scholarly journals Lung Segmentation in 4D CT Volumes Based on Robust Active Shape Model Matching

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Gurman Gill ◽  
Reinhard R. Beichel
Keyword(s):  
Image Data ◽  
Active Shape Model ◽  
Data Sets ◽  
Segmentation Method ◽  
Data Set ◽  
Shape Model ◽  
Lung Segmentation ◽  
4D Ct ◽  
Active Shape ◽  
Ct Data

Dynamic and longitudinal lung CT imaging produce 4D lung image data sets, enabling applications like radiation treatment planning or assessment of response to treatment of lung diseases. In this paper, we present a 4D lung segmentation method that mutually utilizes all individual CT volumes to derive segmentations for each CT data set. Our approach is based on a 3D robust active shape model and extends it to fully utilize 4D lung image data sets. This yields an initial segmentation for the 4D volume, which is then refined by using a 4D optimal surface finding algorithm. The approach was evaluated on a diverse set of 152 CT scans of normal and diseased lungs, consisting of total lung capacity and functional residual capacity scan pairs. In addition, a comparison to a 3D segmentation method and a registration based 4D lung segmentation approach was performed. The proposed 4D method obtained an average Dice coefficient of0.9773±0.0254, which was statistically significantly better (pvalue≪0.001) than the 3D method (0.9659±0.0517). Compared to the registration based 4D method, our method obtained better or similar performance, but was 58.6% faster. Also, the method can be easily expanded to process 4D CT data sets consisting of several volumes.

Influence of Active Shape Model Segmentation Method on Optical Reconstruction

2018 ◽  
Vol 38 (2) ◽  
pp. 0211001
Author(s):  
侯榆青 Hou Yuqing ◽  
胡昊文 Hu Haowen ◽  
赵凤军 Zhao Fengjun ◽  
何雪磊 He Xuelei ◽  
易黄建 Yi Huangjian ◽  
...  
Keyword(s):  
Active Shape Model ◽  
Segmentation Method ◽  
Shape Model ◽  
Model Segmentation ◽  
Active Shape ◽  
Optical Reconstruction

Motion Artifact Reducing Reconstruction of 4D CT Image Data for the Analysis of Respiratory Dynamics

2007 ◽  
Vol 46 (03) ◽  
pp. 254-260 ◽  
Author(s):  
J. Ehrhardt ◽  
T. Frenzel ◽  
D. Säring ◽  
W. Lu ◽  
D. Low ◽  
...  
Keyword(s):  
Optical Flow ◽  
Motion Analysis ◽  
Respiratory Motion ◽  
Image Data ◽  
Motion Artifacts ◽  
Data Sets ◽  
Ct Image ◽  
Ct Reconstruction ◽  
4D Ct ◽  
Ct Data

Summary Objectives: Respiratory motion represents a major problem in radiotherapy of thoracic and abdominal tumors. Methods for compensation require comprehensive knowledge of underlying dynamics. Therefore, 4D (= 3D + t) CT data can be helpful. But modern CT scanners cannot scan a large region of interest simultaneously. So patients have to be scanned in segments. Commonly used approaches for reconstructing the data segments into 4D CT images cause motion artifacts. In orderto reduce the artifacts, a new method for 4D CT reconstruction is presented. The resulting data sets are used to analyze respiratory motion. Methods: Spatiotemporal CT image sequences of lung cancer patients were acquired using a multi-slice CT in cine mode during free breathing. 4D CT reconstruction was done by optical flow based temporal interpolation. The resulting 4D image data were compared with data generated bythe commonly used nearest neighbor reconstruction. Subsequent motion analysis is mainly concerned with tumor mobility. Results: The presented optical flow-based method enables the reconstruction of 3D CT images at arbitrarily chosen points of the patient’s breathing cycle. A considerable reduction of motion artifacts has been proven in eight patient data sets. Motion analysis showed that tumor mobility differs strongly between the patients. Conclusions: Due to the proved reduction of motion artifacts, the optical flow-based 4D CT reconstruction offers the possibility of high-quality motion analysis. Because the method is based on an interpolation scheme, it additionally has the potential to enable the reconstruction of 4D CT data from a lesser number of scans.

Segmentation method for cardiac region in CT images based on active shape model

ICCAS 2010 ◽  
2010 ◽  
Author(s):  
Hiroki Takahashi ◽  
Masafumi Komatsu ◽  
Hyoungseop Kim ◽  
Joo Kooi Tan ◽  
Seiji Ishikawa ◽  
...  
Keyword(s):  
Ct Images ◽  
Active Shape Model ◽  
Segmentation Method ◽  
Shape Model ◽  
Cardiac Region ◽  
Active Shape

scholarly journals Ultrasound Common Carotid Artery Segmentation Based on Active Shape Model

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Xin Yang ◽  
Jiaoying Jin ◽  
Mengling Xu ◽  
Huihui Wu ◽  
Wanji He ◽  
...  
Keyword(s):  
Carotid Artery ◽  
Common Carotid Artery ◽  
Carotid Atherosclerosis ◽  
Clinical Care ◽  
Active Shape Model ◽  
Dice Similarity Coefficient ◽  
Volume Data ◽  
Data Set ◽  
Shape Model ◽  
Active Shape

