Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results
BackgroundSegmentation of ischaemic stroke lesions from magnetic resonance images (MRI) remains a challenging task mainly due to the confounding appearance of these lesions with other pathologies, and variations in their presentation depending on the lesion stage (i.e., hyper-acute, acute, subacute...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-06-01
|
| Series: | Frontiers in Medical Technology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmedt.2025.1491197/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850119779620225024 |
|---|---|
| author | Makram Baaklini Maria del C. Valdés Hernández |
| author_facet | Makram Baaklini Maria del C. Valdés Hernández |
| author_sort | Makram Baaklini |
| collection | DOAJ |
| description | BackgroundSegmentation of ischaemic stroke lesions from magnetic resonance images (MRI) remains a challenging task mainly due to the confounding appearance of these lesions with other pathologies, and variations in their presentation depending on the lesion stage (i.e., hyper-acute, acute, subacute and chronic). Works on the theme have been reviewed, but none of the reviews have addressed the seminal question on what would be the optimal architecture to address this challenge. We systematically reviewed the literature (2015–2023) for deep learning algorithms that segment acute and/or subacute stroke lesions on brain MRI seeking to address this question, meta-analysed the data extracted, and evaluated the results.Methods and materialsOur review, registered in PROSPERO (ID: CRD42023481551), involved a systematic search from January 2015 to December 2023 in the following databases: IEE Explore, MEDLINE, ScienceDirect, Web of Science, PubMed, Springer, and OpenReview.net. We extracted sample characteristics, stroke stage, imaging protocols, and algorithms, and meta-analysed the data extracted. We assessed the risk of bias using NIH's study quality assessment tool, and finally, evaluated our results using data from the ISLES-2015-SISS dataset.ResultsFrom 1485 papers, 41 were ultimately retained. 13/41 studies incorporated attention mechanisms in their architecture, and 39/41 studies used the Dice Similarity Coefficient to assess algorithm performance. The generalisability of the algorithms reviewed was generally below par. In our pilot analysis, the UResNet50 configuration, which was developed based on the most comprehensive architectural components identified from the reviewed studies, demonstrated a better segmentation performance than the attention-based AG-UResNet50.ConclusionWe found no evidence that favours using attention mechanisms in deep learning architectures for acute stroke lesion segmentation on MRI data, and the use of a U-Net configuration with residual connections seems to be the most appropriate configuration for this task.Systematic Review Registrationhttps://www.crd.york.ac.uk/PROSPERO/view/CRD42023481551, PROSPERO CRD42023481551. |
| format | Article |
| id | doaj-art-48d43dcd7d6043a39bc556933ef7a71f |
| institution | OA Journals |
| issn | 2673-3129 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medical Technology |
| spelling | doaj-art-48d43dcd7d6043a39bc556933ef7a71f2025-08-20T02:35:33ZengFrontiers Media S.A.Frontiers in Medical Technology2673-31292025-06-01710.3389/fmedt.2025.14911971491197Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key resultsMakram Baaklini0Maria del C. Valdés Hernández1Edinburgh Imaging Academy, College of Medicine and Veterinary Medicine, University of Edinburgh, Edinburgh, United KingdomDepartment of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United KingdomBackgroundSegmentation of ischaemic stroke lesions from magnetic resonance images (MRI) remains a challenging task mainly due to the confounding appearance of these lesions with other pathologies, and variations in their presentation depending on the lesion stage (i.e., hyper-acute, acute, subacute and chronic). Works on the theme have been reviewed, but none of the reviews have addressed the seminal question on what would be the optimal architecture to address this challenge. We systematically reviewed the literature (2015–2023) for deep learning algorithms that segment acute and/or subacute stroke lesions on brain MRI seeking to address this question, meta-analysed the data extracted, and evaluated the results.Methods and materialsOur review, registered in PROSPERO (ID: CRD42023481551), involved a systematic search from January 2015 to December 2023 in the following databases: IEE Explore, MEDLINE, ScienceDirect, Web of Science, PubMed, Springer, and OpenReview.net. We extracted sample characteristics, stroke stage, imaging protocols, and algorithms, and meta-analysed the data extracted. We assessed the risk of bias using NIH's study quality assessment tool, and finally, evaluated our results using data from the ISLES-2015-SISS dataset.ResultsFrom 1485 papers, 41 were ultimately retained. 13/41 studies incorporated attention mechanisms in their architecture, and 39/41 studies used the Dice Similarity Coefficient to assess algorithm performance. The generalisability of the algorithms reviewed was generally below par. In our pilot analysis, the UResNet50 configuration, which was developed based on the most comprehensive architectural components identified from the reviewed studies, demonstrated a better segmentation performance than the attention-based AG-UResNet50.ConclusionWe found no evidence that favours using attention mechanisms in deep learning architectures for acute stroke lesion segmentation on MRI data, and the use of a U-Net configuration with residual connections seems to be the most appropriate configuration for this task.Systematic Review Registrationhttps://www.crd.york.ac.uk/PROSPERO/view/CRD42023481551, PROSPERO CRD42023481551.https://www.frontiersin.org/articles/10.3389/fmedt.2025.1491197/fullacute ischaemic strokedeep learningMRIattention mechanismslesion segmentation |
| spellingShingle | Makram Baaklini Maria del C. Valdés Hernández Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results Frontiers in Medical Technology acute ischaemic stroke deep learning MRI attention mechanisms lesion segmentation |
| title | Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results |
| title_full | Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results |
| title_fullStr | Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results |
| title_full_unstemmed | Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results |
| title_short | Deep learning for MRI-based acute and subacute ischaemic stroke lesion segmentation—a systematic review, meta-analysis, and pilot evaluation of key results |
| title_sort | deep learning for mri based acute and subacute ischaemic stroke lesion segmentation a systematic review meta analysis and pilot evaluation of key results |
| topic | acute ischaemic stroke deep learning MRI attention mechanisms lesion segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fmedt.2025.1491197/full |
| work_keys_str_mv | AT makrambaaklini deeplearningformribasedacuteandsubacuteischaemicstrokelesionsegmentationasystematicreviewmetaanalysisandpilotevaluationofkeyresults AT mariadelcvaldeshernandez deeplearningformribasedacuteandsubacuteischaemicstrokelesionsegmentationasystematicreviewmetaanalysisandpilotevaluationofkeyresults |