EUVIMEDEUVIMED entdecken
Crossref

From Speech to Sonography: Spectral Networks for Ultrasound Microstructure Classification

Ali K Z Tehrani, An Tang, Mirco Ravanelli, Guy Cloutier, Iman Rafati, Bich Ngoc Nguyen, Quoc-Huy Trinh, Ivan Rosado-Mendez, Hassan Rivaz

IEEE Transactions on Biomedical Engineering · 2026-07 · 73 (7) · 2572-2581

DOI: 10.1109/tbme.2025.3638249 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Biomedical Engineering, 2026-07. Verfasst von Ali K Z Tehrani und 8 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Interpretation, Computer-Assisted, Signal Processing, Computer-Assisted, Speech. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: Fonds de recherche du Québec en Santé, Clinical Research Scholarship, Government of Canada's New Frontiers in Research Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The frequency dependence of backscattered radiofrequency (RF) signals produced by ultrasound scanners carries rich information related to the tissue microstructure (i.e., scatterer size, attenuation). This information can be sue to classify tissues based on microstructural changes associated to disease onset and progression. Conventional convolutional neural networks (CNNs) can learn this information directly from radio-frequency (RF) data, but they often struggle to achieve adequate frequency selectivity. This increases model complexity and convergence time, and limits generalization. To overcome these challenges, SincNet, originally developed for speech processing, was adapted to classify RF data based on differences in frequency properties. Rather than learning every filter coefficient, SincNet only learns each filter's low frequency and bandwidth, dramatically reducing the number of parameters and improving frequency resolution. For model interpretability, a GradientWeighted Filter Contribution is introduced, which highlights the importance of spectral bands. The approach was validated on three datasets: simulated data with different scatterer sizes, experimental phantom data, and in vivo data of rats which were fed a methionine and choline- deficient diet to develop liver steatosis, inflammation, and fibrosis. The modified SincNet consistently achieved the best results in material/tissue classifications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Interpretation, Computer-AssistedSignal Processing, Computer-AssistedSpeechAnimalsUltrasonographyRatsConvolutional Neural NetworksLiverPhantoms, ImagingHumans

Förderung

  • Fonds de recherche du Québec en Santé
  • Clinical Research Scholarship
  • Government of Canada's New Frontiers in Research Fund
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Tehrani, A. K. Z., Tang, A., Ravanelli, M., Cloutier, G., Rafati, I., Nguyen, B. N., Trinh, Q. H., Rosado-Mendez, I., & Rivaz, H. (2026). From Speech to Sonography: Spectral Networks for Ultrasound Microstructure Classification. IEEE Transactions on Biomedical Engineering, 73(7), 2572-2581. https://doi.org/10.1109/tbme.2025.3638249

Vancouver

Tehrani AKZ, Tang A, Ravanelli M, Cloutier G, Rafati I, Nguyen BN, et al. From Speech to Sonography: Spectral Networks for Ultrasound Microstructure Classification. IEEE Transactions on Biomedical Engineering. 2026;73(7):2572-2581. doi:10.1109/tbme.2025.3638249

BibTeX
@article{Tehrani2026,
  author = {Tehrani, Ali K Z and Tang, An and Ravanelli, Mirco and Cloutier, Guy and Rafati, Iman and Nguyen, Bich Ngoc and Trinh, Quoc-Huy and Rosado-Mendez, Ivan and Rivaz, Hassan},
  title = {From Speech to Sonography: Spectral Networks for Ultrasound Microstructure Classification},
  journal = {IEEE Transactions on Biomedical Engineering},
  year = {2026},
  volume = {73},
  number = {7},
  pages = {2572--2581},
  doi = {10.1109/tbme.2025.3638249}
}
Kostenlos starten →