scholarly journals High-Resolution Encoder–Decoder Networks for Low-Contrast Medical Image Segmentation

2020 ◽  
Vol 29 ◽  
pp. 461-475 ◽  
Author(s):  
Sihang Zhou ◽  
Dong Nie ◽  
Ehsan Adeli ◽  
Jianping Yin ◽  
Jun Lian ◽  
...  
Keyword(s):  
Image Segmentation ◽  
High Resolution ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Low Contrast

CS-LBF Improved Model for 3D Medical Image Segmentation

2013 ◽  
Vol 303-306 ◽  
pp. 2272-2279 ◽  
Author(s):  
Wen Cang Zhao ◽  
Jun Bo Zhang
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Contrast Ratio ◽  
Three Dimensional ◽  
Medical Image Segmentation ◽  
Low Contrast ◽  
Shape Constraint ◽  
Local Binary Fitting Model ◽  
Improved Model ◽  
Fitting Model

This paper presents an algorithm for three-dimensional medical image segmentation based on the Contrast and Shape Constrained Local Binary Fitting improved model. Due to Local Binary Fitting model is sensitive to initialization and easy to fall into local extreme value, the new algorithm adds contrast constraint term to the Local Binary Fitting model, aiming at solving the common existed problem of inconsistent brightness and low contrast ratio. Adding shape constraint term can improve the original Local Binary Fitting model by constructing shape constraint energy field around the average shape by the level set method to deal with the leak of deformation curve. In order to promote the speed of model evolution, the kernel function is simplified. Two-dimensional Contrast and Shape Constrained Local Binary Fitting model is then extended to three-dimensional and a three-dimensional dental pulp image is segmented. Experimental results show that the segmentation accuracy, the connection degree and the efficiency of the new method are greatly improved compared to original LBF model.

scholarly journals Investigations of Medical Image Segmentation Methods with Inclusion Mathematical Morphological Operations

2021 ◽  
Vol 38 (5) ◽  
pp. 1531-1540
Author(s):  
Bokka Sridhar
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Performance Metrics ◽  
Medical Image Segmentation ◽  
High Rate ◽  
Morphological Operations ◽  
Low Contrast ◽  
Cad System ◽  
Specificity And Sensitivity ◽  
The Masses

Medical image segmentation research is becoming efficient by using mathematical morphological (MM) operators. There are different methods in image segmentation such as supervised and unsupervised segmentations. The MM operators are much effective, in developing a computer aided diagnosis (CAD) system. Medical image such as mammograms, generally they are of low contrast, such that radiologists face difficulties in observing the results. Due to this, diagnosis fails to generate high rate false positives and false negatives. In the proposed work improvement of quality of image segmentation with inclusion of morphological operations with other methods such as watershed transform, fuzzy logic based techniques, curvelets and MRF to detect the masses and calcifications in mammograms. Classification of masses and evaluation of segmentation process are done with artificial neural network and other performance metrics. These methods lead to increase in the accuracy, specificity and sensitivity of mammography and reduce unnecessary biopsies.

Design of Superpiexl U-Net Network for Medical Image Segmentation

2019 ◽  
Vol 31 (6) ◽  
pp. 1007 ◽  
Author(s):  
Haiou Wang ◽  
Hui Liu ◽  
Qiang Guo ◽  
Kai Deng ◽  
Caiming Zhang
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Medical Image Segmentation

scholarly journals A Self-Spatial Adaptive Weighting Based U-Net for Image Segmentation

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 348
Author(s):  
Choongsang Cho ◽  
Young Han Lee ◽  
Jongyoul Park ◽  
Sangkeun Lee
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Feature Maps ◽  
Data Set ◽  
Feature Map ◽  
Adaptive Weighting ◽  
Spatially Adaptive ◽  
Wide Range ◽  
Decoder Architecture

Semantic image segmentation has a wide range of applications. When it comes to medical image segmentation, its accuracy is even more important than those of other areas because the performance gives useful information directly applicable to disease diagnosis, surgical planning, and history monitoring. The state-of-the-art models in medical image segmentation are variants of encoder-decoder architecture, which is called U-Net. To effectively reflect the spatial features in feature maps in encoder-decoder architecture, we propose a spatially adaptive weighting scheme for medical image segmentation. Specifically, the spatial feature is estimated from the feature maps, and the learned weighting parameters are obtained from the computed map, since segmentation results are predicted from the feature map through a convolutional layer. Especially in the proposed networks, the convolutional block for extracting the feature map is replaced with the widely used convolutional frameworks: VGG, ResNet, and Bottleneck Resent structures. In addition, a bilinear up-sampling method replaces the up-convolutional layer to increase the resolution of the feature map. For the performance evaluation of the proposed architecture, we used three data sets covering different medical imaging modalities. Experimental results show that the network with the proposed self-spatial adaptive weighting block based on the ResNet framework gave the highest IoU and DICE scores in the three tasks compared to other methods. In particular, the segmentation network combining the proposed self-spatially adaptive block and ResNet framework recorded the highest 3.01% and 2.89% improvements in IoU and DICE scores, respectively, in the Nerve data set. Therefore, we believe that the proposed scheme can be a useful tool for image segmentation tasks based on the encoder-decoder architecture.

Multi-Encoder Parse-Decoder Network for Sequential Medical Image Segmentation

2021 ◽  
Author(s):  
Dachuan Shi ◽  
Ruiyang Liu ◽  
Linmi Tao ◽  
Zuoxiang He ◽  
Li Huo
Keyword(s):  
Image Segmentation ◽  
Medical Image ◽  
Medical Image Segmentation

Automatic segmentation of medical images using a novel Harris Hawk optimization method and an active contour model

2021 ◽  
pp. 1-19
Author(s):  
Maria Tamoor ◽  
Irfan Younas
Keyword(s):  
Image Segmentation ◽  
Active Contour ◽  
Medical Image ◽  
Active Contour Model ◽  
Heart Diseases ◽  
Medical Image Segmentation ◽  
Gaussian Kernel ◽  
Initial Contour ◽  
Automated Method ◽  
Contour Model

Medical image segmentation is a key step to assist diagnosis of several diseases, and accuracy of a segmentation method is important for further treatments of different diseases. Different medical imaging modalities have different challenges such as intensity inhomogeneity, noise, low contrast, and ill-defined boundaries, which make automated segmentation a difficult task. To handle these issues, we propose a new fully automated method for medical image segmentation, which utilizes the advantages of thresholding and an active contour model. In this study, a Harris Hawks optimizer is applied to determine the optimal thresholding value, which is used to obtain the initial contour for segmentation. The obtained contour is further refined by using a spatially varying Gaussian kernel in the active contour model. The proposed method is then validated using a standard skin dataset (ISBI 2016), which consists of variable-sized lesions and different challenging artifacts, and a standard cardiac magnetic resonance dataset (ACDC, MICCAI 2017) with a wide spectrum of normal hearts, congenital heart diseases, and cardiac dysfunction. Experimental results show that the proposed method can effectively segment the region of interest and produce superior segmentation results for skin (overall Dice Score 0.90) and cardiac dataset (overall Dice Score 0.93), as compared to other state-of-the-art algorithms.

Sign in / Sign up

Export Citation Format

Share Document