Search

Deep learning techniques can accurately detect and grade abnormal findings on images from Wireless Capsule Endoscopy (WCE). However, the prediction accuracy of handcrafted or deep learning in red Lesion, polyp and ulcer diseases is still under investigation. Knowing the utility of an automatic method for abnormalities detection from WCE images and how helpful it might be for the physicians, we proposed a new methodology in approaching this field. In this paper, patches with fixed size are extracted from WCE images, then, encoded using linear projection and position embedding and passed through an embedding model in a forward pass. Moreover, triplet loss is employed to adjust the embeddings. Afterwards, the trained embedding model is exploited for classification. Two strategies are followed in the design of the embedding model namely; training from scratch and fine tuning. The presented scheme, attains satisfactory results in different datasets compared to existing approaches. The detection accuracy has reached 99.9% in some used datasets. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy (WCE) is a technology that uses a pill-sized camera to visualize images of the digestive tract. It presents several advantages, since it is far less invasive, does not require sedation and has less potential 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, Crohn's disease and hemorrhages. Nevertheless, WCE videos can contain thousands of images per patient that must be screened by medical specialists, besides, the capsule free mobility and technological limits cause production of a low quality images. In this paper, a Nouvel method based on Dense-UNet deep learning segmentation model is presented. This approach aims at red lesion, ulcer and polyp detection from WCE images. Then, we propose a modified residual attention network for images classification. The proposed methods training and validation accuracies are 97.57% and 92.70%, with training and validation intersection over union and dice coefficients of 75.31%, 71.29%, 83.50% and 80.66%, respectively, in the red lesion dataset. In the polyp dataset, the method achieved a training and validation accuracies of 98.26% and 92.33%, with training and validation intersection over union and dice coefficients of 92.09%, 95.62%, 80.13% and 87.14%, respectively. Besides, the proposed architecture reached an average accuracy of 99.30%, sensitivity, specificity and F1 score of 98.61%, 100% and 99.30%, respectively. These results demonstrate that the proposed approach is satisfactory in polyp and red lesion segmentation and ulcer detection. [ABSTRACT FROM AUTHOR]

Colorectal cancer is one of the leading causes of cancer death worldwide. It can appear in different forms depending on its location, and in most cases, these are tumors called polyps. A diagnostic model which is built can aid doctors but can not replace them. Thus, automated diagnostic technics to detect symptoms of illness or abnormalities in video colonoscopy or wireless capsule endoscopy (WCE) are adopted as an excellent enhancement technique for doctors. In this work, a new computer-assisted diagnosis method for polyp detection is proposed. After a preprocessing step, a fusion of two deep neural networks (DNNs), which were pre-trained on millions of labeled natural images (ImageNet), are fine-tuned and used to extract deep features to perform the polyp detection. The fine-tuning is employed using the Kvasir-seg dataset images. Moreover, the weights of the initial layers of the networks used in this work are frozen. Finally, we concatenated the fully connected outputs of the fine-tuned models to perform the binary classification. The proposed method achieved 0.919, 0.897, and 0.907 on the CVC-ClinicDB dataset, and 0.876, 0.910, and 0.893 on the ETIS-LaribPolypDB dataset in terms of precision, recall, and F-measure metrics, respectively. The results obtained are satisfactory when compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Skin cancer is considered one of the most dangerous and popular sorts of cancer. The deadliest form of this type of cancer is called melanoma, it happens while pigmented cells named melanocytes begin to subdivide tensely. If early detected melanoma could be easily and accurately healed. Hence, immediate diagnosis of this kind of skin cancer is crucial. Currently, dermoscopy has become one of the most efficient tools utilized in pigmented skin lesions diagnosis. Due to the expense of processing each patient by dermatologists, a computerized recognition system is highly required to evaluate every patient's state. This paper aims to automatize the process of classifying dermoscopic images containing skin lesions into benign or malignant. Therefore an improved deep learning-based solution with a convolutional neural network is proposed. Regularization, dropout, and data augmentation are used to avoid the CNN model over-fitting. The proposed method has been tested on three different publicly available datasets and the obtained results demonstrate its effectiveness when compared to the state-of-the-art methods. Thus, the proposed framework can be adopted for assisting dermatologists with melanoma diagnosis. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy (WCE) is a device that can move through human body and capture the small bowel entirely. Thus, it is presented as an excellent diagnostic tool for evaluation of gastrointestinal diseases compared with traditional endoscopies. However, the diagnosis by the physicians is tedious since it requires reviewing the video extracted from the capsule and analysing all of its frames. This tedious task has fuelled the efforts of researchers to provide automated diagnostic techniques for WCE frameworks to detect symptoms of gastrointestinal illness. In this paper, a new computer-aided diagnosis method for abnormalities detection in WCE images is proposed. After a preprocessing step, we extract from these images the descriptor we feed to a kernel extreme learning machine to perform the classification process. The descriptor used in this work is a combination between the histogram of oriented gradients (HOG) that were extracted using the hue component of the HSV colour space, and a modified rotation-invariant local binary pattern. The proposed approach has been tested on different datasets, and the results obtained are satisfactory when compared to the state-of-the-art works. [ABSTRACT FROM AUTHOR]

