scholarly journals A method for improving semantic segmentation using thermographic images in infants

2022 ◽  
Vol 22 (1) ◽  
Author(s):  
Hidetsugu Asano ◽  
Eiji Hirakawa ◽  
Hayato Hayashi ◽  
Keisuke Hamada ◽  
Yuto Asayama ◽  
...  
Keyword(s):  
Temperature Distribution ◽  
Semantic Segmentation ◽  
The Body ◽  
Whole Body ◽  
Clinical Settings ◽  
Generative Adversarial Network ◽  
Thermal Images ◽  
Adversarial Network ◽  
Manual Selection ◽  
Peripheral Temperature

Abstract Background Regulation of temperature is clinically important in the care of neonates because it has a significant impact on prognosis. Although probes that make contact with the skin are widely used to monitor temperature and provide spot central and peripheral temperature information, they do not provide details of the temperature distribution around the body. Although it is possible to obtain detailed temperature distributions using multiple probes, this is not clinically practical. Thermographic techniques have been reported for measurement of temperature distribution in infants. However, as these methods require manual selection of the regions of interest (ROIs), they are not suitable for introduction into clinical settings in hospitals. Here, we describe a method for segmentation of thermal images that enables continuous quantitative contactless monitoring of the temperature distribution over the whole body of neonates. Methods The semantic segmentation method, U-Net, was applied to thermal images of infants. The optimal combination of Weight Normalization, Group Normalization, and Flexible Rectified Linear Unit (FReLU) was evaluated. U-Net Generative Adversarial Network (U-Net GAN) was applied to thermal images, and a Self-Attention (SA) module was finally applied to U-Net GAN (U-Net GAN + SA) to improve precision. The semantic segmentation performance of these methods was evaluated. Results The optimal semantic segmentation performance was obtained with application of FReLU and Group Normalization to U-Net, showing accuracy of 92.9% and Mean Intersection over Union (mIoU) of 64.5%. U-Net GAN improved the performance, yielding accuracy of 93.3% and mIoU of 66.9%, and U-Net GAN + SA showed further improvement with accuracy of 93.5% and mIoU of 70.4%. Conclusions FReLU and Group Normalization are appropriate semantic segmentation methods for application to neonatal thermal images. U-Net GAN and U-Net GAN + SA significantly improved the mIoU of segmentation.

scholarly journals Improving Road Semantic Segmentation Using Generative Adversarial Network

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 64381-64392
Author(s):  
Abolfazl Abdollahi ◽  
Biswajeet Pradhan ◽  
Gaurav Sharma ◽  
Khairul Nizam Abdul Maulud ◽  
Abdullah Alamri
Keyword(s):  
Semantic Segmentation ◽  
Generative Adversarial Network ◽  
Adversarial Network

FISS GAN: A Generative Adversarial Network for Foggy Image Semantic Segmentation

2021 ◽  
Vol 8 (8) ◽  
pp. 1428-1439
Author(s):  
Kunhua Liu ◽  
Zihao Ye ◽  
Hongyan Guo ◽  
Dongpu Cao ◽  
Long Chen ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Generative Adversarial Network ◽  
Adversarial Network

scholarly journals Semantic Segmentation of White Matter in FDG-PET Using Generative Adversarial Network

2020 ◽  
Vol 33 (4) ◽  
pp. 816-825
Author(s):  
Kyeong Taek Oh ◽  
Sangwon Lee ◽  
Haeun Lee ◽  
Mijin Yun ◽  
Sun K. Yoo
Keyword(s):  
White Matter ◽  
Fdg Pet ◽  
Semantic Segmentation ◽  
Generative Adversarial Network ◽  
Adversarial Network

scholarly journals Separating Chinese Character from Noisy Background Using GAN

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Bin Huang ◽  
Jiaqi Lin ◽  
Jinming Liu ◽  
Jie Chen ◽  
Jiemin Zhang ◽  
...  
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Complex Structure ◽  
Real Data ◽  
Semantic Segmentation ◽  
Chinese Characters ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Basic Network ◽  
Noisy Background

Separating printed or handwritten characters from a noisy background is valuable for many applications including test paper autoscoring. The complex structure of Chinese characters makes it difficult to obtain the goal because of easy loss of fine details and overall structure in reconstructed characters. This paper proposes a method for separating Chinese characters based on generative adversarial network (GAN). We used ESRGAN as the basic network structure and applied dilated convolution and a novel loss function that improve the quality of reconstructed characters. Four popular Chinese fonts (Hei, Song, Kai, and Imitation Song) on real data collection were tested, and the proposed design was compared with other semantic segmentation approaches. The experimental results showed that the proposed method effectively separates Chinese characters from noisy background. In particular, our methods achieve better results in terms of Intersection over Union (IoU) and optical character recognition (OCR) accuracy.

scholarly journals Semantic Segmentation of Remote Sensing Image Based on GAN and FCN Network Model

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Liang Tian ◽  
Xiaorou Zhong ◽  
Ming Chen
Keyword(s):  
Remote Sensing ◽  
High Efficiency ◽  
Semantic Segmentation ◽  
Remote Sensing Image ◽  
Image Feature ◽  
Generative Adversarial Network ◽  
Current Image ◽  
Adversarial Network ◽  
Complex Image ◽  
Segmentation Methods

Accurate remote sensing image segmentation can guide human activities well, but current image semantic segmentation methods cannot meet the high-precision semantic recognition requirements of complex images. In order to further improve the accuracy of remote sensing image semantic segmentation, this paper proposes a new image semantic segmentation method based on Generative Adversarial Network (GAN) and Fully Convolutional Neural Network (FCN). This method constructs a deep semantic segmentation network based on FCN, which can enhance the receptive field of the model. GAN is integrated into FCN semantic segmentation network to synthesize the global image feature information and then accurately segment the complex remote sensing image. Through experiments on a variety of datasets, it can be seen that the proposed method can meet the high-efficiency requirements of complex image semantic segmentation and has good semantic segmentation capabilities.

