EUVIMEDEUVIMED entdecken
Crossref

Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease

Haiyan Wang, Han Jiang, Gefei Chen, Yu Du, Zhonglin Lu, Zhanli Hu, Greta S. P. Mok

IEEE Transactions on Radiation and Plasma Medical Sciences · 2024-09 · 8 (7) · 752-761

DOI: 10.1109/trpms.2024.3398360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2024-09. Verfasst von Haiyan Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Collaborative Research Grant from University of Macau, Science and Technology Development Fund of Macau, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Striatum segmentation on Dopamine transporter (DaT) SPECT is necessary to quantify striatal uptake for Parkinsons disease (PD), but is challenging due to the inferior resolution. This work proposes a cross-modality automatic striatum segmentation, estimating MR-derived striatal contours from clinical SPECT images using deep learning (DL) methods. 123I-Ioflupane DaT SPECT and T1-weighted MR images from 200 subjects with 152 PD and 48 healthy controls are analyzed from the PPMI database. SPECT and MR images are registered, and 4 striatal compartment contours are manually segmented from MR images as the label. DL methods including nnU-Net, U-Net, generative adversarial networks, and SPECT thresholding-based method are implemented for comparison. SPECT and MR label pairs are split into train, validation, and test groups (136:24:40). Dice, Hausdorff distance (HD) 95% and relative volume difference (RVD), striatal binding ratio (SBR) and asymmetry index (ASI) are analyzed. Results show that nnU-Net achieves better Dice ( 0.7), HD 95% ( 1.8) and RVD ( 0.1) as compared to other methods for all striatal compartments and whole striatum. For clinical PD evaluation, nnU-Net also yields strong SBR consistency (mean difference, -0.012) and ASI correlation (Pearson correlation coefficient, 0.81). The proposed DL-based cross-modality striatum segmentation method is feasible for clinical DaT SPECT in PD.

Förderung

  • Collaborative Research Grant from University of Macau
  • Science and Technology Development Fund of Macau
  • National Natural Science Foundation of China
  • Shenzhen Excellent Technological Innovation Talent Training Project of China
  • Shenzhen Science and Technology Program of China

Zitieren

APA

Wang, H., Jiang, H., Chen, G., Du, Y., Lu, Z., Hu, Z., & Mok, G. S. P. (2024). Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease. IEEE Transactions on Radiation and Plasma Medical Sciences, 8(7), 752-761. https://doi.org/10.1109/trpms.2024.3398360

Vancouver

Wang H, Jiang H, Chen G, Du Y, Lu Z, Hu Z, et al. Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease. IEEE Transactions on Radiation and Plasma Medical Sciences. 2024;8(7):752-761. doi:10.1109/trpms.2024.3398360

BibTeX
@article{Wang2024,
  author = {Wang, Haiyan and Jiang, Han and Chen, Gefei and Du, Yu and Lu, Zhonglin and Hu, Zhanli and Mok, Greta S. P.},
  title = {Deep-Learning-Based Cross-Modality Striatum Segmentation for Dopamine Transporter SPECT in Parkinson’s Disease},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2024},
  volume = {8},
  number = {7},
  pages = {752--761},
  doi = {10.1109/trpms.2024.3398360}
}
Kostenlos starten →