no code implementations • 15 Aug 2023 • Po-Jui Lu, Benjamin Odry, Muhamed Barakovic, Matthias Weigel, Robin Sandkühler, Reza Rahmanzadeh, Xinjie Chen, Mario Ocampo-Pineda, Jens Kuhle, Ludwig Kappos, Philippe Cattin, Cristina Granziera
To fully utilize the qMRI, GAMER-MRIL extended a gated-attention-based CNN (GAMER-MRI), which was developed to select patch-based qMRI important for a given task/question, to the whole-brain image.
1 code implementation • 27 Mar 2023 • Florentin Bieder, Julia Wolleb, Alicia Durrer, Robin Sandkühler, Philippe C. Cattin
Denoising diffusion models have recently achieved state-of-the-art performance in many image-generation tasks.
no code implementations • 14 Mar 2023 • Alicia Durrer, Julia Wolleb, Florentin Bieder, Tim Sinnecker, Matthias Weigel, Robin Sandkühler, Cristina Granziera, Özgür Yaldizli, Philippe C. Cattin
We map images from the source contrast to the target contrast for both directions, from 3 T to 1. 5 T and from 1. 5 T to 3 T. As we only want to change the contrast, not the anatomical information, our method uses the original image to guide the image-to-image translation process by adding structural information.
1 code implementation • 19 Jan 2023 • Florentin Bieder, Julia Wolleb, Robin Sandkühler, Philippe C. Cattin
Most current anomaly detection methods for medical images are based on image reconstruction.
no code implementations • 6 Apr 2022 • Julia Wolleb, Robin Sandkühler, Florentin Bieder, Philippe C. Cattin
We build on a method for image-to-image translation using denoising diffusion implicit models and include a regression problem and a segmentation problem for guiding the image generation to the desired output.
2 code implementations • 8 Mar 2022 • Julia Wolleb, Florentin Bieder, Robin Sandkühler, Philippe C. Cattin
In medical applications, weakly supervised anomaly detection methods are of great interest, as only image-level annotations are required for training.
3 code implementations • 6 Dec 2021 • Julia Wolleb, Robin Sandkühler, Florentin Bieder, Philippe Valmaggia, Philippe C. Cattin
By modifying the training and sampling scheme, we show that diffusion models can perform lesion segmentation of medical images.
1 code implementation • 13 Oct 2021 • Julia Wolleb, Robin Sandkühler, Florentin Bieder, Muhamed Barakovic, Nouchine Hadjikhani, Athina Papadopoulou, Özgür Yaldizli, Jens Kuhle, Cristina Granziera, Philippe C. Cattin
The limited availability of large image datasets, mainly due to data privacy and differences in acquisition protocols or hardware, is a significant issue in the development of accurate and generalizable machine learning methods in medicine.
no code implementations • 2 Mar 2021 • Florentin Bieder, Robin Sandkühler, Philippe C. Cattin
Max- and average-pooling are the most popular pooling methods for downsampling in convolutional neural networks.
1 code implementation • 28 Jul 2020 • Julia Wolleb, Robin Sandkühler, Philippe C. Cattin
In this work, we present a weakly supervised and detail-preserving method that is able to detect structural changes of existing anatomical structures.
no code implementations • 26 Aug 2019 • Christoph Jud, Damien Nguyen, Alina Giger, Robin Sandkühler, Miriam Krieger, Tony Lomax, Rares Salomir, Oliver Bieri, Philippe C. Cattin
A recently proposed MR imaging approach copes with motion by observing the motion patterns during the acquisition.
1 code implementation • NeurIPS 2019 • Robin Sandkühler, Simon Andermatt, Grzegorz Bauman, Sylvia Nyilas, Christoph Jud, Philippe C. Cattin
We trained our network on 2D magnetic resonance images of the lung and compared our method to a standard parametric B-spline registration.
3 code implementations • 26 Jun 2018 • Robin Sandkühler, Christoph Jud, Simon Andermatt, Philippe C. Cattin
With the "Autograd Image Registration Laboratory" (AIRLab), we introduce an open laboratory for image registration tasks, where the analytic gradients of the objective function are computed automatically and the device where the computations are performed, on a CPU or a GPU, is transparent.