Evaluation of 4 three-dimensional representation algorithms in capsule endoscopy images

被引:13
作者
Karargyris, Alexandros [1 ]
Rondonotti, Emanuele [2 ]
Mandelli, Giovanna [2 ]
Koulaouzidis, Anastasios [3 ]
机构
[1] NIH, Natl Lib Med, Bethesda, MD 20892 USA
[2] Osped Valduce, Gastroenterol Unit, I-22100 Como, Italy
[3] Royal Infirm Edinburgh NHS Trust, Ctr Liver & Digest Disorders, Edinburgh EH16 4SA, Midlothian, Scotland
关键词
Capsule endoscopy; Small-bowel; Three-dimensional; Software; Algorithm; Reconstruction; Technology; Advance; SMALL-BOWEL; SHAPE; RECONSTRUCTION;
D O I
10.3748/wjg.v19.i44.8028
中图分类号
R57 [消化系及腹部疾病];
学科分类号
摘要
AIM: To evaluate the three-dimensional (3-D) representation performance of 4 publicly available Shape-from-Shading (SfS) algorithms in small-bowel capsule endoscopy (SBCE). METHODS: SfS techniques recover the shape of objects using the gradual variation of shading. There are 4 publicly available SfS algorithms. To the best of our knowledge, no comparative study with images obtained during clinical SBCE has been performed to date. Three experienced reviewers were asked to evaluate 54 two-dimensional (2-D) images (categories: protrusion/inflammation/vascular) transformed to 3-D by the aforementioned SfS 3-D algorithms. The best algorithm was selected and inter-rater agreement was calculated. RESULTS: Four publicly available SfS algorithms were compared. Tsai's SfS algorithm outperformed the rest (selected as best performing in 45/54 SBCE images), followed by Ciuti's algorithm (best performing in 7/54 images) and Torreao's (in 1/54 images). In 26/54 images; Tsai's algorithm was unanimously selected as the best performing 3-D representation SfS software. Tsai's 3-D algorithm superiority was independent of lesion category (protrusion/inflammatory/vascular; P = 0.678) and/or CE system used to obtain the 2-D images (MiroCam (R)/PillCam (R); P = 0.558). Lastly, the inter-observer agreement was good (kappa = 0.55). CONCLUSION: 3-D representation software offers a plausible alternative for 3-D representation of conventional capsule endoscopy images (until optics technology matures enough to allow hardware enabled-"real" 3-D reconstruction of the gastrointestinal tract). (C) 2013 Baishideng Publishing Group Co., Limited. All rights reserved.
引用
收藏
页码:8028 / 8033
页数:6
相关论文
共 25 条
[1]  
Barron JT, 2012, LECT NOTES COMPUT SC, V7575, P57, DOI 10.1007/978-3-642-33765-9_5
[2]   Review of 20 years of range sensor development [J].
Blais, F .
JOURNAL OF ELECTRONIC IMAGING, 2004, 13 (01) :231-243
[3]   Use of shape-from-shading to estimate three-dimensional architecture in the small intestinal lumen of celiac and control patients [J].
Ciaccio, Edward J. ;
Tennyson, Christina A. ;
Bhagat, Govind ;
Lewis, Suzanne K. ;
Green, Peter H. R. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2013, 111 (03) :676-684
[4]   Implementation of a polling protocol for predicting celiac disease in videocapsule analysis [J].
Ciaccio, Edward J. ;
Tennyson, Christina A. ;
Bhagat, Govind ;
Lewis, Suzanne K. ;
Green, Peter H. .
WORLD JOURNAL OF GASTROINTESTINAL ENDOSCOPY, 2013, 5 (07) :313-322
[5]  
Ciuti G, 2012, P IEEE RAS-EMBS INT, P768, DOI 10.1109/BioRob.2012.6290771
[6]   Video capsule endoscopy of the small bowel [J].
Eliakim, Rami .
CURRENT OPINION IN GASTROENTEROLOGY, 2013, 29 (02) :133-139
[7]   New vision in video capsule endoscopy: current status and future directions [J].
Fisher, Laurel R. ;
Hasler, William L. .
NATURE REVIEWS GASTROENTEROLOGY & HEPATOLOGY, 2012, 9 (07) :392-405
[8]  
Fu YA, 2012, IEEE INT C AUTOMAT L, P300, DOI 10.1109/ICAL.2012.6308215
[9]   CT-Enterography May Identify Small Bowel Tumors Not Detected by Capsule Endoscopy: Eight Years Experience at Mayo Clinic Rochester [J].
Hakim, Fayaz A. ;
Alexander, Jeffrey A. ;
Huprich, James E. ;
Grover, Madhusudan ;
Enders, Felicity T. .
DIGESTIVE DISEASES AND SCIENCES, 2011, 56 (10) :2914-2919
[10]   Wireless capsule endoscopy [J].
Iddan, G ;
Meron, G ;
Glukhovsky, A ;
Swain, P .
NATURE, 2000, 405 (6785) :417-417