TY - JOUR
T1 - Computer-Assisted Differentiation between Colon-Mesocolon and Retroperitoneum Using Hyperspectral Imaging (HSI) Technology
AU - Okamoto, Nariaki
AU - Rodríguez-Luna, María Rita
AU - Bencteux, Valentin
AU - Al-Taher, Mahdi
AU - Cinelli, Lorenzo
AU - Felli, Eric
AU - Urade, Takeshi
AU - Nkusi, Richard
AU - Mutter, Didier
AU - Marescaux, Jacques
AU - Hostettler, Alexandre
AU - Collins, Toby
AU - Diana, Michele
N1 - Funding Information:
This study was funded by the ARC Foundation for Cancer Research (9, rue Guy Môquet, BP 90003, 94803 Villejuif CEDEX, France) through the ELIOS grant (Endoscopic Luminescent Imaging for precision Oncologic Surgery; https://www.fondation-arc.org/projets/ameliorer-diagnostic-et-traitement-chirurgical-cancers-digestifs (accessed on 24 July 2022)).
Funding Information:
M.D. is the recipient of the ELIOS grant from the ARC Foundation. M.D. is a member of the Advisory Board of Diagnostic Green. M.R.R.L. was supported by the following project grant: European Union’s Horizon 2020 research and innovation program, under the Marie Skłodowska-Curie grant agreement No. 857894—CAST. J.M. is the President of IRCAD, which is partly funded by KARL STORZ and Medtronic. N.O., V.B., M.A., L.C., E.F., T.U., R.N., D.M., A.H. and T.C. have no conflicts of interest or financial ties to disclose.
Publisher Copyright:
© 2022 by the authors.
PY - 2022/9/15
Y1 - 2022/9/15
N2 - Complete mesocolic excision (CME), which involves the adequate resection of the tumor-bearing colonic segment with "en bloc" removal of its mesocolon along embryological fascial planes is associated with superior oncological outcomes. However, CME presents a higher complication rate compared to non-CME resections due to a higher risk of vascular injury. Hyperspectral imaging (HSI) is a contrast-free optical imaging technology, which facilitates the quantitative imaging of physiological tissue parameters and the visualization of anatomical structures. This study evaluates the accuracy of HSI combined with deep learning (DL) to differentiate the colon and its mesenteric tissue from retroperitoneal tissue. In an animal study including 20 pig models, intraoperative hyperspectral images of the sigmoid colon, sigmoid mesentery, and retroperitoneum were recorded. A convolutional neural network (CNN) was trained to distinguish the two tissue classes using HSI data, validated with a leave-one-out cross-validation process. The overall recognition sensitivity of the tissues to be preserved (retroperitoneum) and the tissues to be resected (colon and mesentery) was 79.0 ± 21.0% and 86.0 ± 16.0%, respectively. Automatic classification based on HSI and CNNs is a promising tool to automatically, non-invasively, and objectively differentiate the colon and its mesentery from retroperitoneal tissue.
AB - Complete mesocolic excision (CME), which involves the adequate resection of the tumor-bearing colonic segment with "en bloc" removal of its mesocolon along embryological fascial planes is associated with superior oncological outcomes. However, CME presents a higher complication rate compared to non-CME resections due to a higher risk of vascular injury. Hyperspectral imaging (HSI) is a contrast-free optical imaging technology, which facilitates the quantitative imaging of physiological tissue parameters and the visualization of anatomical structures. This study evaluates the accuracy of HSI combined with deep learning (DL) to differentiate the colon and its mesenteric tissue from retroperitoneal tissue. In an animal study including 20 pig models, intraoperative hyperspectral images of the sigmoid colon, sigmoid mesentery, and retroperitoneum were recorded. A convolutional neural network (CNN) was trained to distinguish the two tissue classes using HSI data, validated with a leave-one-out cross-validation process. The overall recognition sensitivity of the tissues to be preserved (retroperitoneum) and the tissues to be resected (colon and mesentery) was 79.0 ± 21.0% and 86.0 ± 16.0%, respectively. Automatic classification based on HSI and CNNs is a promising tool to automatically, non-invasively, and objectively differentiate the colon and its mesentery from retroperitoneal tissue.
U2 - 10.3390/diagnostics12092225
DO - 10.3390/diagnostics12092225
M3 - Article
C2 - 36140626
SN - 2075-4418
VL - 12
JO - Diagnostics
JF - Diagnostics
IS - 9
M1 - 2225
ER -