Pedro Vianna
banner
pvianna.bsky.social
Pedro Vianna
@pvianna.bsky.social
Researcher @chumontreal. Specialist in Quantitative Ultrasound Imaging
Our paper on domain adaptation was accepted at the WACV 2026.

arxiv.org/abs/2511.03148

Congratulations to the entire team, and special thanks to Paria for her hard work!
Test Time Adaptation Using Adaptive Quantile Recalibration
Domain adaptation is a key strategy for enhancing the generalizability of deep learning models in real-world scenarios, where test distributions often diverge significantly from the training domain. H...
arxiv.org
November 11, 2025 at 3:22 PM
September 3, 2025 at 9:13 PM
And now it is out of early access!
May 8, 2025 at 2:02 PM
It was a great opportunity to present our work on MASH classification using 1D deep learning during UITC
April 29, 2025 at 1:24 AM
Just arrived in Washington DC for the Ultrasonic Imaging and Tissue Characterization Symposium tomorrow
April 27, 2025 at 5:34 PM
Yesterday, I had the opportunity to attend a presentation given by Dr Andreia V. Faria (from @jhu.edu) at the Université de Montréal.

Excellent discussion encouraging FAIR principles for data sharing and her group’s research on AI applications for clinical strokes MRI.
April 25, 2025 at 11:13 PM
I am happy to share that our newest paper is available in Early Access.

"Unsupervised Test-Time Adaptation for Hepatic Steatosis Grading Using Ultrasound B-Mode Images," in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

ieeexplore.ieee.org/abstract/doc...
Unsupervised Test-Time Adaptation for Hepatic Steatosis Grading Using Ultrasound B-Mode Images
Ultrasound is considered a key modality for the clinical assessment of hepatic steatosis (i.e., fatty liver) due to its non-invasiveness and availability. Deep learning methods have attracted consider...
ieeexplore.ieee.org
April 1, 2025 at 2:54 PM