Computer-Aided Analysis of Transient and Steady State Temperature Distribution in Human Brain During Selective Cooling of Head Surface and Rewarming for Head Injury Patients

2002 ◽  
Author(s):  
Liang Zhu ◽  
Chenguang Diao
Keyword(s):  
Steady State ◽  
Temperature Distribution ◽  
Brain Temperature ◽  
The Body ◽  
Whole Body ◽  
Surface Cooling ◽  
Steady State Temperature ◽  
Head Surface ◽  
The Brain ◽  
Transient And Steady State

In recent years, mild or moderate hypothermia during which brain temperature is reduced to 30–35°C has been proposed for clinical use as an adjunct for achieving protection from cerebral ischemia and traumatic brain injury. There are two approaches for achieving a reduction in brain temperature. One is via systemic hypothermia where the whole body is cooled. This approach may produce deleterious systemic complications and require intensive monitoring. Another approach is called selective brain cooling (SBC) in which the brain is selectively cooled while the rest of the body is kept at normal temperature. Clinically feasible SBC protocols include head hood or helmet with water or chemical cooling, head immersion in iced water, nasophyaryngeal cooling after tracheal intubation, and intro-carotid flushing. Simply packing ice or wearing cooling helmet is easy to implement. Previous theoretical study [Zhu and Diao, 2001] suggests that it is feasible to achieve mild hypothermia via head surface cooling. However, most physicians believe that it takes a much longer time to reduce the brain temperature using head surface cooling. In this study, a three-dimensional theoretical model is developed to study the transient and steady state temperature distribution in the brain during SBC. The effect of regionally varying local blood perfusion rate in the brain tissue on the temporal and spatial temperature gradient is examined. Other factors including the brain size and the thermal contact resistance between the cooling medium and the head scalp are evaluated in the simulation.

Semi-supervised semantic segmentation using an improved generative adversarial network

2021 ◽  
pp. 1-11
Author(s):  
Di Xu ◽  
Zhili Wang
Keyword(s):  
Semantic Segmentation ◽  
The Other ◽  
Dynamic Threshold ◽  
Generative Adversarial Network ◽  
Probability Map ◽  
Adversarial Network ◽  
Pascal Voc ◽  
Predicted Probability

This paper proposes a better semi-supervised semantic segmentation network using an improved generative adversarial network. It is important for the discriminator on the pixel level to know whether it correctly distinguishes the predicted probability map. However, currently there is no correlation between the actual credibility and the confidence map generated by the pixel-level discriminator. We study this problem and a new network is proposed, which includes one generator and two discriminators. One of the discriminators can output more reliable confidence maps on the pixel level and the other is trained to generate the probability on the image level, which is used as the dynamic threshold in the semi-supervised module instead of being set manually. In addition, the trusted region shared by the two discriminators is used to provide the semi-supervised reference. Through experiments on the PASCAL VOC 2012 and Cityscapes datasets, the proposed network brings better gains, proving the effectiveness of the network.

scholarly journals Generative Learning for Postprocessing Semantic Segmentation Predictions: A Lightweight Conditional Generative Adversarial Network Based on Pix2pix to Improve the Extraction of Road Surface Areas

Land ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 79
Author(s):  
Calimanut-Ionut Cira ◽  
Miguel-Ángel Manso-Callejo ◽  
Ramón Alcarria ◽  
Teresa Fernández Pareja ◽  
Borja Bordel Sánchez ◽  
...  
Keyword(s):  
Semantic Segmentation ◽  
Road Surface ◽  
Complex Nature ◽  
Generative Learning ◽  
Generative Adversarial Network ◽  
Maximum Increase ◽  
Qualitative Comparison ◽  
The Road ◽  
Surface Areas ◽  
Adversarial Network

Remote sensing experts have been actively using deep neural networks to solve extraction tasks in high-resolution aerial imagery by means of supervised semantic segmentation operations. However, the extraction operation is imperfect, due to the complex nature of geospatial objects, limitations of sensing resolution, or occlusions present in the scenes. In this work, we tackle the challenge of postprocessing semantic segmentation predictions of road surface areas obtained with a state-of-the-art segmentation model and present a technique based on generative learning and image-to-image translations concepts to improve these initial segmentation predictions. The proposed model is a conditional Generative Adversarial Network based on Pix2pix, heavily modified for computational efficiency (92.4% decrease in the number of parameters in the generator network and 61.3% decrease in the discriminator network). The model is trained to learn the distribution of the road network present in official cartography, using a novel dataset containing 6784 tiles of 256 × 256 pixels in size, covering representative areas of Spain. Afterwards, we conduct a metrical comparison using the Intersection over Union (IoU) score (measuring the ratio between the overlap and union areas) on a novel testing set containing 1696 tiles (unseen during training) and observe a maximum increase of 11.6% in the IoU score (from 0.6726 to 0.7515). In the end, we conduct a qualitative comparison to visually assess the effectiveness of the technique and observe great improvements with respect to the initial semantic segmentation predictions.

Sign in / Sign up

Export Citation Format

Share Document