Filters








1,143 Hits in 3.9 sec

Fully-automated Body Composition Analysis in Routine CT Imaging Using 3D Semantic Segmentation Convolutional Neural Networks [article]

Sven Koitka, Lennard Kroll, Eugen Malamutmann, Arzu Oezcelik, Felix Nensa
2020 arXiv   pre-print
Multi-resolution U-Net 3D neural networks were employed for segmenting these body regions, followed by subclassifying adipose tissue and muscle using known hounsfield unit limits.  ...  tissue, and thoracic cavity.  ...  For quantifying tissues, the reporting system uses a mixture of classical thresholding and modern semantic segmentation neural networks for building the semantic relationships.  ... 
arXiv:2002.10776v1 fatcat:mhkaus2gybeyliox42wedg7f64

Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

Sven Koitka, Lennard Kroll, Eugen Malamutmann, Arzu Oezcelik, Felix Nensa
2020 European Radiology  
Multi-resolution U-Net 3D neural networks were employed for segmenting these body regions, followed by subclassifying adipose tissue and muscle using known Hounsfield unit limits.  ...  subcutaneous tissue, and thoracic cavity.  ...  For quantifying tissues, the reporting system uses a mixture of classical thresholding and modern semantic segmentation neural networks for building semantic relationships.  ... 
doi:10.1007/s00330-020-07147-3 pmid:32945971 fatcat:dtes3tnzurgjxpe35b4yny6puy

Deep Learning Automated Segmentation for Muscle and Adipose Tissue from Abdominal Computed Tomography in Polytrauma Patients

Leanne L. G. C. Ackermans, Leroy Volmer, Leonard Wee, Ralph Brecheisen, Patricia Sánchez-González, Alexander P. Seiffert, Enrique J. Gómez, Andre Dekker, Jan A. Ten Bosch, Steven M. W. Olde Damink, Taco J. Blokhuis
2021 Sensors  
A prototype deep learning neural network was trained on a multi-center collection of 3413 abdominal cancer surgery subjects to automatically segment truncal muscle, subcutaneous adipose tissue and visceral  ...  adipose tissue at the L3 lumbar vertebral level.  ...  Materials and Methods Training and Validation Set: Cancer Surgery Cases A deep learning neural network was trained on a multi-center collection of 3413 abdominal cancer surgery subjects to automatically  ... 
doi:10.3390/s21062083 pmid:33809710 pmcid:PMC8002279 fatcat:4fo65lhbkjgulpojellf4plvla

Front Matter: Volume 10133

Proceedings of SPIE, Martin A. Styner, Elsa D. Angelini
2017 Medical Imaging 2017: Image Processing  
to motion artifacts in chest CT using a convolutional neural network [10133-27] 10133 0S Automatic quality assessment of apical four-chamber echocardiograms using deep convolutional neural networks  ...  evaluation of physician-modified stent grafts for juxta-renal abdominal aortic aneurysms [10133-85] 10133 2D Multi-scale hippocampal parcellation improves atlas-based segmentation accuracy [10133  ... 
doi:10.1117/12.2270368 dblp:conf/miip/X17 fatcat:resfpzholvbtbalfkbg3pj64gu

A two-step convolutional neural network based computer-aided detection scheme for automatically segmenting adipose tissue volume depicting on CT images

Yunzhi Wang, Yuchen Qiu, Theresa Thai, Kathleen Moore, Hong Liu, Bin Zheng
2017 Computer Methods and Programs in Biomedicine  
Accurately assessment of adipose tissue volume inside a human body plays an important role in predicting disease or cancer risk, diagnosis and prognosis.  ...  The proposed CAD framework consisted of two steps with two convolution neural networks (CNNs) namely, Selection-CNN and Segmentation-CNN.  ...  This is because that each adipose pixel is used as an independent input of the deep network and the CAD scheme needs to scan all the pixels in the image.  ... 
doi:10.1016/j.cmpb.2017.03.017 pmid:28495009 pmcid:PMC5441239 fatcat:roy3amqeqrbwpdckiyj4djy53q

FatSegNet : A Fully Automated Deep Learning Pipeline for Adipose Tissue Segmentation on Abdominal Dixon MRI [article]

