scholarly journals Magnetic Resonance Imaging Feature Analysis and Evaluation of Tubal Patency under Convolutional Neural Network in the Diagnosis of Infertility

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Na Liu ◽  
Qingling Ren
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Clinical Diagnosis ◽  
Fallopian Tube ◽  
The Other ◽  
Reconstruction Method ◽  
Inspection Method ◽  
Reconstruction Methods ◽  
Imaging Results ◽  
Imaging Artifacts

To explore the diagnostic value of MRI image features based on convolutional neural network for tubal unobstructed infertility, 30 infertile female patients were first selected as the research objects, who admitted to the hospital from May 2018 to January 2020. They all underwent routine MRI examinations and CNN-based MR-hysteron-salpingography (HSG) examinations, in order to discuss the diagnostic accuracy of the two examinations. In the research, it was necessary to observe the patients’ imaging results, calculate the diagnosis rate of the two examination results, and analyze the application effect of the CNN algorithm, thereby selecting the best reconstruction method. In this study, the analysis was conducted on the basis of no statistical difference in the baseline data of the included patients. The results of undersampling reconstruction at 2-fold, 4-fold, and 6-fold showed that CNN for data consistency layer (CNN_DC) had a better effect, and its peak signal-to-noise ratio (PSNR) was lower sharply than that of the other two reconstruction methods, while the normalized mean square error (NMSE) and structural similarity index measure (SSIM) were higher markedly than the values of the other two reconstruction methods. The diagnostic rate of routine MRI examination of the fallopian tube and other parts of the uterus was lower than or equal to that of MR-HSG examination by CNN. Routine MRI examinations of fallopian tube imaging artifacts were large, and the definition was reduced, which increased the difficulty of identification. However, MR-HSG examination by CNN indicated that the imaging artifacts were low, the clarity was high, and the influence of noise was small, which was conducive to clinical diagnosis and identification. For endometriosis, the accuracy of MR-HSG was 33.33% and the accuracy of MRI was 46.67%. CNN MR-HSG inspection method was significantly better than the conventional MRI inspection method P < 0.05 . Therefore, the results of this study revealed that MR-HSG examination by CNN had a clear imaging effect and obvious inhibition effect on background signals and rapid image generation without the need for reconstruction with the same spatial resolution, which improved the imaging quality and could provide a reference value for clinical diagnosis and subsequent related studies.

scholarly journals Distinguishing Felsenstein zone from Farris zone using neural networks

2019 ◽  
Author(s):  
Tamara Drucks ◽  
Alina F. Leuchtenberger ◽  
Sebastian Burgstaller-Muehlbacher ◽  
Stephen M. Crotty ◽  
Heiko A. Schmidt ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Maximum Likelihood ◽  
Maximum Parsimony ◽  
The Other ◽  
Reconstruction Method ◽  
Long Branch Attraction ◽  
Tree Reconstruction ◽  
Reconstruction Methods ◽  
The Neural Network

AbstractMaximum likelihood and maximum parsimony are two key methods for phylogenetic tree reconstruction. Under certain conditions, each of these two methods can perform more or less efficiently than the other. We show that a neural network can efficiently distinguish between four-taxon alignments that were evolved under conditions conducive to long-branch attraction, or long-branch repulsion. The feedback from the neural network can be used to select the most efficient tree reconstruction method yielding increased accuracy, when compared to a rigid choice of reconstruction methods. When applied to the contentious case of Strepsiptera evolution, our method agrees with the current scientific view.

