Filters








17 Hits in 8.6 sec

Semi-automatic RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networks [chapter]

Youbao Tang, Adam P. Harrison, Mohammadhadi Bagheri, Jing Xiao, Ronald M. Summers
2018 Lecture Notes in Computer Science  
To alleviate these problems, we propose a cascaded convolutional neural network based method to semi-automatically label RECIST annotations and drastically reduce annotation time.  ...  We train our system on the DeepLesion dataset, obtaining a consensus model trained on RECIST annotations performed by multiple radiologists over a multi-year period.  ...  To overcome these problems, we propose a RECIST estimation method that uses a cascaded convolutional neural network (CNN) approach.  ... 
doi:10.1007/978-3-030-00937-3_47 fatcat:wtwlt5kcr5ch5pdw7xnrshitbq

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
RECIST Labeling on CT Scans with Cascaded Convolutional Neural Networks 306 A Weakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma Images 310 A novel mixed reality  ...  Images 566 Towards MR-Only Radiotherapy Treatment Planning: Synthetic CT Generation Using Multi-view Deep Convolutional Neural Networks 567 Deep learning with synthetic diffusion MRI data for free-water  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Weakly supervised segmentation from extreme points [article]

Holger Roth, Ling Zhang, Dong Yang, Fausto Milletari, Ziyue Xu, Xiaosong Wang, Daguang Xu
2019 arXiv   pre-print
This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks.  ...  We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm.  ...  Segmentation via deep fully convolutional network: Next, given all pairs of images X and pseudo labelsŶ , we can train a fully convolutional neural network to segment the given foreground class, with P  ... 
arXiv:1910.01236v1 fatcat:joub4vndynfllbhkqma6fsdhim

Automated liver tissues delineation techniques: A systematic survey on machine learning current trends and future orientations [article]

Ayman Al-Kababji, Faycal Bensaali, Sarada Prasad Dakua, Yassine Himeur
2022 arXiv   pre-print
challenge and why their absence needs to be dealt with sooner than later.  ...  We divide the surveyed studies based on the tissue of interest (hepatic-parenchyma, hepatic-tumors, or hepatic-vessels), highlighting the studies that tackle more than one task simultaneously.  ...  The latter, on the other hand, depends on either hand-crafted features as in conventional machine learning (ML) algorithms or empirically-found features as in the case of convolutional neural network (  ... 
arXiv:2103.06384v2 fatcat:w6dxpyxhzzhs3gel25pgy6fqke

The Liver Tumor Segmentation Benchmark (LiTS) [article]

Patrick Bilic, Patrick Ferdinand Christ, Eugene Vorontsov, Grzegorz Chlebus, Hao Chen, Qi Dou, Chi-Wing Fu, Xiao Han, Pheng-Ann Heng, Jürgen Hesser, Samuel Kadoury, Tomasz Konopczyǹski (+44 others)
2019 arXiv   pre-print
Twenty four valid state-of-the-art liver and liver tumor segmentation algorithms were applied to a set of 131 computed tomography (CT) volumes with different types of tumor contrast levels (hyper-/hypo-intense  ...  In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LITS) organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2016 and International  ...  Today convolutional neural networks are widely used in automatic semantic segmentation tasks in medical imaging without reliance on hand-crafted features [52] .  ... 
arXiv:1901.04056v1 fatcat:25ekt2znl5adnd5laap4ez6a4y

AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging: Towards Radiophenomics [article]

Fereshteh Yousefirizi, Pierre Decazes, Amine Amyar, Su Ruan, Babak Saboury, Arman Rahmim
2022 arXiv   pre-print
This work reviews AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks.  ...  AI-based detection searches the image space to find the regions of interest based on patterns and features.  ...  [110] applied the deep convolutional neural network (CNN), You Only Look (YOLO) [111] , to detect HNA on 2D PET images.  ... 
arXiv:2110.10332v4 fatcat:vmpxhoolarbrve5ddyfn5umfim

ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans

Alex Noel Joseph Raj, Haipeng Zhu, Asiya Khan, Zhemin Zhuang, Zengbiao Yang, Vijayalakshmi G. V. Mahesh, Ganesan Karthik
2021 PeerJ Computer Science  
Automatic detection from computed tomography (CT) scans is a classic method to detect lung infection, but it faces problems such as high variations in intensity, indistinct edges near lung infected region  ...  Therefore, this article proposes a new COVID-19 pulmonary infection segmentation depth network referred as the Attention Gate-Dense Network- Improved Dilation Convolution-UNET (ADID-UNET).  ...  ACKNOWLEDGEMENTS We are very grateful to the Italian Society of medicine and interventional radiology, Radiopedia, and Ma et al. (2020) for providing the COVID-19 CT scan segmentation database.  ... 
doi:10.7717/peerj-cs.349 pmid:33816999 pmcid:PMC7924694 fatcat:2tmaagjsuzemdiactjy7jna4hu

Reinventing 2D Convolutions for 3D Images [article]

Jiancheng Yang, Xiaoyang Huang, Yi He, Jingwei Xu, Canqian Yang, Guozheng Xu, Bingbing Ni
2021 arXiv   pre-print
Even without pretraining, the ACS convolution can be used as a plug-and-play replacement of standard 3D convolution, with smaller model size and less computation.  ...  In ACS convolutions, 2D convolution kernels are split by channel into three parts, and convoluted separately on the three views (axial, coronal and sagittal) of 3D representations.  ...  There are 2, 635 lung nodules annotated by at most 4 experts, from 1, 018 CT scans.  ... 
arXiv:1911.10477v4 fatcat:4edvnulc2fcahk6pbjx5pfkk2q

