OSCR

Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study.

Overview

Authors: Chiao-Hua Lee1, Hikam Muzakky1, Cheng-En Juan2,3, Chia-Ching Chang1,4, Ya-Hui Li1,5, Tung-Yang Lee6, Cheng-Hsuan Juan5,7, Ming-Ting Tsai1, Chun-Jung Juan1,7,8,9,10
  1. Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan
  2. China Medical University Hospital, Taichung 404, Taiwan
  3. Master’s Program of Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung 407, Taiwan
  4. Department of Management Science, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan
  5. Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106, Taiwan
  6. Show Chwan Memorial Hospital, Changhua 500, Taiwan
  7. Department of Medical Imaging, China Medical University Hospital, Taichung 404, Taiwan
  8. Department of Radiology, School of Medicine, College of Medicine, China Medical University, Taichung 406, Taiwan
  9. Department of Biomedical Engineering and Environmental Sciences, National Tsing Hua University, Hsinchu 300, Taiwan
  10. Department of Computer Science and Information Engineering, National Taiwan University, Taipei 106, Taiwan
Journal: Diagnostics (Basel, Switzerland), volume 16, issue 11, article 1705
Dates: received 22 April 2026; accepted 27 May 2026; published online 2 June 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/diagnostics16111705 · PMID 42279573 · PMCID PMC13256447 · OpenAlex W7163214037
Open access: gold, a free copy (OpenAlex)
Categories: other (modality), human (organism), stroke (population), methods / tools (subfield)
Methods: Connectivity, Statistics, Machine learning
Keywords: intracranial hemorrhage, noncontrast head CT, deep learning, object localization
Topic: Intracerebral and Subarachnoid Hemorrhage Research (Clinical Neurology, Medicine), according to OpenAlex
Funding: China Medical University Hsinchu Hospital (CMUHCHDMR-112-001, CMUHCH-DMR-112-024, CMUHCH-DMR-112-027); National Science and Technology Council (NSTC 112-2314-B-039-059MY3)
Citations: not cited yet (Europe PMC); 31 references in the paper

Abstract

Background/Objectives: To evaluate the effect of detector architecture and dataset characteristics on intracranial hemorrhage (ICH) subtype localization on noncontrast head CT, with emphasis on bidirectional cross-dataset generalization. Methods: This retrospective study analyzed two publicly available datasets: the Brain Hemorrhage Extended (BHX) dataset and the RSNA 2019+ dataset. Models were trained and internally validated on one dataset and externally tested on the other dataset in both directions: BHX-to-RSNA+ and RSNA+-to-BHX. Six representative deep learning detectors, including CNN-based one-stage and two-stage detectors and a Swin Transformer-based RT-DETR (Swin-RT-DETR) variant, were evaluated. Localization performance was assessed using mean average precision at a bounding-box intersection-over-union threshold of 0.5, bounding-box Dice similarity coefficient (BB-DSC), and bounding-box intersection-over-union (BB-IoU). Image-level and patient-level analyses were performed, with Bonferroni correction applied for statistical comparisons. Dataset characterization analyses were performed to compare subtype prevalence, bounding-box geometry, lesion burden, annotation density, and spatial distribution. Results: Under internal validation, Swin-RT-DETR achieved competitive or superior performance across several ICH subtypes, but its advantage was subtype-dependent rather than uniform. Faster R-CNN with a ResNeXt101 backbone achieved comparable IVH performance and higher IPH BB-DSC and BB-IoU, whereas Swin-RT-DETR performed better for SAH, SDH, and EDH. External validation showed substantial performance degradation across architectures, subtypes, and validation directions. Absolute BB-DSC reductions for Swin-RT-DETR ranged from approximately 0.54–0.79 in the BHX-to-RSNA+ direction and 0.17–0.74 in the RSNA+-to-BHX direction. Similar degradation patterns were observed at the patient level. Statistical comparisons showed fewer significant model-level differences under external validation, suggesting attenuation of architecture-specific advantages under domain shift. Dataset characterization analysis demonstrated differences in subtype distribution, bounding-box geometry, lesion burden, annotation density, and spatial localization patterns between BHX and RSNA+. Conclusions: ICH subtype localization performance is strongly influenced by dataset characteristics, annotation heterogeneity, and domain shift. Although Transformer-based hierarchical feature extraction showed subtype-dependent advantages under internal validation, these advantages diminished under bidirectional external validation. These findings highlight the need for dataset characterization, external validation, patient-level evaluation, and task-specific clinical benchmarks before automated ICH localization models can be considered for real-world clinical integration

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data Availability Statement

The datasets used in this study are publicly available. The Brain Hemorrhage Extended (BHX) dataset is available at PhysioNet (https://physionet.org/content/bhx-brain-bounding-box/1.1/) (accessed on 1 November 2025). The RSNA 2019+ dataset is available at (http://www.multi-lesions.top) as provided by Liu et al [14] (accessed on 25 November 2025). Additional data generated or analyzed during this study are available from the corresponding author upon reasonable request.

Reproduced under the paper's license (CC BY), from the paper cited above.

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 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 9 authors, 4 keywords, 2 funders, 24 references.