Image-Based Comprehensive Maintenance and Inspection Method for Bridges Using Deep Learning

2018 ◽  
Author(s):  
Xuefeng Zhao ◽  
Shengyuan Li ◽  
Hongguo Su ◽  
Lei Zhou ◽  
Kenneth J. Loh
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Visual Inspection ◽  
Health State ◽  
Bridge Management ◽  
Inspection Method ◽  
Maintenance Work ◽  
Maintenance And Inspection ◽  
Fine Turning

Bridge management and maintenance work is an important part for the assessment the health state of bridge. The conventional management and maintenance work mainly relied on experienced engineering staffs by visual inspection and filling in survey forms. However, the human-based visual inspection is a difficult and time-consuming task and its detection results significantly rely on subjective judgement of human inspectors. To address the drawbacks of human-based visual inspection method, this paper proposes an image-based comprehensive maintenance and inspection method for bridges using deep learning. To classify the types of bridges, a convolutional neural network (CNN) classifier established by fine-turning the AlexNet is trained, validated and tested using 3832 images with three types of bridges (arch, suspension and cable-stayed bridge). For the recognition of bridge components (tower and deck of bridges), a Faster Region-based Convolutional Neural Network (Faster R-CNN) based on modified ZF-net is trained, validated and tested by utilizing 600 bridge images. To implement the strategy of a sliding window technique for the crack detection, another CNN from fine-turning the GoogLeNet is trained, validated and tested by employing a databank with cropping 1455 raw concrete images into 60000 intact and cracked images. The performance of the trained CNNs and Faster R-CNN is tested on some new images which are not used for training and validation processes. The test results substantiate the proposed method can indeed recognize the types and components and detect cracks for a bridges.

scholarly journals 3D particle field reconstruction method based on convolutional neural network for SAPIV

2019 ◽  
Vol 27 (8) ◽  
pp. 11413 ◽  
Author(s):  
Xiangju Qu ◽  
Yang Song ◽  
Ying Jin ◽  
Zhenyan Guo ◽  
Zhenhua Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Reconstruction Method ◽  
Particle Field ◽  
Field Reconstruction

scholarly journals Superresolution Reconstruction of Video Based on Efficient Subpixel Convolutional Neural Network for Urban Computing

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Jie Shen ◽  
Mengxi Xu ◽  
Xinyu Du ◽  
Yunbo Xiong
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Optical Flow ◽  
Video Surveillance ◽  
Reconstruction Method ◽  
Motion Information ◽  
Learning Networks ◽  
Urban Computing ◽  
Deep Convolution Network

Video surveillance is an important data source of urban computing and intelligence. The low resolution of many existing video surveillance devices affects the efficiency of urban computing and intelligence. Therefore, improving the resolution of video surveillance is one of the important tasks of urban computing and intelligence. In this paper, the resolution of video is improved by superresolution reconstruction based on a learning method. Different from the superresolution reconstruction of static images, the superresolution reconstruction of video is characterized by the application of motion information. However, there are few studies in this area so far. Aimed at fully exploring motion information to improve the superresolution of video, this paper proposes a superresolution reconstruction method based on an efficient subpixel convolutional neural network, where the optical flow is introduced in the deep learning network. Fusing the optical flow features between successive frames can compensate for information in frames and generate high-quality superresolution results. In addition, in order to improve the superresolution, a superpixel convolution layer is added after the deep convolution network. Finally, experimental evaluations demonstrate the satisfying performance of our method compared with previous methods and other deep learning networks; our method is more efficient.

scholarly journals Multidimensional Face Representation in a Deep Convolutional Neural Network Reveals the Mechanism Underlying AI Racism

2021 ◽  
Vol 15 ◽  
Author(s):  
Jinhua Tian ◽  
Hailun Xie ◽  
Siyuan Hu ◽  
Jia Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Underlying Mechanism ◽  
Deep Convolutional Neural Network ◽  
The Other ◽  
Training Data ◽  
Identification Accuracy ◽  
Social Bias ◽  
Novel Approach ◽  
Ai Ethics

