scholarly journals Enhancing U-Net with Spatial-Channel Attention Gate for Abnormal Tissue Segmentation in Medical Imaging

2020 ◽  
Vol 10 (17) ◽  
pp. 5729
Author(s):  
Trinh Le Ba Khanh ◽  
Duy-Phuong Dao ◽  
Ngoc-Huynh Ho ◽  
Hyung-Jeong Yang ◽  
Eu-Tteum Baek ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Spatial Information ◽  
Multiple Scales ◽  
Contextual Information ◽  
Poor Performance ◽  
Medical Image Segmentation ◽  
Tissue Segmentation ◽  
Low Level ◽  
Computational Overhead ◽  
Segmentation Task

In recent years, deep learning has dominated medical image segmentation. Encoder-decoder architectures, such as U-Net, can be used in state-of-the-art models with powerful designs that are achieved by implementing skip connections that propagate local information from an encoder path to a decoder path to retrieve detailed spatial information lost by pooling operations. Despite their effectiveness for segmentation, these naïve skip connections still have some disadvantages. First, multi-scale skip connections tend to use unnecessary information and computational sources, where likable low-level encoder features are repeatedly used at multiple scales. Second, the contextual information of the low-level encoder feature is insufficient, leading to poor performance for pixel-wise recognition when concatenating with the corresponding high-level decoder feature. In this study, we propose a novel spatial-channel attention gate that addresses the limitations of plain skip connections. This can be easily integrated into an encoder-decoder network to effectively improve the performance of the image segmentation task. Comprehensive results reveal that our spatial-channel attention gate remarkably enhances the segmentation capability of the U-Net architecture with a minimal computational overhead added. The experimental results show that our proposed method outperforms the conventional deep networks in term of Dice score, which achieves 71.72%.

The Image Segmentation System Based on Gauss Process

2013 ◽  
Vol 421 ◽  
pp. 523-527
Author(s):  
Lei Ling ◽  
Pan Chen ◽  
Li Ping
Keyword(s):  
Image Segmentation ◽  
Spatial Information ◽  
Target Position ◽  
Training Sample ◽  
Target Object ◽  
Medical Image Segmentation ◽  
Training Samples ◽  
Gauss Process ◽  
Segmentation Image ◽  
Valid Information

This paper gave an example for the design of automatic image segmentation system by using deep staining of blood cell image. The paper also described how to auto-locate the target position, and how to collect training samples with large entropy further. The spatial information of target object also contained valid information, so this paper put forward to use the relative distance between the inner points and the centre of a circle as a feature of a training sample to work together with the RGB features. And for the segmentation image can be applied to the later medical diagnosis conveniently, the Gauss process classifier had been used in medical image segmentation firstly because of its clear probabilistic interpretation. Compared with SVM, GP is better in this system.

Parallel Capsule Net for Ischemic Stroke Segmentation

2019 ◽  
Author(s):  
MD Sharique ◽  
Bondi Uday Pundarikaksha ◽  
Pradeeba Sridar ◽  
R S Rama Krishnan ◽  
Ramarathnam Krishnakumar
Keyword(s):  
Image Segmentation ◽  
Ischemic Stroke ◽  
Spatial Information ◽  
Automatic Segmentation ◽  
Class Imbalance ◽  
Medical Image Segmentation ◽  
Brain Images ◽  
Data Set ◽  
Max Pooling ◽  
Mri Brain Images

AbstractStroke is one of the leading causes of disability. Segmentation of ischemic stroke could help in planning an optimal treatment. Currently, radiologists use manual segmentation, which can often be time-consuming, laborious and error-prone. Automatic segmentation of ischemic stroke in MRI brain images is a challenging problem due to its small size, multiple occurrences and the need to use multiple image modalities. In this paper, we propose a new architecture for image segmentation, called Parallel Capsule Net, which uses max pooling in every parallel pathways along with dense connections between the parallel layers. We hypothesise that the spatial information lost due to max pooling in these layers can be retrieved by the use of such dense connections. In order to combine the information encoded by the parallel layers, outputs of the layers are concatenated before upsampling. We also propose the use of a modified loss function which consists of a regional term (Generalized Dice loss + Focal Loss) and a boundary term (Boundary loss) to address the problem of class imbalance which is prevalent in medical images. We achieved a competitive Dice score of 0.754, on ISLES SISS data set, compared to a score of 0.67 reported in earlier studies. We also obtained a Dice score of 0.902 with another popular data set, ATLAS. The proposed parallel capsule net can be extended to other similar medical image segmentation problems.

