Cargando…
Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning
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...
Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8466415/ https://www.ncbi.nlm.nih.gov/pubmed/34573963 http://dx.doi.org/10.3390/diagnostics11091621 |
_version_ | 1784573132485427200 |
---|---|
author | Zoetmulder, Riaan Konduri, Praneeta R. Obdeijn, Iris V. Gavves, Efstratios Išgum, Ivana Majoie, Charles B.L.M. Dippel, Diederik W.J. Roos, Yvo B.W.E.M. Goyal, Mayank Mitchell, Peter J. Campbell, Bruce C. V. Lopes, Demetrius K. Reimann, Gernot Jovin, Tudor G. Saver, Jeffrey L. Muir, Keith W. White, Phil Bracard, Serge Chen, Bailiang Brown, Scott Schonewille, Wouter J. van der Hoeven, Erik Puetz, Volker Marquering, Henk A. |
author_facet | Zoetmulder, Riaan Konduri, Praneeta R. Obdeijn, Iris V. Gavves, Efstratios Išgum, Ivana Majoie, Charles B.L.M. Dippel, Diederik W.J. Roos, Yvo B.W.E.M. Goyal, Mayank Mitchell, Peter J. Campbell, Bruce C. V. Lopes, Demetrius K. Reimann, Gernot Jovin, Tudor G. Saver, Jeffrey L. Muir, Keith W. White, Phil Bracard, Serge Chen, Bailiang Brown, Scott Schonewille, Wouter J. van der Hoeven, Erik Puetz, Volker Marquering, Henk A. |
author_sort | Zoetmulder, Riaan |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-8466415 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-84664152021-09-27 Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning Zoetmulder, Riaan Konduri, Praneeta R. Obdeijn, Iris V. Gavves, Efstratios Išgum, Ivana Majoie, Charles B.L.M. Dippel, Diederik W.J. Roos, Yvo B.W.E.M. Goyal, Mayank Mitchell, Peter J. Campbell, Bruce C. V. Lopes, Demetrius K. Reimann, Gernot Jovin, Tudor G. Saver, Jeffrey L. Muir, Keith W. White, Phil Bracard, Serge Chen, Bailiang Brown, Scott Schonewille, Wouter J. van der Hoeven, Erik Puetz, Volker Marquering, Henk A. Diagnostics (Basel) Article 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. MDPI 2021-09-04 /pmc/articles/PMC8466415/ /pubmed/34573963 http://dx.doi.org/10.3390/diagnostics11091621 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Zoetmulder, Riaan Konduri, Praneeta R. Obdeijn, Iris V. Gavves, Efstratios Išgum, Ivana Majoie, Charles B.L.M. Dippel, Diederik W.J. Roos, Yvo B.W.E.M. Goyal, Mayank Mitchell, Peter J. Campbell, Bruce C. V. Lopes, Demetrius K. Reimann, Gernot Jovin, Tudor G. Saver, Jeffrey L. Muir, Keith W. White, Phil Bracard, Serge Chen, Bailiang Brown, Scott Schonewille, Wouter J. van der Hoeven, Erik Puetz, Volker Marquering, Henk A. Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title | Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title_full | Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title_fullStr | Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title_full_unstemmed | Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title_short | Automated Final Lesion Segmentation in Posterior Circulation Acute Ischemic Stroke Using Deep Learning |
title_sort | automated final lesion segmentation in posterior circulation acute ischemic stroke using deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8466415/ https://www.ncbi.nlm.nih.gov/pubmed/34573963 http://dx.doi.org/10.3390/diagnostics11091621 |
work_keys_str_mv | AT zoetmulderriaan automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT konduripraneetar automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT obdeijnirisv automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT gavvesefstratios automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT isgumivana automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT majoiecharlesblm automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT dippeldiederikwj automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT roosyvobwem automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT goyalmayank automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT mitchellpeterj automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT campbellbrucecv automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT lopesdemetriusk automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT reimanngernot automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT jovintudorg automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT saverjeffreyl automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT muirkeithw automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT whitephil automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT bracardserge automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT chenbailiang automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT brownscott automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT schonewillewouterj automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT vanderhoevenerik automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT puetzvolker automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning AT marqueringhenka automatedfinallesionsegmentationinposteriorcirculationacuteischemicstrokeusingdeeplearning |