X-ray Image Segmentation using Multi-task Learning

Today, a large number of x-ray images are interpreted in hospitals and computer-aided system that can perform some intelligent task and analysis is needed in order to raise the accuracy and bring down the miss rate in hospitals, particularly when it comes to diagnosis of hairline fractures and fissures in bone joints. This research considered some segmentation techniques that have been used in the processing and analysis of medical images and a system design was proposed to efficiently compare these techniques. The designed system was tested successfully on a hand X-ray image which led to the proposal of simple techniques to eliminate intrinsic properties of x-ray imaging systems such as noise. The performance and accuracy of image segmentation techniques in bone structures were compared and these eliminated time wasting on the choice of image segmentation algorithms. Although there are several practical applications of image segmentation such as content-based image retrieval, machine vision, medical imaging, object detection, recognition tasks, etc., this study focuses on the performance comparison of several image segmentation techniques for medical X-ray images.

Download Full-text

Image segmentation of nanoscale Zernike phase contrast X-ray computed tomography images

Journal of Applied Physics ◽

10.1063/1.4919835 ◽

2015 ◽

Vol 117 (18) ◽

pp. 183102 ◽

Cited By ~ 15

Author(s):

Arjun S. Kumar ◽

Pratiti Mandal ◽

Yongjie Zhang ◽

Shawn Litster

Keyword(s):

Computed Tomography ◽

Image Segmentation ◽

Phase Contrast ◽

X Ray ◽

Computed Tomography Images ◽

X Ray Computed

Download Full-text

Multi-task Learning for Newspaper Image Segmentation and Baseline Detection Using Attention-Based U-Net Architecture

10.1007/978-3-030-86159-9_32 ◽

2021 ◽

pp. 440-454

Author(s):

Anukriti Bansal ◽

Prerana Mukherjee ◽

Divyansh Joshi ◽

Devashish Tripathi ◽

Arun Pratap Singh

Keyword(s):

Image Segmentation ◽

Task Learning ◽

Baseline Detection

Download Full-text

An Adaptive Generative Adversarial Network for Cardiac Segmentation from X-ray Chest Radiographs

Applied Sciences ◽

10.3390/app10155032 ◽

2020 ◽

Vol 10 (15) ◽

pp. 5032

Author(s):

Xiaochang Wu ◽

Xiaolin Tian

Keyword(s):

Image Segmentation ◽

Medical Image Segmentation ◽

Chest Radiographs ◽

Generative Adversarial Networks ◽

Generative Adversarial Network ◽

X Ray ◽

Adversarial Network ◽

Cardiac Segmentation ◽

Adversarial Networks ◽

Feature Extractor

Medical image segmentation is a classic challenging problem. The segmentation of parts of interest in cardiac medical images is a basic task for cardiac image diagnosis and guided surgery. The effectiveness of cardiac segmentation directly affects subsequent medical applications. Generative adversarial networks have achieved outstanding success in image segmentation compared with classic neural networks by solving the oversegmentation problem. Cardiac X-ray images are prone to weak edges, artifacts, etc. This paper proposes an adaptive generative adversarial network for cardiac segmentation to improve the segmentation rate of X-ray images by generative adversarial networks. The adaptive generative adversarial network consists of three parts: a feature extractor, a discriminator and a selector. In this method, multiple generators are trained in the feature extractor. The discriminator scores the features of different dimensions. The selector selects the appropriate features and adjusts the network for the next iteration. With the help of the discriminator, this method uses multinetwork joint feature extraction to achieve network adaptivity. This method allows features of multiple dimensions to be combined to perform joint training of the network to enhance its generalization ability. The results of cardiac segmentation experiments on X-ray chest radiographs show that this method has higher segmentation accuracy and less overfitting than other methods. In addition, the proposed network is more stable.

Download Full-text