scholarly journals Developing and testing an algorithm for automatic segmentation of the fetal face from three-dimensional ultrasound images

2020 ◽  
Vol 7 (11) ◽  
pp. 201342
Author(s):  
A. E. Clark ◽  
B. Biffi ◽  
R. Sivera ◽  
A. Dall'Asta ◽  
L. Fessey ◽  
...  
Keyword(s):  
Automatic Segmentation ◽  
Three Dimensional ◽  
Objective Measure ◽  
Segmentation Algorithm ◽  
Automated System ◽  
Computational Time ◽  
Ultrasound Images ◽  
Improved Performance ◽  
Automatic Algorithm ◽  
Volume Difference

Fetal craniofacial abnormalities are challenging to detect and diagnose on prenatal ultrasound (US). Image segmentation and computer analysis of three-dimensional US volumes of the fetal face may provide an objective measure to quantify fetal facial features and identify abnormalities. We have developed and tested an atlas-based partially automated facial segmentation algorithm; however, the volumes require additional manual segmentation (MS), which is time and labour intensive and may preclude this method from clinical adoption. These manually refined segmentations can then be used as a reference (atlas) by the partially automated segmentation algorithm to improve algorithmic performance with the aim of eliminating the need for manual refinement and developing a fully automated system. This study assesses the inter- and intra-operator variability of MS and tests an optimized version of our automatic segmentation (AS) algorithm. The manual refinements of 15 fetal faces performed by three operators and repeated by one operator were assessed by Dice score, average symmetrical surface distance and volume difference. The performance of the partially automatic algorithm with difference size atlases was evaluated by Dice score and computational time. Assessment of the manual refinements showed low inter- and intra-operator variability demonstrating its suitability for optimizing the AS algorithm. The algorithm showed improved performance following an increase in the atlas size in turn reducing the need for manual refinement.

scholarly journals A Fast, Automatic Segmentation Algorithm for Locating and Delineating Touching Cell Boundaries in Imaged Histopathology

2012 ◽  
Vol 51 (03) ◽  
pp. 260-267 ◽  
Author(s):  
F. Xing ◽  
D. J. Foran ◽  
L. Yang ◽  
X. Qi
Keyword(s):  
Parallel Implementation ◽  
Automatic Segmentation ◽  
Automated Analysis ◽  
Segmentation Algorithm ◽  
Cell Segmentation ◽  
Image Patches ◽  
Segmentation Algorithms ◽  
Salient Regions ◽  
Sequential Implementation ◽  
Automatic Algorithm

SummaryBackground: Automated analysis of imaged histopathology specimens could potentially provide support for improved reliability in detection and classification in a range of investigative and clinical cancer applications. Automated segmentation of cells in the digitized tissue microarray (TMA) is often the prerequisite for quantitative analysis. However overlapping cells usually bring significant challenges for traditional segmentation algorithms.Objectives: In this paper, we propose a novel, automatic algorithm to separate overlapping cells in stained histology specimens acquired using bright-field RGB imaging.Methods: It starts by systematically identifying salient regions of interest throughout the image based upon their underlying visual content. The segmentation algorithm subsequently performs a quick, voting based seed detection. Finally, the contour of each cell is obtained using a repulsive level set deformable model using the seeds generated in the previous step. We compared the experimental results with the most current literature, and the pixel wise accuracy between human experts’ annotation and those generated using the automatic segmentation algorithm.Results: The method is tested with 100 image patches which contain more than 1000 overlapping cells. The overall precision and recall of the developed algorithm is 90% and 78%, respectively. We also implement the algorithm on GPU. The parallel implementation is 22 times faster than its C/C++ sequential implementation.Conclusion: The proposed segmentation algorithm can accurately detect and effectively separate each of the overlapping cells. GPU is proven to be an efficient parallel platform for overlapping cell segmentation.

scholarly journals Internet of Medical Things–based decision system for automated classification of Alzheimer’s using three-dimensional views of magnetic resonance imaging scans