scholarly journals Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation

2019 ◽  
Vol 33 ◽  
pp. 865-872 ◽  
Author(s):  
Cheng Chen ◽  
Qi Dou ◽  
Hao Chen ◽  
Jing Qin ◽  
Pheng-Ann Heng
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Medical Image Segmentation ◽  
Target Domain ◽  
Learning Procedure ◽  
The Neural Networks ◽  
Feature Adaptation ◽  
Segmentation Task

This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in recent studies on deep learning, aiming to recover performance degradation when applying the neural networks to new testing domains. Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features towards the segmentation task. The feature encoder layers are shared by both perspectives to grasp their mutual benefits during the end-to-end learning procedure. Without using any annotation from the target domain, the learning of our unified model is guided by adversarial losses, with multiple discriminators employed from various aspects. We have extensively validated our method with a challenging application of crossmodality medical image segmentation of cardiac structures. Experimental results demonstrate that our SIFA model recovers the degraded performance from 17.2% to 73.0%, and outperforms the state-of-the-art methods by a significant margin.

scholarly journals An Improved Mask R-CNN Model for Multiorgan Segmentation

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Jian-Hua Shu ◽  
Fu-Dong Nian ◽  
Ming-Hui Yu ◽  
Xu Li
Keyword(s):  
Image Segmentation ◽  
Radiation Treatment ◽  
Left Lung ◽  
Region Of Interest ◽  
Target Volume ◽  
Medical Image Segmentation ◽  
Natural Image ◽  
Target Area ◽  
Semantic Features ◽  
Segmentation Task

Medical image segmentation is a key topic in image processing and computer vision. Existing literature mainly focuses on single-organ segmentation. However, since maximizing the concentration of radiotherapy drugs in the target area with protecting the surrounding organs is essential for making effective radiotherapy plan, multiorgan segmentation has won more and more attention. An improved Mask R-CNN (region-based convolutional neural network) model is proposed for multiorgan segmentation to aid esophageal radiation treatment. Due to the fact that organ boundaries may be fuzzy and organ shapes are various, original Mask R-CNN works well on natural image segmentation while leaves something to be desired on the multiorgan segmentation task. Addressing it, the advantages of this method are threefold: (1) a ROI (region of interest) generation method is presented in the RPN (region proposal network) which is able to utilize multiscale semantic features. (2) A prebackground classification subnetwork is integrated to the original mask generation branch to improve the precision of multiorgan segmentation. (3) 4341 CT images of 44 patients are collected and annotated to evaluate the proposed method. Additionally, extensive experiments on the collected dataset demonstrate that the proposed method can segment the heart, right lung, left lung, planning target volume (PTV), and clinical target volume (CTV) accurately and efficiently. Specifically, less than 5% of the cases were missed detection or false detection on the test set, which shows a great potential for real clinical usage.

scholarly journals An Improved FCM Medical Image Segmentation Algorithm Based on MMTD

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Ningning Zhou ◽  
Tingting Yang ◽  
Shaobai Zhang
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Spatial Information ◽  
Clustering Algorithms ◽  
Medical Image Segmentation ◽  
Segmentation Algorithm ◽  
Fuzzy Information ◽  
Spatial Features ◽  
Image Segmentation Algorithm ◽  
Truth Degree

Image segmentation plays an important role in medical image processing. Fuzzy c-means (FCM) is one of the popular clustering algorithms for medical image segmentation. But FCM is highly vulnerable to noise due to not considering the spatial information in image segmentation. This paper introduces medium mathematics system which is employed to process fuzzy information for image segmentation. It establishes the medium similarity measure based on the measure of medium truth degree (MMTD) and uses the correlation of the pixel and its neighbors to define the medium membership function. An improved FCM medical image segmentation algorithm based on MMTD which takes some spatial features into account is proposed in this paper. The experimental results show that the proposed algorithm is more antinoise than the standard FCM, with more certainty and less fuzziness. This will lead to its practicable and effective applications in medical image segmentation.

scholarly journals Hybrid Bee Colony and Cuckoo Search based centroid initialization for fuzzy c-means clustering in bio-medical image segmentation

2019 ◽  
Vol 8 (9) ◽  
pp. 1684-1688
Keyword(s):  
Image Segmentation ◽  
Brain Tissue ◽  
Medical Image ◽  
Cuckoo Search ◽  
Medical Image Segmentation ◽  
Tissue Segmentation ◽  
Bee Colony ◽  
Brain Tissue Segmentation ◽  
Fuzzy C Means Clustering ◽  
Number Of Iterations

