Filters








12,914 Hits in 7.1 sec

Positional Contrastive Learning for Volumetric Medical Image Segmentation [article]

Dewen Zeng, Yawen Wu, Xinrong Hu, Xiaowei Xu, Haiyun Yuan, Meiping Huang, Jian Zhuang, Jingtong Hu, Yiyu Shi
2021 arXiv   pre-print
To address this issue, we propose a novel positional contrastive learning (PCL) framework to generate contrastive data pairs by leveraging the position information in volumetric medical images.  ...  A critical step in contrastive learning is the generation of contrastive data pairs, which is relatively simple for natural image classification but quite challenging for medical image segmentation due  ...  Supplementary: Positional Contrastive Learning for Volumetric Medical Image Segmentation Table 1 : Ablation study. The influence of threshold on contrastive learning accuracy.  ... 
arXiv:2106.09157v3 fatcat:pxxuucvxofdcjiym6nzyxcfjem

Federated Contrastive Learning for Volumetric Medical Image Segmentation [chapter]

Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu
2021 Lecture Notes in Computer Science  
In this work, we propose an FCL framework for volumetric medical image segmentation with limited annotations.  ...  However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.  ...  learning for volumetric medical image segmentation with limited annotations.  ... 
doi:10.1007/978-3-030-87199-4_35 fatcat:h5ekgozd45b4vab43djcsxvr6q

Momentum Contrastive Voxel-wise Representation Learning for Semi-supervised Volumetric Medical Image Segmentation [article]

Chenyu You, Ruihan Zhao, Lawrence Staib, James S. Duncan
2022 arXiv   pre-print
Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation.  ...  Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the same image) against a set of negatives within the entire remainder of the batch by simply mapping all input features  ...  medical image segmentation.  ... 
arXiv:2105.07059v4 fatcat:2le4sldtendypal37dggq5hwki

3D-RADNet: Extracting labels from DICOM metadata for training general medical domain deep 3D convolution neural networks

Richard Du, Varut Vardhanabhuti
2020 International Conference on Medical Imaging with Deep Learning  
However, as of now, there has not been a popular dataset for training 3D volumetric medical images. This is mainly due to the time and expert knowledge required to accurately annotate medical images.  ...  Our proposed network shows promising results to be used as a backbone network for transfer learning to another task.  ...  ResNet may not be optimal for volumetric medical images. Alternative network architecture tailed for medical images may increase the performance of the network.  ... 
dblp:conf/midl/DuV20 fatcat:vhzjmnc3cray5cvctp3jcyuycy

Self-Supervised Generative Style Transfer for One-Shot Medical Image Segmentation [article]

Devavrat Tomar, Behzad Bozorgtabar, Manana Lortkipanidze, Guillaume Vray, Mohammad Saeed Rad, Jean-Philippe Thiran
2021 arXiv   pre-print
Motivated by atlas-based segmentation, we propose a novel volumetric self-supervised learning for data augmentation capable of synthesizing volumetric image-segmentation pairs via learning transformations  ...  In medical image segmentation, supervised deep networks' success comes at the cost of requiring abundant labeled data.  ...  Conclusion and Future Work We proposed the novel volumetric contrastive loss used for style transfer by leveraging unlabeled data for oneshot medical image segmentation.  ... 
arXiv:2110.02117v1 fatcat:ampolwvdi5hkrcz4goo5lcjlh4

Biomarkers for Hypoxia, HPVness, and Proliferation from Imaging Perspective [chapter]

Sebastian Sanduleanu, Simon Keek, Lars Hoezen, Philippe Lambin
2021 Critical Issues in Head and Neck Oncology  
AbstractRecent advances in quantitative imaging with handcrafted radiomics and unsupervised deep learning have resulted in a plethora of validated imaging biomarkers in the field of head and neck oncology  ...  OS) or progression free survival (PFS), automatically segment a region of interest e.g. an organ at risk for radiotherapy dose or the gross tumor volume (GTV).  ...  Medical images are acquired, pre-processed, and are provided to the deep learning/radiomics workflow.  ... 
doi:10.1007/978-3-030-63234-2_2 fatcat:w3flgmddefhadnbinuzii2hldm

Contrastive Learning with Temporal Correlated Medical Images: A Case Study using Lung Segmentation in Chest X-Rays [article]

Dewen Zeng, John N. Kheir, Peng Zeng, Yiyu Shi
2021 arXiv   pre-print
In this work, we use lung segmentation in chest X-rays as a case study and propose a contrastive learning framework with temporal correlated medical images, named CL-TCI, to learn superior encoders for  ...  Many existing works have demonstrated improved results by applying contrastive learning in classification and object detection tasks for either natural images or medical images.  ...  All chest radiographs for a series of consecutive cardiac patients receiving a chest radiograph in June 2021 were identified, anonymized, and exported for review.  ... 
arXiv:2109.03233v2 fatcat:h7gdikhrgbcjhnxp2o6qcuurpe

Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation [article]

Kiran Kokilepersaud and Mohit Prabhushankar and Ghassan AlRegib
2022 arXiv   pre-print
In order to incorporate this context within contrastive learning, we propose a novel positive pair selection strategy based on the position of slices within a seismic volume.  ...  However, traditional contrastive learning approaches are based on assumptions from the domain of natural images that do not make use of seismic context.  ...  Figure 3 : 3 Figure 3: Seismic volumetric contrastive learning overall approach. 1) Supervised contrastive learning by assigning labels based on position within F3 Block. 2) Use representations learnt  ... 
arXiv:2206.08158v1 fatcat:hsuzvfbmsnfu7mrthi67366wya

