Journal ArticleDOI
3D deeply supervised network for automated segmentation of volumetric medical images.
TLDR
The proposed 3D DSN is capable of conducting volume‐to‐volume learning and inference, which can eliminate redundant computations and alleviate the risk of over‐fitting on limited training data, and the3D deep supervision mechanism can effectively cope with the optimization problem of gradients vanishing or exploding when training a 3D deep model.About:
This article is published in Medical Image Analysis.The article was published on 2017-10-01. It has received 507 citations till now. The article focuses on the topics: Scale-space segmentation & Image segmentation.read more
Citations
More filters
Journal ArticleDOI
Quality-driven deep active learning method for 3D brain MRI segmentation
TL;DR: A segmentation framework combined with the quality-driven active learning (QDAL) module for suggestive annotation is developed and a high correlation coefficient is observed between the proposed two surrogate metrics and the real segmentation accuracy of per slice in one scan.
Journal ArticleDOI
White matter hyperintensities segmentation using the ensemble U-Net with multi-scale highlighting foregrounds.
TL;DR: U-Net with multi-scale highlighting foregrounds (HF) as mentioned in this paper was proposed to improve the detection of the WMH voxels with partial volume effects, which achieved the best overall evaluation scores, the highest dice similarity index, and the best F1-score among 39 WMH segmentation methods submitted on the MICCAI 2017 Challenge.
Book ChapterDOI
3D Tiled Convolution for Effective Segmentation of Volumetric Medical Images
Guodong Zeng,Guoyan Zheng +1 more
TL;DR: A 3D Tiled Convolution (3D-TC) which learn a number of separate kernels within the same layer which has the advantage of significantly reducing the required GPU memory for 3D medical image processing task but with improved performance.
Proceedings ArticleDOI
3D Cnn-Based Soma Segmentation from Brain Images at Single-Neuron Resolution
TL;DR: This paper presents a weakly supervised learning strategy to deal with the inaccurate training data problem, and thus adopts 3D CNN to perform automatic soma segmentation from brain images, and results show that3D CNN-based method outperforms the traditional methods by a significant margin.
Journal ArticleDOI
Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach.
Pedro M. Vieira,Nuno R. Freitas,Veríssimo B. Lima,Veríssimo B. Lima,Dalila Costa,Carla Rolanda,Carlos S. Lima +6 more
TL;DR: In this article, a multi-pathology system that can be applied to WCE images, which uses the Mask Improved RCNN (MI-RCNN), a new mask subnet scheme which has shown to significantly improve mask predictions of the high performing state-of-the-art Mask-RCN and PANet systems.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.