In current years, the grouping has become well identified for numerous investigators due to several application fields like communication, wireless networking, and biomedical domain and so on. So, much different research has already been made by the investigators to progress an improved system for grouping. One of the familiar investigations is an optimization that has been efficiently applied for grouping. In this paper, propose a method of Hybrid Bee Colony and Cuckoo Search (HBCCS) based centroid initialization for fuzzy c-means clustering (FCM) in bio-medical image segmentation (HBCC-KFCM-BIM). For MRI brain tissue segmentation, KFCM is most preferable technique because of its performance. The major limitation of the conventional KFCM is random centroids initialization because it leads to rising the execution time to reach the best resolution. In order to accelerate the segmentation process, HBCCS is used to adjust the centroids of required clusters. The quantitative measures of results were compared using the metrics are the number of iterations and processing time. The number of iterations and processing of HBCC-KFCM-BIM method take minimum value while compared to conventional KFCM. The HBCC-KFCM-BIM method is very efficient and faster than conventional KFCM for brain tissue segmentation.

Deep Learning Models for Semantic Multi-Modal Medical Image Segmentation

2020 ◽  
pp. 12-30
Author(s):  
V. R. S. Mani
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Deep Learning ◽  
Medical Image Segmentation ◽  
Learning Models ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Comprehensive Picture ◽  
Application Methods ◽  
Segmentation Task

In this chapter, the author paints a comprehensive picture of different deep learning models used in different multi-modal image segmentation tasks. This chapter is an introduction for those new to the field, an overview for those working in the field, and a reference for those searching for literature on a specific application. Methods are classified according to the different types of multi-modal images and the corresponding types of convolution neural networks used in the segmentation task. The chapter starts with an introduction to CNN topology and describes various models like Hyper Dense Net, Organ Attention Net, UNet, VNet, Dilated Fully Convolutional Network, Transfer Learning, etc.

scholarly journals Spatial information of fuzzy clustering based mean best artificial bee colony algorithm for phantom brain image segmentation

2021 ◽  
Vol 11 (5) ◽  
pp. 4050
Author(s):  
Waleed Alomoush ◽  
Ayat Alrosan ◽  
Ammar Almomani ◽  
Khalid Alissa ◽  
Osama A. Khashan ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Fuzzy Clustering ◽  
Artificial Bee Colony Algorithm ◽  
Artificial Bee Colony ◽  
Clustering Algorithm ◽  
Spatial Information ◽  
Medical Image Segmentation ◽  
Local Optimum ◽  
Brain Image ◽  
Bee Colony

Fuzzy c-means algorithm (FCM) is among the most commonly used in the medical image segmentation process. Nevertheless, the traditional FCM clustering approach has been several weaknesses such as noise sensitivity and stuck in local optimum, due to FCM hasn’t able to consider the information of contextual. To solve FCM problems, this paper presented spatial information of fuzzy clustering-based mean best artificial bee colony algorithm, which is called SFCM-MeanABC. This proposed approach is used contextual information in the spatial fuzzy clustering algorithm to reduce sensitivity to noise and its used MeanABC capability of balancing between exploration and exploitation that is explore the positive and negative directions in search space to find the best solutions, which leads to avoiding stuck in a local optimum. The experiments are carried out on two kinds of brain images the Phantom MRI brain image with a different level of noise and simulated image. The performance of the SFCM-MeanABC approach shows promising results compared with SFCM-ABC and other stats of the arts.

scholarly journals Transformer Based Multi-model Fusion for Medical Image Segmentation

2021 ◽  
Vol 1 (1) ◽  
pp. 50-52
Author(s):  
Bo Dong ◽  
Wenhai Wang ◽  
Jinpeng Li
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
State Of The Art ◽  
Medical Image Segmentation ◽  
Model Fusion ◽  
Backbone Network ◽  
Segmentation Task ◽  
Complete Solutions ◽  
Segmentation Models

We present our solutions to the MedAI for all three tasks: polyp segmentation task, instrument segmentation task, and transparency task. We use the same framework to process the two segmentation tasks of polyps and instruments. The key improvement over last year is new state-of-the-art vision architectures, especially transformers which significantly outperform ConvNets for the medical image segmentation tasks. Our solution consists of multiple segmentation models, and each model uses a transformer as the backbone network. we get the best IoU score of 0.915 on the instrument segmentation task and 0.836 on polyp segmentation task after submitting. Meanwhile, we provide complete solutions in https://github.com/dongbo811/MedAI-2021.

Sign in / Sign up

Export Citation Format

Share Document