EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation

Haiyan Liu, Yu Zeng, Hao Li, Fuxin Wang, Jianjun Chang, Huaping Guo iD, Jian Zhang

IET Systems Biology · 2024

DOI: 10.1049/syb2.12103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Systems Biology, 2024. Verfasst von Haiyan Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Xinyang Central Hospital, Xinyang, China. Hauptthemen laut MEDLINE: Cerebral Hemorrhage. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Plan Project of Henan Province, Henan Province Key Research and Development Project, Research Project on the Curriculum Reform of Teacher Education in Henan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Intracranial haemorrhage (ICH) is an urgent and potentially fatal medical condition caused by brain blood vessel rupture, leading to blood accumulation in the brain tissue. Due to the pressure and damage it causes to brain tissue, ICH results in severe neurological impairment or even death. Recently, deep neural networks have been widely applied to enhance the speed and precision of ICH detection yet they are still challenged by small or subtle hemorrhages. The authors introduce DDANet, a novel haematoma segmentation model for brain CT images. Specifically, a dilated convolution pooling block is introduced in the intermediate layers of the encoder to enhance feature extraction capabilities of middle layers. Additionally, the authors incorporate a self‐attention mechanism to capture global semantic information of high‐level features to guide the extraction and processing of low‐level features, thereby enhancing the model's understanding of the overall structure while maintaining details. DDANet also integrates residual networks, channel attention, and spatial attention mechanisms for joint optimisation, effectively mitigating the severe class imbalance problem and aiding the training process. Experiments show that DDANet outperforms current methods, achieving the Dice coefficient, Jaccard index, sensitivity, accuracy, and a specificity of 0.712, 0.601, 0.73, 0.997, and 0.998, respectively. The code is available at https://github.com/hpguo1982/DDANet .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cerebral HemorrhageHumansTomography, X-Ray ComputedNeural Networks, ComputerImage Processing, Computer-AssistedBrainDeep LearningAlgorithms

Stichwörter der Autor:innen

bioinformaticsimage segmentationlearning (artificial intelligence)medical image processingpatient diagnosis

Autor:innen und Institutionen

  • Department of Neurology, Xinyang Central Hospital, Xinyang, China.
  • School of Medicine, Xinyang Normal University, Xinyang, China.
  • School of Computer and Information Techonology, Xinyang Normal University, Xinyang, China.

ORCID-Profile: Huaping Guo

Förderung

  • Science and Technology Plan Project of Henan Province
  • Henan Province Key Research and Development Project
  • Research Project on the Curriculum Reform of Teacher Education in Henan Province
  • Key Scientific Research Projects of Higher Education Institutions in Henan Province

Zitieren

APA

Liu, H., Zeng, Y., Li, H., Wang, F., Chang, J., Guo, H., & Zhang, J. (2024). DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation. IET Systems Biology. https://doi.org/10.1049/syb2.12103

Vancouver

Liu H, Zeng Y, Li H, Wang F, Chang J, Guo H, et al. DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation. IET Systems Biology. 2024. doi:10.1049/syb2.12103

BibTeX
@article{Liu2024,
  author = {Liu, Haiyan and Zeng, Yu and Li, Hao and Wang, Fuxin and Chang, Jianjun and Guo, Huaping and Zhang, Jian},
  title = {DDANet: A deep dilated attention network for intracerebral haemorrhage segmentation},
  journal = {IET Systems Biology},
  year = {2024},
  doi = {10.1049/syb2.12103}
}
Kostenlos starten →