2,197 Hits in 8.7 sec

PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation [article]

Guotai Wang, Xiangde Luo, Ran Gu, Shuojue Yang, Yijie Qu, Shuwei Zhai, Qianfei Zhao, Kang Li, Shaoting Zhang
2022 arXiv   pre-print
PyMIC is built on the PyTorch framework and supports development of semi-supervised, weakly supervised and noise-robust learning methods for medical image segmentation.  ...  Methods: Our proposed toolkit named PyMIC is a modular deep learning platform for medical image segmentation tasks.  ...  It's modular functionalities support fast development of medical image segmentation models with limited annotations based on the buildin implementations of semi-supervised, weakly-supervised and noisy-label  ... 
arXiv:2208.09350v1 fatcat:roolgrrxcbecnnknah2i4f72ge

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  
For weakly supervised learning approaches, we investigate literature according to data augmentation, transfer learning, and interactive segmentation, separately.  ...  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.  ...  In addition, transfer learning is an important way to achieve weakly supervised medical image segmentation.  ... 
doi:10.1049/ipr2.12419 fatcat:zvgj3vdzqbfbzjoglgmtnn6ukq

Weakly Supervised Object Localization and Detection: A Survey [article]

Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
2021 arXiv   pre-print
In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets  ...  applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.  ...  Discussion Compared with the off-the-shelf deep model-based weakly supervised object detection and localization methods, the deep weakly supervised learning methods exploits the merits of deep learning  ... 
arXiv:2104.07918v1 fatcat:dwl6sjfzibdilnvjnrbifp4uke

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
For weakly supervised learning approaches, we investigate literature according to data augmentation, transfer learning, and interactive segmentation, separately.  ...  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.  ...  In addition, transfer learning is an important way to achieve weakly supervised medical image segmentation.  ... 
arXiv:2009.13120v3 fatcat:ntgbqwkz55axrjum72elbm6rry

IEEE Access Special Section Editorial: Emerging Deep Learning Theories and Methods for Biomedical Engineering

Yu-Dong Zhang, Zhengchao Dong, Juan Manuel Gorriz, Yizhang Jiang, Ming Yang, Shui-Hua Wang
2021 IEEE Access  
., master's, and doctor's degrees in medical imaging from Southeast University, Nanjing, China, in 1995China, in , 2004China, in , and 2011.  ...  Her research interests include functional MRI, radiomics, and cardiovascular imaging, especially in pediatric patients.  ...  In the article ''Weakly supervised deep learning for COVID-19 infection detection and classification from CT images,'' by Hu et al., the authors propose a weakly supervised deep learning strategy for detecting  ... 
doi:10.1109/access.2021.3080355 fatcat:oez6u3npt5ff7aw7tscwyvlmvq

Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images

Seung Yeon Shin, Soochahn Lee, Il Dong Yun, Sun Mi Kim, Kyoung Mu Lee
2019 IEEE Transactions on Medical Imaging  
We propose a systematic weakly and semi-supervised training scenario with appropriate training loss selection.  ...  The results trained with only 10 strongly annotated images along with weakly annotated images were comparable to results trained from 800 strongly annotated images, with the 95% confidence interval (CI  ...  Methods that incorporate MIL into the deep learning framework have also been proposed for medical imaging problems [18] , [19] . The method proposed by Yan et al.  ... 
doi:10.1109/tmi.2018.2872031 pmid:30273145 fatcat:57g2ijygvrexzovwsurqlt2jni

Deep Complementary Joint Model for Complex Scene Registration and Few-shot Segmentation on Medical Images [article]

Yuting He, Tiantian Li, Guanyu Yang, Youyong Kong, Yang Chen, Huazhong Shu, Jean-Louis Coatrieux, Jean-Louis Dillenseger, Shuo Li
2020 arXiv   pre-print
Deep learning-based medical image registration and segmentation joint models utilize the complementarity (augmentation data or weakly supervised data from registration, region constraints from segmentation  ...  However, further adoption of the joint models are hindered: 1) the diversity of augmentation data is reduced limiting the further enhancement of segmentation, 2) misaligned regions in weakly supervised  ...  supported by the National Natural Science Foundation under grants (61828101,31571001,31800825), the Short-Term Recruitment Program of Foreign Experts (WQ20163200398), and Southeast University-Nanjing Medical  ... 
arXiv:2008.00710v1 fatcat:dhdwvcdskvb4hgfmbqp3lroeoe

Tackling the Problem of Limited Data and Annotations in Semantic Segmentation [article]

Ahmadreza Jeddi
2020 arXiv   pre-print
In this work, the case of semantic segmentation on a small image dataset (simulated by 1000 randomly selected images from PASCAL VOC 2012), where only weak supervision signals (scribbles from user interaction  ...  Especially, to tackle the problem of limited data annotations in image segmentation, transferring different pre-trained models and CRF based methods are applied to enhance the segmentation performance.  ...  Another class of segmentation methods that can be effective for my case of study (small and weakly-supervised dataset), are non deep learning based ones 1 ; before the deep learning era, these methods  ... 
arXiv:2007.07357v1 fatcat:ftd5uszayvhyppqlaqblxlc4rm

