Object Localization improved GrabCut for Lung Parenchyma Segmentation

Sheng-chao, Zhang; Zhao, Yuhai; Bai, Pengcheng

doi:10.1016/j.procs.2018.04.330

Cited by 9 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our data sets show these problematic characteristics, and perfect automatic lung segmentation was therefore unlikely regardless of the technique applied. We applied the OpenCV GrabCut [38] function, which was previously used for CT scans [39] as a simple tool implement segmentation technique on our equalized images. We reasoned that the lung area could be considered the foreground of the X-Ray image.…”

Section: ) Segmentation Based Noise Reductionmentioning

confidence: 99%

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

Horry¹,

Chakraborty²,

Paul³

et al. 2020

Preprint

View full text Add to dashboard Cite

Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how pre-trained deep learning models can be adopted to perform COVID-19 detection using X-Ray images. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent image classification models. We highlight the challenges (including dataset size and quality) in utilising current publicly available COVID-19 datasets for developing useful deep learning models. We propose a semi-automated image pre-processing model to create a trustworthy image dataset for developing and testing deep learning models. The new approach is aimed to reduce unwanted noise from X-Ray images so that deep learning models can focus on detecting diseases with specific features from them. Next, we devise a deep learning experimental framework, where we utilise the processed dataset to perform comparative testing for several popular and widely available deep learning model families such as VGG, Inception, Xception, and Resnet. The experimental results highlight the suitability of these models for current available dataset and indicates that models with simpler networks such as VGG19 performs relatively better with up to 83% precision. This will provide a solid pathway for researchers and practitioners to develop improved models in the future.

show abstract

Section: ) Segmentation Based Noise Reductionmentioning

confidence: 99%

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

Horry¹,

Chakraborty²,

Paul³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to improve the quality of CT images, the literature [8] has reviewed the reconstruction of CT images, noise in CT images, and CT denoising techniques. CT imaging systems are widely used, especially in the diagnosis of lung diseases [9] [10] . MRI images are a powerful non-invasive medical imaging diagnostic technique [ 11 ] , which visualizes the body's tissues and organs based on the difference in the rate of decay of the released energy in different structures, which is detected by magnetic resonance instrumentation for precise localization and differentiation.…”

Section: Medical Image Modalitiesmentioning

confidence: 99%

Medical Image Segmentation Research Status and Development Trends

2023

HSET

View full text Add to dashboard Cite

As one of the important steps in medical image processing, medical image segmentation plays a pivotal role in clinical surgery and is widely used in application scenarios such as preoperative diagnosis, intraoperative navigation, and postoperative evaluation. In this paper, medical image segmentation technology is studied, and a variety of medical image segmentation methods are categorized and compared in an attempt to explore the development law of medical image segmentation technology. Firstly, the medical image segmentation technology is classified and studied according to its different methods, and this paper mainly researches and organizes the deep learning method for medical image segmentation; secondly, the principle, advantages and disadvantages, and applicable scenarios of each model are analyzed; and lastly, the latest progress of the medical image segmentation technology is objectively described. inherent deficiencies and solutions of the existing techniques, and provides a direction for continued improvement in the future. As one of the important steps in medical image processing, medical image segmentation plays a pivotal role in clinical surgery and is widely used in application scenarios such as preoperative diagnosis, intraoperative navigation, and postoperative evaluation. In this paper, we explore the critical role of medical image segmentation in medical image processing, particularly in clinical surgery and its various applications such as preoperative diagnosis, intraoperative navigation, and postoperative evaluation. Our study focuses on categorizing and comparing different medical image segmentation methods, with a special emphasis on deep learning techniques. We delve into the principles, advantages, disadvantages, and suitable scenarios for each model. Additionally, we objectively present the latest progress in medical image segmentation technology, addressing existing deficiencies and proposing potential solutions. This research provides valuable insights to foster continuous advancements in the field.

show abstract

“…In addition, the segmented lung parenchyma from the Gaussian Mixture model (GMM) undergoes an Adaptive Morphological Filtering (AMF) to reduce the boundary errors. Zhang et al [9] proposed an object localization improved GrabCut algorithm for lung parenchyma segmentation that can automatically select the appropriate bounding box that relatives to lung parenchyma, then use GrabCut algorithm. The algorithm can adapt to different forms of lung parenchyma and effectively improve the accuracy of segmentation.…”

Section: ) Lung Segmentation Algorithms Based On Gradients Of Lung Cmentioning

confidence: 99%

A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Lung parenchyma segmentation is the prerequisite for an automatic diagnosis system to analyze lung CT (computed tomography) images. However, traditional lung segmentation algorithms have poor adaptability and are not effectively robust regarding lung databases with blood vessels and small voids which can interfere the segmentation. The main work of this paper is as follows: Firstly, a lung dense deep convolutional neural network (LDDNet) is proposed, which adopts some popular optimizer methods, such as dense block, batch normalization (BN) and dropout. The performance of LDDNet is tested on the public lung database LIDC-IDRI which contains many cases of interference for segmentation. Secondly, the labeled with blood vessels and small voids are not contained by the public ground-truth masks of the LIDC-IDRI database, therefore these regions are labeled by us with LabelMe software. Thirdly, for the aim of exploring the effect of image preprocessing on segmenting lung CT images with deep neural network, contrast enhancing, median filtering and Laplacian filtering are used to preprocess the image as comparative experiments. Finally, dataset is classified into four classes by the geometrical shapes to test the performance of LDDNet. The accuracy of the segmentation experiment reaches over 99% and the four classes can all reach over 95%. Additionally, blood vessels and small voids are segmented out from the lung parenchyma which is not achieved by other methods. Experimental results confirm that the proposed LDDNet can segment the lung parenchymal area more accurately and has better robustness in comparison with other neural networks and most of the traditional methods. INDEX TERMS Deep dense neural network, lung segmentation, robustness.

show abstract

Object Localization improved GrabCut for Lung Parenchyma Segmentation

Cited by 9 publications

References 10 publications

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

X-Ray Image based COVID-19 Detection using Pre-trained Deep Learning Models

Medical Image Segmentation Research Status and Development Trends

A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation

Contact Info

Product

Resources

About