Filters








24 Hits in 10.6 sec

Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation

Ozan Oktay, Enzo Ferrante, Konstantinos Kamnitsas, Mattias Heinrich, Wenjia Bai, Jose Caballero, Stuart A. Cook, Antonio de Marvao, Timothy Dawes, Declan P. O'Regan, Bernhard Kainz, Ben Glocker (+1 others)
2018 IEEE Transactions on Medical Imaging  
We show that the proposed approach can be easily adapted to different analysis tasks (e.g. image enhancement, segmentation) and improve the prediction accuracy of the state-of-the-art models.  ...  The applicability of our approach is shown on multi-modal cardiac datasets and public benchmarks.  ...  The models are trained with full images without a need for patch extraction since the cardiac 2D MR image stack size is relatively smaller compared to the available GPU memory (Nvidia GTX-1080).  ... 
doi:10.1109/tmi.2017.2743464 pmid:28961105 fatcat:b73x5zpp7fhbbkgujckcymf5we

Best Paper Selection

2019 IMIA Yearbook of Medical Informatics  
Anatomically Constrained Neural Networks (ACNNs): application to cardiac image enhancement and segmentation.  ...  Mechanistic machine learning: how data assimilation leverages physiological knowledge using bayesian inference to forecast the future, infer the present, and phenotype.  ...  These anatomically constrained neural networks demonstrated excellent performance in image segmentation of multimodal two-dimensional magnetic resonance imaging (MRI) and three-dimensional ultrasound cardiac  ... 
doi:10.1055/s-0039-1677926 fatcat:wg75rxeb6bdmhi2r3htl6vk64i

Cardiac Segmentation with Strong Anatomical Guarantees [article]

Nathan Painchaud, Youssef Skandarani, Thierry Judge, Olivier Bernard, Alain Lalande, Pierre-Marc Jodoin
2020 IEEE Transactions on Medical Imaging   pre-print
Convolutional neural networks (CNN) have had unprecedented success in medical imaging and, in particular, in medical image segmentation.  ...  The idea behind our method is to use a well-trained CNN, have it process cardiac images, identify the anatomically implausible results and warp these results toward the closest anatomically valid cardiac  ...  As a solution, several authors incorporate a shape prior to their model. Oktay et al. uses an approach named anatomically constrained neural network (ACNN) [6] .  ... 
doi:10.1109/tmi.2020.3003240 pmid:32746116 arXiv:2006.08825v1 fatcat:bgaiehfszjakzi3qgojdhb7xrm

Artificial Intelligence in Health in 2018: New Opportunities, Challenges, and Practical Implications

Gretchen Jackson, Jianying Hu, Section Editors for the IMIA Yearbook Section on Artificial Intelligence in Health
2019 IMIA Yearbook of Medical Informatics  
Queries employed Medical Subject Heading (MeSH®) terms and keywords representing AI methodologies and limited results to health applications.  ...  Conclusions: Performance of state-of-the-art AI machine learning algorithms can be enhanced by approaches that employ a multidisciplinary biomedical informatics pipeline to incorporate domain knowledge  ...  Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation. IEEE Trans Med Imaging 2018;37(2):384-95.  ... 
doi:10.1055/s-0039-1677925 pmid:31419815 pmcid:PMC6697508 fatcat:qhflemhlp5euvp5xmc4njd5pxq

Context-aware virtual adversarial training for anatomically-plausible segmentation [article]

Ping Wang and Jizong Peng and Marco Pedersoli and Yuanfeng Zhou and Caiming Zhang and Christian Desrosiers
2021 arXiv   pre-print
The proposed method offers a generic and efficient way to add any constraint on top of any segmentation network.  ...  Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance  ...  Anatomically constrained neural networks (acnns): application to cardiac image enhancement and segmentation. IEEE transactions on medical imaging 37, 384–395.  ... 
arXiv:2107.05532v2 fatcat:ksdfzfugqjdqretsilmvrcxodu

Accurate Segmentation of Heart Volume in CTA with Landmark-based Registration and Fully Convolutional Network

Fengjun Zhao, Haowen Hu, Yibing Chen, Jimin Liang, Xiaowei He, Yuqing Hou
2019 IEEE Access  
Second, the registration between the landmarks in each training image and the test image was performed by a shallow neural network, which guided the label propagation from atlases to the test image.  ...  First, we defined uniformity constrained landmarks in the training images and then trained a regression forest model (RFM) to detect these landmarks in the testing image.  ...  Actually, more and more deep learning methods based on U-Net/V-Net were devoted to the segmentation of myocardium or four heart chambers, such as the anatomically constrained neural networks (ACNNs) [  ... 
doi:10.1109/access.2019.2912467 fatcat:e2hhgtkp4facjdfk7b3rfazjc4

ResDUnet: A Deep Learning-Based Left Ventricle Segmentation Method for Echocardiography

Alyaa Amer, Xujiong Ye, Faraz Janan
2021 IEEE Access  
the application of AI to echocardiographic imaging.  ...  Segmentation of echocardiographic images is an essential step for assessing the cardiac functionality, as indicative clinical measures can be obtained from the delineation of the left ventricle chamber  ...  [15] used convolution neural network (CNN) to propose an approach named anatomically constrained neural network (ACNN), that uses auto-encoder to fit non-linear compact representation of the LV structure  ... 
doi:10.1109/access.2021.3122256 fatcat:3x3zwimy75bslmy7jvabieox7m

