+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

A statistical method for lung tumor segmentation uncertainty in PET images based on user inference



A statistical method for lung tumor segmentation uncertainty in PET images based on user inference



Conference Proceedings 2015: 2255-2258



PET has been widely accepted as an effective imaging modality for lung tumor diagnosis and treatment. However, standard criteria for delineating tumor boundary from PET are yet to develop largely due to relatively low quality of PET images, uncertain tumor boundary definition, and variety of tumor characteristics. In this paper, we propose a statistical solution to segmentation uncertainty on the basis of user inference. We firstly define the uncertainty segmentation band on the basis of segmentation probability map constructed from Random Walks (RW) algorithm; and then based on the extracted features of the user inference, we use Principle Component Analysis (PCA) to formulate the statistical model for labeling the uncertainty band. We validated our method on 10 lung PET-CT phantom studies from the public RIDER collections [1] and 16 clinical PET studies where tumors were manually delineated by two experienced radiologists. The methods were validated using Dice similarity coefficient (DSC) to measure the spatial volume overlap. Our method achieved an average DSC of 0.878 ± 0.078 on phantom studies and 0.835 ± 0.039 on clinical studies.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 057099742

Download citation: RISBibTeXText

PMID: 26736741

DOI: 10.1109/embc.2015.7318841


Related references

Globally optimal tumor segmentation in PET-CT images: a graph-based co-segmentation method. Information Processing in Medical Imaging 22: 245-256, 2011

Unsupervised Segmentation of Greenhouse Plant Images Based on Statistical Method. Scientific Reports 8: 4465, 2018

Tumor or abnormality identification from magnetic resonance images using statistical region fusion based segmentation. Magnetic Resonance Imaging 34(9): 1292-1304, 2016

A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images; application in segmentation of pelvic X-ray images. Bmc Medical Informatics and Decision Making 9(Suppl. 1): S2, 2009

Knowledge-based method for segmentation and analysis of lung boundaries in chest X-ray images. Computerized Medical Imaging and Graphics 22(6): 463-477, 1999

Knowledge-based method for segmentation and analysis of lung boundaries in chest X-ray images. Computerized Medical Imaging & Graphics 22(6): 463-477, 1998

A new method based on both fuzzy set and possibility theories for tumor volume segmentation on PET images. Conference Proceedings 2008: 3122-3125, 2008

A method for tumor dosimetry based on hybrid planar-SPECT/CT images and semiautomatic segmentation. Medical Physics 45(11): 5004-5018, 2018

A vessel segmentation method for multi-modality angiographic images based on multi-scale filtering and statistical models. Biomedical Engineering Online 15(1): 120, 2016

Segmentation of human brain MR images using rule-based fuzzy logic inference. Studies in Health Technology and Informatics 105: 264-272, 2004

Lung tumor segmentation methods: Impact on the uncertainty of radiomics features for non-small cell lung cancer. Plos one 13(10): E0205003, 2018

Segmentation of myocardium from cardiac MR images using a novel dynamic programming based segmentation method. Medical Physics 42(3): 1424-1435, 2015

Statistical Physics-based Framework and Bayesian Inference for Model Selection and Uncertainty Quantification. Microscopy and Microanalysis 25(S2): 130-131, 2019

OASIS is Automated Statistical Inference for Segmentation, with applications to multiple sclerosis lesion segmentation in MRI. Neuroimage. Clinical 2: 402-413, 2013

Atlas-based segmentation of brain tumor images using a Markov random field-based tumor growth model and non-rigid registration. Conference Proceedings 2010: 4080-4083, 2010