Uli Fehrenbach1, Siyi Xin2, Alexander Hartenstein1,3, Timo Alexander Auer1,4, Franziska Dräger1, Konrad Froböse1, Henning Jann2, Martina Mogl5, Holger Amthauer6, Dominik Geisel1, Timm Denecke7, Bertram Wiedenmann2, Tobias Penzkofer1,4. 1. Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany. 2. Division of Gastroenterology, Medical Department, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany. 3. Bayer AG, 13353 Berlin, Germany. 4. Berlin Institute of Health, 10178 Berlin, Germany. 5. Department of Surgery Campus Charité Mitte/Campus Virchow-Klinikum, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany. 6. Department of Nuclear Medicine, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany. 7. Department of Diagnostic and Interventional Radiology, University Hospital Leipzig, 04103 Leipzig, Germany.
Abstract
BACKGROUND: Rapid quantification of liver metastasis for diagnosis and follow-up is an unmet medical need in patients with secondary liver malignancies. We present a 3D-quantification model of neuroendocrine liver metastases (NELM) using gadoxetic-acid (Gd-EOB)-enhanced MRI as a useful tool for multidisciplinary cancer conferences (MCC). METHODS: Manual 3D-segmentations of NELM and livers (149 patients in 278 Gd-EOB MRI scans) were used to train a neural network (U-Net architecture). Clinical usefulness was evaluated in another 33 patients who were discussed in our MCC and received a Gd-EOB MRI both at baseline and follow-up examination (n = 66) over 12 months. Model measurements (NELM volume; hepatic tumor load (HTL)) with corresponding absolute (ΔabsNELM; ΔabsHTL) and relative changes (ΔrelNELM; ΔrelHTL) between baseline and follow-up were compared to MCC decisions (therapy success/failure). RESULTS: Internal validation of the model's accuracy showed a high overlap for NELM and livers (Matthew's correlation coefficient (φ): 0.76/0.95, respectively) with higher φ in larger NELM volume (φ = 0.80 vs. 0.71; p = 0.003). External validation confirmed the high accuracy for NELM (φ = 0.86) and livers (φ = 0.96). MCC decisions were significantly differentiated by all response variables (ΔabsNELM; ΔabsHTL; ΔrelNELM; ΔrelHTL) (p < 0.001). ΔrelNELM and ΔrelHTL showed optimal discrimination between therapy success or failure (AUC: 1.000; p < 0.001). CONCLUSION: The model shows high accuracy in 3D-quantification of NELM and HTL in Gd-EOB-MRI. The model's measurements correlated well with MCC's evaluation of therapeutic response.
BACKGROUND: Rapid quantification of liver metastasis for diagnosis and follow-up is an unmet medical need in patients with secondary liver malignancies. We present a 3D-quantification model of neuroendocrine liver metastases (NELM) using gadoxetic-acid (Gd-EOB)-enhanced MRI as a useful tool for multidisciplinary cancer conferences (MCC). METHODS: Manual 3D-segmentations of NELM and livers (149 patients in 278 Gd-EOB MRI scans) were used to train a neural network (U-Net architecture). Clinical usefulness was evaluated in another 33 patients who were discussed in our MCC and received a Gd-EOB MRI both at baseline and follow-up examination (n = 66) over 12 months. Model measurements (NELM volume; hepatic tumor load (HTL)) with corresponding absolute (ΔabsNELM; ΔabsHTL) and relative changes (ΔrelNELM; ΔrelHTL) between baseline and follow-up were compared to MCC decisions (therapy success/failure). RESULTS: Internal validation of the model's accuracy showed a high overlap for NELM and livers (Matthew's correlation coefficient (φ): 0.76/0.95, respectively) with higher φ in larger NELM volume (φ = 0.80 vs. 0.71; p = 0.003). External validation confirmed the high accuracy for NELM (φ = 0.86) and livers (φ = 0.96). MCC decisions were significantly differentiated by all response variables (ΔabsNELM; ΔabsHTL; ΔrelNELM; ΔrelHTL) (p < 0.001). ΔrelNELM and ΔrelHTL showed optimal discrimination between therapy success or failure (AUC: 1.000; p < 0.001). CONCLUSION: The model shows high accuracy in 3D-quantification of NELM and HTL in Gd-EOB-MRI. The model's measurements correlated well with MCC's evaluation of therapeutic response.
Entities:
Keywords:
MRI; automatized quantification; deep learning; liver metastases; multidisciplinary cancer conference; neuroendocrine neoplasms
Authors: Angela Lamarca; Joakim Crona; Maxime Ronot; Marta Opalinska; Carlos Lopez Lopez; Daniela Pezzutti; Pavan Najran; Luciana Carvhalo; Regis Otaviano Franca Bezerra; Philip Borg; Naik Vietti Violi; Hector Vidal Trueba; Louis de Mestier; Niklaus Schaefer; Anders Sundin; Frederico Costa; Marianne Pavel; Clarisse Dromain Journal: Oncologist Date: 2019-03-25
Authors: Clarisse Dromain; Thierry de Baere; Jean Lumbroso; Hubert Caillet; Agnès Laplanche; Valerie Boige; Michel Ducreux; Pierre Duvillard; Dominique Elias; Martin Schlumberger; Robert Sigal; Eric Baudin Journal: J Clin Oncol Date: 2005-01-01 Impact factor: 44.544
Authors: T Lestra; L Kanagaratnam; S Mulé; A Janvier; H Brixi; G Cadiot; A Dohan; C Hoeffel Journal: Diagn Interv Imaging Date: 2018-01-12 Impact factor: 4.026
Authors: Jules H Sumkin; Wendie A Berg; Gloria J Carter; Andriy I Bandos; Denise M Chough; Marie A Ganott; Christiane M Hakim; Amy E Kelly; Margarita L Zuley; Golbahar Houshmand; Maria I Anello; David Gur Journal: Radiology Date: 2019-10-29 Impact factor: 11.105
Authors: Artur J Sankowski; Jarosław B Ćwikla; Mirosław L Nowicki; Sławomir Chaberek; Maciej Pech; Anna Lewczuk; Jerzy Walecki Journal: Med Sci Monit Date: 2012-05
Authors: Raimunda S S Azevedo; Jorge R de Sousa; Marialva T F Araujo; Arnaldo J Martins Filho; Bianca N de Alcantara; Fernanda M C Araujo; Maria G L Queiroz; Ana C R Cruz; Beatriz H Baldez Vasconcelos; Jannifer O Chiang; Lívia C Martins; Livia M N Casseb; Eliana V da Silva; Valéria L Carvalho; Barbara C Baldez Vasconcelos; Sueli G Rodrigues; Consuelo S Oliveira; Juarez A S Quaresma; Pedro F C Vasconcelos Journal: Sci Rep Date: 2018-01-08 Impact factor: 4.379