Reproducing DeepTFUS | projects
Focused ultrasound can reach targets deep inside the brain non-invasively, but figuring out where the beam actually lands through someone's skull takes ~30 minutes of physics simulation per patient. I reproduced [DeepTFUS](https://arxiv.org/abs/2505.12998), a 3D model that **predicts the same result in under a second**, and open-sourced the trained weights + training code the paper didn't release.
DeepTFUS is a proposed model that, given a CT + ultrasound transducer placement, predicts the resulting pressure field inside the head in <1s instead of the ~30m a physics simulator would take. Model weights and training code are not released, so I: open-source my reproduction , walk through some new loss functions I tried , and poke around with the trained model Update: My reproduction has 11x less parameters (3.4M vs ~38M; post written before the authors got back with architecture details, now in the Update ). This was a 36-hour learning sprint on an H100, no sweeps or anything rigorous. gro
saved by
related reading
- Ultrasound imaging of the brain — Alephalephneuro.com
- Silent speech with ultrasound — Alephalephneuro.com
- Determine exact optimal parameters of 3D-printed holographic acoustic lenses for transcranial FUSemergentmind.com
- The Little Book of Deep Learningfleuret.org
- How to build a full body ultrasoundyoutube.com
- DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation | PDFarxiv.org
- Scalable Diffusion Models with Transformersopenaccess.thecvf.com
- Fast Training of Diffusion Models with Masked Transformers | PDFarxiv.org
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow | PDFarxiv.org
- [2207.13807] Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldsarxiv.org
- Learning 3D object-centric representation through predictionarxiv.org
- BabelBrainproteusmrighifu.github.io