Going to Extremes: Weakly Supervised Medical Image Segmentation

Holger R. Roth, Dong Yang, Ziyue Xu, Xiaosong Wang, Daguang Xu
2021 Machine Learning and Knowledge Extraction  
This initial segmentation is then used as a noisy supervision signal to train a fully convolutional network that can segment the organ of interest, based on the provided user clicks.  ...  Through experimentation on several medical imaging datasets, we show that the predictions of the network can be refined using several rounds of training with the prediction from the same weakly annotated  ...  Data Availability Statement: A pre-print is available on arxiv https://arxiv.org/abs/2009.11988, accessed on 28 May 2021. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/make3020026 fatcat:vpy3rtl63rctjcv3sgtd7mn56u

Guest Editorial Annotation-Efficient Deep Learning: The Holy Grail of Medical Imaging

Nima Tajbakhsh, Holger Roth, Demetri Terzopoulos, Jianming Liang
2021 IEEE Transactions on Medical Imaging  
They exploit a deep neural network pretrained on a different imaging modality, fluorescein angiography, together with multimodel registration to iteratively train their model and simultaneously refine  ...  by clinicians (e.g., RECIST) or image-level labels provided in clinical reporting.  ... 
doi:10.1109/tmi.2021.3089292 pmid:34795461 pmcid:PMC8594751 fatcat:t7kufjbdyfgazng3gcuyuhawxu

Computer-Assisted Analysis of Biomedical Images [article]

Leonardo Rundo
2021 arXiv   pre-print
In this regard, frameworks based on advanced Machine Learning and Computational Intelligence can significantly improve traditional Image Processing and Pattern Recognition approaches.  ...  [255] adapted Convolutional Neural Network (CNN) architectures specifically to the task of brain tumor segmentation on multispectral MRI data.  ...  Chapter 6 Deep Neural Networks Convolutional Neural Networks In the latest years, DNNs have been exploited to learn a hierarchy of increasingly complex features from the processed data, enabling multiple  ... 
arXiv:2106.04381v1 fatcat:osqiyd3sbja3zgrby7bf4eljfm

The Future of Cancer Diagnosis, Treatment and Surveillance: A Systemic Review on Immunotherapy and Immuno-PET Radiotracers

Virginia Liberini, Riccardo Laudicella, Martina Capozza, Martin W. Huellner, Irene A. Burger, Sergio Baldari, Enzo Terreno, Désirée Deandreis
2021 Molecules  
Patients are mainly stratified using an immunohistochemical analysis of the expression of antigens on biopsy specimens, such as PD-L1 and PD-1, on tumor cells, on peritumoral immune cells and/or in the  ...  Today, positron emission tomography (PET) with 2-deoxy-2-[18F]fluoro-D-glucose ([18F]FDG) is used routinely to evaluate tumor metabolism, and also to predict and monitor response to immunotherapy.  ...  ", "PET/MR", "convolutional", "neural", "network", "machine", "learning".  ... 
doi:10.3390/molecules26082201 pmid:33920423 fatcat:uletxs4gufefxgriqonyed6adq

Special/Poster Abstracts

2022
The architecture of the convolutional neural network (CNN) was based on AlexNet and we constructed a network that consisted of 11 layers.  ...  If synthetic CT (sCT) images based on magnetic resonance imaging (MRI) can be directly obtained using a deep convolutional neural network (DCNN), the CTAC method can be applied to PET-only systems without  ...  The new automated software Arimaru (PDR pharma) and the semi-automatic software PETquact (Nihon Medi-physics) were used for the analysis.  ... 
doi:10.18893/kakuigaku.59.s41 pmid:36002329 fatcat:vwq75w7n3rektgua5yy2v53dzm

The Future of Cancer Diagnosis, Treatment and Surveillance: A Systemic Review on Immunotherapy and Immuno-PET Radiotracers

Virginia Liberini, Riccardo Laudicella, Martina Capozza, Martin W Huellner, Irene A Burger, Sergio Baldari, Enzo Terreno, Désirée Deandreis
2021
Patients are mainly stratified using an immunohistochemical analysis of the expression of antigens on biopsy specimens, such as PD-L1 and PD-1, on tumor cells, on peritumoral immune cells and/or in the  ...  Today, positron emission tomography (PET) with 2-deoxy-2-[ 18 F]fluoro-D-glucose ([ 18 F]FDG) is used routinely to evaluate tumor metabolism, and also to predict and monitor response to immunotherapy.  ...  ", "PET/MR", "convolutional", "neural", "network", "machine", "learning".  ... 
doi:10.5167/uzh-208845 fatcat:m27nxk56xrfbbg6u2w7s44en7i

The 49th Congress of the European Society for Surgical Research May 21-24, 2014, Budapest, Hungary: Abstracts

2014 European Surgical Research  
Conclusion: These data demonstrate that inhibition of complement cascade components has beneficial effects on the oxygen extraction in experimental sepsis and suggest that the C5aA treatment could be a  ...  Dynamic PET scan revealed altered FDG kinetics in both ligated and non-ligated liver lobes.  ...  A volumetric measurement of the perirenal fat mass in mm3 was carried out based on CT-scans.  ... 
doi:10.1159/000363269 pmid:24854186 fatcat:ofafa5cf4vhknamsraqekjznpy
« Previous Showing results 1 — 15 out of 17 results