EUVIMEDEUVIMED entdecken
Crossref

Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography

Jia-Sheng Hong iD, Weir-Chiang You, Ming-Hsi Sun, Hung-Chuan Pan, Yi-Hui Lin, Yung-Fa Lu, Kuan-Ming Chen, Tzu-Hsuan Huang, Wei-Kai Lee, Yu-Te Wu iD

Journal of Magnetic Resonance Imaging · 2024-02 · 59 (2) · 587-598

DOI: 10.1002/jmri.28795 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 23.05.2023. Verfasst von Jia-Sheng Hong und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei City, 112, Taiwan. Hauptthemen laut MEDLINE: Deep Learning, Intracranial Arteriovenous Malformations. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Ministry of Education (MOE) in Taiwan, National Science and Technology Council in Taiwan, National Yang Ming Chiao Tung University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The delineation of brain arteriovenous malformations (bAVMs) is crucial for subsequent treatment planning. Manual segmentation is time‐consuming and labor‐intensive. Applying deep learning to automatically detect and segment bAVM might help to improve clinical practice efficiency.

Purpose

To develop an approach for detecting bAVM and segmenting its nidus on Time‐of‐flight magnetic resonance angiography using deep learning methods. Study Type Retrospective. Subjects 221 bAVM patients aged 7–79 underwent radiosurgery from 2003 to 2020. They were split into 177 training, 22 validation, and 22 test data. Field Strength/Sequence 1.5 T , Time‐of‐flight magnetic resonance angiography based on 3D gradient echo. Assessment The YOLOv5 and YOLOv8 algorithms were utilized to detect bAVM lesions and the U‐Net and U‐Net++ models to segment the nidus from the bounding boxes. The mean average precision, F1, precision, and recall were used to assess the model performance on the bAVM detection. To evaluate the model's performance on nidus segmentation, the Dice coefficient and balanced average Hausdorff distance (rbAHD) were employed. Statistical Tests The Student's t ‐test was used to test the cross‐validation results ( P < 0.05). The Wilcoxon rank test was applied to compare the median for the reference values and the model inference results ( P < 0.05).

Results

The detection results demonstrated that the model with pretraining and augmentation performed optimally. The U‐Net++ with random dilation mechanism resulted in higher Dice and lower rbAHD, compared to that without that mechanism, across varying dilated bounding box conditions ( P < 0.05). When combining detection and segmentation, the Dice and rbAHD were statistically different from the references calculated using the detected bounding boxes ( P < 0.05). For the detected lesions in the test dataset, it showed the highest Dice of 0.82 and the lowest rbAHD of 5.3%. Data Conclusion This study showed that pretraining and data augmentation improved YOLO detection performance. Properly limiting lesion ranges allows for adequate bAVM segmentation. Level of Evidence 4 Technical Efficacy Stage 1

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningIntracranial Arteriovenous MalformationsHumansBrainImage Processing, Computer-AssistedMagnetic Resonance AngiographyMagnetic Resonance ImagingRetrospective StudiesChildAdolescentYoung AdultAdultMiddle AgedAged

Stichwörter der Autor:innen

U-NetYOLObrain arteriovenous malformationsdeep learningdetection and segmentationtime-of-flight magnetic resonance angiography

Autor:innen und Institutionen

  • Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei City, 112, Taiwan.
  • Department of Radiation Oncology, Taichung Veterans General Hospital, Taichung, 407, Taiwan.
  • Department of Neurosurgery, Taichung Veterans General Hospital, Taichung, 407, Taiwan.
  • Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei City, 112, Taiwan.
  • Brain Research Center, National Yang Ming Chiao Tung University, Taipei City, 112, Taiwan.

ORCID-Profile: Jia-Sheng Hong, Yu-Te Wu

Förderung

  • Ministry of Education (MOE) in Taiwan
  • National Science and Technology Council in Taiwan
  • National Yang Ming Chiao Tung University
  • Taichung Veterans General Hospital

Zitieren

APA

Hong, J. S., You, W. C., Sun, M. H., Pan, H. C., Lin, Y. H., Lu, Y. F., Chen, K. M., Huang, T. H., Lee, W. K., & Wu, Y. T. (2024). Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography. Journal of Magnetic Resonance Imaging, 59(2), 587-598. https://doi.org/10.1002/jmri.28795

Vancouver

Hong JS, You WC, Sun MH, Pan HC, Lin YH, Lu YF, et al. Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography. Journal of Magnetic Resonance Imaging. 2024;59(2):587-598. doi:10.1002/jmri.28795

BibTeX
@article{Hong2024,
  author = {Hong, Jia-Sheng and You, Weir-Chiang and Sun, Ming-Hsi and Pan, Hung-Chuan and Lin, Yi-Hui and Lu, Yung-Fa and Chen, Kuan-Ming and Huang, Tzu-Hsuan and Lee, Wei-Kai and Wu, Yu-Te},
  title = {Deep Learning Detection and Segmentation of Brain Arteriovenous Malformation on Magnetic Resonance Angiography},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2024},
  volume = {59},
  number = {2},
  pages = {587--598},
  doi = {10.1002/jmri.28795}
}
Kostenlos starten →