Carotid atherosclerosis is a major reason of stroke, a leading cause of death and disability. In this paper, a segmentation method based on Active Shape Model (ASM) is developed and evaluated to outline common carotid artery (CCA) for carotid atherosclerosis computer-aided evaluation and diagnosis. The proposed method is used to segment both media-adventitia-boundary (MAB) and lumen-intima-boundary (LIB) on transverse views slices from three-dimensional ultrasound (3D US) images. The data set consists of sixty-eight, 17 × 2 × 2, 3D US volume data acquired from the left and right carotid arteries of seventeen patients (eight treated with 80 mg atorvastatin and nine with placebo), who had carotid stenosis of 60% or more, at baseline and after three months of treatment. Manually outlined boundaries by expert are adopted as the ground truth for evaluation. For the MAB and LIB segmentations, respectively, the algorithm yielded Dice Similarity Coefficient (DSC) of 94.4% ± 3.2% and 92.8% ± 3.3%, mean absolute distances (MAD) of 0.26 ± 0.18 mm and 0.33 ± 0.21 mm, and maximum absolute distances (MAXD) of 0.75 ± 0.46 mm and 0.84 ± 0.39 mm. It took 4.3 ± 0.5 mins to segment single 3D US images, while it took 11.7 ± 1.2 mins for manual segmentation. The method would promote the translation of carotid 3D US to clinical care for the monitoring of the atherosclerotic disease progression and regression.

scholarly journals Does Motion Assessment With 4-Dimensional Computed Tomographic Imaging for Non–Small Cell Lung Cancer Radiotherapy Improve Target Volume Coverage?

2017 ◽  
Vol 11 ◽  
pp. 117955491769846 ◽  
Author(s):  
Naseer Ahmed ◽  
Sankar Venkataraman ◽  
Kate Johnson ◽  
Keith Sutherland ◽  
Shaun K Loewen
Keyword(s):  
Lung Cancer ◽  
Gross Tumor Volume ◽  
Tumor Volume ◽  
Target Volume ◽  
Data Sets ◽  
Nodal Disease ◽  
Dice Coefficient ◽  
Data Set ◽  
4D Ct ◽  
Ct Data

Introduction: Modern radiotherapy with 4-dimensional computed tomographic (4D-CT) image acquisition for non–small cell lung cancer (NSCLC) captures respiratory-mediated tumor motion to provide more accurate target delineation. This study compares conventional 3-dimensional (3D) conformal radiotherapy (3DCRT) plans generated with standard helical free-breathing CT (FBCT) with plans generated on 4D-CT contoured volumes to determine whether target volume coverage is affected. Materials and methods: Fifteen patients with stage I to IV NSCLC were enrolled in the study. Free-breathing CT and 4D-CT data sets were acquired at the same simulation session and with the same immobilization. Gross tumor volume (GTV) for primary and/or nodal disease was contoured on FBCT (GTV_3D). The 3DCRT plans were obtained, and the patients were treated according to our institution’s standard protocol using FBCT imaging. Gross tumor volume was contoured on 4D-CT for primary and/or nodal disease on all 10 respiratory phases and merged to create internal gross tumor volume (IGTV)_4D. Clinical target volume margin was 5 mm in both plans, whereas planning tumor volume (PTV) expansion was 1 cm axially and 1.5 cm superior/inferior for FBCT-based plans to incorporate setup errors and an estimate of respiratory-mediated tumor motion vs 8 mm isotropic margin for setup error only in all 4D-CT plans. The 3DCRT plans generated from the FBCT scan were copied on the 4D-CT data set with the same beam parameters. GTV_3D, IGTV_4D, PTV, and dose volume histogram from both data sets were analyzed and compared. Dice coefficient evaluated PTV similarity between FBCT and 4D-CT data sets. Results: In total, 14 of the 15 patients were analyzed. One patient was excluded as there was no measurable GTV. Mean GTV_3D was 115.3 cm3 and mean IGTV_4D was 152.5 cm3 ( P = .001). Mean PTV_3D was 530.0 cm3 and PTV_4D was 499.8 cm3 ( P = .40). Both gross primary and nodal disease analyzed separately were larger on 4D compared with FBCT. D95 (95% isodose line) covered 98% of PTV_3D and 88% of PTV_4D ( P = .003). Mean dice coefficient of PTV_3D and PTV_4D was 84%. Mean lung V20 was 24.0% for the 3D-based plans and 22.7% for the 4D-based plans ( P = .057). Mean heart V40 was 12.1% for the 3D-based plans and 12.7% for the 4D-based plans ( P = .53). Mean spinal cord Dmax was 2517 and 2435 cGy for 3D-based and 4D-based plans, respectively ( P = .019). Mean esophageal dose was 1580 and 1435 cGy for 3D and 4D plans, respectively ( P = .13). Conclusions: IGTV_4D was significantly larger than GTV_3D for both primary and nodal disease combined or separately. Mean PTV_3D was larger than PTV_4D, but the difference was not statistically significant. The PTV_4D coverage with 95% isodose line was inferior, indicating the importance of incorporating the true size and shape of the target volume. Relatively less dose was delivered to spinal cord and esophagus with plans based on 4D data set. Dice coefficient analysis for degree of similarity revealed that 16% of PTVs from both data sets did not overlap, indicating different anatomical positions of the PTV due to tumor/nodal motion during a respiratory cycle. All patients with lung cancer planned for radical radiotherapy should have 4D-CT simulation to ensure accurate coverage of the target volumes.

Sign in / Sign up

Export Citation Format

Share Document