Akshat Gotra1, Gabriel Chartrand2, Karine Massicotte-Tisluck3, Florence Morin-Roy3, Franck Vandenbroucke-Menu4, Jacques A de Guise2, An Tang5. 1. Department of Radiology, Saint-Luc Hospital, University of Montreal, 1058 rue Saint-Denis, Montreal, Quebec, Canada H2X 3J4; Department of Radiology, Montreal General Hospital, McGill University, Montreal, Quebec, Canada. 2. Imaging and Orthopaedics Research Laboratory (LIO), École de technologie supérieure, Centre de recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM), Montreal, Quebec, Canada. 3. Department of Radiology, Saint-Luc Hospital, University of Montreal, 1058 rue Saint-Denis, Montreal, Quebec, Canada H2X 3J4. 4. Department of Hepato-biliary and Pancreatic Surgery, Saint-Luc Hospital, University of Montreal, Montreal, Quebec, Canada. 5. Department of Radiology, Saint-Luc Hospital, University of Montreal, 1058 rue Saint-Denis, Montreal, Quebec, Canada H2X 3J4; Centre de recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM), Montreal, Quebec, Canada. Electronic address: an.tang@umontreal.ca.
Abstract
RATIONALE AND OBJECTIVES: To compare the repeatability and agreement of a semiautomated liver segmentation method with manual segmentation for assessment of total liver volume on CT (computed tomography). MATERIALS AND METHODS: This retrospective, institutional review board-approved study was conducted in 41 subjects who underwent liver CT for preoperative planning. The major pathologies encountered were colorectal cancer metastases, benign liver lesions and hepatocellular carcinoma. This semiautomated segmentation method is based on variational interpolation and 3D minimal path-surface segmentation. Total and subsegmental liver volumes were segmented from contrast-enhanced CT images in venous phase. Two image analysts independently performed semiautomated segmentations and two other image analysts performed manual segmentations. Repeatability and agreement of both methods were evaluated with intraclass correlation coefficients (ICC) and Bland-Altman analysis. Interaction time was recorded for both methods. RESULTS: Bland-Altman analysis revealed an intrareader agreement of -1 ± 27 mL (mean ± 1.96 standard deviation) with ICC of 0.999 (P < .001) for manual segmentation and 12 ± 97 mL with ICC of 0.991 (P < .001) for semiautomated segmentation. Bland-Altman analysis revealed an interreader agreement of -4 ± 22 mL with ICC of 0.999 (P < .001) for manual segmentation and 5 ± 98 mL with ICC of 0.991 (P < .001) for semiautomated segmentation. Intermethod agreement was found to be 3 ± 120 mL with ICC of 0.988 (P < .001). Mean interaction time was 34.3 ± 16.7 minutes for the manual method and 8.0 ± 1.2 minutes for the semiautomated method (P < .001). CONCLUSIONS: A semiautomated segmentation method can substantially shorten interaction time while preserving a high repeatability and agreement with manual segmentation.
RATIONALE AND OBJECTIVES: To compare the repeatability and agreement of a semiautomated liver segmentation method with manual segmentation for assessment of total liver volume on CT (computed tomography). MATERIALS AND METHODS: This retrospective, institutional review board-approved study was conducted in 41 subjects who underwent liver CT for preoperative planning. The major pathologies encountered were colorectal cancer metastases, benign liver lesions and hepatocellular carcinoma. This semiautomated segmentation method is based on variational interpolation and 3D minimal path-surface segmentation. Total and subsegmental liver volumes were segmented from contrast-enhanced CT images in venous phase. Two image analysts independently performed semiautomated segmentations and two other image analysts performed manual segmentations. Repeatability and agreement of both methods were evaluated with intraclass correlation coefficients (ICC) and Bland-Altman analysis. Interaction time was recorded for both methods. RESULTS: Bland-Altman analysis revealed an intrareader agreement of -1 ± 27 mL (mean ± 1.96 standard deviation) with ICC of 0.999 (P < .001) for manual segmentation and 12 ± 97 mL with ICC of 0.991 (P < .001) for semiautomated segmentation. Bland-Altman analysis revealed an interreader agreement of -4 ± 22 mL with ICC of 0.999 (P < .001) for manual segmentation and 5 ± 98 mL with ICC of 0.991 (P < .001) for semiautomated segmentation. Intermethod agreement was found to be 3 ± 120 mL with ICC of 0.988 (P < .001). Mean interaction time was 34.3 ± 16.7 minutes for the manual method and 8.0 ± 1.2 minutes for the semiautomated method (P < .001). CONCLUSIONS: A semiautomated segmentation method can substantially shorten interaction time while preserving a high repeatability and agreement with manual segmentation.
Authors: S C Lin; E Heba; R Bettencourt; G Y Lin; M A Valasek; O Lunde; G Hamilton; C B Sirlin; R Loomba Journal: Aliment Pharmacol Ther Date: 2017-01-24 Impact factor: 8.171
Authors: Eugene Vorontsov; Milena Cerny; Philippe Régnier; Lisa Di Jorio; Christopher J Pal; Réal Lapointe; Franck Vandenbroucke-Menu; Simon Turcotte; Samuel Kadoury; An Tang Journal: Radiol Artif Intell Date: 2019-03-13
Authors: Brett Marinelli; Martin Kang; Michael Martini; John R Zech; Joseph Titano; Samuel Cho; Anthony B Costa; Eric K Oermann Journal: Radiol Artif Intell Date: 2019-01-30
Authors: Aniek T Zwart; Jan-Niklas Becker; Maria J Lamers; Rudi A J O Dierckx; Geertruida H de Bock; Gyorgy B Halmos; Anouk van der Hoorn Journal: Eur Radiol Date: 2020-11-21 Impact factor: 5.315