Tessera
Folgen

Aitor González-Marfil

@aaitorg.bsky.social

PhD student | Deep Learning | Computer Vision | Biomedical Images

9 Posts79 Follower27 Folgt
Estibaliz Gómez de Mariscal, PhD@gomez-mariscal.bsky.social · 5mo ago

🚨Our preprint on DL for single-image super-resolution in microscopy is out!🌟 sl1nk.com/p62yedg Our benchmark recaps an adventure of learning and questioning with @ivanhcenalmor.bsky.social & @iarganda.eurosky.social 🌟 how to objectively assess SISR models & ease the choice for their use in👉 biology🔬

BildBildBild
Iván Hidalgo-Cenalmor@ivanhcenalmor.bsky.social · 5mo ago

Super excited to share a project I’ve worked on since my Master’s thesis, what a journey!🚵 Finally out as a Nature Methods Stage 1 Registered Report preprint doi.org/10.6084/m9.f... We benchmark deep learning-based single-image super-resolution methods for microscopy imaging. Interested? Check out 🧵

Iván Hidalgo-Cenalmor@ivanhcenalmor.bsky.social · 5mo ago

Super excited to share a project I’ve worked on since my Master’s thesis, what a journey!🚵 Finally out as a Nature Methods Stage 1 Registered Report preprint doi.org/10.6084/m9.f... We benchmark deep learning-based single-image super-resolution methods for microscopy imaging. Interested? Check out 🧵

Accuracy versus Perception: a Benchmark of Deep Learning Models for Single-Image Super-Resolution in Microscopy

Virtual super-resolution deep learning methods provide a powerful solution to overcome the physical and temporal constraints of microscopy imaging. Yet, assessing and choosing an ideal methodological strategy complicates their use in life sciences and creates a lack of trust in these methods. Here we propose an objective comparison of nine popular single-image super-resolution (SISR) models in a collection of publicly available microscopy datasets, including cell components like microtubules, endoplasmic reticulum, and actin, using confocal microscopy, SEM, SIM, SMLM and STED microscopy modalities for fixed and live-cell microscopy data. The proposed models will be assessed quantitatively with a collection of metrics in microscopy and computer vision, and qualitatively by experts in the field. The proposed models will be made accessible through open, user-friendly, containerised notebooks. This systematic assessment of SISR approaches will provide a more comprehensive understanding of these methods' performance and contribute to standardising SISR methods in microscopy.

doi.org

Estibaliz Gómez de Mariscal, PhD@gomez-mariscal.bsky.social · last yr.

🚨Alô #bsky and #microscopy community, we got #ReScale4DL, our new work in @aiopticalbiolab.bsky.social , out today!😍 🥳 We present the #imageresolutionparadox phenomenon for #DL-results 🤓 👇Check it out!!

Ricardo Henriques@henriqueslab.bsky.social · last yr.

Why do lower-resolution images sometimes yield better results in deep learning for bioimaging analyses? 🤔📉 Mariana Ferreira's new preprint on #ReScale4DL explores this paradox and introduces optimal resolution design! @gomez-mariscal.bsky.social brainchild🧑‍🔬✨ Check: www.biorxiv.org/content/10.1...