288 Hits in 2.9 sec

Deep Geodesic Learning for Segmentation and Anatomical Landmarking

Neslisah Torosdagli, Denise K. Liberton, Payal Verma, Murat Sincan, Janice S. Lee, Ulas Bagci
2019 IEEE Transactions on Medical Imaging  
In this paper, we propose a novel deep learning framework for anatomy segmentation and automatic landmarking.  ...  In the second step, we formulate the landmark localization problem directly on the geodesic space for sparsely-spaced anatomical landmarks.  ...  For an extremely challenging dataset, the proposed geodesic deep learning algorithm is shown to be robust by successfully segmenting the mandible bones and providing highly accurate anatomical landmarks  ... 
doi:10.1109/tmi.2018.2875814 pmid:30334750 pmcid:PMC6475529 fatcat:ub7hwjh2nbhb3ockc2f37zfb3y

Machine learning and patient-specific biomechanical methods for assessing outcome in total shoulder arthroplasty

Osman Berk Satir
2021 Zenodo  
Poster: Machine learning and patient-specific biomechanical methods for assessing outcome in total shoulder arthroplasty  ...  potential causes for the observed complications. • Thus, we propose image analysis and deep learning-based approaches to quantify all potential preoperative mechanical markers and identify the ones that  ...  landmarks on scapula. • Two different approaches are being investigated:  Image space  Geodesic distance between all voxels and predetermined landmarks with CNN  Shape space  Geodesic distance between  ... 
doi:10.5281/zenodo.4767454 fatcat:dnko2mlp3re5fhkpx3idx63beq

Learning Deep Features for Shape Correspondence with Domain Invariance [article]

Praful Agrawal, Ross T. Whitaker, Shireen Y. Elhabian
2021 arXiv   pre-print
Results on anatomical datasets of human scapula, femur, and pelvis bones demonstrate that features learned in supervised fashion show improved performance for correspondence estimation compared to the  ...  However, they heavily rely on manual expertise to create domain-specific features and consistent landmarks.  ...  In this regard and to alleviate the need for manual intervention through the selection of anatomical landmarks for network training, we make use of recent advances in machine learning for domain adaptation  ... 
arXiv:2102.10493v1 fatcat:qqjt5txznrfxlbh742h5tuqa5u

Relational Reasoning Network (RRN) for Anatomical Landmarking [article]

Neslisah Torosdagli, Mary McIntosh, Denise K. Liberton, Payal Verma, Murat Sincan, Wade W. Han, Janice S. Lee, Ulas Bagci
2019 arXiv   pre-print
The proposed RRN works in an end-to-end manner, utilizing learned relations of the landmarks based on dense-block units and without the need for segmentation.  ...  To the best of our knowledge, this is the first of its kind algorithm finding anatomical relations of the objects using deep learning.  ...  More recently, we integrated the manifold information (geodesic) in a deep learning architecture to improve robustness of the segmentation based strategies for landmarking [4] , and obtained promising  ... 
arXiv:1904.04354v1 fatcat:i345rml2m5evta5p2uzpnwvsge

Feature-based Characterisation of Patient-specific 3D Anatomical Models

Imon Banerjee, Martina Paccini, Enrico Ferrari, Chiara Eva Catalano, Silvia Biasotti, Michela Spagnuolo
2019 Smart Tools and Applications in Graphics  
The performance of both state of the art and novel features has been evaluated in a machine learning setting to identify a set of significant anatomical landmarks on patient data.  ...  In particular, we introduce an approach specially designed for the characterisation of anatomical landmarks on patient-specific 3D carpal bone models represented as triangular meshes.  ...  On average, 10 -12 anatomical landmarks are listed for each carpal bone, and in total 64 anatomical landmarks are catalogued for the whole carpal district. 3.  ... 
doi:10.2312/stag.20191362 dblp:conf/egItaly/BanerjeePFCBS19 fatcat:bixc767f7rbqloarobyfoynmq4

