Yechiel Lamash1, Sila Kurugol1, Moti Freiman1, Jeannette M Perez-Rossello2, Michael J Callahan2, Athos Bousvaros3, Simon K Warfield1. 1. Computational Radiology Laboratory, Department of Radiology, Children's Hospital Boston, Harvard Medical School, Boston, Massachusetts, USA. 2. Department of Radiology, Children's Hospital Boston, Harvard Medical School, Boston, Massachusetts, USA. 3. Center for Inflammatory Bowel Disease Treatment and Research, Children's Hospital Boston, Harvard Medical School, Boston, Massachusetts, USA.
Abstract
BACKGROUND: Contrast-enhanced MRI of the small bowel is an effective imaging sequence for the detection and characterization of disease burden in pediatric Crohn's disease (CD). However, visualization and quantification of disease burden requires scrolling back and forth through 3D images to follow the anatomy of the bowel, and it can be difficult to fully appreciate the extent of disease. PURPOSE: To develop and evaluate a method that offers better visualization and quantitative assessment of CD from MRI. STUDY TYPE: Retrospective. POPULATION: Twenty-three pediatric patients with CD. FIELD STRENGTH/SEQUENCE: 1.5T MRI system and T1 -weighted postcontrast VIBE sequence. ASSESSMENT: The convolutional neural network (CNN) segmentation of the bowel's lumen, wall, and background was compared with manual boundary delineation. We assessed the reproducibility and the capability of the extracted markers to differentiate between different levels of disease defined after a consensus review by two experienced radiologists. STATISTICAL TESTS: The segmentation algorithm was assessed using the Dice similarity coefficient (DSC) and boundary distances between the CNN and manual boundary delineations. The capability of the extracted markers to differentiate between different disease levels was determined using a t-test. The reproducibility of the extracted markers was assessed using the mean relative difference (MRD), Pearson correlation, and Bland-Altman analysis. RESULTS: Our CNN exhibited DSCs of 75 ± 18%, 81 ± 8%, and 97 ± 2% for the lumen, wall, and background, respectively. The extracted markers of wall thickness at the location of min radius (P = 0.0013) and the median value of relative contrast enhancement (P = 0.0033) could differentiate active and nonactive disease segments. Other extracted markers could differentiate between segments with strictures and segments without strictures (P < 0.05). The observers' agreement in measuring stricture length was >3 times superior when computed on curved planar reformatting images compared with the conventional scheme. DATA CONCLUSION: The results of this study show that the newly developed method is efficient for visualization and assessment of CD. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1565-1576.
BACKGROUND: Contrast-enhanced MRI of the small bowel is an effective imaging sequence for the detection and characterization of disease burden in pediatric Crohn's disease (CD). However, visualization and quantification of disease burden requires scrolling back and forth through 3D images to follow the anatomy of the bowel, and it can be difficult to fully appreciate the extent of disease. PURPOSE: To develop and evaluate a method that offers better visualization and quantitative assessment of CD from MRI. STUDY TYPE: Retrospective. POPULATION: Twenty-three pediatric patients with CD. FIELD STRENGTH/SEQUENCE: 1.5T MRI system and T1 -weighted postcontrast VIBE sequence. ASSESSMENT: The convolutional neural network (CNN) segmentation of the bowel's lumen, wall, and background was compared with manual boundary delineation. We assessed the reproducibility and the capability of the extracted markers to differentiate between different levels of disease defined after a consensus review by two experienced radiologists. STATISTICAL TESTS: The segmentation algorithm was assessed using the Dice similarity coefficient (DSC) and boundary distances between the CNN and manual boundary delineations. The capability of the extracted markers to differentiate between different disease levels was determined using a t-test. The reproducibility of the extracted markers was assessed using the mean relative difference (MRD), Pearson correlation, and Bland-Altman analysis. RESULTS: Our CNN exhibited DSCs of 75 ± 18%, 81 ± 8%, and 97 ± 2% for the lumen, wall, and background, respectively. The extracted markers of wall thickness at the location of min radius (P = 0.0013) and the median value of relative contrast enhancement (P = 0.0033) could differentiate active and nonactive disease segments. Other extracted markers could differentiate between segments with strictures and segments without strictures (P < 0.05). The observers' agreement in measuring stricture length was >3 times superior when computed on curved planar reformatting images compared with the conventional scheme. DATA CONCLUSION: The results of this study show that the newly developed method is efficient for visualization and assessment of CD. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:1565-1576.
Authors: David H Bruining; Ellen M Zimmermann; Edward V Loftus; William J Sandborn; Cary G Sauer; Scott A Strong Journal: Radiology Date: 2018-01-10 Impact factor: 11.105
Authors: Dwarikanath Mahapatra; Peter J Schuffler; Jeroen A W Tielbeek; Jesica C Makanyanga; Jaap Stoker; Stuart A Taylor; Franciscus M Vos; Joachim M Buhmann Journal: IEEE Trans Med Imaging Date: 2013-09-16 Impact factor: 10.048
Authors: Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez Journal: Med Image Anal Date: 2017-07-26 Impact factor: 8.545
Authors: Sila Kurugol; Moti Freiman; Onur Afacan; Liran Domachevsky; Jeannette M Perez-Rossello; Michael J Callahan; Simon K Warfield Journal: Med Image Anal Date: 2017-05-03 Impact factor: 8.545
Authors: Franciscus M Vos; Jeroen A W Tielbeek; Robiel E Naziroglu; Zhang Li; Peter Schueffler; Dwarikanath Mahapatra; Alexander Wiebel; C Lavini; Joachim M Buhmann; Hans-Christian Hege; Jaap Stoker; Lucas J van Vliet Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2012
Authors: Dwarikanath Mahapatra; Peter J Schüffler; Jeroen A W Tielbeek; Franciscus M Vos; Joachim M Buhmann Journal: Med Image Comput Comput Assist Interv Date: 2013
Authors: Polo A M S; Velo-Gala I; Sánchez-Polo M; von Gunten U; López-Peñalver J J; Rivera-Utrilla J Journal: Sci Total Environ Date: 2016-09-30 Impact factor: 7.963
Authors: J Rimola; S Rodriguez; O García-Bosch; I Ordás; E Ayala; M Aceituno; M Pellisé; C Ayuso; E Ricart; L Donoso; J Panés Journal: Gut Date: 2009-01-09 Impact factor: 23.059
Authors: Thomas Hampshire; Alex Menys; Asif Jaffer; Gauraang Bhatnagar; Shonit Punwani; David Atkinson; Steve Halligan; David J Hawkes; Stuart A Taylor Journal: PLoS One Date: 2017-01-10 Impact factor: 3.240
Authors: John Gubatan; Steven Levitte; Akshar Patel; Tatiana Balabanis; Mike T Wei; Sidhartha R Sinha Journal: World J Gastroenterol Date: 2021-05-07 Impact factor: 5.742