scholarly journals Joint Segmentation Methods of Tumor Delineation in PET – CT Images: A Review

2018 ◽  
Vol 7 (3.32) ◽  
pp. 137
Author(s):  
Farli Rossi ◽  
Ashrani Aizzuddin Abd Rahni
Keyword(s):  
Image Segmentation ◽  
Ct Images ◽  
Basic Knowledge ◽  
Low Contrast ◽  
Tumor Delineation ◽  
Innovative Methods ◽  
Pet Ct ◽  
Segmentation Methods ◽  
Disease Staging ◽  
Puzzle Task

Segmentation is one of the crucial steps in applications of medical diagnosis. The accurate image segmentation method plays an important role in proper detection of disease, staging, diagnosis, radiotherapy treatment planning and monitoring. In the advances of image segmentation techniques, joint segmentation of PET-CT images has increasingly received much attention in the field of both clinic and image processing. PET - CT images have become a standard method for tumor delineation and cancer assessment. Due to low spatial resolution in PET and low contrast in CT images, automated segmentation of tumor in PET - CT images is a well-known puzzle task. This paper attempted to describe and review four innovative methods used in the joint segmentation of functional and anatomical PET - CT images for tumor delineation. For the basic knowledge, the state of the art image segmentation methods were briefly reviewed and fundamental of PET and CT images were briefly explained. Further, the specific characteristics and limitations of four joint segmentation methods were critically discussed.  

Lung Tumor Delineation Based on Novel Tumor-Background Likelihood Models in PET-CT Images

2014 ◽  
Vol 61 (1) ◽  
pp. 218-224 ◽  
Author(s):  
Xiuying Wang ◽  
Cherry Ballangan ◽  
Hui Cui ◽  
Michael Fulham ◽  
Stefan Eberl ◽  
...  
Keyword(s):  
Lung Tumor ◽  
Ct Images ◽  
Tumor Delineation ◽  
Pet Ct

Automated liver segmentation for whole-body low-contrast CT images from PET-CT scanners

2009 ◽  
Author(s):  
Xiuying Wang ◽  
Changyang Li ◽  
S. Eberl ◽  
M. Fulham ◽  
Dagan Feng
Keyword(s):  
Ct Images ◽  
Whole Body ◽  
Liver Segmentation ◽  
Low Contrast ◽  
Pet Ct ◽  
Ct Scanners ◽  
Contrast Ct

PD-0293 REPRODUCIBILITY AND VOLUME SEGMENTATION METHODS ON F-MISO AND FLT PET-CT IMAGES IN PATIENTS WITH LUNG CANCER

2012 ◽  
Vol 103 ◽  
pp. S115
Author(s):  
S. Thureau ◽  
P. Chaumet-Riffaud ◽  
P. Fernandez ◽  
B. Bridji ◽  
C. Houzard ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Ct Images ◽  
Volume Segmentation ◽  
Flt Pet ◽  
Pet Ct ◽  
Segmentation Methods

PROBABILITY RANDOM INDEX BASED CLUSTERING FOR SEGMENTATION OF PET-CT IMAGES

2019 ◽  
Vol 31 (02) ◽  
pp. 1950011
Author(s):  
S. Guruprasad ◽  
M. Z. Kurian ◽  
H. N. Suma
Keyword(s):  
Structural Information ◽  
Medical Image Segmentation ◽  
Response To Therapy ◽  
Low Contrast ◽  
Positron Emission ◽  
Pet Ct ◽  
Segmentation Methods ◽  
Random Index ◽  
Anatomical Information ◽  
Single Modality

Medical image segmentation is a vital process in medical diagnosis and evaluation of tumor response to therapy. Current segmentation methods works only on single modality image like positron emission tomography has low resolution and gives only functional information; Computed Tomography has low contrast and provides structural information. This paper focus on segmentation of multimodality PET-CT image. In recent days PET-CT is advanced multimodal imaging equipment, which gives both functional and anatomical information in a single image. Probability random index is a new methodology adopted to segment the portion of an image, which is most essential for determining the actual intricacies involved in the portion of a body. The clustering is another methodology used to group similar pixel locations into a single group based on unpredictable random values of an image. The probability based clustering has been incorporated to overcome the drawbacks of existing methods of segmentation like over segmentation and under segmentation. The over segmentation has been eliminated by incorporating random values generated from the features of dataset of images. Similarly under segmentation has been eliminated by removing barriers of lack of collecting similarly values from clustering. Thus, the proposed method eliminates both over segmentation and under segmentation drawbacks of the existing methods. The proposed probability random index based clustering has yielded good results in comparision with other contemporary methods, which shall be observed from the section, results and analysis. The proposed probability random indexed clustering has yielded a good result of 88.41% on benchmark dataset.

Sign in / Sign up

Export Citation Format

Share Document