Activation function unit is an extremely important part of convolution neural networks; it is the nonlinear transformation that we do over the input data. Using hidden layer incorporating with a well-chosen activation function improves both the accuracy and the CNN convergence speed. This paper proposes a parametric rectified nonlinear function unit (PRenu). The proposed activation function is nearly similar to Relu. It returns x - α log (x + 1) for positive values (α is between 0 and 1) and zero for negative parts. In contrast to Relu that returns the same received gradient for all positive values in its back-propagation, the PRenu multiplies it by values between 1 - α and 1 depending on the value with which each neuron was involved. The PRenu has been tested on three datasets: CIFAR-10, CIFAR-100 and Oxflower17, and compared to the activation function Relu. The experimental results show that using the proposed activation function PRenu, the CNN convergence is faster and the accuracy is also improved. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy (WCE) is a novel imaging technique that can view the entire small bowel in human body. Therefore, it has been gradually adopted compared with traditional endoscopies for gastrointestinal diseases. However, the task of reviewing the vast amount of images produced by a WCE test is exhaustive for the physicians. This paper presents a new feature extraction scheme for pathological inflammation and ulcer regions discrimination in WCE images. In addition, the novel approach is adopted for polyp recognition in colonoscopy videos. A novel idea based on extracting certain local features from the image is proposed. Then, the occurrence histogram of these features is used as descriptor of the image. The new feature descriptor scheme is grayscale rotation invariant and computationally simple as the operator can be realized with a few operations in a small neighborhood. The proposed operator does not discard the contrast information. Besides, we propose to test the quality of the model using logarithmic loss metric and show how calibration can be useful in reducing the aforementioned measure. Extensive classification experiments have been applied on different datasets, which prove that the occurrence histogram of the extracted features is powerful. The proposed method achieved 99.1%, 99.7% and 99.2% in terms of the precision in the first, second and third datasets, respectively, and surpassed some known local descriptors on a texture dataset. [ABSTRACT FROM AUTHOR]

Wireless capsule endoscopy (WCE) is a novel imaging technique that can travel through human body and image the small bowel entirely. Therefore, it has been gradually adopted compared with traditional endoscopies for gastrointestinal diseases. However, the big number of the produced images by a WCE test makes their review exhaustive for the physicians. It is helpful for clinicians if we can develop a computer-aided diagnosis system for the task of identifying the images with potential problems. The aim of this paper is to automatize the process of WCE images abnormalities detection by presenting a new texture extraction scheme for pathological inflammation, polyp, and bleeding regions discrimination in WCE images. A new approach based on local binary pattern variance and discrete wavelet transform is proposed. The new textural features scheme has many advantages, e.g., it detects multi-directional characteristics and overcomes the illuminations changes in WCE images. Intensive experiments are conducted on two datasets constructed from several WCE exams. The promising results make the presented method suitable for abnormalities detection in WCE images. [ABSTRACT FROM AUTHOR]