Georgios A Kaissis1, Fabian K Lohöfer1, Marie Hörl1, Irina Heid1, Katja Steiger2, Kim Agnes Munoz-Alvarez3, Markus Schwaiger3, Ernst J Rummeny1, Wilko Weichert2, Philipp Paprottka1, Rickmer Braren4. 1. Institute for Diagnostic and Interventional Radiology, Klinikum rechts der Isar der Technischen Universität München, Ismaninger Straße 22, D-81675 München, Germany. 2. Institute of Pathology, Klinikum rechts der Isar der Technischen Universität München, Ismaninger Straße 22, D-81675 München, Germany. 3. Clinic and Policlinic for Nuclear Medicine, Klinikum rechts der Isar der Technischen Universität München, Ismaninger Straße 22, D-81675 München, Germany. 4. Institute for Diagnostic and Interventional Radiology, Klinikum rechts der Isar der Technischen Universität München, Ismaninger Straße 22, D-81675 München, Germany. Electronic address: rbraren@tum.de.
Abstract
PURPOSE: To test combined dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and 18F-FDG positron emission tomography (FDG-PET)-derived parameters for prediction of histopathological grading in a rat Diethyl Nitrosamine (DEN)-induced hepatocellular carcinoma (HCC) model. METHODS: 15 male Wistar rats, aged 10 weeks were treated with oral DEN 0.01 % in drinking water and monitored until HCCs were detectable. DCE-MRI and PET were performed consecutively on small animal scanners. 38 tumors were identified and manually segmented based on HCC-specific contrast enhancement patterns. Grading (G2/3: 24 tumors, G1:14 tumors) alongside other histopathological parameters, tumor volume, contrast agent and 18F-FDG uptake metrics were noted. Class imbalance was addressed using SMOTE and collinearity was removed using hierarchical clustering and principal component analysis. A logistic regression model was fit separately to the individual parameter groups (DCE-MRI-derived, PET-derived, tumor volume) and the combined parameters. RESULTS: The combined model using all imaging-derived parameters achieved a mean ± STD sensitivity of 0.88 ± 0.16, specificity of 0.70 ± 0.20 and AUC of 0.90 ± 0.03. No correlation was found between tumor grading and tumor volume, morphology, necrosis, extracellular matrix, immune cell infiltration or underlying liver fibrosis. CONCLUSION: A combination of DCE-MRI- and 18F-FDG-PET-derived parameters provides high accuracy for histopathological grading of hepatocellular carcinoma in a relevant translational model system.
PURPOSE: To test combined dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and 18F-FDG positron emission tomography (FDG-PET)-derived parameters for prediction of histopathological grading in a ratDiethyl Nitrosamine (DEN)-induced hepatocellular carcinoma (HCC) model. METHODS: 15 male Wistar rats, aged 10 weeks were treated with oral DEN 0.01 % in drinking water and monitored until HCCs were detectable. DCE-MRI and PET were performed consecutively on small animal scanners. 38 tumors were identified and manually segmented based on HCC-specific contrast enhancement patterns. Grading (G2/3: 24 tumors, G1:14 tumors) alongside other histopathological parameters, tumor volume, contrast agent and 18F-FDG uptake metrics were noted. Class imbalance was addressed using SMOTE and collinearity was removed using hierarchical clustering and principal component analysis. A logistic regression model was fit separately to the individual parameter groups (DCE-MRI-derived, PET-derived, tumor volume) and the combined parameters. RESULTS: The combined model using all imaging-derived parameters achieved a mean ± STD sensitivity of 0.88 ± 0.16, specificity of 0.70 ± 0.20 and AUC of 0.90 ± 0.03. No correlation was found between tumor grading and tumor volume, morphology, necrosis, extracellular matrix, immune cell infiltration or underlying liver fibrosis. CONCLUSION: A combination of DCE-MRI- and 18F-FDG-PET-derived parameters provides high accuracy for histopathological grading of hepatocellular carcinoma in a relevant translational model system.
Authors: Elisabeth Bliemsrieder; Georgios Kaissis; Martin Grashei; Geoffrey Topping; Jennifer Altomonte; Christian Hundshammer; Fabian Lohöfer; Irina Heid; Dominik Keim; Selamawit Gebrekidan; Marija Trajkovic-Arsic; A M Winkelkotte; Katja Steiger; Roman Nawroth; Jens Siveke; Markus Schwaiger; Marcus Makowski; Franz Schilling; Rickmer Braren Journal: Sci Rep Date: 2021-01-13 Impact factor: 4.379