The increasingly popular application of AI runs the risk of amplifying social bias, such as classifying non-white faces as animals. Recent research has largely attributed this bias to the training data implemented. However, the underlying mechanism is poorly understood; therefore, strategies to rectify the bias are unresolved. Here, we examined a typical deep convolutional neural network (DCNN), VGG-Face, which was trained with a face dataset consisting of more white faces than black and Asian faces. The transfer learning result showed significantly better performance in identifying white faces, similar to the well-known social bias in humans, the other-race effect (ORE). To test whether the effect resulted from the imbalance of face images, we retrained the VGG-Face with a dataset containing more Asian faces, and found a reverse ORE that the newly-trained VGG-Face preferred Asian faces over white faces in identification accuracy. Additionally, when the number of Asian faces and white faces were matched in the dataset, the DCNN did not show any bias. To further examine how imbalanced image input led to the ORE, we performed a representational similarity analysis on VGG-Face's activation. We found that when the dataset contained more white faces, the representation of white faces was more distinct, indexed by smaller in-group similarity and larger representational Euclidean distance. That is, white faces were scattered more sparsely in the representational face space of the VGG-Face than the other faces. Importantly, the distinctiveness of faces was positively correlated with identification accuracy, which explained the ORE observed in the VGG-Face. In summary, our study revealed the mechanism underlying the ORE in DCNNs, which provides a novel approach to studying AI ethics. In addition, the face multidimensional representation theory discovered in humans was also applicable to DCNNs, advocating for future studies to apply more cognitive theories to understand DCNNs' behavior.

Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure

2020 ◽  
pp. 147592172096544
Author(s):  
Aravinda S Rao ◽  
Tuan Nguyen ◽  
Marimuthu Palaniswami ◽  
Tuan Ngo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Detection ◽  
Concrete Structures ◽  
Area Under The Curve ◽  
Network Models ◽  
Condition Assessment ◽  
Neural Network Models ◽  
Data Set ◽  
Inspection Method

With the growing number of aging infrastructure across the world, there is a high demand for a more effective inspection method to assess its conditions. Routine assessment of structural conditions is a necessity to ensure the safety and operation of critical infrastructure. However, the current practice to detect structural damages, such as cracks, depends on human visual observation methods, which are prone to efficiency, cost, and safety concerns. In this article, we present an automated detection method, which is based on convolutional neural network models and a non-overlapping window-based approach, to detect crack/non-crack conditions of concrete structures from images. To this end, we construct a data set of crack/non-crack concrete structures, comprising 32,704 training patches, 2074 validation patches, and 6032 test patches. We evaluate the performance of our approach using 15 state-of-the-art convolutional neural network models in terms of number of parameters required to train the models, area under the curve, and inference time. Our approach provides over 95% accuracy and over 87% precision in detecting the cracks for most of the convolutional neural network models. We also show that our approach outperforms existing models in literature in terms of accuracy and inference time. The best performance in terms of area under the curve was achieved by visual geometry group-16 model (area under the curve = 0.9805) and best inference time was provided by AlexNet (0.32 s per image in size of 256 × 256 × 3). Our evaluation shows that deeper convolutional neural network models have higher detection accuracies; however, they also require more parameters and have higher inference time. We believe that this study would act as a benchmark for real-time, automated crack detection for condition assessment of infrastructure.

scholarly journals Super-resolution reconstruction of seismic section image via multi-scale convolution neural network

2021 ◽  
Vol 303 ◽  
pp. 01058
Author(s):  
Meng-Di Deng ◽  
Rui-Sheng Jia ◽  
Hong-Mei Sun ◽  
Xing-Li Zhang
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Convolutional Neural Network ◽  
Super Resolution ◽  
Image Features ◽  
Image Feature ◽  
Reconstruction Method ◽  
Low Resolution ◽  
Seismic Section ◽  
Multi Scale

The resolution of seismic section images can directly affect the subsequent interpretation of seismic data. In order to improve the spatial resolution of low-resolution seismic section images, a super-resolution reconstruction method based on multi-scale convolution is proposed. This method designs a multi-scale convolutional neural network to learn high-low resolution image feature pairs, and realizes mapping learning from low-resolution seismic section images to high-resolution seismic section images. This multi-scale convolutional neural network model consists of four convolutional layers and a sub-pixel convolutional layer. Convolution operations are used to learn abundant seismic section image features, and sub-pixel convolution layer is used to reconstruct high-resolution seismic section image. The experimental results show that the proposed method is superior to the comparison method in peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the total training time and reconstruction time, our method is about 22% less than the FSRCNN method and about 18% less than the ESPCN method.

Sign in / Sign up

Export Citation Format

Share Document