scholarly journals DL-inferencing for 3D Cephalometric Landmarks Regression task using OpenVINO

2020 ◽  
pp. paper35-1-paper35-11
Author(s):  
Evgeny Vasiliev ◽  
Dmitrii Lachinov ◽  
Alexandra Getmanskaya
Keyword(s):  
Neural Networks ◽  
Great Increase ◽  
Three Dimensional ◽  
Ct Scans ◽  
Cephalometric Analysis ◽  
Skull Shape ◽  
Computing Environments ◽  
Hourglass Model ◽  
Direct Regression ◽  
Tomography Data

In this paper, we evaluate the performance of the Intel Distribution of OpenVINO toolkit in practical solving of the problem of automatic three-dimensional Cephalometric analysis using deep learning methods. This year, the authors proposed an approach to the detection of cephalometric landmarks from CT-tomography data, which is resistant to skull deformities and use convolutional neural networks (CNN). Resistance to deformations is due to the initial detection of 4 points that are basic for the parameterization of the skull shape. The approach was explored on CNN for three architectures. A record regression accuracy in comparison with analogs was obtained. This paper evaluates the perfor- mance of decision making for the trained CNN-models at the inference stage. For a comparative study, the computing environments PyTorch and Intel Distribution of OpenVINO were selected, and 2 of 3 CNN architectures: based on VGG for regression of cephalometric landmarks and an Hourglass-based model, with the RexNext backbone for the land- marks heatmap regression. The experimental dataset was consist of 20 CT of patients with acquired craniomaxillofacial deformities and was in- clude pre- and post-operative CT scans whose format is 800x800x496 with voxel spacing of 0.2x0.2x0.2 mm. Using OpenVINO showed a great increase in performance over the PyTorch, with inference speedup from 13 to 16 times for a Direct Regression model and from 3.5 to 3.8 times for a more complex and precise Hourglass model.

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Identification of Mode Shapes of a Composite Cylinder Using Convolutional Neural Networks

Materials ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 2801
Author(s):  
Bartosz Miller ◽  
Leonard Ziemiański
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Composite Structures ◽  
Three Dimensional ◽  
Mode Shapes ◽  
Identification Algorithm ◽  
Material Degradation ◽  
Local Material ◽  
Noisy Input ◽  
Shape Vector

The aim of the following paper is to discuss a newly developed approach for the identification of vibration mode shapes of multilayer composite structures. To overcome the limitations of the approaches based on image analysis (two-dimensional structures, high spatial resolution of mode shapes description), convolutional neural networks (CNNs) are applied to create a three-dimensional mode shapes identification algorithm with a significantly reduced number of mode shape vector coordinates. The CNN-based procedure is accurate, effective, and robust to noisy input data. The appearance of local damage is not an obstacle. The change of the material and the occurrence of local material degradation do not affect the accuracy of the method. Moreover, the application of the proposed identification method allows identifying the material degradation occurrence.

Morphometry of the sacrum and its implication on trans-sacral corridors using a computed tomography data-based three-dimensional statistical model

2017 ◽  
Vol 17 (8) ◽  
pp. 1141-1147 ◽  
Author(s):  
Daniel Wagner ◽  
Lukas Kamer ◽  
Takeshi Sawaguchi ◽  
Robert Geoff Richards ◽  
Hansrudi Noser ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Statistical Model ◽  
Three Dimensional ◽  
Tomography Data

scholarly journals Validation of three-dimensional diffraction contrast tomography reconstructions by means of electron backscatter diffraction characterization

2013 ◽  
Vol 46 (4) ◽  
pp. 1145-1150 ◽  
Author(s):  
Melanie Syha ◽  
Andreas Trenkle ◽  
Barbara Lödermann ◽  
Andreas Graff ◽  
Wolfgang Ludwig ◽  
...  
Keyword(s):  
Electron Backscatter Diffraction ◽  
Three Dimensional ◽  
Data Reconstruction ◽  
Characterization Methods ◽  
Diffraction Contrast ◽  
Ebsd Data ◽  
Electron Backscatter ◽  
Backscatter Diffraction ◽  
Tomography Data ◽  
Good Agreement

Microstructure reconstructions resulting from diffraction contrast tomography data of polycrystalline bulk strontium titanate were reinvestigated by means of electron backscatter diffraction (EBSD) characterization. Corresponding two-dimensional grain maps from the two characterization methods were aligned and compared, focusing on the spatial resolution at the internal interfaces. The compared grain boundary networks show a remarkably good agreement both morphologically and in crystallographic orientation. Deviations are critically assessed and discussed in the context of diffraction data reconstruction and EBSD data collection techniques.

scholarly journals Convolutional Neural Networks and Geometric Moments to Identify the Bilateral Symmetric Midplane in Facial Skeletons from CT Scans

Biology ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 182
Author(s):  
Rodrigo Dalvit Carvalho da Silva ◽  
Thomas Richard Jenkyn ◽  
Victor Alexander Carranza
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Surgical Planning ◽  
Good Accuracy ◽  
Bilateral Symmetry ◽  
Ct Scans ◽  
Facial Skeleton ◽  
Intact Side ◽  
Geometric Moments ◽  
The Face

In reconstructive craniofacial surgery, the bilateral symmetry of the midplane of the facial skeleton plays an important role in surgical planning. Surgeons can take advantage of the intact side of the face as a template for the malformed side by accurately locating the midplane to assist in the preparation of the surgical procedure. However, despite its importance, the location of the midline is still a subjective procedure. The aim of this study was to present a 3D technique using a convolutional neural network and geometric moments to automatically calculate the craniofacial midline symmetry of the facial skeleton from CT scans. To perform this task, a total of 195 skull images were assessed to validate the proposed technique. In the symmetry planes, the technique was found to be reliable and provided good accuracy. However, further investigations to improve the results of asymmetric images may be carried out.

Diagnosis of COVID-19 using 3D CT scans and vaccination for COVID-19

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Gangadhar Ch ◽  
S. Jana ◽  
Sankararao Majji ◽  
Prathyusha Kuncha ◽  
Fantin Irudaya Raj E. ◽  
...  
Keyword(s):  
Virus Isolate ◽  
Research Work ◽  
Three Dimensional ◽  
Ct Scans ◽  
Data Sets ◽  
Content Type ◽  
Infected People ◽  
3D Data ◽  
Ct Classification ◽  
First Time

Purpose For the first time in a decade, a new form of pneumonia virus, coronavirus, COVID-19, appeared in Wuhan, China. To date, it has affected millions of people, killed thousands and resulted in thousands of deaths around the world. To stop the spread of this virus, isolate the infected people. Computed tomography (CT) imaging is very accurate in revealing the details of the lungs and allows oncologists to detect COVID. However, the analysis of CT scans, which can include hundreds of images, may cause delays in hospitals. The use of artificial intelligence (AI) in radiology could help to COVID-19-positive cancer in this manner is the main purpose of the work. Design/methodology/approach CT scans are a medical imaging procedure that gives a three-dimensional (3D) representation of the lungs for clinical purposes. The volumetric 3D data sets can be regarded as axial, coronal and transverse data sets. By using AI, we can diagnose the virus presence. Findings The paper discusses the use of an AI for COVID-19, and CT classification issue and vaccination details of COVID-19 have been detailed in this paper. Originality/value Originality of the work is, all the data can be collected genuinely and did research work doneown methodology.

Sign in / Sign up

Export Citation Format

Share Document