Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation

Ren, Xuhua; Ahmad, Sahar; Zhang, Lichi; Xiang, Lei; Nie, Dong; Yang, Fan; Wang, Qian; Shen, Dinggang

doi:10.1109/tip.2020.3003735

Cited by 17 publications

(13 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work aimed to enhance the segmentation at the region of interest (ROI) edges within an image by using two losses, i.e., los Lce and loss Lhp. Task decomposition technique has been used by [59] for semantic segmentation of Robotics scene, Brain tumour, and Retinal fundus images. To reduce the distance between the results of pixel-level semantic segmentation and the instance class prediction tasks, they used a novel sync-regularization multi-step approach.…”

Section: Related Workmentioning

confidence: 99%

Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network

Shahzad¹,

Umar

Shirazi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Pixel-level analysis of blood images plays a pivotal role in diagnosing blood-related diseases, especially Anaemia. These analyses mainly rely on an accurate diagnosis of morphological deformities like shape, size, and precise pixel counting. In traditional segmentation approaches, instance or object-based approaches have been adopted that are not feasible for pixel-level analysis. The convolutional neural network (CNN) model required a large dataset with detailed pixellevel information for the semantic segmentation of red blood cells in the deep learning domain. In current research work, we address these problems by proposing a multi-level deep convolutional encoder-decoder network along with two state-of-theart healthy and Anaemic-RBC datasets. The proposed multi-level CNN model preserved pixel-level semantic information extracted in one layer and then passed to the next layer to choose relevant features. This phenomenon helps to precise pixellevel counting of healthy and anaemic-RBC elements along with morphological analysis. For experimental purposes, we proposed two state-of-the-art RBC datasets, i.e., Healthy-RBCs and Anaemic-RBCs dataset. Each dataset contains 1000 images, ground truth masks, relevant, complete blood count (CBC), and morphology reports for performance evaluation. The proposed model results were evaluated using crossmatch analysis with ground truth mask by finding IoU, individual training, validation, testing accuracies, and global accuracies using a 05-fold training procedure. This model got training, validation, and testing accuracies as 0.9856, 0.9760, and 0.9720 on the Healthy-RBC dataset and 0.9736, 0.9696, and 0.9591 on an Anaemic-RBC dataset. The IoU and BFScore of the proposed model were 0.9311, 0.9138, and 0.9032, 0.8978 on healthy and anaemic datasets, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network

Shahzad¹,

Umar

Shirazi

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…If the convolutional layer has learned some useful information, it may perform better than learning the identity function. (2) In backpropagation, the residual module is more sensitive to changes in output, and the weight can be adjusted more finely than the standard convolutional layer.…”

Section: Residual Thoughtmentioning

confidence: 99%

“…The goal is to label each pixel in the image with semantic information, thereby dividing the image into several areas with different attributes and categories. The application field of semantic segmentation is very wide, and it will be involved in automatic driving, geographic information system, smart medical treatment and people's daily work and life [1][2][3][4][5], which has a very important practical application significance. In the application of vehicle automatic driving, the image captured by the vehicle camera or detected by the lidar is input into the neural network, which can realize the automatic segmentation of the image, and realize the recognition and avoidance of different types of targets.…”

Section: Introductionmentioning

confidence: 99%

Image semantic segmentation method based on GAN network and FCN model

Zhao¹

2021

The Journal of Engineering

View full text Add to dashboard Cite

In order to improve the accuracy of image semantic segmentation, an image semantic segmentation method based on generative adversarial network (GAN) and fully convolutional network (FCN) model is proposed. First of all, the network structure of the generator is improved. Introducing the residual module in the convolutional layer for difference learning makes the network structure sensitive to changes in the output, so as to better adjust the weight of the generator. Second in order to reduce the number of parameters and calculations, a small convolution kernel is used to halve the number of channels of the input feature map before using the large convolution kernel. Finally, the output of the convolutional layer and the output of the deconvolutional layer are connected by using the idea of a U‐shaped network to avoid low‐level information sharing. The proposed method was experimentally demonstrated on the PASCAL VOC 2012 and CamVid datasets. Experimental results show that the proposed method effectively improves the accuracy of image segmentation, and avoids inaccurate detection caused by insufficient image pixel information and noise interference. Its mean pixel accuracy (MPA) and mean intersection over union (MIOU) are higher than other comparison methods.

show abstract

“…S EMANTIC segmentation is a basic task in which each pixel of input images should be assigned to the corresponding label [1]- [3]. It plays a vital role in many practical applications such as medical image segmentation, navigation of autonomous vehicles and robots [4], [5].…”

Section: Introductionmentioning

confidence: 99%

Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes

Hong,

Pan,

Sun

et al. 2021

Preprint

View full text Add to dashboard Cite

Semantic segmentation is a critical technology for autonomous vehicles to understand surrounding scenes. For practical autonomous vehicles, it is undesirable to spend a considerable amount of inference time to achieve high-accuracy segmentation results. Using light-weight architectures (encoderdecoder or two-pathway) or reasoning on low-resolution images, recent methods realize very fast scene parsing which even run at more than 100 FPS on single 1080Ti GPU. However, there are still evident gaps in performance between these real-time methods and models based on dilation backbones. To tackle this problem, we propose novel deep dual-resolution networks (DDRNets) for real-time semantic segmentation of road scenes. Besides, we design a new contextual information extractor named Deep Aggregation Pyramid Pooling Module (DAPPM) to enlarge effective receptive fields and fuse multi-scale context. Our method achieves new state-of-the-art trade-off between accuracy and speed on both Cityscapes and CamVid dataset. Specially, on single 2080Ti GPU, DDRNet-23-slim yields 77.4% mIoU at 109 FPS on Cityscapes test set and 74.4% mIoU at 230 FPS on CamVid test set. Without utilizing attention mechanism, pretraining on larger semantic segmentation dataset or inference acceleration, DDRNet-39 attains 80.4% test mIoU at 23 FPS on Cityscapes. With widely used test augmentation, our method is still superior to most state-of-the-art models, requiring much less computation. Codes and trained models will be made publicly available.

show abstract

Task Decomposition and Synchronization for Semantic Biomedical Image Segmentation

Cited by 17 publications

References 38 publications

Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network

Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network

Image semantic segmentation method based on GAN network and FCN model

Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes

Contact Info

Product

Resources

About