Filters








18 Hits in 24.4 sec

Multiclass Brain Tissue Segmentation in 4D CT Using Convolutional Neural Networks

Sil C. Van De Leemput, Midas Meijs, Ajay Patel, Frederick J. A. Meijer, Bram Van Ginneken, Rashindra Manniesing
2019 IEEE Access  
A fully convolutional neural network (CNN) for 3D multiclass segmentation in 4D CT is presented, which can be trained end-to-end from sparse 2D annotations.  ...  The proposed method is, therefore, a promising deep neural network for multiclass segmentation in 4D spatiotemporal imaging data.  ...  ACKNOWLEDGMENT The authors would like to thank Lisan Kaal, BSc. and Loes Vos, BSc. (medical students at Radboud UMC, the Netherlands) for annotating.  ... 
doi:10.1109/access.2019.2910348 fatcat:ymgk2h5m5vgpvkylj7ghcbpfxm

CARS 2020—Computer Assisted Radiology and Surgery Proceedings of the 34th International Congress and Exhibition, Munich, Germany, June 23–27, 2020

2020 International Journal of Computer Assisted Radiology and Surgery  
A hybrid (analogue and digital) CARS 2020 has therefore been envisaged to take place at the University Hospital in Munich, with a balanced combination of analogue/personal and digital presentations and  ...  In the times of COVID-19 overshadowing CARS 2020 and what the future may hold, a CARS meeting with these numbers of participants is not feasible anymore and new ways have to be explored to still fulfill  ...  We thank NVIDIA for the Titan X hardware grant that allowed us to process the images in a faster way. ].  ... 
doi:10.1007/s11548-020-02171-6 pmid:32514840 fatcat:lyhdb2zfpjcqbf4mmbunddwroq

B - Scientific Sessions

2010 Insights into Imaging  
Purpose: To evaluate perfusion differences between oedemic and necrotic pancreatic tissue in patients with initial stage of acute pancreatitis using 320-slice dynamic volume CT.  ...  After intravenous contrast media injection (8 ml/s, 350 mg iodine/ml) and dynamic density measurements in the right ventricle, dynamic scanning was initiated manually. 15 low-dose 16 cm volume scans were  ...  The method was evaluated using: a) manual and b) automatic region maps on two annotated data sets: 1) hand radiographs, 2) heart MRI slices.  ... 
doi:10.1007/s13244-010-0011-1 pmid:23099631 pmcid:PMC3534347 fatcat:yfnq3lgteja2lfjl66ivdfnoum

SPR 2020

2020 Pediatric Radiology  
A convolutional neural network with the U-Net architecture was used to train the segmentation model.  ...  A novel, fully connected CNN based on a 3D modification of the U-Net architecture was trained on the output volumes (n=70) to generate segmentation masks of only the distal femoral physis.  ...  SSTE was found in 37% (108/294). Compared to those without SSTE, patients with SSTE had a higher total contrast volume (p<0.0001) and higher contrast volume per body surface area (BSA) (p<0.0001).  ... 
doi:10.1007/s00247-020-04679-0 pmid:32435980 fatcat:y6da6d4blvaxlkus6w6zahpwlu

A combined local and global motion estimation and compensation method for cardiac CT

Qiulin Tang, Beshan Chiang, Akinola Akinyemi, Alexander Zamyatin, Bibo Shi, Satoru Nakanishi, Bruce R. Whiting, Christoph Hoeschen
2014 Medical Imaging 2014: Physics of Medical Imaging  
For evaluation, a head&neck bone atlas created from 15 manually annotated training images was adapted to 58 clinically acquired head&neck CT datasets.  ...  This prior is commonly derived from a set of manually segmented training data from the population of interest.  ...  This is a manual process and can be time consuming in cases where several sections using different stains are required.  ... 
doi:10.1117/12.2043492 fatcat:fyzpc5m6jbh7fjohqpdmtzkhte

2021 AIUM Award Winners

2021 Journal of ultrasound in medicine  
A S82 Moreno M S102 Morgan T S68, S107 Morris R S65 Muhtadi S S5 Munjal H S97, S104 Murrett J S74, S77 Mutambuze J S44, S45, S47 N Nagarajan E S34, S35 Nagdev A S145 Naief A S16 Narayanamoorthy S S65  ...  S133 McWhirter A S123 Mehta-Lee S S55, S64 Melniker L S71 Mendez A S105 Mendez K S74 Mengsteab P S132 Messina M S33 Meteer S S138 Meyer M S54, S63 Michael S S139 Michel B S167 Miller D S11 Miller H S125  ...  The 3D images were resliced at random planes resulting in 6773 2D images used to train a modified U-net.  ... 
doi:10.1002/jum.15752 fatcat:v4nx5fvjwndrzfppaiaylgon64

Clinical Radiology Exhibits

2021 Journal of Medical Imaging and Radiation Oncology  
Acute in-stent thrombotic occlusion occurred in 3 of 46 cases (6.5%), with 7 of 34 patients (20.6%) imaged within 72 hours having >50% stenosis, commonly due to extrinsic plaque compression (57.1%).  ...  Successful recanalisation rate was 98% with a mTICI score of 3 achieved in 84% of patients.  ...  A convolutional neural net (CNN) was trained to segment white matter lesions in imagesthe previously described 3D residual U-Net (3DUNet) architecture (3).  ... 
doi:10.1111/1754-9485.13301 fatcat:x3hy5vd2lzarld4p2vvirlvncq

