1
|
Fehrenbach U, Xin S, Hartenstein A, Auer TA, Dräger F, Froböse K, Jann H, Mogl M, Amthauer H, Geisel D, Denecke T, Wiedenmann B, Penzkofer T. Automatized Hepatic Tumor Volume Analysis of Neuroendocrine Liver Metastases by Gd-EOB MRI-A Deep-Learning Model to Support Multidisciplinary Cancer Conference Decision-Making. Cancers (Basel) 2021; 13:2726. [PMID: 34072865 PMCID: PMC8199286 DOI: 10.3390/cancers13112726] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2021] [Revised: 05/22/2021] [Accepted: 05/25/2021] [Indexed: 12/12/2022] Open
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.
Collapse
Affiliation(s)
- Uli Fehrenbach
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
| | - Siyi Xin
- Division of Gastroenterology, Medical Department, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany; (S.X.); (H.J.); (B.W.)
| | - Alexander Hartenstein
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
- Bayer AG, 13353 Berlin, Germany
| | - Timo Alexander Auer
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
- Berlin Institute of Health, 10178 Berlin, Germany
| | - Franziska Dräger
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
| | - Konrad Froböse
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
| | - Henning Jann
- Division of Gastroenterology, Medical Department, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany; (S.X.); (H.J.); (B.W.)
| | - Martina Mogl
- Department of Surgery Campus Charité Mitte/Campus Virchow-Klinikum, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany;
| | - Holger Amthauer
- Department of Nuclear Medicine, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany;
| | - Dominik Geisel
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
| | - Timm Denecke
- Department of Diagnostic and Interventional Radiology, University Hospital Leipzig, 04103 Leipzig, Germany;
| | - Bertram Wiedenmann
- Division of Gastroenterology, Medical Department, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany; (S.X.); (H.J.); (B.W.)
| | - Tobias Penzkofer
- Department of Radiology, Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany; (A.H.); (T.A.A.); (F.D.); (K.F.); (D.G.); (T.P.)
- Berlin Institute of Health, 10178 Berlin, Germany
| |
Collapse
|
2
|
Garcia-Torralba E, Spada F, Lim KHJ, Jacobs T, Barriuso J, Mansoor W, McNamara MG, Hubner RA, Manoharan P, Fazio N, Valle JW, Lamarca A. Knowns and unknowns of bone metastases in patients with neuroendocrine neoplasms: A systematic review and meta-analysis. Cancer Treat Rev 2021; 94:102168. [PMID: 33730627 DOI: 10.1016/j.ctrv.2021.102168] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2020] [Revised: 02/03/2021] [Accepted: 02/05/2021] [Indexed: 12/11/2022]
Abstract
OBJECTIVE This systematic review and meta-analysis aimed to develop an evidence-based summary of current knowledge of bone metastases (BMs) in neuroendocrine neoplasms (NENs), inform diagnosis and treatment and standardise management between institutions. METHODS PubMed, Medline, EMBASE and meeting proceedings were searched for eligible studies reporting data on patients with BMs and NENs of any grade of differentiation and site; poorly-differentiated large/small cell lung cancer were excluded. Data were extracted and analysed using STATA v.12. Meta-analysis of proportions for calculation of estimated pooled prevalence of BM and calculation of weighted pooled frequency and weighted pooled mean for other variables of interest was performed . RESULTS A total of 149 studies met the eligibility criteria. Pooled prevalence of BMs was 18.4% (95% CI 15.4-21.5). BMs were mainly metachronous with initial diagnosis of NEN (61.2%) and predominantly osteoblastic; around 61% were multifocal, with a predisposition in axial skeleton. PET/CT seemed to provide (together with MRI) the highest sensitivity and specificity for BM detection. Almost half of patients (46.4%) reported BM-related symptoms: pain (66%) and skeletal-related events (SREs, fracture/spinal cord compression) (26.2%; weightedweighted mean time-to-SRE 9.9 months). Management of BMs was multimodal [bisphosphonates and bone-modifying agents (45.2%), external beam radiotherapy (34.9%), surgery (14.8%)] and supported by little evidence. Overall survival (OS) from the time of diagnosis of BMs was long [weighted mean 50.9 months (95% CI 40.0-61.9)]. Patients with BMs had shorter OS [48.8 months (95% CI 37.9-59.6)] compared to patients without BMs [87.4 months (95% CI 74.9-100.0); p = 0.001]. Poor performance status and BM-related symptoms were also associated with worse OS. CONCLUSIONS BMs in patients with NENs remain underdiagnosed and undertreated. Recommendations for management of BMs derived from current knowledge are provided. Prospective studies to inform management are required.
Collapse
Affiliation(s)
- Esmeralda Garcia-Torralba
- Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom; Department of Haematology and Medical Oncology, Hospital Morales Meseguer, Murcia, Spain
| | - Francesca Spada
- Division of Gastrointestinal Medical Oncology and Neuroendocrine Tumors, European Institute of Oncology, IEO, IRCCS, Milan, Italy
| | - Kok Haw Jonathan Lim
- Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom; Department of Immunology and Inflammation, Imperial College London, London, United Kingdom
| | - Timothy Jacobs
- Medical Library, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Jorge Barriuso
- Division of Cancer Sciences, University of Manchester, Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Was Mansoor
- Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Division of Cancer Sciences, University of Manchester, Manchester, United Kingdom
| | - Mairéad G McNamara
- Division of Cancer Sciences, University of Manchester, Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Richard A Hubner
- Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Division of Cancer Sciences, University of Manchester, Manchester, United Kingdom
| | - Prakash Manoharan
- Department of Radiology and Nuclear Medicine, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Nicola Fazio
- Division of Gastrointestinal Medical Oncology and Neuroendocrine Tumors, European Institute of Oncology, IEO, IRCCS, Milan, Italy
| | - Juan W Valle
- Division of Cancer Sciences, University of Manchester, Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Manchester, United Kingdom
| | - Angela Lamarca
- Department of Medical Oncology, ENETS Centre of Excellence, The Christie NHS Foundation Trust, Division of Cancer Sciences, University of Manchester, Manchester, United Kingdom.
| |
Collapse
|