasive, does not need sedation and has less possible complications compared to standard endoscopy. Hence, it might be exploited as alternative to the standard procedure. WCE is used to diagnosis a variety of gastro‐intestinal diseases such as polyps, ulcers, crohns disease, and hemorrhages. Nevertheless, WCE videos produced after a test may consist of thousands of frames per patient that must be viewed by medical specialists, besides, the capsule free mobility and technological limits cause production of a low quality images. Hence, development of an automatic tool based on artificial intelligence might be very helpful. Moreover, most state‐of‐the‐art works aim at images classification (normal/abnormal) while ignoring diseases segmentation. Therefore, in this work a novel method based on Feature Pyramid Network model is presented. This approach aims at diseases segmentation from WCE images. In this model, modules to optimize and combine features were employed. Specifically, semantic and spatial features were mutually compensated by spatial attention and cross‐level global feature fusion modules. The proposed method testing F1‐score and mean intersection over union are 94.149% and 89.414%, respectively, in the MICCAI 2017 dataset. In the KID Atlas dataset, the method achieved a testing F1‐score and mean intersection over union of 94.557% and 90.416%, respectively. Through the performance analysis, the mean intersection over union in the MICCAI 2017 dataset is 20.414%, 18.484%, 11.444%, 8.794% more than existing approaches. Moreover, the proposed scheme surpassed the methods used for comparison by 29.986% and 9.416% in terms of mean intersection over union in KID Atlas dataset. These results indicate that the proposed approach is promising in diseases segmentation from WCE images. [ABSTRACT FROM AUTHOR]

This paper proposes a new edge based stereo matching approach for road applications. The new approach consists in matching the edge points extracted from the input stereo images using temporal constraints. At the current frame, we propose to estimate a disparity range for each image line based on the disparity map of its preceding one. The stereo images are divided into multiple parts according to the estimated disparity ranges. The optimal solution of each part is independently approximated via the state-of-the-art energy minimization approach Graph cuts. The disparity search space at each image part is very small compared to the global one, which improves the results and reduces the execution time. Furthermore, as a similarity criterion between corresponding edge points, we propose a new cost function based on the intensity, the gradient magnitude and gradient orientation. The proposed method has been tested on virtual stereo images, and it has been compared to a recently proposed method and the results are satisfactory.

Colorectal cancer is one of the most common malignancies and the leading cause of cancer death worldwide. Wireless capsule endoscopy is currently the most frequent method for detecting precancerous digestive diseases. Thus, precise and early polyps segmentation has significant clinical value in reducing the probability of cancer development. However, the manual examination is a time-consuming and tedious task for doctors. Therefore, scientists have proposed many computational techniques to automatically segment the anomalies from endoscopic images. In this paper, we present an end-to-end 2D attention residual U-Net architecture (AttResU-Net), which concurrently integrates the attention mechanism and residual units into U-Net for further polyp and bleeding segmentation performance enhancement. To reduce outside areas in an input image while emphasizing salient features, AttResU-Net inserts a sequence of attention units among related downsampling and upsampling steps. On the other hand, the residual block propagates information across layers, allowing for the construction of a deeper neural network capable of solving the vanishing gradient issue in each encoder. This improves the channel interdependencies while lowering the computational cost. Multiple publicly available datasets were employed in this work, to evaluate and verify the proposed method. Our highest-performing model was AttResU-Net, on the MICCAI 2017 WCE dataset, which achieved an accuracy of 99.16%, a Dice coefficient of 94.91%, and a Jaccard index of 90.32%. The experiment findings show that the proposed AttResU-Net overcomes its baselines and provides performance comparable to existing polyp segmentation approaches. [ABSTRACT FROM AUTHOR]

Small bowel polyps exhibit variations related to color, shape, morphology, texture, and size, as well as to the presence of artifacts, irregular polyp borders, and the low illumination condition inside the gastrointestinal GI tract. Recently, researchers developed many highly accurate polyp detection models based on one-stage or two-stage object detector algorithms for wireless capsule endoscopy (WCE) and colonoscopy images. However, their implementation requires a high computational power and memory resources, thus sacrificing speed for an improvement in precision. Although the single-shot multibox detector (SSD) proves its effectiveness in many medical imaging applications, its weak detection ability for small polyp regions persists due to the lack of information complementary between features of low- and high-level layers. The aim is to consecutively reuse feature maps between layers of the original SSD network. In this paper, we propose an innovative SSD model based on a redesigned version of a dense convolutional network (DenseNet) which emphasizes multiscale pyramidal feature maps interdependence called DC-SSDNet (densely connected single-shot multibox detector). The original backbone network VGG-16 of the SSD is replaced with a modified version of DenseNet. The DenseNet-46 front stem is improved to extract highly typical characteristics and contextual information, which improves the model's feature extraction ability. The DC-SSDNet architecture compresses unnecessary convolution layers of each dense block to reduce the CNN model complexity. Experimental results showed a remarkable improvement in the proposed DC-SSDNet to detect small polyp regions achieving an mAP of 93.96%, F1-score of 90.7%, and requiring less computational time. [ABSTRACT FROM AUTHOR]

The AFB BJ+ DAC∗ is the latest variant of asynchronous forward bounding algorithms used to solve Distributed Constraint Optimization Problems (DCOPs). It uses Directional Arc Consistency (DAC∗) to remove, from domains of a given DCOP, values that do not belong to its optimal solution. However, in some cases, DAC∗ does not remove all suboptimal values, which causes more unnecessary research to reach the optimal solution. In this paper, to clear more and more suboptimal values from a DCOP, we use a higher level of DAC∗ called Full Directional Arc Consistency (FDAC∗). This level is based on reapplying AC∗ several times, which gives the possibility of making more deletions and thus quickly reaching the optimal solution. Experiments on some benchmarks show that the new algorithm, AFB BJ+ FDAC∗, is better in terms of communication load and computation effort. [ABSTRACT FROM AUTHOR]

Defining the correct number of clusters is one of the most fundamental tasks in graph clustering. When it comes to large graphs, this task becomes more challenging because of the lack of prior information. This paper presents an approach to solve this problem based on the Bat Algorithm, one of the most promising swarm intelligence based algorithms. We chose to call our solution, "Bat-Cluster (BC)." This approach allows an automation of graph clustering based on a balance between global and local search processes. The simulation of four benchmark graphs of different sizes shows that our proposed algorithm is efficient and can provide higher precision and exceed some best-known values. [ABSTRACT FROM AUTHOR]

Graph Visualization is a technique that helps users to easily comprehend connected data (social networks, semantic networks, etc.) based on human perception. With the prevalence of Big Data, these graphs tend to be too large to decipher by the user's visual abilities alone. One of the leading causes of this problem is when the nodes leave the visualization space. Many attempts have been made to optimize large graph visualization, but they all have limitations. Among these attempts, the most famous one is the Force Directed Placement Algorithm. This algorithm can provide beautiful visualizations for small to medium graphs, but when it comes to larger graphs it fails to keep some independent nodes or even subgraphs inside the visualization space. In this paper, we present an algorithm that we have named "Forced Force Directed Placement". This algorithm provides an enhancement of the classical Force Directed Placement algorithm by proposing a stronger force function. The "FForce", as we have named it, can bring related nodes closer to each other before reaching an equilibrium position. This helped us gain more display space and that gave us the possibility to visualize larger graphs. [ABSTRACT FROM AUTHOR]