Convolutional neural networks on surfaces via seamless toric covers

Haggai Maron, Meirav Galun, Noam Aigerman, Miri Trope, Nadav Dym, Ersin Yumer, Vladimir G. Kim, Yaron Lipman
2017 ACM Transactions on Graphics  
We show that our algorithm compares favorably with competing geometric deep-learning algorithms for segmentation tasks, and is able to produce meaningful correspondences on anatomical surfaces where hand-crafted  ...  We demonstrate the usefulness of our approach by presenting two applications: human body segmentation, and automatic landmark detection on anatomical surfaces.  ...  The authors would like to thank Ayan Sinha and Karthik Ramani for sharing their code, Shahar Kovalsky and Julia Winchester for providing biological insights, and the anonymous reviewers for their useful  ... 
doi:10.1145/3072959.3073616 fatcat:whqvm77hdfedho5zkfw4b2nck4

Geodesic Information Flows [chapter]

M. Jorge Cardoso, Robin Wolz, Marc Modat, Nick C. Fox, Daniel Rueckert, Sebastien Ourselin
2012 Lecture Notes in Computer Science  
Due to the time consuming nature of manually segmenting, parcellating and localising landmarks in medical images, these sources of information tend to be scarce and limited to small, and sometimes morphologically  ...  Comparison to state-of-the-art propagation methods showed highly statistically significant (p < 10 −4 ) improvements in accuracy when propagating both structural parcelations and brain segmentations geodesically  ...  This study was supported by the EPSRC (EP/H046410/1), the CBRC Strategic Investment Award (Ref. 168) and the 7th Framework Programme by the European Commission (  ... 
doi:10.1007/978-3-642-33418-4_33 fatcat:2r4glsu245g3xg3szb5nwvphfu

Deep learning-based detection of anthropometric landmarks in 3D infants head models

Helena R. Torres, Bruno Oliveira, Fernando Veloso, Mario Ruediger, Wolfram Burkhardt, António Moreira, Nuno Dias, Pedro Morais, Jaime C. Fonseca, João L. Vilaça, Kensaku Mori, Horst K. Hahn
2019 Medical Imaging 2019: Computer-Aided Diagnosis  
The proposed method is divided into two stages: (i) unfolding of the 3D head model surface; and (ii) landmarks' detection through a deep learning strategy.  ...  In the second stage, a deep learning strategy is used to detect the anthropometric landmarks in a 3-channel image constructed using the combination of informational maps.  ...  Furthermore, the authors acknowledge FCT, Portugal, and the European Social Found, European Union, for funding support through the "Programa Operacional Capital Humano" (POCH) in the scope of the PhD grants  ... 
doi:10.1117/12.2512196 dblp:conf/micad/Torres0VRBMDMFV19 fatcat:ws3vqfxdhrfkxoykeom4v7shza

Machine learning in orthodontics: Challenges and perspectives

Jialing Liu, Ye Chen, Shihao Li, Zhihe Zhao, Zhihong Wu
2021 Advances in Clinical and Experimental Medicine  
Machine learning models have been found to perform similar to or with even higher accuracy than humans in landmark identification, skeletal classification, bone age prediction, and tooth segmentation.  ...  It is hopeful that AI, especially machine learning (ML), due to its powerful capacity for image processing and decision support systems, will find extensive application in orthodontics in the future.  ...  idea, orthodontists could develop deep learning models for more accurate diagnosis.  ... 
doi:10.17219/acem/138702 pmid:34610222 fatcat:re6hs745sjdfhjapvmwzioms44

Deep Nested Level Sets: Fully Automated Segmentation of Cardiac MR Images in Patients with Pulmonary Hypertension [chapter]

Jinming Duan, Jo Schlemper, Wenjia Bai, Timothy J. W. Dawes, Ghalib Bello, Georgia Doumou, Antonio De Marvao, Declan P. O'Regan, Daniel Rueckert
2018 Lecture Notes in Computer Science  
The proposed method explicitly takes into account the image features learned from a deep neural network.  ...  We demonstrate that the proposed deep nested level set (DNLS) method outperforms existing state-of-the-art methods for CMR segmentation in PH patients.  ...  Second, existing approaches rely on manual initialisation of the image segmentation or definition of key anatomical landmarks [1, 2, 3] .  ... 
doi:10.1007/978-3-030-00937-3_68 fatcat:ogo6mymnrzdfpkbfo7tmtpovze

