Bénédicte Cayot1,2, Laurent Milot3,4, Olivier Nempont3,5, Anna S Vlachomitrou3,5, Carole Langlois-Jacques3,6, Jérôme Dumortier3,7,8, Olivier Boillot3,8,9, Karine Arnaud3,10, Thijs R M Barten3,11, Joost P H Drenth3,12, Pierre-Jean Valette3,4. 1. Department of Medical Imaging, Hospices Civils de Lyon, University of Lyon, Lyon, France. benedicte.cayot@chu-lyon.fr. 2. Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France. benedicte.cayot@chu-lyon.fr. 3. Service d'imagerie médicale et interventionnelle, Hôpital Edouard Herriot, 5 Place d'Arsonval, 69003, Lyon, France. 4. Department of Medical Imaging, Edouard Herriot Hospital, Civil Hospices of Lyon, University of Lyon, Lyon, France. 5. Philips France, 33 rue de Verdun, CS 60 055, Cedex 92156, Suresnes, France. 6. Unit of Biostatistics, Civil Hospices of Lyon, Lyon ,CNRS UMR5558, Laboratory of Biometry and Evolutionary Biology, Biostatistics-Health Team, Lyon, France. 7. Department of Hepatology and Gastroenterology, Civil Hospices of Lyon, Edouard Herriot Hospital, Federation of Digestive Specialties, University of Lyon, Lyon, France. 8. University of Lyon, Lyon, France. 9. Department of Hepatobiliary-Pancreatic Surgery and Hepatology, Civil Hospices of Lyon, Edouard Herriot Hospital, University of Lyon, Lyon, France. 10. Edouard Herriot Hospital, Civil Hospices of Lyon, Lyon, France. 11. Radboud University Medical Center, Nijmegen, the Netherlands. 12. Department of Gastroenterology and Hepatology, Radboud University Medical Center, Nijmegen, the Netherlands.
Abstract
OBJECTIVE: This study aimed to develop and investigate the performance of a deep learning model based on a convolutional neural network (CNN) for the automatic segmentation of polycystic livers at CT imaging. METHOD: This retrospective study used CT images of polycystic livers. To develop the CNN, supervised training and validation phases were performed using 190 CT series. To assess performance, the test phase was performed using 41 CT series. Manual segmentation by an expert radiologist (Rad1a) served as reference for all comparisons. Intra-observer variability was determined by the same reader after 12 weeks (Rad1b), and inter-observer variability by a second reader (Rad2). The Dice similarity coefficient (DSC) evaluated overlap between segmentations. CNN performance was assessed using the concordance correlation coefficient (CCC) and the two-by-two difference between the CCCs; their confidence interval was estimated with bootstrap and Bland-Altman analyses. Liver segmentation time was automatically recorded for each method. RESULTS: A total of 231 series from 129 CT examinations on 88 consecutive patients were collected. For the CNN, the DSC was 0.95 ± 0.03 and volume analyses yielded a CCC of 0.995 compared with reference. No statistical difference was observed in the CCC between CNN automatic segmentation and manual segmentations performed to evaluate inter-observer and intra-observer variability. While manual segmentation required 22.4 ± 10.4 min, central and graphics processing units took an average of 5.0 ± 2.1 s and 2.0 ± 1.4 s, respectively. CONCLUSION: Compared with manual segmentation, automated segmentation of polycystic livers using a deep learning method achieved much faster segmentation with similar performance. KEY POINTS: • Automatic volumetry of polycystic livers using artificial intelligence method allows much faster segmentation than expert manual segmentation with similar performance. • No statistical difference was observed between automatic segmentation, inter-observer variability, or intra-observer variability.
OBJECTIVE: This study aimed to develop and investigate the performance of a deep learning model based on a convolutional neural network (CNN) for the automatic segmentation of polycystic livers at CT imaging. METHOD: This retrospective study used CT images of polycystic livers. To develop the CNN, supervised training and validation phases were performed using 190 CT series. To assess performance, the test phase was performed using 41 CT series. Manual segmentation by an expert radiologist (Rad1a) served as reference for all comparisons. Intra-observer variability was determined by the same reader after 12 weeks (Rad1b), and inter-observer variability by a second reader (Rad2). The Dice similarity coefficient (DSC) evaluated overlap between segmentations. CNN performance was assessed using the concordance correlation coefficient (CCC) and the two-by-two difference between the CCCs; their confidence interval was estimated with bootstrap and Bland-Altman analyses. Liver segmentation time was automatically recorded for each method. RESULTS: A total of 231 series from 129 CT examinations on 88 consecutive patients were collected. For the CNN, the DSC was 0.95 ± 0.03 and volume analyses yielded a CCC of 0.995 compared with reference. No statistical difference was observed in the CCC between CNN automatic segmentation and manual segmentations performed to evaluate inter-observer and intra-observer variability. While manual segmentation required 22.4 ± 10.4 min, central and graphics processing units took an average of 5.0 ± 2.1 s and 2.0 ± 1.4 s, respectively. CONCLUSION: Compared with manual segmentation, automated segmentation of polycystic livers using a deep learning method achieved much faster segmentation with similar performance. KEY POINTS: • Automatic volumetry of polycystic livers using artificial intelligence method allows much faster segmentation than expert manual segmentation with similar performance. • No statistical difference was observed between automatic segmentation, inter-observer variability, or intra-observer variability.
Authors: Marie C Hogan; Kaleab Abebe; Vicente E Torres; Arlene B Chapman; Kyongtae T Bae; Cheng Tao; Hongliang Sun; Ronald D Perrone; Theodore I Steinman; William Braun; Franz T Winklhofer; Dana C Miskulin; Frederic Rahbari-Oskoui; Godela Brosnahan; Amirali Masoumi; Irina O Karpov; Susan Spillane; Michael Flessner; Charity G Moore; Robert W Schrier Journal: Clin Gastroenterol Hepatol Date: 2014-08-09 Impact factor: 11.382
Authors: Titus F M Wijnands; Myrte K Neijenhuis; Wietske Kievit; Frederik Nevens; Marie C Hogan; Vicente E Torres; Tom J G Gevers; Joost P H Drenth Journal: Liver Int Date: 2014-01-09 Impact factor: 5.828
Authors: Maatje D A van Gastel; Marie E Edwards; Vicente E Torres; Bradley J Erickson; Ron T Gansevoort; Timothy L Kline Journal: J Am Soc Nephrol Date: 2019-07-03 Impact factor: 10.121
Authors: Edwin M Spithoven; Maatje D A van Gastel; A Lianne Messchendorp; Niek F Casteleijn; Joost P H Drenth; Carlo A Gaillard; Johan W de Fijter; Esther Meijer; Dorien J M Peters; Peter Kappert; Remco J Renken; Folkert W Visser; Jack F M Wetzels; Robert Zietse; Ron T Gansevoort Journal: Am J Kidney Dis Date: 2015-07-31 Impact factor: 8.860
Authors: Akshat Gotra; Lojan Sivakumaran; Gabriel Chartrand; Kim-Nhien Vu; Franck Vandenbroucke-Menu; Claude Kauffmann; Samuel Kadoury; Benoît Gallix; Jacques A de Guise; An Tang Journal: Insights Imaging Date: 2017-06-14
Authors: Grzegorz Chlebus; Hans Meine; Smita Thoduka; Nasreddin Abolmaali; Bram van Ginneken; Horst Karl Hahn; Andrea Schenk Journal: PLoS One Date: 2019-05-20 Impact factor: 3.240