Cite

This paper

Lee, C.-H., Muzakky, H., Juan, C.-E., Chang, C.-C., Li, Y.-H., Lee, T.-Y., Juan, C.-H., Tsai, M.-T., & Juan, C.-J. (2026). Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study. Diagnostics (Basel, Switzerland), 16(11), 1705. https://doi.org/10.3390/diagnostics16111705

BibTeX

@article{lee2026cross,
author = {Lee, Chiao-Hua and Muzakky, Hikam and Juan, Cheng-En and Chang, Chia-Ching and Li, Ya-Hui and Lee, Tung-Yang and Juan, Cheng-Hsuan and Tsai, Ming-Ting and Juan, Chun-Jung},
title = {{Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study}},
journal = {Diagnostics (Basel, Switzerland)},
year = {2026},
month = jun,
volume = {16},
number = {11},
pages = {1705},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2075-4418},
doi = {10.3390/diagnostics16111705},
url = {https://doi.org/10.3390/diagnostics16111705},
pmid = {42279573},
pmcid = {PMC13256447}
}

RIS

TY - JOUR
AU - Lee, Chiao-Hua
AU - Muzakky, Hikam
AU - Juan, Cheng-En
AU - Chang, Chia-Ching
AU - Li, Ya-Hui
AU - Lee, Tung-Yang
AU - Juan, Cheng-Hsuan
AU - Tsai, Ming-Ting
AU - Juan, Chun-Jung
TI - Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study
T2 - Diagnostics (Basel, Switzerland)
J2 - Diagnostics (Basel)
PY - 2026
DA - 2026/06/02
VL - 16
IS - 11
SP - 1705
SN - 2075-4418
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/diagnostics16111705
UR - https://doi.org/10.3390/diagnostics16111705
LA - en
ER -

CSL-JSON

{
"id": "10.3390/diagnostics16111705",
"type": "article-journal",
"title": "Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study",
"container-title": "Diagnostics (Basel, Switzerland)",
"author": [
{
"family": "Lee",
"given": "Chiao-Hua"
},
{
"family": "Muzakky",
"given": "Hikam"
},
{
"family": "Juan",
"given": "Cheng-En"
},
{
"family": "Chang",
"given": "Chia-Ching"
},
{
"family": "Li",
"given": "Ya-Hui"
},
{
"family": "Lee",
"given": "Tung-Yang"
},
{
"family": "Juan",
"given": "Cheng-Hsuan"
},
{
"family": "Tsai",
"given": "Ming-Ting"
},
{
"family": "Juan",
"given": "Chun-Jung"
}
],
"container-title-short": "Diagnostics (Basel)",
"volume": "16",
"issue": "11",
"page": "1705",
"DOI": "10.3390/diagnostics16111705",
"PMID": "42279573",
"PMCID": "PMC13256447",
"ISSN": "2075-4418",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/diagnostics16111705",
"language": "en",
"issued": {
"date-parts": [
[
2026,
6,
2
]
]
}
}

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:10.3390/diagnostics16172776
A Resource-Efficient Hybrid Deep Learning Framework with External Validation for Intracranial Hemorrhage Detection in CT Scans.
Journal: Diagnostics (Basel, Switzerland)
In common: physionet.org/content/bhx-brain-bounding-box, other, 2 references
[2] doi:10.1038/s41598-024-79090-y [code]
Dual-task vision transformer for rapid and accurate intracerebral hemorrhage CT image classification.
Journal: Scientific reports
In common: stroke, other, 2 references
[3] doi:10.3390/bioengineering11121274 [code]
A Hybrid Transformer-Convolutional Neural Network for Segmentation of Intracerebral Hemorrhage and Perihematomal Edema on Non-Contrast Head Computed Tomography (CT) with Uncertainty Quantification to Improve Confidence.
Journal: Bioengineering (Basel, Switzerland)
In common: stroke, other, methods / tools, 2 references
[4] doi:10.1186/s41747-023-00330-3 [code]
Evaluation of techniques to improve a deep learning algorithm for the automatic detection of intracranial haemorrhage on CT head imaging.
Journal: European radiology experimental
In common: other, 2 references
[5] doi:10.3390/bioengineering11070643 [code]
Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network.
Journal: Bioengineering (Basel, Switzerland)
In common: methods / tools, 2 references
[6] doi:10.3390/biomedinformatics5020020
Strategies to Improve the Robustness and Generalizability of Deep Learning Segmentation and Classification in Neuroimaging.
Journal: BioMedInformatics
In common: 2 references
[7] doi:10.1111/cns.70119 [code]
Automated Hematoma Detection and Outcome Prediction in Patients With Traumatic Brain Injury.
Journal: CNS neuroscience & therapeutics
In common: 2 references
[8] doi:10.1016/j.mcpdig.2023.08.009 [code]
Hemorrhage Evaluation and Detector System for Underserved Populations: HEADS-UP.
Journal: Mayo Clinic proceedings. Digital health
In common: 2 references
[9] doi:10.3389/fnimg.2023.1157565
Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans.
Journal: Frontiers in neuroimaging
In common: stroke, other, methods / tools, 1 reference
[10] doi:10.3390/brainsci15121295
A Mask R-CNN-Based Approach for Brain Aneurysm Detection and Segmentation from TOF-MRA Data.
Journal: Brain sciences
In common: stroke, other, methods / tools, 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.

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: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.