Abstracts for the Joint Meeting of Anatomical Societies, 19-22 May 2011, Bursa, Turkey

2011 Anatomy (International Journal of Experimental and Clinical Anatomy)  
In all these cases continuous longitudinal domains can be distinguished, as well as a number of anteroposterior (transverse) neuromeric units of the neural wall.  ...  region lying ventral to the telencephalon and rostral to the diencephalon; the latter separates it from the midbrain.  ...  Endonasal approaches to the midline cranial base were performed with 2D endoscopes. Then we applied the 3D technique to illustrate the 3D pictures.  ... 
doi:10.2399/ana.11.001s fatcat:e6qs7cmzqreejhsdrol7i665c4

ECR 2016 Book of Abstracts - A - Postgraduate Educational Programme

2016 Insights into Imaging  
In both cases at least two 3D volumes of image data are needed.  ...  To learn about posttraumatic findings in CT and MR imaging. A-061 09:23 C. Extremities U.  ...  In addition to the Level I and II curricula of the ETC, level III curricula for subspecialty training and an undergraduate (U level) curriculum are currently being prepared. Learning Objective: 1.  ... 
doi:10.1007/s13244-016-0474-9 pmid:26873353 pmcid:PMC4762839 fatcat:itxslbcacjhh3kixfkcwmdbt44

ECR 2013 Book of Abstracts - A - Postgraduate Educational Programme

2013 Insights into Imaging  
In both cases at least two 3D volumes of image data are needed.  ...  To learn about posttraumatic findings in CT and MR imaging. A-061 09:23 C. Extremities U.  ...  In addition to the Level I and II curricula of the ETC, level III curricula for subspecialty training and an undergraduate (U level) curriculum are currently being prepared. Learning Objective: 1.  ... 
doi:10.1007/s13244-013-0227-y pmid:23468009 pmcid:PMC3666656 fatcat:yitsk227mba2pl7wcypouf6tz4

ECR 2015 Book of Abstracts - A - Postgraduate Educational Programme

2015 Insights into Imaging  
In both cases at least two 3D volumes of image data are needed.  ...  To learn about posttraumatic findings in CT and MR imaging. A-061 09:23 C. Extremities U.  ...  In addition to the Level I and II curricula of the ETC, level III curricula for subspecialty training and an undergraduate (U level) curriculum are currently being prepared. Learning Objective: 1.  ... 
doi:10.1007/s13244-015-0386-0 pmid:25708993 pmcid:PMC4349897 fatcat:m7eyvqcwojfpvf3lr5hy6dwjb4

ECR 2011 Book of Abstracts - A - Postgraduate Educational Programme

2011 Insights into Imaging  
In both cases at least two 3D volumes of image data are needed.  ...  To learn about posttraumatic findings in CT and MR imaging. A-061 09:23 C. Extremities U.  ...  In addition to the Level I and II curricula of the ETC, level III curricula for subspecialty training and an undergraduate (U level) curriculum are currently being prepared. Learning Objective: 1.  ... 
doi:10.1007/s13244-011-0078-3 pmid:23100070 pmcid:PMC3533621 fatcat:qa3ln4hhvve2hhumgwwnmykgoe

Abstracts

2006 Cerebrovascular Diseases  
Methods: The aim of SPARCL was to assess whether atorvastatin 80 mg reduces the incidence of recurrent strokes in patients without a history of CHD who have had a recent stroke or transient ischemic attack  ...  The adenosine diphosphate receptor antagonist clopidogrel when added to aspirin reduces ischemic events in patients with both ST-segment and non-ST-segment elevation acute coronary syndromes.  ...  Infarct volume was determined from manual segmentation of infarcts on CT images. Linear regression was used to estimate the regional volume associated with each ASPECTS region.  ... 
doi:10.1159/000093822 fatcat:zlkvlediy5ea3eepiunfetasjm

Computer-support for intracranial aneurysms [article]

Sylvia Saalfeld, Universitäts- Und Landesbibliothek Sachsen-Anhalt, Martin-Luther Universität, Bernhard Preim
2020
To determine the intracranial aneurysm rupture risk is an active research area, including computer support for the segmentation and subsequent extraction of 3D morphological shape information, paving the  ...  Application areas do not only cover the aforementioned aneurysm rupture risk assessment but also the planning of treatment and therapy as well as possible training scenarios.  ...  Acknowledgments We would like to give thanks to Prof. Christina Iosif for her participation in our evaluation and the very useful feedback she provided.  ... 
doi:10.25673/35206 fatcat:excf6slbfbhrfdj6kyyjgeytve

Collaborative optimisation of focused anatomy observation and drawing techniques for enhancing cognitive memorisation. S149, (page 63). In: International Federation of Associations of Anatomists 19th Congress Abstracts 9th – 11th August 2019 London, UK

Leonard Shapiro, Iain Keenan
2020
In: International Federation of Associations of Anatomists 19th Congress Abstracts 9th – 11th August 2019 London, UK.  ...  Thanks to the segmentation data, the structures on the volume model could be automatically annotated.  ...  Photogrammetry was used to convert photos into 3D models. A dedicated application was built using a gameengine, and the digitized 3D-prosections were annotated using a digital sculpting program.  ... 
doi:10.25375/uct.12824237 fatcat:i777oabeinfclgsi7ecwcve3sy
« Previous Showing results 1 — 15 out of 18 results