13,574 Hits in 5.1 sec

ENRIch: Exploiting Image Similarity to Maximize Efficient Machine Learning in Medical Imaging [article]

Erin M Chinn, Rohit Arora, Ramy Arnaout, Rima Arnaout
2021 medRxiv   pre-print
First, we compute pairwise similarity metrics for images in a given dataset, resulting in a matrix of pairwise similarity values.  ...  Deep learning (DL) has been applied with success in proofs of concept across biomedical imaging, including across modalities and medical specialties1-17.  ...  Introduction Labeling and annotation can be costly bottlenecks for supervised learning tasks in medical imaging.  ... 
doi:10.1101/2021.05.22.21257645 fatcat:qh5nmhmv4ned7liu2g7zmayafe

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

Guotai Wang, Maria A. Zuluaga, Wenqi Li, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sebastien Ourselin, Tom Vercauteren
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications.  ...  We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy.  ...  In this paper, we propose a novel interactive method for 2D and 3D medical image segmentation that leverages deep learning.  ... 
doi:10.1109/tpami.2018.2840695 pmid:29993532 pmcid:PMC6594450 fatcat:u4ljunhfarclzlmlipbprvdi2e

A Spatially Constrained Deep Convolutional Neural Network for Nerve Fiber Segmentation in Corneal Confocal Microscopic Images using Inaccurate Annotations [article]

Ning Zhang, Susan Francis, Rayaz Malik, Xin Chen
2020 arXiv   pre-print
Semantic image segmentation is one of the most important tasks in medical image analysis.  ...  In our proposed method, image segmentation is formulated as a graph optimization problem that is solved by a DCNN model learning process.  ...  ABSTRACT Semantic image segmentation is one of the most important tasks in medical image analysis.  ... 
arXiv:2004.09443v1 fatcat:mjlw2jzynjhypharr5iqqjxzqy

Using the Pn Potts model with learning methods to segment live cell images

Christopher Russell, Dimitris Metaxas, Christophe Restif, Philip Torr
2007 2007 IEEE 11th International Conference on Computer Vision  
We present a segmentation method for live cell images, using graph cuts and learning methods.  ...  We present the model and the learning methods we used, and compare our segmentation results with similar work in cytometry.  ...  To the best of our knowledge this is the first use of learning methods combined with P n Potts model in medical imaging.  ... 
doi:10.1109/iccv.2007.4409131 dblp:conf/iccv/RussellMRT07 fatcat:wjhbgaq7mjc6zgs5bssaa5muxq

Discriminative learning of deformable contour models

Haithem Boussaid, Iasonas Kokkinos, Nikos Paragios
2014 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)  
In this work we propose a machine learning approach to improve shape detection accuracy in medical images with deformable contour models (DCMs).  ...  Our algorithm trains DCMs in an joint manner -all the parameters are learned simultaneously, while we use rich local features for landmark localization.  ...  INTRODUCTION Precisely localizing shapes in medical images is of paramount importance in a host of medical image applications, involving organ segmentation, tracking, registration and atlas building.  ... 
doi:10.1109/isbi.2014.6867948 dblp:conf/isbi/BoussaidKP14 fatcat:46f27w6tb5dddfvgu3bgl4cvom

Comparative Study of Retinal Blood Vessel Segmentation based on SVM and K-NN Classification

Syed Akhter Hussain
2019 International Journal for Research in Applied Science and Engineering Technology  
Parameters of the method are learned automatically using a structured output support vector machine and k-nearest neighbour, a supervised technique widely used for structured prediction in a number of  ...  Glaucoma is one of the most leading eye disease in the world it damages the optic nerve, the part of the eye which carries the images in the form of electrical signals to the brain, and leads to loss of  ...  Learning CRFs with Structured Output SVM Our aim is to learn a vector , where , and are the weights for the unary features, for the bias term and for the pairwise kernels, respectively.  ... 
doi:10.22214/ijraset.2019.4193 fatcat:65jifbbw2fcb7mwmlnrt7m22au

Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation [article]

Ho Hin Lee, Yucheng Tang, Qi Yang, Xin Yu, Shunxing Bao, Leon Y. Cai, Lucas W. Remedios, Bennett A. Landman, Yuankai Huo
2021 arXiv   pre-print
Compared with current state-of-the-art training strategies, our proposed pipeline yields a substantial improvement of 5.53% and 6.09% on Dice score for both medical image segmentation cohorts respectively  ...  However, multiple target objects (with different semantic meanings) may exist in a single image, which poses a problem for adapting traditional contrastive learning methods from prevalent 'image-level  ...  loss for medical image segmentation with multi-object images in single network architecture.  ... 
arXiv:2106.01596v2 fatcat:cm7xh4qrarewjj5gegpudldzve

Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Images [article]

