No abstract

No abstract

No abstract

No abstract

the retention of a capsule endoscope (ce) in the stomach and the duodenal bulb during the examination is a troublesome problem, which can make the medical staff spend several hours observing whether the ce enters the descending segment of the duodenum (DSD). this paper investigated and evaluated the convolution neural network (cnn) for automatic retention-monitoring of the ce in the stomach or the duodenal bulb. A trained CNN system based on 180,000 CE images of the DSD, stomach, and duodenal bulb was used to assess its recognition of the accuracy by calculating the area under the receiver operating characteristic curve (ROC-AUC), sensitivity and specificity. The AUC for distinguishing the DSD was 0.984. The sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 97.8%, 96.0%, 96.1% and 97.8%, respectively, at a cut-off value of 0.42 for the probability score. the deviated rate of the time into the DSD marked by the cnn at less than ±8 min was 95.7% (P < 0.01). these results indicate that the cnn for automatic retention-monitoring of the ce in the stomach or the duodenal bulb can be used as an efficient auxiliary measure in the clinical practice.Capsule endoscope (CE) has become one of the best diagnostic tools for diagnosing small intestinal diseases because of its painless and non-invasive nature 1-4 , but it has some weaknesses. One of these is that after the CE is swallowed, its movement in the digestive tract is completely dependent on gastrointestinal motility, especially the gastroduodenal emptying velocity. If the gastroduodenal emptying velocity is too slow, the CE can become stagnated in the stomach or duodenal bulb for several hours, which can cause energy loss of the built-in battery. Thus, examination of the whole small intestine may not be finished. How to predict the residence time of the CE in the stomach or duodenal bulb has not been solved, and medical staff may have to wait for several hours in the examination room to monitor whether the CE enters the descending segment of the duodenum (DSD) 5,6 . If the CE cannot enter the DSD in 2-3 h, some interventions, e.g., drugs or gastroscopy, can be used to push the CE forward into the DSD 7 , which is a tedious and boring task, especially for some patients who have to undergo the CE examination at the same time, which could greatly increase the monitoring workload for the medical staff.Artificial intelligence (AI), as a new technique, has been developed in the recent years, which includes Autoencoder 8 , Deep Belief Network 9 , Convolution Neural Network (CNN) 10 , and Deep Residual Network 11 , and they have been used in the medical image analysis and have been proved to be effective in some medical diagnostic fields, such as pulmonary nodules 12 , breast lesions 13,14 , skin cancer 15 , early gastrointestinal cancers 16,17 , polyps 18 , and small-bowel diseases [19][20][21][22][23] .Of those techniques, the CNN 24 is a type of deep learning mode 25-27 that requires the preprocessing of the image data inputt...

Ancylostomiasis is a fairly common small bowel parasite disease identified by capsule endoscopy (CE) for which a computer-aided clinical detection method has not been established. We sought to develop an artificial intelligence system with a convolutional neural network (CNN) to automatically detect hookworms in CE images. We trained a deep CNN system based on a YOLO-V4 (You Look Only Once-Version4) detector using 11236 CE images of hookworms. We assessed its performance by calculating the area under the receiver operating characteristic curve and its sensitivity, specificity, and accuracy using an independent test set of 10,529 small-bowel images including 531 images of hookworms. The trained CNN system required 403 seconds to evaluate 10,529 test images. The area under the curve for the detection of hookworms was 0.972 (95% confidence interval (CI), 0.967-0.978). The sensitivity, specificity, and accuracy of the CNN system were 92.2%, 91.1%, and 91.2%, respectively, at a probability score cut-off of 0.485. We developed and validated a CNN-based system for detecting hookworms in CE images. By combining this high-accuracy, high-speed, and oversight-preventing system with other CNN systems, we hope it will become an important supplement for detecting intestinal abnormalities in CE images. This trial is registered with ChiCTR2000034546 (a clinical research of artificial-intelligence-aided diagnosis for hookworms in small intestine by capsule endoscope images).

In this paper, we introduce a new framework for unsupervised deep homography estimation. Our contributions are 3 folds. First, unlike previous methods that regress 4 offsets for a homography, we propose a homography flow representation, which can be estimated by a weighted sum of 8 pre-defined homography flow bases. Second, considering a homography contains 8 Degree-of-Freedoms (DOFs) that is much less than the rank of the network features, we propose a Low Rank Representation (LRR) block that reduces the feature rank, so that features corresponding to the dominant motions are retained while others are rejected. Last, we propose a Feature Identity Loss (FIL) to enforce the learned image feature warp-equivariant, meaning that the result should be identical if the order of warp operation and feature extraction is swapped. With this constraint, the unsupervised optimization is achieved more effectively and more stable features are learned. Extensive experiments are conducted to demonstrate the effectiveness of all the newly proposed components, and results show our approach outperforms the state-of-the-art on the homography benchmark datasets both qualitatively and quantitatively.

Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. However, pre-trained models are hard to obtain in real-world tasks. In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data. To achieve this, DaST utilizes specially designed generative adversarial networks (GANs) to train the substitute models. In particular, we design a multi-branch architecture and label-control loss for the generative model to deal with the uneven distribution of synthetic samples. The substitute model is then trained by the synthetic samples generated by the generative model, which are labeled by the attacked model subsequently. The experiments demonstrate the substitute models produced by DaST can achieve competitive performance compared with the baseline models which are trained by the same train set with attacked models. Additionally, to evaluate the practicability of the proposed method on the real-world task, we attack an online machine learning model on the Microsoft Azure platform. The remote model misclassifies 98.35% of the adversarial examples crafted by our method. To the best of our knowledge, we are the first to train a substitute model for adversarial attacks without any real data. Our codes are publicly available 1 .