A Level Set Based Unified Framework for Pulmonary Nodule Segmentation

Roy, Rukhmini; Banerjee, Pranavesh; Chowdhury, Ananda S.

doi:10.1109/lsp.2020.3016563

Cited by 10 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Preprocessing Generally, to reduce the radiation hazard, radiologists reduce the radiation dose in CT scans, which can degrade the image quality and produce extraneous information such as noise, artifacts [24], etc., and therefore the images need to go through a pre-processing step. The common filters used in this stage of the method are the median filter [25], Gaussian filter [26], point enhancement filter [27], histogram equalization filter [16], and Laplacian of Gaussian (LoG) filter [28].…”

Section: Cade System For Lung Nodule Detectionmentioning

confidence: 99%

Deep learning-based lung nodule detection: a review

Zhou

2024

EAI Endorsed Trans e-Learn

View full text Add to dashboard Cite

CT scan acquisition is fast and cost-effective and has become the main lung imaging tool. However, the increase in large numbers of CT scans has placed a heavy burden on radiologists; therefore, automated lung nodule detection techniques are needed to reduce the workload of radiologists and computer-aided detection systems are proposed for further accurate diagnosis of the condition. This review provides a comprehensive overview of recent automated lung nodule detection techniques and challenges, etc., as well as a detailed overview and discussion of current research gaps, future developments, and research trends. Relevant articles published in databases such as IEEE Xplore, Science Direct, PubMed, and Web of Science cover research algorithms published from 2014 to 2023, mainly discussing deep learning-based techniques. The schemes presented in these articles, the databases used, the experimental results, and the performance of the algorithms are compared and discussed. This work aims to introduce researchers and readers to the latest techniques and their advances in the detection of lung nodules in the last decade, which will help researchers and radiologists to further understand the latest techniques in this field.

show abstract

Section: Cade System For Lung Nodule Detectionmentioning

confidence: 99%

Deep learning-based lung nodule detection: a review

Zhou

2024

EAI Endorsed Trans e-Learn

View full text Add to dashboard Cite

show abstract

“…The approach by Roy et al [10] stands out by merging a level-set model, effectively combining intensity-based and boundary-based attributes to accurately segment nodules within lung regions. Rakesh and Mahesh [11] presented a holistic approach involving thresholding, morphological operations, and region growing, allowing for multiple stages of nodule segmentation.…”

Section: A Related Workmentioning

confidence: 99%

Integrated Deep Learning and Stochastic Models for Accurate Segmentation of Lung Nodules From Computed Tomography Images: A Novel Framework

Youssef,

Alksas,

Shalaby

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This paper introduces an innovative model for precise extraction of lung nodules from 3D computed tomography (CT) scans. Our approach comprises two essential preprocessing stages aimed at refining search accuracy and nodule segmentation. Initially, we leverage a two-level joint Markov-Gibbs random field (MGRF) model to delineate the lung region, effectively distinguishing lung wall nodules from the chest region with shared visual characteristics. Subsequently, employing a deep learning U-net technique, we pinpoint the region of interest (ROI) housing the lung nodule, minimizing the inclusion of surrounding lung tissues. Further enhancement comes from a 3D U-net, trained with a novel loss function to mitigate under-or over-segmentation issues. The resulting segmentation robustly outlines lung nodules in terms of morphology and volume metrics, validated by Dice coefficient (DCE), absolute volume difference (AVD), 95 th -percentile Hausdorff distance (HD), sensitivity, and specificity metrics. To assess our approach, we conducted comprehensive experiments. Our evaluation encompasses in vivo data from 50 patients and employs 679 subjects from the publicly available dataset of the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The LIDC-IDRI dataset, a seminal resource for computer-aided diagnosis (CAD) in lung nodules, offers annotations enabling tasks like detection, segmentation, classification, and quantification. Our experiments showcase our model's superiority over existing deep learning methods, particularly evident in metrics such as the 95 th -percentile HD and DCE. While limited demographic information constrains a comprehensive analysis, our approach's robust performance underlines its potential integration into nodule assessment AI systems.

show abstract

“…The conventional mathematical segmentation method is developed mainly based on the CT value distribution and shape characteristics of pulmonary nodules. Several novel algorithms have been proposed to segment nodules in CT images, which include the level set‐based segmentation method, 9 Markov random field energy and Bayesian probability difference algorithm, 10 asymmetric multi‐phase deformable model, 11 and so on. This type of segmentation method performs well on the solitary solid nodules that have homogeneity gray values and high contrast surrounding tissue in CT images, but its performance decreases with the increased blur degree of the boundary between surrounding tissue and the nodule adhesion regions, that is, GGNs and juxta‐vascular nodule 12 …”

Section: Introductionmentioning

confidence: 99%

Volumetric segmentation of ground glass nodule based on 3D attentional cascaded residual U‐Net and conditional random field

et al. 2022

View full text Add to dashboard Cite

Background: Ground glass nodule (GGN) segmentation is one of the important and challenging tasks in diagnosing early-stage lung adenocarcinomas. Manually delineating of 3D GGN in a computed tomography (CT) image is a subjective, laborious, and tedious task, which presents poor repeatability. Purpose: To reduce the annotation burden and improve the segmentation performance, this study proposes a 3D deep learning-based volumetric segmentation model to segment the GGN in CT images. Methods: A total of 379 GGNs were retrospectively collected from the public database, Shanghai Pulmonary Hospital (SHPH), and Fudan University Shanghai Cancer Center (FUSCC). First, a series of image preprocessing techniques involving image resampling, intensity normalization, 3D nodule patch cropping, and data augmentation, were adopted to generate the input images for the deep learning model by using CT scans.Then,a 3D attentional cascaded residual network (ACRU-Net) was proposed to develop the deep learning-based segmentation model by using the residual network and the atrous spatial pyramid pooling module. To improve the model performance, a voxel-based conditional random field (CRF) method was used to optimize the segmentation results. Finally, a balanced cross-entropy and Dice combined loss function was applied to train and build the segmentation model. Results: Testing on SHPH and FUSCC datasets, the proposed method generates the Dice coefficients of 0.721 ± 0.167 and 0.733 ± 0.100, respectively, which are higher than those of 3D residual U-Net and ACRU-Net without CRF optimization. Conclusions:The results demonstrated that combining 3D ACRU-Net and CRF effectively improved the GGN segmentation performance. The proposed segmentation model may provide a potential tool to help the radiologist in the segmentation and diagnosis of 3D GGN.

show abstract

A Level Set Based Unified Framework for Pulmonary Nodule Segmentation

Cited by 10 publications

References 34 publications

Deep learning-based lung nodule detection: a review

Deep learning-based lung nodule detection: a review

Integrated Deep Learning and Stochastic Models for Accurate Segmentation of Lung Nodules From Computed Tomography Images: A Novel Framework

Volumetric segmentation of ground glass nodule based on 3D attentional cascaded residual U‐Net and conditional random field

Contact Info

Product

Resources

About