Joint Lung CT Image Segmentation: A Hierarchical Bayesian Approach

Accurate lung CT image segmentation is of great clinical value, especially when it comes to delineate pathological regions including lung tumor. In this paper, we present a novel framework that jointly segments multiple lung computed tomography (CT) images via hierarchical Dirichlet process (HDP). In specifics, based on the assumption that lung CT images from different patients share similar image structure (organ sets and relative positioning), we derive a mathematical model to segment them simultaneously so that shared information across patients could be utilized to regularize each individual segmentation. Moreover, compared to many conventional models, the algorithm requires little manual involvement due to the nonparametric nature of Dirichlet process (DP). We validated proposed model upon clinical data consisting of healthy and abnormal (lung cancer) patients. We demonstrate that, because of the joint segmentation fashion, more accurate and consistent segmentations could be obtained.

• Publication year

  2016

• Venue

  PLoS ONE

• Publication date

  2016-09-09

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1371/journal.pone.0162211PMID 27611188PMCID 5017654
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Lung nodule diagnosis from CT images based on ensemble learning

  2015cited by this paper
• Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field.

  2013cited by this paper
• Automated lung CT image segmentation using kernel mean shift analysis

  2013cited by this paper
• 3D random walk based segmentation for lung tumor delineation in PET imaging

  2012cited by this paper
• Automated 3-D Segmentation of Lungs With Lung Cancer in CT Data Using a Novel Robust Active Shape Model Approach

  2012cited by this paper
• Robust Active Shape Model Based Lung Segmentation in CT Scans

  2011cited by this paper
• Automatic CT Image Segmentation of the Lungs with Region Growing Algorithm

  2011cited by this paper
• Tractography segmentation using a hierarchical Dirichlet processes mixture model

  2011cited by this paper
• Multiple-subjects connectivity-based parcellation using hierarchical Dirichlet process mixture models

  2009cited by this paper
• Tractography Segmentation Using a Hierarchical Dirichlet Processes Mixture Model

  2009cited by this paper
• Nonparametric Bayesian Image Segmentation

  2008influential reference
• Adaptive border marching algorithm: Automatic lung segmentation on chest CT images

  2008cited by this paper
• Hierarchical Dirichlet Processes

  2006cited by this paper
• Active shape model segmentation with optimal features

  2002cited by this paper
• Estimating mixture of dirichlet process models

  1998cited by this paper
• Estimation of regional pleural surface expansile forces in intact dogs.

  1983cited by this paper
• A Bayesian Analysis of Some Nonparametric Problems

  1973cited by this paper

• Cone-beam X-ray luminescence computed tomography via Laplacian scale mixture prior-driven variational Bayesian method.

  2025cites this paper
• Evaluation of a fusion model combining deep learning models based on enhanced CT images with radiological and clinical features in distinguishing lipid-poor adrenal adenoma from metastatic lesions

  2025cites this paper
• Lung image quality assessment and diagnosis using generative autoencoders in unsupervised ensemble learning

  2025cites this paper
• Unsupervised machine learning detection of iceberg populations within sea ice from dual-polarisation SAR imagery

  2023cites this paper
• Statistical robustness of Markov chain Monte Carlo accelerators

  2021cites this paper
• Automated approach for segmenting gross tumor volumes for lung cancer stereotactic body radiation therapy using CT-based dense V-networks

  2021cites this paper
• Accelerating Markov Random Field Inference with Uncertainty Quantification

  2021cites this paper
• Computed Tomography Image Segmentation Using Edge Correction Algorithm for Refractory Mycoplasma Pneumonia in Children

  2021cites this paper
• A Random Point Initialization Approach to Image Segmentation with Variational Level-sets

  2021cites this paper
• Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators

  2020cites this paper
• An Improved Lung Parenchyma Segmentation Using the Maximum Inter-Class Variance Method (OTSU)

  2020cites this paper
• Statistical Robustness of MCMC Accelerators

  2020cites this paper
• Statistical Robustness of Markov Chain Monte Carlo Accelerators Extended Abstract

  2020cites this paper
• Fuzzy relevance vector machine based classification of lung nodules in computed tomography images

  2019cites this paper
• Performance Evaluation of Lung Segmentation Techniques in Computer Aided Lung Nodule Detection System

  2019cites this paper
• A Kinect-Based Segmentation of Touching-Pigs for Real-Time Monitoring

  2018cites this paper
• Performance comparisons of the soft computing algorithms in lung segmentation and nodule identification

  2017cites this paper