Santiago Estrada, Ran Lu, Sailesh Conjeti, Ximena Orozco-Ruiz, Joana Panos-Willuhn, Monique M.B Breteler, Martin Reuter
2019 arXiv   pre-print
Method: FatSegNet is composed of three stages: (i) consistent localization of the abdominal region using two 2D-Competitive Dense Fully Convolutional Networks (CDFNet), (ii) segmentation of adipose tissue  ...  Purpose: Development of a fast and fully automated deep learning pipeline (FatSegNet) to accurately identify, segment, and quantify abdominal adipose tissue on Dixon MRI from the Rhineland Study - a large  ...  Abbreviations: SAT-V: volume of abdominal subcutaneous adipose tissue; VAT-V: volume of abdominal visceral adipose tissue in liters. based on deep learning models, it can be easily updated and retrained  ... 
arXiv:1904.02082v1 fatcat:zrn235wnkff55hm6h524o5vgua

Front Matter: Volume 10575

Proceedings of SPIE, Kensaku Mori, Nicholas Petrick
2018 Medical Imaging 2018: Computer-Aided Diagnosis  
using a Base 36 numbering system employing both numerals and letters.  ...  Please use the following format to cite material from these proceedings: Publication of record for individual papers is online in the SPIE Digital Library.  ...  in lung CT images using multilevel thresholding on supervoxels [10575-110] 10575 34 Opacity annotation of diffuse lung diseases using deep convolutional neural network with multi-channel information  ... 
doi:10.1117/12.2315758 fatcat:kqpt2ugrxrgx7m5rhasawarque

Uncertainty-Aware Body Composition Analysis with Deep Regression Ensembles on UK Biobank MRI [article]

Taro Langner, Fredrik K. Gustafsson, Benny Avelin, Robin Strand, Håkan Ahlström, Joel Kullberg
2021 arXiv   pre-print
In this work, six measurements of body composition and adipose tissues were automatically estimated by image-based, deep regression with ResNet50 neural networks from neck-to-knee body MRI.  ...  Despite the potential for high speed and accuracy, these networks produce no output segmentations that could indicate the reliability of individual measurements.  ...  Acknowledgment This work was supported by a research grant from the Swedish Heart-Lung Foundation and the Swedish Research Council (2016-01040, 2019-04756, 2020-0500, 2021-70492) and used the UK Biobank  ... 
arXiv:2101.06963v3 fatcat:m5ms7watejaz5dvlhlqpxgi5qy

Fully Automated and Standardized Segmentation of Adipose Tissue Compartments by Deep Learning in Three-dimensional Whole-body MRI of Epidemiological Cohort Studies [article]

Thomas Küstner, Tobias Hepp, Marc Fischer, Martin Schwartz, Andreas Fritsche, Hans-Ulrich Häring, Konstantin Nikolaou, Fabian Bamberg, Bin Yang, Fritz Schick, Sergios Gatidis, Jürgen Machann
2020 arXiv   pre-print
In this work we propose a 3D convolutional neural network (DCNet) to provide a robust and objective segmentation.  ...  For correct identification and phenotyping of individuals at increased risk for metabolic diseases, a reliable automatic segmentation of adipose tissue into subcutaneous and visceral adipose tissue is  ...  Deep convolutional neural networks with merge-and-run mappings. arXiv preprint arXiv:161107718. 2016. 47. Lin T, Goyal P, Girshick R, He K, Dollár P.  ... 
arXiv:2008.02251v1 fatcat:egrvlizw6fccdkvfgdaflubcju

Front Matter: Volume 10578

Barjor Gimi, Andrzej Krol
2018 Medical Imaging 2018: Biomedical Applications in Molecular, Structural, and Functional Imaging  
neural networks [10578-69] 10578 1Z Exploit 18 F-FDG enhanced urinary bladder in PET data for deep learning ground truth generation in CT scans [10578-70] 10578 20 Unsupervised segmentation of  ...  in cardiac MR using convolutional neural networks [10578-77] POSTERS: NEUROLOGICAL IMAGING 10578 27 Diffusion tensor imaging of the spine in pediatric patients [10578-78] 10578 28 Altered structural-functional  ... 
doi:10.1117/12.2323952 fatcat:om4wezsn3vgr7mebecadzuy5ly

