Automated Volume Analysis of Head and Neck Lesions on CT Scans Using 3D Level Set Segmentation

Overview

Journal Med Phys

Specialty Biophysics

Date 2007 Dec 13

PMID 18072505

Citations 21

Authors

Ethan Street

Lubomir Hadjiiski

Berkman Sahiner

Sachin Gujar

Mohannad Ibrahim

Suresh K Mukherji

Heang-Ping Chan

Affiliations

Soon will be listed here.

Abstract

The authors have developed a semiautomatic system for segmentation of a diverse set of lesions in head and neck CT scans. The system takes as input an approximate bounding box, and uses a multistage level set to perform the final segmentation. A data set consisting of 69 lesions marked on 33 scans from 23 patients was used to evaluate the performance of the system. The contours from automatic segmentation were compared to both 2D and 3D gold standard contours manually drawn by three experienced radiologists. Three performance metric measures were used for the comparison. In addition, a radiologist provided quality ratings on a 1 to 10 scale for all of the automatic segmentations. For this pilot study, the authors observed that the differences between the automatic and gold standard contours were larger than the interobserver differences. However, the system performed comparably to the radiologists, achieving an average area intersection ratio of 85.4% compared to an average of 91.2% between two radiologists. The average absolute area error was 21.1% compared to 10.8%, and the average 2D distance was 1.38 mm compared to 0.84 mm between the radiologists. In addition, the quality rating data showed that, despite the very lax assumptions made on the lesion characteristics in designing the system, the automatic contours approximated many of the lesions very well.

Citing Articles

A convolutional neural network for contouring metastatic lymph nodes on diffusion-weighted magnetic resonance images for assessment of radiotherapy response.

Gurney-Champion O, Kieselmann J, Wong K, Ng-Cheng-Hin B, Harrington K, Oelfke U Phys Imaging Radiat Oncol. 2020; 15:1-7.

PMID: 33043156 PMC: 7536306. DOI: 10.1016/j.phro.2020.06.002.

Deep-learning convolutional neural network: Inner and outer bladder wall segmentation in CT urography.

Gordon M, Hadjiiski L, Cha K, Samala R, Chan H, Cohan R Med Phys. 2018; 46(2):634-648.

PMID: 30520055 PMC: 6367014. DOI: 10.1002/mp.13326.

A Unified Level Set Framework Combining Hybrid Algorithms for Liver and Liver Tumor Segmentation in CT Images.

Zheng Z, Zhang X, Xu H, Liang W, Zheng S, Shi Y Biomed Res Int. 2018; 2018:3815346.

PMID: 30159326 PMC: 6106976. DOI: 10.1155/2018/3815346.

Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning.

Wang Z, Wei L, Wang L, Gao Y, Chen W, Shen D IEEE Trans Image Process. 2018; 27(2):923-937.

PMID: 29757737 PMC: 5954838. DOI: 10.1109/TIP.2017.2768621.

Bladder Cancer Segmentation in CT for Treatment Response Assessment: Application of Deep-Learning Convolution Neural Network-A Pilot Study.

Cha K, Hadjiiski L, Samala R, Chan H, Cohan R, Caoili E Tomography. 2017; 2(4):421-429.

PMID: 28105470 PMC: 5241049. DOI: 10.18383/j.tom.2016.00184.

References

Sahiner B, Petrick N, Chan H, Hadjiiski L, Paramagul C, Helvie M . Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization. IEEE Trans Med Imaging. 2002; 20(12):1275-84. DOI: 10.1109/42.974922. View

Beichel R, Bischof H, Leberl F, Sonka M . Robust active appearance models and their application to medical image analysis. IEEE Trans Med Imaging. 2005; 24(9):1151-69. DOI: 10.1109/TMI.2005.853237. View

Way T, Hadjiiski L, Sahiner B, Chan H, Cascade P, Kazerooni E . Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours. Med Phys. 2006; 33(7):2323-37. PMC: 2728558. DOI: 10.1118/1.2207129. View

Cates J, Lefohn A, Whitaker R . GIST: an interactive, GPU-based level set segmentation tool for 3D medical images. Med Image Anal. 2004; 8(3):217-31. DOI: 10.1016/j.media.2004.06.022. View

Colliot O, Mansi T, Bernasconi N, Naessens V, Klironomos D, Bernasconi A . Segmentation of focal cortical dysplasia lesions on MRI using level set evolution. Neuroimage. 2006; 32(4):1621-30. DOI: 10.1016/j.neuroimage.2006.04.225. View

Sahiner B, Chan H, Petrick N, Helvie M, Hadjiiski L . Improvement of mammographic mass characterization using spiculation meausures and morphological features. Med Phys. 2001; 28(7):1455-65. DOI: 10.1118/1.1381548. View

Chen D, Chang R, Wu W, Moon W, Wu W . 3-D breast ultrasound segmentation using active contour model. Ultrasound Med Biol. 2003; 29(7):1017-26. DOI: 10.1016/s0301-5629(03)00059-0. View

Sahiner B, Chan H, Roubidoux M, Helvie M, Hadjiiski L, Ramachandran A . Computerized characterization of breast masses on three-dimensional ultrasound volumes. Med Phys. 2004; 31(4):744-54. DOI: 10.1118/1.1649531. View

Banks J, Bennamoun M . Reliability analysis of the rank transform for stereo matching. IEEE Trans Syst Man Cybern B Cybern. 2008; 31(6):870-80. DOI: 10.1109/3477.969491. View

10.

Droske M, Meyer B, Rumpf M, Schaller C . An adaptive level set method for interactive segmentation of intracranial tumors. Neurol Res. 2005; 27(4):363-70. DOI: 10.1179/016164105X48842. View

11.

Chen W, Giger M, Bick U . A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. Acad Radiol. 2006; 13(1):63-72. DOI: 10.1016/j.acra.2005.08.035. View

12.

Chong V, Zhou J, Khoo J, Huang J, Lim T . Nasopharyngeal carcinoma tumor volume measurement. Radiology. 2004; 231(3):914-21. DOI: 10.1148/radiol.2313030358. View

13.

Uzumcu M, van der Geest R, Sonka M, Lamb H, Reiber J, Lelieveldt B . Multiview active appearance models for simultaneous segmentation of cardiac 2- and 4-chamber long-axis magnetic resonance images. Invest Radiol. 2005; 40(4):195-203. DOI: 10.1097/01.rli.0000154216.94316.f7. View

14.

Lee F, Yeung D, King A, Leung S, Ahuja A . Segmentation of nasopharyngeal carcinoma (NPC) lesions in MR images. Int J Radiat Oncol Biol Phys. 2005; 61(2):608-20. DOI: 10.1016/j.ijrobp.2004.09.024. View

15.

Chang R, Wu W, Moon W, Chen W, Lee W, Chen D . Segmentation of breast tumor in three-dimensional ultrasound images using three-dimensional discrete active contour model. Ultrasound Med Biol. 2003; 29(11):1571-81. DOI: 10.1016/s0301-5629(03)00992-x. View

16.

Liu W, Zagzebski J, Varghese T, Dyer C, Techavipoo U, Hall T . Segmentation of elastographic images using a coarse-to-fine active contour model. Ultrasound Med Biol. 2006; 32(3):397-408. PMC: 1764611. DOI: 10.1016/j.ultrasmedbio.2005.11.011. View

17.

Popovic A, Wu T, Engelhardt M, Radermacher K . Modeling of intensity priors for knowledge-based level set algorithm in calvarial tumors segmentation. Med Image Comput Comput Assist Interv. 2007; 9(Pt 2):864-71. DOI: 10.1007/11866763_106. View