2019 ◽  
Vol 15 (3) ◽  
pp. 155014771983118 ◽  
Author(s):  
Umair Khan ◽  
Armughan Ali ◽  
Salabat Khan ◽  
Farhan Aadil ◽  
Mehr Yahya Durrani ◽  
...  
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Three Dimensional ◽  
Automated System ◽  
Computational Time ◽  
Daily Routine ◽  
Automated Classification ◽  
Human Beings ◽  
Resonance Imaging ◽  
Internet Of Medical Things

Internet of Medical Things is a smart provision of medical services to patients interacting with the doctors in harmony to uplift healthcare facilities. It enables the automated diagnosis of diseases for patients in remote areas. Alzheimer’s disease is one of the most chronic diseases and the main cause of dementia in human beings. Dementia affects the patient by a process of gradual degeneration of the human brain and results in an inability to perform daily routine tasks and actions. An automated system needs to be developed, to classify the subject with dementia and to determine the prodromal stage of dementia. Considering such requirement, a fully automated classification system is proposed. The proposed algorithm works on the hybrid feature vector combining the textural, statistical, and shape features extracted from three-dimensional views. The feature length is reduced using principal component analysis and relevant features are extracted for classification. The proposed algorithm is tested for both binary and multi-class problems. The method achieves the average precision of 99.2% and 99.02% for binary and multi-class classifications, respectively. The results outperform the existing methods. The algorithm showed accurate results with the average computational time of 0.05 s per magnetic resonance imaging scan.

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 A Proof-of-Concept Algorithm for the Retrieval of Total Column Amount of Trace Gases in a Multi-Dimensional Atmosphere

2021 ◽  
Vol 13 (2) ◽  
pp. 270
Author(s):  
Adrian Doicu ◽  
Dmitry S. Efremenko ◽  
Thomas Trautmann
Keyword(s):  
Trace Gases ◽  
Three Dimensional ◽  
Principal Component ◽  
Radiative Transfer Model ◽  
Computational Time ◽  
Transfer Model ◽  
Proof Of Concept ◽  
Discrete Ordinate ◽  
Distribution Method ◽  
Total Column

An algorithm for the retrieval of total column amount of trace gases in a multi-dimensional atmosphere is designed. The algorithm uses (i) certain differential radiance models with internal and external closures as inversion models, (ii) the iteratively regularized Gauss–Newton method as a regularization tool, and (iii) the spherical harmonics discrete ordinate method (SHDOM) as linearized radiative transfer model. For efficiency reasons, SHDOM is equipped with a spectral acceleration approach that combines the correlated k-distribution method with the principal component analysis. The algorithm is used to retrieve the total column amount of nitrogen for two- and three-dimensional cloudy scenes. Although for three-dimensional geometries, the computational time is high, the main concepts of the algorithm are correct and the retrieval results are accurate.

scholarly journals Three-dimensional ultrasound for knee osteophyte depiction: a comparative study to computed tomography

2021 ◽  
Author(s):  
Valeria Vendries ◽  
Tamas Ungi ◽  
Jordan Harry ◽  
Manuela Kunz ◽  
Jana Podlipská ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Automatic Segmentation ◽  
Three Dimensional ◽  
3D Ultrasound ◽  
Surgical Interventions ◽  
Structured Light Scanner ◽  
Joint Surfaces ◽  
Operative Planning ◽  
Rms Error ◽  
Tissue Characteristics

Abstract Purpose Osteophytes are common radiographic markers of osteoarthritis. However, they are not accurately depicted using conventional imaging, thus hampering surgical interventions that rely on pre-operative images. Studies have shown that ultrasound (US) is promising at detecting osteophytes and monitoring the progression of osteoarthritis. Furthermore, three-dimensional (3D) ultrasound reconstructions may offer a means to quantify osteophytes. The purpose of this study was to compare the accuracy of osteophyte depiction in the knee joint between 3D US and conventional computed tomography (CT). Methods Eleven human cadaveric knees were pre-screened for the presence of osteophytes. Three osteoarthritic knees were selected, and then, 3D US and CT images were obtained, segmented, and digitally reconstructed in 3D. After dissection, high-resolution structured light scanner (SLS) images of the joint surfaces were obtained. Surface matching and root mean square (RMS) error analyses of surface distances were performed to assess the accuracy of each modality in capturing osteophytes. The RMS errors were compared between 3D US, CT and SLS models. Results Average RMS error comparisons for 3D US versus SLS and CT versus SLS models were 0.87 mm ± 0.33 mm (average ± standard deviation) and 0.95 mm ± 0.32 mm, respectively. No statistical difference was found between 3D US and CT. Comparative observations of imaging modalities suggested that 3D US better depicted osteophytes with cartilage and fibrocartilage tissue characteristics compared to CT. Conclusion Using 3D US can improve the depiction of osteophytes with a cartilaginous portion compared to CT. It can also provide useful information about the presence and extent of osteophytes. Whilst algorithm improvements for automatic segmentation and registration of US are needed to provide a more robust investigation of osteophyte depiction accuracy, this investigation puts forward the potential application for 3D US in routine diagnostic evaluations and pre-operative planning of osteoarthritis.