A residual dense network assisted sparse view reconstruction for breast computed tomography

Zhiyang Fu, Hsin Wu Tseng, Srinivasan Vedantham, Andrew Karellas, Ali Bilgin
2020 Scientific Reports  
3D sparse-view cone-beam acquisition with a multi-slice residual dense network (MS-RDN) reconstruction.  ...  AbstractTo develop and investigate a deep learning approach that uses sparse-view acquisition in dedicated breast computed tomography for radiation dose reduction, we propose a framework that combines  ...  Deep neural network reconstruction.  ... 
doi:10.1038/s41598-020-77923-0 pmid:33273541 fatcat:nyszsj7hqvh7bg77ypuf66u2sa

Machine Learning based histology phenotyping to investigate epidemiologic and genetic basis of adipocyte morphology and cardiometabolic traits [article]

Craig A Glastonbury, Sara L Pulit, Julius Honecker, Jenny C Censin, Samantha Laber, Hanieh Yaghootkar, Nilufer Rahmioglu, Emilie Pastel, Katarina Kos, Andrew Pitt, Michelle Hudson, Christoffer Nellåker (+7 others)
2019 biorxiv/medrxiv   pre-print
To perform the first large-scale study of automatic adipocyte phenotyping using both histological and genetic data, we developed a deep learning-based method, the Adipocyte U-Net, to rapidly derive area  ...  Despite having twice the number of samples than any similar study, we found no genome-wide significant associations, suggesting that larger sample sizes and a homogenous collection of adipose tissue are  ...  Acknowledgments We thank study participants who donated adipose tissue to this study. Author Contributions Conceptualization: Craig A. Glastonbury. Data curation: Craig A.  ... 
doi:10.1101/680637 fatcat:axesmeoy6fb75ficlbfa2hn64y

Front Matter: Volume 9785

2016 Medical Imaging 2016: Computer-Aided Diagnosis  
using a Base 36 numbering system employing both numerals and letters.  ...  Vol. 9785 978501-4 Downloaded From: https://www.spiedigitallibrary.org/conference-proceedings-of-spie on 7/22/2018 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use  ...  28 Colonoscopic polyp detection using convolutional neural networks [9785-79] 9785 29 Normalization of T2W-MRI prostate images using Rician a priori [9785-80] 9785 2B Deep transfer learning of  ... 
doi:10.1117/12.2240961 dblp:conf/micad/X16 fatcat:b5addnksdrgp3ixwvbjt53xeqe

Automatic Segmentation and Quantification of White and Brown Adipose Tissues from PET/CT Scans

Sarfaraz Hussein, Aileen Green, Arjun Watane, David Reiter, Xinjian Chen, Georgios Z. Papadakis, Bradford Wood, Aaron Cypess, Medhat Osman, Ulas Bagci
2017 IEEE Transactions on Medical Imaging  
In the first module, we detect white adipose tissue (WAT) and its two sub-types from CT scans: Visceral Adipose Tissue (VAT) and Subcutaneous Adipose Tissue (SAT).  ...  In the second module, we automatically detect, segment, and quantify brown adipose tissue (BAT) using PET scans because unlike WAT, BAT is metabolically active.  ...  To benefit from this rich representation of image features, we use Convolutional Neural Network (CNN) features (i.e., deep learning features) as image attributes extracted from the first fully-connected  ... 
doi:10.1109/tmi.2016.2636188 pmid:28114010 fatcat:pibwd2ckhrfrjde5s3h756pqna

MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI [article]

Taro Langner, Andrés Martínez Mora, Robin Strand, Håkan Ahlström, Joel Kullberg
2021 arXiv   pre-print
The underlying methodology utilizes convolutional neural networks for image-based mean-variance regression on two-dimensional representations of the MRI data.  ...  With up to 170,000 mounting MR images, various methodologies are accordingly engaged in large-scale image analysis.  ...  METHODS Based on convolutional neural networks, MIMIR performs an image-based, deep regression [11] .  ... 
arXiv:2106.11731v2 fatcat:fbqwicmzuvhzbd525vh7r4zdoy
« Previous Showing results 1 — 15 out of 1,143 results