Julian Alberto Palladino, Diego Fernandez Slezak, Enzo Ferrante
2020 arXiv   pre-print
We aim at learning a mapping function to transform volumetric MR images between domains, which are characterized by different medical centers and MR machines with varying brand, model and configuration  ...  During the last years, convolutional neural networks (CNN) specifically tailored for biomedical image segmentation have outperformed all previous techniques in this task.  ...  captured in three different medical centers alongside their manual WMH segmentations.  ... 
arXiv:2009.04985v1 fatcat:vnk77kisdrf7teo6eo26zeqs2q

Learning Fully-Connected CRFs for Blood Vessel Segmentation in Retinal Images [chapter]

José Ignacio Orlando, Matthew Blaschko
2014 Lecture Notes in Computer Science  
In this work, we present a novel method for blood vessel segmentation in fundus images based on a discriminatively trained, fully connected conditional random field model.  ...  Retinal image analysis is greatly aided by blood vessel segmentation as the vessel structure may be considered both a key source of signal, e.g. in the diagnosis of diabetic retinopathy, or a nuisance,  ...  The test set provides two manual segmentations generated by two different experts for each image.  ... 
doi:10.1007/978-3-319-10404-1_79 fatcat:2mrhizuwqze75f6ne7txtfi37q

MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation [article]

Xinzhe Luo, Xiahai Zhuang
2020 arXiv   pre-print
We highlight the versatility of the proposed framework for various applications on multimodal cardiac images, including single-atlas-based segmentation (SAS) via pairwise registration and multi-atlas segmentation  ...  The results show that the proposed framework achieved an average Dice score of 0.871± 0.025 for whole-heart segmentation on MR images and 0.783± 0.082 for myocardium segmentation on LGE MR images.  ...  Pairwise MvMM-RegNet for SAS.  ... 
arXiv:2006.15573v2 fatcat:q5lqfvqcendurp46eii5n42lby

Learning Low-order Models for Enforcing High-order Statistics

Patrick Pletscher, Pushmeet Kohli
2012 Journal of machine learning research  
We test the efficacy of our method on the problem of foreground-background image segmentation.  ...  Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines.  ...  Acknowledgements We would like to thank Pablo Márquez Neila for sharing the mitochondria cell segmentation data set and the unary classifier responses. We would also like to thank D.  ... 
dblp:journals/jmlr/PletscherK12 fatcat:e6ql54dle5aufoo3suc4soe25e

Pairwise Relation Learning for Semi-supervised Gland Segmentation [article]

Yutong Xie, Jianpeng Zhang, Zhibin Liao, Chunhua Shen, Johan Verjans, Yong Xia
2020 arXiv   pre-print
In this paper, we propose the pairwise relation-based semi-supervised (PRS^2) model for gland segmentation on histology images.  ...  Since both networks share their encoders, the image representation ability learned by PR-Net can be transferred to S-Net to improve its segmentation performance.  ...  The PR-Net exploits the semantic consistency between each pair of images for unsupervised pairwise relation learning.  ... 
arXiv:2008.02699v1 fatcat:rdi7qjk67fbdzm4jd43foo2wte

Context Enhanced Graphical Model for Object Localization in Medical Images [chapter]

Yang Song, Weidong Cai, Heng Huang, Yue Wang, David Dagan Feng
2013 Lecture Notes in Computer Science  
Successful applications on two different medical imaging applications -lesion dissimilarity on thoracic PET-CT images and cell segmentation on microscopic imagesare demonstrated in the experimental results  ...  This object localization method is generally applicable to different medical imaging applications, in which the objects can be distinguished from the background mainly based on feature differences.  ...  Summary In this Chapter, we describe a new method for object localization in medical images [20] .  ... 
doi:10.1007/978-3-642-36620-8_19 fatcat:23otoqlim5eejpe4to6a2r7dey

Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation [article]

Li Sulimowicz, Ishfaq Ahmad, Alexander Aved
2018 arXiv   pre-print
SP-Pairwise potentials incorporate the superpixel-based higher-order cues by conditioning on a segment filtered image and share the same set of parameters as the conventional pairwise potentials.  ...  However, their major short coming is considerably longer time to learn higher-order potentials and extra hyperparameters and/or weights compared with pairwise models.  ...  Semantic segmentation has numerous promising applications, such as autonomous driving, robotic navigation, computer-aided medical diagnosis, and image editing [21, 11] .  ... 
arXiv:1805.11737v1 fatcat:rt6cok5gzzchhjw3w2givscery

Segmentation Techniques for Brain Tumor from MRI – A Survey [chapter]

Jeevitha R, Selvaraj D
2020 Advances in Parallel Computing  
In the medical science, Biomedical images are the core. Generally, Magnetic Resonance Imaging(MRI) scan is the most usual procedure followed.  ...  Radio waves and strong magnetic flux were used to determine comprehensive images of tissues and organs inside the body. The enhancement in MRI scan has become a large milestone in the medical world.  ...  To handle the inadequate big brain tumor databases and irregular modality of image for deep learning methods, they proposed an augmented brain tumor images to enhance the training dataset by introducing  ... 
doi:10.3233/apc200181 fatcat:fopw7k2twzfftoancsrqdcj4ki
« Previous Showing results 1 — 15 out of 13,574 results