Paul Ritsche

(3/3) we used the benchmark dataset proposed in Ritsche & Sarto et al. (2025) osf.io/preprints/os... for reproducible and comparable algorithm performance analysis.

@mvfranchi.bsky.social @fabiosartophd.bsky.social @olivierseynnes.bsky.social

(2/3) Compared to a recent publication by Van der Zee et al. we show:

1. Improvement of new DL_Track_US models
2. Higher comparability between both approaches
3. Comparison of four different model types

💡Details in the news section of the docs ⤵
paulritsche.github.io/DL_Track_US/...

🚨 DL_Track_US NEWS 🚨 (1/3)

A new release (v0.3.0) 🎉 including:

✅ information transfer between frames
✅ improved UI with live analysis visualization
✅ installation wizard for easy usage
✅ faster processing

Check out the new docs for more info ⤵ paulritsche.github.io/DL_Track_US/...

⏭️ Next up:

⬆️ increase comparability to MR assessed muscle volume by:

🔍 objectifying calibration methods
🐍 automate image analysis

🚨New Preprint 🚨

3D Ultrasound is…
✅ reliable between sessions for muscle volume
✅ valid for ground truth phantom assessment

🔗 doi.org/10.31219/osf...

🔬Methods docs:
github.com/AurelieSar/3...

@mrifranz.bsky.social
With Michele Pansini, Romina Ledergerber & Oliver Faude

Join us tomorrow, in this year's Love Your Data Week to talk about “Open Data in Musculoskeletal Imaging” presented by @serenabonaretti.bsky.social
@ritpau.bsky.social
and Simone Poncioni
Registration still open:
t.co/C77XLy0jfa
#imaging, #msk, #opendata

🚨 Registration Open! 🚨

Join us in Brescia 🇮🇹 for the INcEPTION Winter School 2025 on HDsEMG!

📅 10th–14th March 2025
📍 In-person only | Limited spots!
✅ No registration fee

Don't miss this opportunity! Find further details here: forms.gle/EY4wNMnbYRn9nT…

UMUD is here to support muscle ultrasound research, but we can't do it alone...

We need YOU to:
🤝 Contribute datasets & annotations
🔬 Test & refine algorithms
💬 Share insights & ideas

Together, we can foster open science and reproducible research in ultrasound imaging 🤗

What else does UMUD include? 🤔

📊 Indexing (so far) 11 datasets with 75,569 images & 2,573 videos from 1,769 participants.
🔍 Detailed metadata for easy dataset exploration: muscle groups, devices, demographics, & more.
💡 Guidance on state-of-the-art automated analysis tools

UMUD This app was built in Streamlit! Check it out and visit https://streamlit.io for more awesome community apps. 🎈

A Universal Musculoskeletal Ultrasound Database:

📀 Open data
📊 Benchmarks
🧠 Expert-analyzed datasets

@fabiosartophd.bsky.social @olivierseynnes.bsky.social @mrifranz.bsky.social

🌐 web app: universalmuscledatabase.streamlit.app
📜preprint: doi.org/10.31219/osf...

⚠️ DeepACSA News ⚠️

✅ trained with ultrasonography images, automatic muscle CSA analysis works on populations with ACL rupture as well

🔜 Models will be available online.

Amazing efforts from
Beyza Tayfur & Team
and team!

#Muscle #ImageAnalysis #DeepACSA

Article link ⬇️
t.co/8kOW2TdO8J

Join us in the Reproducibilitea Unibasel this Thursday for the next invited talk “Reproducible Research: An Introduction to The Turing Way and Binder” by Sarah Gibson @turingway
Registration: www.eventbrite.com/e/reproducib...

⚠️ #openhdemg news ⚠️

📅Come visit us at the SwissRN congress in Zurich next Monday (10.06).

✅Learn about #openhdemg (github.com/GiacomoValli...) and reproducibility

🖥️Congress program: www.reproducibility.ch

DL_Track_US This repository contains the example data for the DL_Track_US algorithm. Here, we provide the pre-trained aponeuroses and fascicle neural networks, the training images as well as example and test data...

❗️DL_Track_US News ❗️

*DL_Track_US is a software to automatically analyse fascicle behaviour in dynamic ultrasonography scans*

🆕v0.2.1 is now on pypi and available as .exe

Including:
✅Fascicle filtering
✅Mask inspection

⬇️Check it out #SciSky

osf.io/7mjsc/ (the repo is now on OSF)

GitHub - PaulRitsche/DeepACSA: Automated measurement of muscle anatomical cross-sectional area in ul... Automated measurement of muscle anatomical cross-sectional area in ultrasound images using deep learning - GitHub - PaulRitsche/DeepACSA: Automated measurement of muscle anatomical cross-sectional ...

First Post on #SciSky 🧪

We recently created DeepACSA to automatically analyse muscle ACSA in ultrasonography images 💪

❗ We released a new version ❗

New features:
✅ Labelling of images in GUI
✅ Inspection of Labels in GUI
✅ Restructured GUI

Check it out ⏬
github.com/PaulRitsche/DeepACSA/tree/main

Open Science Basel Year 4 #1 - Daniel S. Quintana First lecture of the fourth year of the Open Science Seminar Series at the University of Basel. Presentation by Daniel S. Quintana on "How Open Science pract...

Here’s a recording of a recent talk on how open science practices can improve research reproducibility, in which I begin by describing the events that led to my interest in open science youtu.be/UDaSaE67E3Y?...

I’m Paul 👋🏼 I study muscle architecture using ultrasonography and how it adapts during maturation, ageing or due to training. I try to automate the analysis of (EFOV) muscle ultrasonography because I got tired of clicking on images. I am currently working in 🇨🇭