A feature-based affine registration method for capturing background lung tissue deformation for ground glass nodule tracking

Author(s):  
Yehuda K. Ben-Zikri ◽  
María Helguera ◽  
David Fetzer ◽  
David A. Shrier ◽  
Stephen. R. Aylward ◽  
...  
Author(s):  
Yehuda Kfir Ben Zikri ◽  
María Helguera ◽  
Nathan D. Cahill ◽  
David Shrier ◽  
Cristian A. Linte

2012 ◽  
Vol 27 (1) ◽  
pp. W15-W17 ◽  
Author(s):  
Gilbert R. Ferretti ◽  
François Arbib ◽  
Jean François Roux ◽  
Vincent Bland ◽  
Sylvie Lantuejoul

2021 ◽  
Vol 11 (Suppl_1) ◽  
pp. S25-S26
Author(s):  
Valeriy Kartashev ◽  
Djamshid Mardonov ◽  
Bahshillo Mamirov ◽  
Azamat Butaev

Background: The main causes of death from Covid-19 are lung lesions with the development of respiratory failure. However, structural changes in the lung tissue in this pathology are poorly studied. We examined autopsy material from patients with Covid-19. The severe condition of patients, the manifestation of pulmonary symptoms of damage (cough, dyspnea) and the high probability of viral pneumonia at COVID-19 led to the widespread use of CT diagnostics in this group of patients, which allowed to identify of the primary signs of the disease, their subsequent transformation as well as the most adverse radiation symptoms corresponding to the severe course of the process (Speranskaya, 2020; Pan et al., 2019). In the cases studied by us, the detection of typical symptoms revealed by radiation diagnostics of COVID-19 was subsequently confirmed by PCR data, which may indicate a high information content and specificity of detecting CT symptoms of a lesion as a method of primary diagnostics. The aim of our study is to confirm at the microscopic level the correspondence of MSCT changes. Methods: The material was taken at autopsy of deceased patients, fixed in 10% formalin solution in phosphate buffer, paraffin sections were stained with hematoxylin and eosin. The autopsy material was examined using a Carl Zeiss light microscope, Axioskop 40. Results: Studies have shown that most of the alveoli of the lung tissue kept their airiness. However, their lumens were significantly reduced due to a significant thickening of the interalveolar septa caused by pronounced inflammatory infiltration mainly by lymphocytes. The most significant changes were revealed from the side of the microvasculature. There are numerous blood clots of various sizes in the lumen of most micro-vessels. The walls of microvessels have been significantly thickened with pronounced inflammatory infiltration and significant edema. The lumens of microvessels have been characterized by significant polymorphism. Intraluminal clots have been also characterized by pronounced polymorphism. The parietal pleura has been thickened. This has been reflected in the MSCT images and corresponds to the processes of perivascular infiltration. Conclusion: The primary CT pattern of COVID-19 is a picture of infiltration of individual secondary pulmonary lobules of the "ground glass" type, followed by a decrease in the lesion volume at a favorable course of the disease, or their increase, the addition of a CT picture of a "cobblestone pavement" and the appearance of alveolar infiltration in the area of "ground glass" at the unfavorable course of the disease.


2021 ◽  
Vol 13 (17) ◽  
pp. 3425
Author(s):  
Xin Zhao ◽  
Hui Li ◽  
Ping Wang ◽  
Linhai Jing

Accurate registration for multisource high-resolution remote sensing images is an essential step for various remote sensing applications. Due to the complexity of the feature and texture information of high-resolution remote sensing images, especially for images covering earthquake disasters, feature-based image registration methods need a more helpful feature descriptor to improve the accuracy. However, traditional image registration methods that only use local features at low levels have difficulty representing the features of the matching points. To improve the accuracy of matching features for multisource high-resolution remote sensing images, an image registration method based on a deep residual network (ResNet) and scale-invariant feature transform (SIFT) was proposed. It used the fusion of SIFT features and ResNet features on the basis of the traditional algorithm to achieve image registration. The proposed method consists of two parts: model construction and training and image registration using a combination of SIFT and ResNet34 features. First, a registration sample set constructed from high-resolution satellite remote sensing images was used to fine-tune the network to obtain the ResNet model. Then, for the image to be registered, the Shi_Tomas algorithm and the combination of SIFT and ResNet features were used for feature extraction to complete the image registration. Considering the difference in image sizes and scenes, five pairs of images were used to conduct experiments to verify the effectiveness of the method in different practical applications. The experimental results showed that the proposed method can achieve higher accuracies and more tie points than traditional feature-based methods.


2021 ◽  
Vol 0 (0) ◽  
pp. 0-0
Author(s):  
Feichao Bao ◽  
Fenghao Yu ◽  
Rui Wang ◽  
Chunji Chen ◽  
Yonghui Zhang ◽  
...  

2019 ◽  
Vol 19 (24) ◽  
pp. 12333-12345
Author(s):  
Wenpeng Zong ◽  
Minglei Li ◽  
Yanglin Zhou ◽  
Li Wang ◽  
Fengzhuo Xiang ◽  
...  

2019 ◽  
Vol 30 (4) ◽  
pp. 1847-1855 ◽  
Author(s):  
Jing Gong ◽  
Jiyu Liu ◽  
Wen Hao ◽  
Shengdong Nie ◽  
Bin Zheng ◽  
...  

Computation ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 47
Author(s):  
Arash Mirhashemi

At the cost of added complexity and time, hyperspectral imaging provides a more accurate measure of the scene’s irradiance compared to an RGB camera. Several camera designs with more than three channels have been proposed to improve the accuracy. The accuracy is often evaluated based on the estimation quality of the spectral data. Currently, such evaluations are carried out with either simulated data or color charts to relax the spatial registration requirement between the images. To overcome this limitation, this article presents an accurately registered image database of six icon paintings captured with five cameras with different number of channels, ranging from three (RGB) to more than a hundred (hyperspectral camera). Icons are challenging topics because they have complex surfaces that reflect light specularly with a high dynamic range. Two contributions are proposed to tackle this challenge. First, an imaging configuration is carefully arranged to control the specular reflection, confine the dynamic range, and provide a consistent signal-to-noise ratio for all the camera channels. Second, a multi-camera, feature-based registration method is proposed with an iterative outlier removal phase that improves the convergence and the accuracy of the process. The method was tested against three other approaches with different features or registration models.


Sign in / Sign up

Export Citation Format

Share Document