Artificial Intelligence in Quantitative Ultrasound Imaging: A Review [article]

Boran Zhou, Xiaofeng Yang, Tian Liu
2020 arXiv   pre-print
Therefore, it is in great need to develop automatic method to improve the imaging quality and aid in measurements in QUS.  ...  The purpose of this paper is to review recent research into the AI applications in QUS. This review first introduces the AI workflow, and then discusses the various AI applications in QUS.  ...  Recently, Oktay et al. developed an anatomically constrained neural network (ACNN) for 3D LV segmentation [150] .  ... 
arXiv:2003.11658v1 fatcat:iujuh7gra5ax7od2gxoo6yrbpe

Medical Image Segmentation Using Deep Learning: A Survey [article]

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi
2021 arXiv   pre-print
Firstly, compared to traditional surveys that directly divide literatures of deep learning on medical image segmentation into many groups and introduce literatures in detail for each group, we classify  ...  Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field.  ...  [68] proposed a novel and general method to combine a priori knowledge of shape and label structure into the anatomically constrained neural networks (ACNN) for medical image analysis tasks.  ... 
arXiv:2009.13120v3 fatcat:ntgbqwkz55axrjum72elbm6rry

Efficient and Robust Instrument Segmentation in 3D Ultrasound Using Patch-of-Interest-FuseNet with Hybrid Loss

Hongxu Yang, Caifeng Shan, Arthur Bouwan, Alexander F. Kolen, Peter H.N. de With
2020 Medical Image Analysis  
Lately, fully convolutional neural networks (FCNs), including 2D and 3D FCNs, have been used in different volumetric segmentation tasks.  ...  Furthermore, we propose a hybrid loss function, which consists of a contextual loss and a class-balanced focal loss, to improve the segmentation performance of the network.  ...  Acknowledgements This research was conducted in the framework of "Impulse-2 for the healthcare flagshiptopic ultrasound" at Eindhoven University of Technology in collaboration with Catharina Hospital Eindhoven and  ... 
doi:10.1016/j.media.2020.101842 pmid:33075639 fatcat:2xzkfkyzefau3fkiowjx4slede

Medical image segmentation using deep learning: A survey

Risheng Wang, Tao Lei, Ruixia Cui, Bingtao Zhang, Hongying Meng, Asoke K. Nandi
2022 IET Image Processing  
Firstly, compared to traditional surveys that directly divide literatures of deep learning on medical image segmentation into many groups and introduce literatures in detail for each group, we classify  ...  Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field.  ...  [68] proposed a novel and general method to combine a priori knowledge of shape and label structure into the anatomically constrained neural networks (ACNN) for medical image analysis tasks.  ... 
doi:10.1049/ipr2.12419 fatcat:zvgj3vdzqbfbzjoglgmtnn6ukq

Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography [article]

Sibo Qiao, Shanchen Pang, Gang Luo, Silin Pan, Xun Wang, Min Wang, Xue Zhai, Taotao Chen
2020 arXiv   pre-print
However, it is a greatly challenging task due to several key factors, such as numerous speckles in US images, the fetal cardiac chambers with small size and unfixed positions, and category indistinction  ...  These factors hinder the process of capturing robust and discriminative features, hence destroying fetal cardiac anatomical chambers precise localization.  ...  [27] present an anatomically constrained neural network (ACNN) to detect left ventricle endocardium in adult US images.  ... 
arXiv:2011.13096v2 fatcat:zojpiwd4qjf45pwu2evrt542oa

Intelligent Objective Osteon Segmentation Based on Deep Learning

Zichuan Qin, Fangbo Qin, Ying Li, Congyu Yu
2022 Frontiers in Earth Science  
Here we develop a deep convolutional neural network-based method for automated osteohistological segmentation.  ...  Raw images are firstly divided into sub-images and the borders are expanded to guarantee the osteon regions integrity.  ...  Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation. IEEE Trans. Med.  ... 
doi:10.3389/feart.2022.783481 fatcat:4h6txaicizag3cunkx6gqwhoaq

Segmentation of Tricuspid Valve Leaflets From Transthoracic 3D Echocardiograms of Children With Hypoplastic Left Heart Syndrome Using Deep Learning

Christian Herz, Danielle F. Pace, Hannah H. Nam, Andras Lasso, Patrick Dinh, Maura Flynn, Alana Cianciulli, Polina Golland, Matthew A. Jolley
2021 Frontiers in Cardiovascular Medicine  
We utilized a Fully Convolutional Network (FCN) to segment tricuspid valves from transthoracic 3DE. We trained on 133 3DE image-segmentation pairs and validated on 28 images.  ...  We are now working to deploy this network for public use.  ...  Anatomically constrained neural networks (ACNNS): application to cardiac image enhancement and segmentation. IEEE Trans Med Imaging.  ... 
doi:10.3389/fcvm.2021.735587 pmid:34957233 pmcid:PMC8696083 fatcat:f6xjcnvoxjhr7nqwz4qtcidrou

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation [article]

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding
2020 arXiv   pre-print
The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks.  ...  We hope this survey article increases the community awareness of the techniques that are available to handle imperfect medical image segmentation datasets.  ...  Chen et al. (2019b) makes use of MUNIT to translate between balanced steady-state free precession (bSSFP) images having masks for 3 cardiac structures and late-gadolinium enhanced (LGE) images that dont  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi
« Previous Showing results 1 — 15 out of 24 results