Thomas Grenier

Author: Thomas

  • Deep learning in veterinary medicine, an approach based on CNN to detect pulmonary abnormalities from lateral thoracic radiographs in cats

    Thoracic radiograph (TR) is a complementary exam widely used in small animal medicine which requires a sharp analysis to take full advantage of Radiographic Pulmonary Pattern (RPP). Although promising advances have been made in deep learning for veterinary imaging, the development of a Convolutional Neural Networks (CNN) to detect specifically RPP from feline TR images…

  • 3rd edition of Deep Learning Medical Image School 2022

    The third edition of the school is almost done. Thanks to participants and the Montreal organizing committee! We had an exciting week. The next edition (4th) will take place in Lyon. Dates are coming soon. Link to 3rd edition ressources: https://event.fourwaves.com/dlmi2022/pages

  • UNet based detection and multiple object tracking of nanoparticles

    https://www.nature.com/articles/s41598-022-06308-2 This work, carried out with IRCELYON and the laboratory Hubert Curien, presents an approach combining deep learning and computer vision for the detection and the tracking of nano-objects in situ ETEM acquisitions. It allows the extraction of complex trajectories of small objects on a noisy and non-uniform background. Its application to the analysis of…

  • Machine learning medical image classification notebooks

    Machine learning medical image classification notebooks

    Image classification is an interesting challenge that requires many images for training. Here we propose to explore 4 different machine learning classification approaches (from random forest to ResNet) on an image set created from the IXI data set using famous python packages: scikit-learn and Keras/TensorFlow. This example is split into 3 parts. The first notebook…

  • Practice on medical image segmentation with UNet

    Here are the hands-on materials to practice deep learning segmentation with UNet (Keras/TF2): TP_UNET_TF2.zip This archive contains jupyter notebooks and necessary functions (i.e. all the code in python). See another post to install TF2/Keras with conda. The data are available here: dlss21_ho4_data.tar.gz The command line to extract the data is: $ tar xzf dlss21_ho4_data.tar.gz The…

  • Using Jupyter Lab and Tensorflow within a conda environment

    1- before launching jupyter, check the environment kernel $ jupyter kernelspec list 2- if nothing appears looking “TF2.6”, add the kernel to jupyter by: $ ipython kernel install –name “TF2.6” –user 3- now you should see TF2.6 with the command: $ jupyter kernelspec list 4 -you can repeat the above kernel installation for other kernels…

  • Nouveau au département GE ?

    Une petite présentation de l’informatique et des systèmes au département Génie Électrique de l’INSA Lyon. (pdf) Une petite visite des salles à 360° ? ici!

  • Simple Filtering and Segmentation of medical image

    Here is the notebook to start with SimpleITK and basics such as N4 bias field correction on MRI and segmentation using region growing and python programming. We also study the k-means segmentation. Python notebook : (zip)

  • Medical Deep Imaging spring school 2021

    Our third edition of the spring/summer school on deep learning for medical images will be ‘virtual’ and from 19 to 24 of April 2021. Visit the official website here. As the previous edition, there are some lectures, practices, and social events. Most of the content will be available after the school. The first edition web…

  • Install Tensorflow2 or PyTorch with conda

    Create a conda environment A short summary of conda utilization: This procedure is the same for PyTorch, just download pytorch1.12-cuda.yml and adapt the previous lines. $ conda env create –prefix /tmp/${USER}/pytorch1.12-cuda -f pytorch1.12-cuda.yml