Reconstruction of three‐dimensional tomographic patient models for radiation dose modulation in CT from two scout views using deep learning

2021 ◽  
Author(s):  
Juan C. Montoya ◽  
Chengzhu Zhang ◽  
Yinsheng Li ◽  
Ke Li ◽  
Guang‐Hong Chen
Keyword(s):  
Deep Learning ◽  
Radiation Dose ◽  
Three Dimensional ◽  
Dose Modulation

scholarly journals Deep learning‐based carotid media‐adventitia and lumen‐intima boundary segmentation from three‐dimensional ultrasound images

2019 ◽  
Vol 46 (7) ◽  
pp. 3180-3193 ◽  
Author(s):  
Ran Zhou ◽  
Aaron Fenster ◽  
Yujiao Xia ◽  
J. David Spence ◽  
Mingyue Ding
Keyword(s):  
Deep Learning ◽  
Three Dimensional ◽  
Ultrasound Images

scholarly journals Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1952
Author(s):  
May Phu Paing ◽  
Supan Tungjitkusolmun ◽  
Toan Huy Bui ◽  
Sarinporn Visitsattapongse ◽  
Chuchart Pintavirooj
Keyword(s):  
Deep Learning ◽  
Brain Infarction ◽  
Three Dimensional ◽  
Dice Similarity Coefficient ◽  
Automated Segmentation ◽  
Variational Mode Decomposition ◽  
Brain Scans ◽  
Automated Method ◽  
Mode Decomposition ◽  
Segmentation Task

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.

scholarly journals Three-dimensional structural measurement and material identification of an all-solid-state lithium-ion battery by X-Ray nanotomography and deep learning

2021 ◽  
Vol 8 ◽  
pp. 100048
Author(s):  
M. Kodama ◽  
A. Ohashi ◽  
H. Adachi ◽  
T. Miyuki ◽  
A. Takeuchi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Solid State ◽  
Lithium Ion Battery ◽  
Three Dimensional ◽  
Lithium Ion ◽  
Material Identification ◽  
X Ray

Diagnostic value of deep learning reconstruction for radiation dose reduction at abdominal ultra-high-resolution CT

2021 ◽  
Author(s):  
Yuko Nakamura ◽  
Keigo Narita ◽  
Toru Higaki ◽  
Motonori Akagi ◽  
Yukiko Honda ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Radiation Dose ◽  
Dose Reduction ◽  
Diagnostic Value ◽  
Radiation Dose Reduction ◽  
High Resolution Ct

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

scholarly journals An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection

2021 ◽  
Author(s):  
Terufumi Kokabu ◽  
Satoshi Kanai ◽  
Noriaki Kawakami ◽  
Koki Uno ◽  
Toshiaki Kotani ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Three Dimensional ◽  
Depth Sensor

Three-Dimensional Reconstruction of Dilute Bubbly Flow Field with Light-Field Images Based on Deep Learning Method

2021 ◽  
pp. 1-1
Author(s):  
Hongyi Wang ◽  
Hongyu Wang ◽  
Xinjun Zhu ◽  
Limei Song ◽  
Qinghua Guo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Flow Field ◽  
Light Field ◽  
Bubbly Flow ◽  
Three Dimensional ◽  
Learning Method ◽  
Three Dimensional Reconstruction ◽  
Dimensional Reconstruction

Preoperative Use of CT Angiography in Infants With Coarctation of the Aorta

2017 ◽  
Vol 8 (2) ◽  
pp. 196-202 ◽  
Author(s):  
Kirsten Rose-Felker ◽  
Joshua D. Robinson ◽  
Carl L. Backer ◽  
Cynthia K. Rigsby ◽  
Osama M. Eltayeb ◽  
...  
Keyword(s):  
Radiation Dose ◽  
Surgical Approach ◽  
New Technology ◽  
Three Dimensional ◽  
Coarctation Of The Aorta ◽  
Computed Tomographic Angiography ◽  
Great Vessel ◽  
Z Score ◽  
Computed Tomographic ◽  
Tomographic Angiography

Background: Computed tomographic angiography (CTA) and echocardiography (echo) are used preoperatively in coarctation of the aorta to define arch hypoplasia and great vessel branching. We sought to determine differences in quantitative measurements, as well as surgical utility, between modalities. Methods: Infants (less than six months) with both CTA and echo prior to coarctation repair from 2004 to 2013 were included. Measurements were compared and correlated with surgical approach. Three surgeons reviewed de-identified images to predict approach and characterize utility. Computed tomographic angiography radiation dose was calculated. Results: Thirty-three patients were included. No differences existed in arch measurements between echo and CTA ( z-score: −2.59 vs −2.43; P = .47). No differences between modalities were seen for thoracotomy ( z-score: −2.48 [echo] vs −2.31 [CTA]; P = .48) or sternotomy ( z-score: −3.13 [echo] vs −3.08 [CTA]; P = .84). Computed tomographic angiography delineated great vessel branching pattern in two patients with equivocal echo findings ( P = .60). Surgeons rated CTA as far more useful than echo in understanding arch hypoplasia and great vessel branching in cases where CTA was done to resolve anatomical questions that remain after echo evaluation. Two of three surgeons were more likely to choose the surgical approach taken based on CTA (surgeon A, P = .02; surgeon B, P = .01). Radiation dose averaged 2.5 (1.6) mSv and trended down from 2.9 mSv (1.8 mSv; n = 20) to 1.6 mSv (0.5 mSv; n = 7) ( P = .06) with new technology. Conclusion: Although CTA and echo measurements of the aorta do not differ, CTA better delineates branching and surgeons strongly prefer it for three-dimensional arch anatomy. We recommend CTA for patients with anomalous arch branching patterns, diffuse or complex hypoplasia, or unusual arch morphology not fully elucidated by echo.

Three-dimensional spatiotemporal wind field reconstruction based on physics-informed deep learning

2021 ◽  
Vol 300 ◽  
pp. 117390
Author(s):  
Jincheng Zhang ◽  
Xiaowei Zhao
Keyword(s):  
Deep Learning ◽  
Wind Field ◽  
Three Dimensional ◽  
Field Reconstruction
Sign in / Sign up

Export Citation Format

Share Document