scholarly journals Simulation of Thermal and Electric Field Distribution in Packaged Sausages Heated in a Stationary Versus a Rotating Microwave Oven

Foods ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 1622
Author(s):  
Wipawee Tepnatim ◽  
Witchuda Daud ◽  
Pitiya Kamonpatana
Keyword(s):  
Temperature Distribution ◽  
Electric Field ◽  
Three Dimensional ◽  
Development Stage ◽  
Microwave Oven ◽  
Computational Time ◽  
Plastic Package ◽  
Heating Uniformity ◽  
The Cost ◽  
Good Agreement

The microwave oven has become a standard appliance to reheat or cook meals in households and convenience stores. However, the main problem of microwave heating is the non-uniform temperature distribution, which may affect food quality and health safety. A three-dimensional mathematical model was developed to simulate the temperature distribution of four ready-to-eat sausages in a plastic package in a stationary versus a rotating microwave oven, and the model was validated experimentally. COMSOL software was applied to predict sausage temperatures at different orientations for the stationary microwave model, whereas COMSOL and COMSOL in combination with MATLAB software were used for a rotating microwave model. A sausage orientation at 135° with the waveguide was similar to that using the rotating microwave model regarding uniform thermal and electric field distributions. Both rotating models provided good agreement between the predicted and actual values and had greater precision than the stationary model. In addition, the computational time using COMSOL in combination with MATLAB was reduced by 60% compared to COMSOL alone. Consequently, the models could assist food producers and associations in designing packaging materials to prevent leakage of the packaging compound, developing new products and applications to improve product heating uniformity, and reducing the cost and time of the research and development stage.

scholarly journals Estimation of 6D Object Pose Using a 2D Bounding Box

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2939
Author(s):  
Yong Hong ◽  
Jin Liu ◽  
Zahid Jahangir ◽  
Sheng He ◽  
Qing Zhang
Keyword(s):  
Neural Network ◽  
Loss Function ◽  
Three Dimensional ◽  
Unit Vector ◽  
Prediction Algorithm ◽  
Computational Time ◽  
Bounding Box ◽  
Dimensional Unit ◽  
Bounding Boxes ◽  
Rgb Image

This paper provides an efficient way of addressing the problem of detecting or estimating the 6-Dimensional (6D) pose of objects from an RGB image. A quaternion is used to define an object′s three-dimensional pose, but the pose represented by q and the pose represented by -q are equivalent, and the L2 loss between them is very large. Therefore, we define a new quaternion pose loss function to solve this problem. Based on this, we designed a new convolutional neural network named Q-Net to estimate an object’s pose. Considering that the quaternion′s output is a unit vector, a normalization layer is added in Q-Net to hold the output of pose on a four-dimensional unit sphere. We propose a new algorithm, called the Bounding Box Equation, to obtain 3D translation quickly and effectively from 2D bounding boxes. The algorithm uses an entirely new way of assessing the 3D rotation (R) and 3D translation rotation (t) in only one RGB image. This method can upgrade any traditional 2D-box prediction algorithm to a 3D prediction model. We evaluated our model using the LineMod dataset, and experiments have shown that our methodology is more acceptable and efficient in terms of L2 loss and computational time.

Sign in / Sign up

Export Citation Format

Share Document