Comparing deep learning stroke segmentation in NCCT, CTA, and CTP: Accuracy, domain transfer, and temporal sampling effect.
The 1 match
- [1] § MATERIALS AND METHODS › Experimental setup › nnU‐Net for stroke segmentation ↔ data_preprocessing.py, lines 74–142 · score 0.53 · gradient descent, mutually, optimizer
Paper
Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 233 lines · 6.9 KB · no license · 1 match
data_preprocessing.py at commit 9ce10f3, no license · at the source
Overview
- Pattern Recognition Lab, Friedrich‐Alexander Universität Erlangen‐Nürnberg, Erlangen, Germany
- Computed Tomography, Siemens Healthineers AG, Forchheim, Germany
- Department of Radiology, Vancouver General Hospital, University of British Columbia, Vancouver, Canada
Abstract
Background: Stroke imaging typically involves multiple CT image types—non‐contrast CT (NCCT), CT angiography (CTA), and CT perfusion (CTP). CTP and multiphase CTA (mCTA) are more advanced acquisitions with multiple timesteps and provide insights on the hemodynamics within the brain. Deep Learning models can help facilitate the diagnostic workflow by automatically identifying the extent of core and penumbra, which influences subsequent treatment decisions. For the use in clinical practice, generalizability of these models to new clinical sites is crucial.
Purpose: We evaluate and compare the usefulness of NCCT, CTA, mCTA, and CTP images for DL‐based stroke lesion segmentation, with the aim of guiding modality selection in settings with and without access to advanced imaging, and with an additional focus on model transferability between clinical sites and the impact of time point selection from the CTP scan.
Methods: The experiments involve model training with a dataset of 91 stroke patients from one clinical site. NCCT, CTA, mCTA, and CTP are used separately to train nnU‐Net models for segmentation of stroke core and hypoperfused volume using uncertainty‐aware labels. To assess site transferability, a model (pre‐)trained on 166 cases from a second clinical site is employed to perform as‐is inference with data from the first site, then contrast it with a variant of the model fine‐tuned using a subset of the data from the first site. Multiple temporal sampling strategies were investigated for the 4D CTP data, choosing different subsets of the time series as the model input.
Results: For automatic segmentation of stroke core, advanced imaging techniques yield improved accuracy with the modified Dice coefficient increasing from 0.36±0.28 (NCCT) to 0.55±0.27 (CTA), 0.71±0.22 (mCTA), and 0.78±0.09 (CTP) for infarcts of size 10–70 mL. A similar trend is observed for smaller infarcts of 1–10 mL. In terms of generalizability, the additional fine‐tuning stage consistently enhances the segmentation results, regardless of the image type used. To leverage the initially large series of perfusion images, different temporal sampling strategies are applied to predict stroke core. The experiments show no clear trend as the results vary across different timing scenarios and infarct sizes.
Conclusions: The study provides an overview of the quality of automated stroke lesion segmentation with nnU‐Net across all relevant CT acquisition types. Hereby, multitimepoint imaging exhibits significantly improved segmentation performance compared to NCCT and CTA.
Reproduced under the paper's license (CC BY), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 1 match between paragraphs and lines of code.
ac74esiw/stroke_segmentation
9ce10f3f414918c8e5c1f81657179bc927d230ff, 2 December 2025Availability: 1 check, the latest on 28 September 2026: the link answers
- 28 September 2026: the link answers
2 files, not copied: shown from their source
OSCR keeps no copy of these files: this repository has no license that allows it. The reader above shows each one from its source, fetched by your browser at commit 9ce10f3, when its fingerprint is the one OSCR verified. How this works.
- data_preprocessing.py — Python, 233 lines, 1 match, shown from its source
- README.md — Text, 43 lines, shown from its source
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 1 script, each with its path and the digest of its content;
- 1 match between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
No dataset and no data link were found in the paper.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 2, 28 September 2026
- Publisher: — → Wiley
Version 1, 28 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 3 keywords, 7 MeSH terms, 31 references.