Liver Segmentation: A Weakly End-to-End Supervised Model

Youssef Ouassit, Reda Moulouki, Mohammed Yassine El Ghoumari, Mohamed Azzouazi, Soufiane Ardchir
2020 International Journal of Online and Biomedical Engineering (iJOE)  
Recently, deep learning models are the state of art in many natural images processing tasks such as detection, classification, and segmentation due to the availability of annotated data.  ...  However, segmentation of the liver is still a challenging task due to the low contrast in medical images, tissue similarity with neighbor abdominal organs and high scale and shape variability.  ...  : A Weakly End-to-End Supervised Model iJOE -Vol.16, No. 9, 2020 Paper-Liver Segmentation: A Weakly End-to-End Supervised Model  ... 
doi:10.3991/ijoe.v16i09.15159 fatcat:canmv7bdwjfmfk4fpvkyocn2ri

Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples [article]

Nir Zabari, Yedid Hoshen
2021 arXiv   pre-print
That means that images containing rare class categories are unlikely to be well segmented by current methods.  ...  Our method is shown quantitatively and qualitatively to outperform methods that use a similar amount of supervision. Our results are particularly remarkable for images containing rare categories.  ...  We experimented Image views. We denote different image transforma- with weakly supervised clustering and interactive segmen- tions as views.  ... 
arXiv:2112.03185v1 fatcat:k7tgvamso5frzkhqmxqrjs77am

WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image [article]

Xiangde Luo, Wenjun Liao, Jianghong Xiao, Jieneng Chen, Tao Song, Xiaofan Zhang, Kang Li, Dimitris N. Metaxas, Guotai Wang, Shaoting Zhang
2022 arXiv   pre-print
Deep learning-based medical image segmentation has shown the potential to reduce manual delineation efforts, but it still requires a large-scale fine annotated dataset for training, and there is a lack  ...  And we also invited three experienced oncologists to revise the model predictions to measure the gap between the deep learning method and oncologists.  ...  investigating the inference-efficient learning for the highresolution abdominal CT image segmentation, (5) introducing scribble-based weakly supervised methods to reduce the labeling cost.  ... 
arXiv:2111.02403v4 fatcat:i4sfqvdbizfnjhy4n6mv62eosa

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation [article]

Xin Sun, Changrui Chen, Xiaorui Wang, Junyu Dong, Huiyu Zhou, Sheng Chen
2021 arXiv   pre-print
Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software.  ...  In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles.  ...  [51] present a scribble-based hierarchical weakly supervised learning pipeline for medical image structure segmentation which integrates graph-based method with only whole tumor/normal brain scribbles  ... 
arXiv:2104.08783v2 fatcat:436t4k5gkra2xhe4nt2fpjwp4m

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning

Guotai Wang, Wenqi Li, Maria A. Zuluaga, Rosalind Pratt, Premal A. Patel, Michael Aertsen, Tom Doel, Anna L. David, Jan Deprest, Sebastien Ourselin, Tom Vercauteren
2018 IEEE Transactions on Medical Imaging  
improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.  ...  To address these problems, we propose a novel deep learning-based framework for interactive segmentation by incorporating CNNs into a bounding box and scribble-based segmentation pipeline.  ...  In conclusion, we propose an efficient deep learning-based framework for interactive 2D/3D medical image segmentation.  ... 
doi:10.1109/tmi.2018.2791721 pmid:29969407 pmcid:PMC6051485 fatcat:2kmadkui2fc77ff5syqfyxhkdu

Cascaded Interactional Targeting Network for Egocentric Video Analysis

Yang Zhou, Bingbing Ni, Richang Hong, Xiaokang Yang, Qi Tian
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Firstly, a novel EM-like learning framework is proposed to train the pixel-level deep convolutional neural network (DCNN) by seamlessly integrating weakly supervised data (i.e., massive bounding box annotations  ...  ) with a small set of strongly supervised data (i.e., fully annotated hand segmentation maps) to achieve stateof-the-art hand segmentation performance.  ...  With the network parameters θ fixed, we generate a set of hand map/mask hypotheses from each weakly supervised hand image (i.e., with bounding box), then search the best hypothesis/proposal for next iteration  ... 
doi:10.1109/cvpr.2016.210 dblp:conf/cvpr/ZhouNHYT16 fatcat:krp3kzvyrzaq5fvjaxspzkp2fm

Survey on Semantic Segmentation using Deep Learning Techniques

Fahad Lateef, Yassine Ruichek
2019 Neurocomputing  
Many of these methods have been built using the deep learning paradigm that has shown a salient performance.  ...  A lot of methods have been developed to tackle this problem ranging from autonomous vehicles, human-computer interaction, to robotics, medical research, agriculture and so on.  ...  co-segmentation, semi & weakly supervised, and fully supervised image segmentation.  ... 
doi:10.1016/j.neucom.2019.02.003 fatcat:aelsfl7unvdw5j2rtyqhtgqrsm
« Previous Showing results 1 — 15 out of 2,197 results