1
|
Zoetmulder R, Konduri PR, Obdeijn IV, Gavves E, Išgum I, Majoie CB, Dippel DW, Roos YB, Goyal M, Mitchell PJ, Campbell BCV, Lopes DK, Reimann G, Jovin TG, Saver JL, Muir KW, White P, Bracard S, Chen B, Brown S, Schonewille WJ, van der Hoeven E, Puetz V, Marquering HA. Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning. Diagnostics (Basel) 2021; 11:1621. [PMID: 34573963 PMCID: PMC8466415 DOI: 10.3390/diagnostics11091621] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2021] [Revised: 08/25/2021] [Accepted: 08/30/2021] [Indexed: 11/17/2022] Open
Abstract
Final lesion volume (FLV) is a surrogate outcome measure in anterior circulation stroke (ACS). In posterior circulation stroke (PCS), this relation is plausibly understudied due to a lack of methods that automatically quantify FLV. The applicability of deep learning approaches to PCS is limited due to its lower incidence compared to ACS. We evaluated strategies to develop a convolutional neural network (CNN) for PCS lesion segmentation by using image data from both ACS and PCS patients. We included follow-up non-contrast computed tomography scans of 1018 patients with ACS and 107 patients with PCS. To assess whether an ACS lesion segmentation generalizes to PCS, a CNN was trained on ACS data (ACS-CNN). Second, to evaluate the performance of only including PCS patients, a CNN was trained on PCS data. Third, to evaluate the performance when combining the datasets, a CNN was trained on both datasets. Finally, to evaluate the performance of transfer learning, the ACS-CNN was fine-tuned using PCS patients. The transfer learning strategy outperformed the other strategies in volume agreement with an intra-class correlation of 0.88 (95% CI: 0.83-0.92) vs. 0.55 to 0.83 and a lesion detection rate of 87% vs. 41-77 for the other strategies. Hence, transfer learning improved the FLV quantification and detection rate of PCS lesions compared to the other strategies.
Collapse
Affiliation(s)
- Riaan Zoetmulder
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands; (R.Z.); (P.R.K.); (I.V.O.); (I.I.)
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
- Informatics Institute, University of Amsterdam, 1097 Amsterdam, The Netherlands;
| | - Praneeta R. Konduri
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands; (R.Z.); (P.R.K.); (I.V.O.); (I.I.)
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
| | - Iris V. Obdeijn
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands; (R.Z.); (P.R.K.); (I.V.O.); (I.I.)
| | - Efstratios Gavves
- Informatics Institute, University of Amsterdam, 1097 Amsterdam, The Netherlands;
| | - Ivana Išgum
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands; (R.Z.); (P.R.K.); (I.V.O.); (I.I.)
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
- Informatics Institute, University of Amsterdam, 1097 Amsterdam, The Netherlands;
| | - Charles B.L.M. Majoie
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
| | - Diederik W.J. Dippel
- Department of Neurology, Erasmus MC University Medical Center, 3015 Rotterdam, The Netherlands;
| | - Yvo B.W.E.M. Roos
- Department of Neurology, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
| | - Mayank Goyal
- Radiology, Foothills Medical Centre, University of Calgary, Calgary, AB T2N 2T9, Canada;
- Department of Clinical Neurosciences, Hotchkiss Brain Institute, University of Calgary, Calgary, AB T2N 4N1, Canada
| | - Peter J. Mitchell
- Department of Radiology, The University of Melbourne & The Royal Melbourne Hospital, Melbourne, VIC 3050, Australia;
| | - Bruce C. V. Campbell
- Department of Medicine and Neurology, Melbourne Brain Centre at the Royal Melbourne Hospital, University of Melbourne, Melbourne, VIC 3052, Australia;
| | - Demetrius K. Lopes
- Department of Neurological Surgery, Rush University Medical Center, Chicago, IL 60612, USA;
| | - Gernot Reimann
- Department of Neurology, Community Hospital Klinikum Dortmund, 44137 Dortmund, Germany;
| | - Tudor G. Jovin
- Cooper Neurological Institute, Cooper University Medical Center, Camden, NJ 08103, USA;
| | - Jeffrey L. Saver
- Department of Neurology and Comprehensive Stroke Center, David Geffen School of Medicine at UCLA, Los Angeles, CA 90095, USA;
| | - Keith W. Muir
- Institute of Neuroscience and Psychology, University of Glasgow, Glasgow G12 8QB, UK;
| | - Phil White
- Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, UK;
- Department of Neuroradiology, Newcastle upon Tyne Hospitals, Newcastle upon Tyne NE1 4LP, UK
| | - Serge Bracard
- INSERM U1254, IADI, University Hospital, Neuroradiology, 54511 Nancy, France;
| | - Bailiang Chen
- INSERM CIC-IT 1433, University Hospital, 54511 Nancy, France;
| | - Scott Brown
- Altair Biostatistics, St Louis Park, MN 55416, USA;
| | | | - Erik van der Hoeven
- Department of Radiology, St. Antonius Hospital, P.O. Box 2500, 3430 Nieuwegein, The Netherlands;
| | - Volker Puetz
- Department of Neurology, Dresden University Stroke Centre, Technical University Dresden, Fetscherstraße 74, 01307 Dresden, Germany;
| | - Henk A. Marquering
- Department of Biomedical Engineering and Physics, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands; (R.Z.); (P.R.K.); (I.V.O.); (I.I.)
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Location AMC, 1105 Amsterdam, The Netherlands;
| |
Collapse
|