Geodesic Information Flows: Spatially-Variant Graphs and Their Application to Segmentation and Fusion

M. Jorge Cardoso, Marc Modat, Robin Wolz, Andrew Melbourne, David Cash, Daniel Rueckert, Sebastien Ourselin
2015 IEEE Transactions on Medical Imaging  
Clinical annotations, such as voxel-wise binary or probabilistic tissue segmentations, structural parcellations, pathological regions-of-interest and anatomical landmarks are key to many clinical studies  ...  We illustrate the utility of the proposed framework on two example applications: brain parcellation using categorical labels and tissue segmentation using probabilistic features.  ...  For example, annotations such as voxel-wise labels (characterising structural parcellations or tissue segmentations), landmarks (localising anatomical features) and diagnosis (characterising the patient  ... 
doi:10.1109/tmi.2015.2418298 pmid:25879909 fatcat:ipq3uexopjdpnhrx2ylttxlqyq

Atlas and snake based segmentation of organs at risk in radiotherapy in head MRIs

Boudahla Mohammed Karim
2014 2014 Third IEEE International Colloquium in Information Science and Technology (CIST)  
We propose a deep learning method for segmentation of organs at risk inside the head, from Magnetic Resonance (MR) images.  ...  Convolutional Neural Networks are suitable for this task, as they have the ability to automatically learn complex and relevant image features.  ...  First, we proposed a deep learning model and a training algorithm for segmentation of multiple and non-exclusive anatomical structures.  ... 
doi:10.1109/cist.2014.7016646 dblp:conf/cist/Karim14 fatcat:jzm3pywrwvbqji6zuyjl6dfc3m

Training models of anatomic shape variability

Derek Merck, Gregg Tracton, Rohit Saboo, Joshua Levy, Edward Chaney, Stephen Pizer, Sarang Joshi
2008 Medical Physics (Lancaster)  
Learning probability distributions of the shape of anatomic structures requires fitting shape representations to human expert segmentations from training sets of medical images.  ...  Our novel method is to jointly estimate both the best geometric model for any given image and the shape distribution for the entire population of training images by iteratively relaxing purely geometric  ...  These LM correspond to a set of explicitly identified anatomic features, LI, landmarks noted by the raters on the segmentations they manually produce.  ... 
doi:10.1118/1.2940188 pmid:18777919 pmcid:PMC2809709 fatcat:tdvcmw7pdzdgxinulk7apipq6u

One-shot Weakly-Supervised Segmentation in Medical Images [article]

Wenhui Lei, Qi Su, Ran Gu, Na Wang, Xinglong Liu, Guotai Wang, Xiaofan Zhang, Shaoting Zhang
2021 arXiv   pre-print
Deep neural networks usually require accurate and a large number of annotations to achieve outstanding performance in medical image segmentation.  ...  One-shot segmentation and weakly-supervised learning are promising research directions that lower labeling effort by learning a new class from only one annotated image and utilizing coarse labels instead  ...  In recent years, deep learning-based segmentation algorithms have achieved superior performance with sufficient annotated data.  ... 
arXiv:2111.10773v1 fatcat:bzryc4hkqnabbifopr3icimdku

Front Matter: Volume 9784

2016 Medical Imaging 2016: Image Processing  
9784 0L Combined self-learning based single-image super-resolution and dual-tree complex wavelet transform denoising for medical images [9784-20] 9784 0M Sinogram smoothing and interpolation via alternating  ...  [9784-22] SESSION 6 SHAPE 9784 0P Landmark based shape analysis for cerebellar ataxia classification and cerebellar atrophy pattern visualization [9784-24] 9784 0Q Multi-object model-based multi-atlas  ...  [9784-44] 9784 1A Learning from redundant but inconsistent reference data: anatomical views and measurements for fetal brain screening [9784-45] SESSION 10 SEGMENTATION 9784 1B Breast segmentation  ... 
doi:10.1117/12.2240619 fatcat:kot6cogf4rf6dcjhkzdrr5gahi
« Previous Showing results 1 — 15 out of 288 results