EUVIMEDEUVIMED entdecken
Crossref

I³Net: Inter-Intra-Slice Interpolation Network for Medical Slice Synthesis

Haofei Song, Xintian Mao, Jing Yu, Qingli Li, Yan Wang

IEEE Transactions on Medical Imaging · 2024-09 · 43 (9) · 3306-3318

DOI: 10.1109/tmi.2024.3394033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2024-09. Verfasst von Haofei Song und 4 weiteren Autor:innen. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Natural Science Foundation, Science and Technology Commission of Shanghai Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical imaging is limited by acquisition time and scanning equipment. CT and MR volumes, reconstructed with thicker slices, are anisotropic with high in-plane resolution and low through-plane resolution. We reveal an intriguing phenomenon that due to the mentioned nature of data, performing slice-wise interpolation from the axial view can yield greater benefits than performing super-resolution from other views. Based on this observation, we propose an Inter-Intra-slice Interpolation Network ( [Formula: see text]Net), which fully explores information from high in-plane resolution and compensates for low through-plane resolution. The through-plane branch supplements the limited information contained in low through-plane resolution from high in-plane resolution and enables continual and diverse feature learning. In-plane branch transforms features to the frequency domain and enforces an equal learning opportunity for all frequency bands in a global context learning paradigm. We further propose a cross-view block to take advantage of the information from all three views online. Extensive experiments on two public datasets demonstrate the effectiveness of [Formula: see text]Net, and noticeably outperforms state-of-the-art super-resolution, video frame interpolation and slice interpolation methods by a large margin. We achieve 43.90dB in PSNR, with at least 1.14dB improvement under the upscale factor of ×2 on MSD dataset with faster inference. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingHumansTomography, X-Ray ComputedAlgorithmsImage Processing, Computer-AssistedImaging, Three-DimensionalBrainNeural Networks, Computer

Förderung

  • National Natural Science Foundation of China
  • Shanghai Natural Science Foundation
  • Science and Technology Commission of Shanghai Municipality

Zitieren

APA

Song, H., Mao, X., Yu, J., Li, Q., & Wang, Y. (2024). I³Net: Inter-Intra-Slice Interpolation Network for Medical Slice Synthesis. IEEE Transactions on Medical Imaging, 43(9), 3306-3318. https://doi.org/10.1109/tmi.2024.3394033

Vancouver

Song H, Mao X, Yu J, Li Q, Wang Y. I³Net: Inter-Intra-Slice Interpolation Network for Medical Slice Synthesis. IEEE Transactions on Medical Imaging. 2024;43(9):3306-3318. doi:10.1109/tmi.2024.3394033

BibTeX
@article{Song2024,
  author = {Song, Haofei and Mao, Xintian and Yu, Jing and Li, Qingli and Wang, Yan},
  title = {I³Net: Inter-Intra-Slice Interpolation Network for Medical Slice Synthesis},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2024},
  volume = {43},
  number = {9},
  pages = {3306--3318},
  doi = {10.1109/tmi.2024.3394033}
}
Kostenlos starten →