EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Chiao-Hua Lee, Hikam Muzakky, Cheng-En Juan, Chia-Ching Chang, Ya-Hui Li, Tung-Yang Lee, Cheng-Hsuan Juan, Ming-Ting Tsai iD, Chun-Jung Juan iD

Diagnostics · 02.06.2026 · 16 (11) · 1705

DOI: 10.3390/diagnostics16111705 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 02.06.2026. Verfasst von Chiao-Hua Lee und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Medical University Hsinchu Hospital, National Science and Technology Council, Taiwan National Science and Technology Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 (mAP@50), 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.

Schlagwörter

Stichwörter der Autor:innen

deep learningintracranial hemorrhagenoncontrast head CTobject localization

Autor:innen und Institutionen

  • Department of Medical Imaging, China Medical University Hsinchu Hospital, Hsinchu 302, Taiwan.
  • China Medical University Hospital, Taichung 404, Taiwan.
  • Master's Program of Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung 407, Taiwan.
  • Department of Management Science, National Yang Ming Chiao Tung University, Hsinchu 300, Taiwan.
  • Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 106, Taiwan.
  • Show Chwan Memorial Hospital, Changhua 500, Taiwan.

ORCID-Profile: Ming-Ting Tsai, Chun-Jung Juan

Förderung

  • China Medical University Hsinchu Hospital
  • National Science and Technology Council
  • Taiwan National Science and Technology Council

Zitieren

APA

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, 16(11), 1705. https://doi.org/10.3390/diagnostics16111705

Vancouver

Lee CH, Muzakky H, Juan CE, Chang CC, Li YH, Lee TY, et al. Cross-Dataset Generalization of Deep Learning-Based Detectors for Intracranial Hemorrhage Subtype Localization on Noncontrast Head CT: A Comparative Study. Diagnostics. 2026;16(11):1705. doi:10.3390/diagnostics16111705

BibTeX
@article{Lee2026,
  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},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {1705},
  doi = {10.3390/diagnostics16111705}
}
Kostenlos starten →