Cite
This paper
Vorberg, L., Ditt, H., Maier, A., Nicolaou, S., Murray, N., & Taubmann, O. (2026). Comparing deep learning stroke segmentation in NCCT, CTA, and CTP: Accuracy, domain transfer, and temporal sampling effect. Medical physics, 53(4), e70419. https://
BibTeX
@article{vorberg2026comp
author = {Vorberg, Linda and Ditt, Hendrik and Maier, Andreas and Nicolaou, Savvas and Murray, Nicolas and Taubmann, Oliver},
title = {{Comparing deep learning stroke segmentation in NCCT, CTA, and CTP: Accuracy, domain transfer, and temporal sampling effect}},
journal = {Medical physics},
year = {2026},
month = apr,
volume = {53},
number = {4},
pages = {e70419},
publisher = {Wiley},
issn = {0094-2405},
doi = {10.1002/
url = {https://
pmid = {41933279},
pmcid = {PMC13049103}
}
RIS
TY - JOUR
AU - Vorberg, Linda
AU - Ditt, Hendrik
AU - Maier, Andreas
AU - Nicolaou, Savvas
AU - Murray, Nicolas
AU - Taubmann, Oliver
TI - Comparing deep learning stroke segmentation in NCCT, CTA, and CTP: Accuracy, domain transfer, and temporal sampling effect
T2 - Medical physics
J2 - Med Phys
PY - 2026
DA - 2026/
VL - 53
IS - 4
SP - e70419
SN - 0094-2405
PB - Wiley
DO - 10.1002/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1002/
"type": "article-journal",
"title": "Comparing deep learning stroke segmentation in NCCT, CTA, and CTP: Accuracy, domain transfer, and temporal sampling effect",
"container-title": "Medical physics",
"author": [
{
"family": "Vorberg",
"given": "Linda"
},
{
"family": "Ditt",
"given": "Hendrik"
},
{
"family": "Maier",
"given": "Andreas"
},
{
"family": "Nicolaou",
"given": "Savvas"
},
{
"family": "Murray",
"given": "Nicolas"
},
{
"family": "Taubmann",
"given": "Oliver"
}
],
"container-title-short":
"volume": "53",
"issue": "4",
"page": "e70419",
"DOI": "10.1002/
"PMID": "41933279",
"PMCID": "PMC13049103",
"ISSN": "0094-2405",
"publisher": "Wiley",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
1
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1002/mrm.70488 [code]
- Advancing the Volumetric Analysis of Ultra-Low-Field Brain MRI Using Image-to-Image Translation.Journal: Magnetic resonance in medicineIn common: SimpleITK, methods / tools, 1 reference
- [2] doi:10.1007/s12021-026-09817-x [code]
- Circle of Willis-Guided Localization for Simultaneous Detection and Classification of Large Vessel Occlusions in Brain CTA.Journal: NeuroinformaticsIn common: SimpleITK, other, 1 reference
- [3] doi:10.21037/qims-2026-0792 [code]
- An nnU-Net-based framework with adaptive feature representation for 3D brain tumor segmentation.Journal: Quantitative imaging in medicine and surgeryIn common: SimpleITK, methods / tools, 1 reference
- [4] doi:10.3389/fmed.2026.1875760 [code]
- Adaptive multi-stage domain unlearning for white-matter lesion segmentation.Journal: Frontiers in medicineIn common: SimpleITK, methods / tools, 1 reference
- [5] doi:10.3390/diagnostics16111588 [code]
- Bridging Annotation Gaps: Hierarchical Self-Support Learning for Brain Tumor Segmentation.Journal: Diagnostics (Basel, Switzerland)In common: SimpleITK, methods / tools, 1 reference
- [6] doi:10.3389/fradi.2026.1785108 [code]
- BT-CAP: a subcomponent-aware and anatomically constrained data augmentation framework for multi-modal brain tumor MRI segmentation.Journal: Frontiers in radiologyIn common: SimpleITK, methods / tools, 1 reference
- [7] doi:10.1007/s00234-026-03993-y [code]
- A comprehensive framework for automated segmentation of perivascular spaces in brain MRI with the nnU-Net.Journal: NeuroradiologyIn common: SimpleITK, methods / tools, 1 reference
- [8] doi:10.1080/07853890.2026.2685416 [code]
- Pulmonary and cerebral damage in COVID-19 survivors: is there any association?Journal: Annals of medicineIn common: SimpleITK, stroke, other
- [9] doi:10.1002/alz.71530 [code]
- Differential associations of plasma biomarkers with Alzheimer's disease and small vessel disease: A multimodal imaging study.Journal: Alzheimer's & dementia : the journal of the Alzheimer's AssociationIn common: SimpleITK, stroke, other
- [10] doi:10.1038/s41598-026-55903-0 [code]
- Towards trustworthy brain stroke diagnosis using a lightweight explainable deep learning framework for CT imaging.Journal: Scientific reportsIn common: stroke, other, 1 reference
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 1 script, and 1 match between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:73de1ca8bedc4295…
Add the badge to its README
The badge links the code to this page. Copy one of these into the README of the paper's code: only you decide where it goes, and nothing is changed for you.
Markdown
[, paste the snippet at the top, then “Commit changes…” and, to review it first, “Create a new branch and start a pull request”. You open the pull request; OSCR asks for no permission.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.
Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.