Dynamic-thresholding level set: a novel computer-aided volumetry method for liver tumors in hepatic CT images

2007 ◽  
Author(s):  
Wenli Cai ◽  
Hiroyuki Yoshida ◽  
Gordon J. Harris
Keyword(s):  
Level Set ◽  
Liver Tumors ◽  
Ct Images ◽  
Computer Aided

scholarly journals Segmentation of Liver Metastases Using a Level Set Method with Spiral-Scanning Technique and Supervised Fuzzy Pixel Classification

2008 ◽  
Author(s):  
Dirk Smeets ◽  
Bert Stijnen ◽  
Dirk Loeckx ◽  
Bart De Dobbelaer ◽  
Paul Suetens
Keyword(s):  
Liver Metastases ◽  
Level Set ◽  
Liver Tumors ◽  
Automatic Segmentation ◽  
Ct Images ◽  
Specific Method ◽  
Pixel Classification ◽  
Spiral Scanning ◽  
Level Set Function ◽  
Scanning Technique

In this paper a specific method is presented to facilitate the semi-automatic segmentation of liver metastases in CT images. Accurate and reliable segmentation of tumors is e.g. essential for the follow-up of cancer treatment. The core of the algorithm is a level set function. The initialization is provided by a spiral-scanning technique based on dynamic programming. The level set evolves according to a speed image that is the result of a statistical pixel classification algorithm with supervised learning. This method is tested on CT images of the abdomen and compared with manual delineations of liver tumors.

Automatic Liver Lesion Extraction from CT Images Based on Distance Regularized Level Set Evolution and Region Growing

2014 ◽  
Vol 556-562 ◽  
pp. 4924-4928 ◽  
Author(s):  
Feng Lian Gao ◽  
Lian Fen Huang ◽  
Jia Kun Wang ◽  
Hai Tao Shuai ◽  
Jian Jun Sun ◽  
...  
Keyword(s):  
Level Set ◽  
Liver Diseases ◽  
Region Growing ◽  
Liver Lesion ◽  
Ct Images ◽  
Abdominal Ct ◽  
Cancerous Lesion ◽  
Computer Aided ◽  
Level Set Evolution ◽  
Aided Diagnosis

Current diagnosis with computed tomography (CT) imaging relies heavily on doctors’ clinical experience and it is difficult to accurately identify and localize lesions from thousands of CT images. Therefore, computer-aided diagnosis with automatic lesion extraction will be helpful for doctors in the diagnosis of liver diseases. In this paper, we proposed a new method for automatic liver lesion extraction from CT images by combining DRLSE (distance regularized level set evolution) and region growing. The method was applied in abdominal CT images with a single liver cancerous lesion and multiple hemangioma lesions at different locations. The results demonstrated the feasibility of our method for automatic lesion extraction with improved diagnostic accuracy and time efficiency.

scholarly journals Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images

2009 ◽  
Vol 56 (7) ◽  
pp. 1810-1820 ◽  
Author(s):  
Xujiong Ye ◽  
Xinyu Lin ◽  
J. Dehmeshki ◽  
G. Slabaugh ◽  
G. Beddoe
Keyword(s):  
Ct Images ◽  
Lung Nodules ◽  
Computer Aided Detection ◽  
Thoracic Ct ◽  
Computer Aided

scholarly journals Regional infarction identification from cardiac CT images: a computer-aided biomechanical approach

2016 ◽  
Vol 11 (9) ◽  
pp. 1573-1583 ◽  
Author(s):  
Ken C. L. Wong ◽  
Michael Tee ◽  
Marcus Chen ◽  
David A. Bluemke ◽  
Ronald M. Summers ◽  
...  
Keyword(s):  
Cardiac Ct ◽  
Ct Images ◽  
Computer Aided ◽  
Biomechanical Approach

SEGMENTATION OF ABDOMEN DISEASES USING ACTIVE CONTOUR MODELS IN CT IMAGES

2015 ◽  
Vol 27 (05) ◽  
pp. 1550047 ◽  
Author(s):  
Gaurav Sethi ◽  
B. S. Saini
Keyword(s):  
Level Set ◽  
Active Contour ◽  
Active Contour Model ◽  
Diagnostic System ◽  
Ct Images ◽  
Active Contour Models ◽  
Segmentation Methods ◽  
Contour Models ◽  
Edge Based ◽  
Level Set Evolution

Precise segmentation of abdomen diseases like tumor, cyst and stone are crucial in the design of a computer aided diagnostic system. The complexity of shapes and similarity of texture of disease with the surrounding tissues makes the segmentation of abdomen related diseases much more challenging. Thus, this paper is devoted to the segmentation of abdomen diseases using active contour models. The active contour models are formulated using the level-set method. Edge-based Distance Regularized Level Set Evolution (DRLSE) and region based Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) are used for segmentation of various abdomen diseases. These segmentation methods are applied on 60 CT images (20 images each of tumor, cyst and stone). Comparative analysis shows that edge-based active contour models are able to segment abdomen disease more accurately than region-based level set active contour model.

Sign in / Sign up

Export Citation Format

Share Document