Yan Wang1, Yue Zhang2,3, Wanling Xuan4, Evan Kao1,5, Peng Cao6, Bing Tian7, Karen Ordovas1, David Saloner1,2, Jing Liu8. 1. Department of Radiology, University of California San Francisco, San Francisco, CA, 94121, USA. 2. Department of Surgery, University of California San Francisco, San Francisco, CA, 94121, USA. 3. Veteran Affairs Medical Center, San Francisco, CA, 94121, USA. 4. The Ohio State University Wexner Medical Center, Columbus, Ohio, 43210, USA. 5. University of California Berkeley, Berkeley, CA, 94720, USA. 6. Department of Radiology, University of California San Francisco, San Francisco, CA, 94107, USA. 7. Department of Radiology, Changhai Hospital, Shanghai, 200433, China. 8. Department of Radiology, University of California San Francisco, San Francisco, CA, 94108, USA.
Abstract
PURPOSE: Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images. METHODS: The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary. RESULTS: This automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively. CONCLUSIONS: We have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.
PURPOSE: Segmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images. METHODS: The proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary. RESULTS: This automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively. CONCLUSIONS: We have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.
Authors: Manuel D Cerqueira; Neil J Weissman; Vasken Dilsizian; Alice K Jacobs; Sanjiv Kaul; Warren K Laskey; Dudley J Pennell; John A Rumberger; Thomas Ryan; Mario S Verani Journal: Circulation Date: 2002-01-29 Impact factor: 29.690
Authors: Steven C Mitchell; Johan G Bosch; Boudewijn P F Lelieveldt; Rob J van der Geest; Johan H C Reiber; Milan Sonka Journal: IEEE Trans Med Imaging Date: 2002-09 Impact factor: 10.048
Authors: Maria Lorenzo-Valdés; Gerardo I Sanchez-Ortiz; Andrew G Elkington; Raad H Mohiaddin; Daniel Rueckert Journal: Med Image Anal Date: 2004-09 Impact factor: 8.545
Authors: Stephanie M Shors; William G Cotts; Biljana Pavlovic-Surjancev; Christopher J François; Mihai Gheorghiade; J Paul Finn Journal: Radiology Date: 2003-12 Impact factor: 11.105
Authors: Duc M Giao; Yan Wang; Renan Rojas; Kiyoaki Takaba; Anusha Badathala; Kimberly A Spaulding; Gilbert Soon; Yue Zhang; Vicky Y Wang; Henrik Haraldsson; Jing Liu; David Saloner; Julius M Guccione; Liang Ge; Arthur W Wallace; Mark B Ratcliffe Journal: PLoS One Date: 2020-06-22 Impact factor: 3.240
Authors: Shabnam Peyvandi; Duan Xu; Yan Wang; Whitnee Hogan; Anita Moon-Grady; A James Barkovich; Orit Glenn; Patrick McQuillen; Jing Liu Journal: J Am Heart Assoc Date: 2020-12-21 Impact factor: 5.501