Automatized hepatic tumor volume analysis of neuroendocrine liver metastases by Gd-EOB MRI - A deep learning model to support multidisciplinary cancer conference decision making

#3164

Introduction: Rapid quantification of liver metastasis for diagnosis and follow-up is an unmet medical need in patients with secondary liver malignancies.

Aim(s): Here, we provide a high-precision model for 3D quantification of neuroendocrine liver metastases (NELM) using gadoxetic-acid (Gd-EOB) enhanced magnetic resonance imaging (MRI) and present a useful, potentially predictive tool for multidisciplinary cancer conferences (MCC).

Materials and methods: 278 Gd-EOB MRI scans of 149 patients with NEN were used for the model’s training (80% training, 20% validation). Manual segmentation of NELM was performed in hepatobiliary phase sequences. The clinical usefulness was evaluated in another 33 patients who were discussed in our MCC and received a Gd-EOB MRI both at baseline as well as follow-up examination (n=66) over a time period of 12 months. Model measurements (NELM volume and hepatic tumor load (HTL)) and the corresponding absolute (ΔabsNELM; ΔabsHTL) and relative changes (ΔrelNELM; ΔrelHTL) between baseline and follow-up were compared to MCC decision.

Conference: 18th Annual ENETS Concerence (2021)

Presenting Author: Fehrenbach U

Authors: Fehrenbach U, Xin S, Hartenstein A, Auer T, Dräger F,

Keywords: liver metastases, automatised 3D quantification, deep learning, hepatic tumor load, response evaluation, MRI,