Distributed Contrastive Learning for Medical Image Segmentation [article]

Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu
2022 arXiv   pre-print
In this work, we propose two federated self-supervised learning frameworks for volumetric medical image segmentation with limited annotations.  ...  However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.  ...  CONCLUSION This work aims to enable federated contrastive learning (FCL) for volumetric medical image segmentation with limited annotations.  ... 
arXiv:2208.03808v1 fatcat:3ruylvqxkfbzbo7db5oiafsupa

Knowledge infused cascade convolutional neural network for segmenting retinal vessels in volumetric optical coherence tomography [article]

Liyang Fang, Jianlong Yang, Lei Mou, Huihong Zhang, Zhenjie Chai, Zhi Chen, Jiang Liu
2019 arXiv   pre-print
We present a cascade deep neural network to segment retinal vessels in volumetric optical coherence tomography (OCT).  ...  for handling such specific tasks.  ...  The U-Net is an efficient fully convolutional network for medical image segmentation.  ... 
arXiv:1910.09187v1 fatcat:rwy4slhvqbc4hgwk6nhbdblok4

VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation [article]

Hao Chen, Qi Dou, Lequan Yu, Pheng-Ann Heng
2016 arXiv   pre-print
However, how to fully leverage contextual representations for recognition tasks from volumetric data has not been well studied, especially in the field of medical image computing, where a majority of image  ...  We believe this work unravels the potential of 3D deep learning to advance the recognition performance on volumetric image segmentation.  ...  However, in the field of medical image computing, volumetric data accounts for a large portion of medical image modalities, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), etc.  ... 
arXiv:1608.05895v1 fatcat:xvg53rucyvgjrookcm73kgymxq

Three Dimensional Root CT Segmentation using Multi-Resolution Encoder-Decoder Networks

Mohammadreza Soltaninejad, Craig J. Sturrock, Marcus Griffiths, Tony P. Pridmore, Michael P. Pound
2020 IEEE Transactions on Image Processing  
We compare against a number of different encoder-decoder based architectures from the literature, as well as a popular existing image analysis tool designed for root CT segmentation.  ...  The complete network is a memory efficient implementation that is still able to resolve small root detail in large volumetric images.  ...  ACKNOWLEDGMENT The work reported here was funded by the US Dept of Energy via the ARPA-e ROOTS project Low Cost X-Ray CT System for in-situ Imaging of Roots.  ... 
doi:10.1109/tip.2020.2992893 pmid:32406835 fatcat:ivqqxptm4bfn5bkkj4b2iywffi

Weakly-supervised Learning For Catheter Segmentation in 3D Frustum Ultrasound [article]

Hongxu Yang, Caifeng Shan, Alexander F. Kolen, Peter H. N. de With
2020 arXiv   pre-print
More crucially, the Frustum image segmentation provides a much faster and cheaper solution for segmentation in 3D US image, which meet the demands of clinical applications.  ...  Accurate and efficient catheter segmentation in 3D ultrasound (US) is essential for cardiac intervention.  ...  Instrument segmentation in 3D US images Medical instrument in 3D medical images, especially 3D US, has been studied in recent years.  ... 
arXiv:2010.09525v1 fatcat:6fg6lspg3rg33lw227yogef7fq

Automated Segmentation of Colorectal Tumor in 3D MRI Using 3D Multiscale Densely Connected Convolutional Neural Network

Mumtaz Hussain Soomro, Matteo Coppotelli, Silvia Conforto, Maurizio Schmid, Gaetano Giunta, Lorenzo Del Secco, Emanuele Neri, Damiano Caruso, Marco Rengo, Andrea Laghi
2019 Journal of Healthcare Engineering  
For such a purpose, a novel deep learning-based algorithm suited for volumetric colorectal tumor segmentation is proposed.  ...  We compared our proposed method to other existing volumetric medical image segmentation baseline methods (particularly 3D U-net and DenseVoxNet) in our segmentation tasks.  ...  Generally, these 2D CNNs with 2D kernels have been used for medical image segmentation where volumetric segmentation was performed in a slice-by-slice sequential order.  ... 
doi:10.1155/2019/1075434 pmid:30838121 pmcid:PMC6374810 fatcat:udcblgpgkjbxdevfh7z2phhjom

A Review of Self-supervised Learning Methods in the Field of Medical Image Analysis

Jiashu Xu, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute", Kyiv, 03056, Ukraine
2021 International Journal of Image Graphics and Signal Processing  
So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets.  ...  This article provides the latest and most detailed overview of self-supervised learning in the medical field and promotes the development of unsupervised learning in the field of medical imaging.  ...  Acknowledgment This research has been partially supported by China Scholarship Council (CSC), and Special thanks should go to my supervisor professor Sergii Stirenko, for his instructive advice and useful  ... 
doi:10.5815/ijigsp.2021.04.03 fatcat:ff7ybaplqncthgswf3zy7cbeza
« Previous Showing results 1 — 15 out of 12,914 results