From d6839f13494bba708c13a66ee3de2b88874cfdca Mon Sep 17 00:00:00 2001 From: Naga Karthik Date: Mon, 4 Nov 2024 16:09:31 +0100 Subject: [PATCH] brief update to readme --- README.md | 41 ++++++++++++++--------------------------- 1 file changed, 14 insertions(+), 27 deletions(-) diff --git a/README.md b/README.md index 2a1c3a3..797c86c 100644 --- a/README.md +++ b/README.md @@ -1,17 +1,14 @@ -# SCISeg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury - -[![medRxiv](https://img.shields.io/badge/medRxiv-10.1101/2024.01.03.24300794v2-blue.svg)](https://www.medrxiv.org/content/10.1101/2024.01.03.24300794v2.full.pdf) - -This repository contains the code for deep learning-based segmentation of the spinal cord and hyperintense lesions in spinal cord injury (SCI). The code is based on the [nnUNetv2 framework](https://github.com/MIC-DKFZ/nnUNet). +# Assessing the Impact of Spinal Cord Curvature in Axial T2-weighted Intramedullary MS Lesion Segmentation +This repository contains the code for deep learning-based segmentation of the spinal cord and intramedullary MS lesions in Axial T2-weighted MRI scans. The model is based on the [nnUNetv2 framework](https://github.com/MIC-DKFZ/nnUNet). This project is a collaboration between NeuroPoly (Polytechnique Montreal, Quebec) and TUM (Munich, Bavaria) ## Model Overview -The model was trained on raw T2-weighted images of SCI patients from multiple (three) sites. The data included images with both axial and sagittal resolutions. To ensure uniformity across sites, all images were initially re-oriented to RPI. Given an input image, the model is able to segment *both* the lesion and the spinal cord. The model also works well on degenerative cervical myelopathy (DCM) lesions. +The model was trained on raw T2-weighted axial images of MS patients from multiple (four) sites. The TUM dataset is longitudinal (two sessions) and consisted of individual chunks (cervical, thoracic and lumbar) covering the entire spine. The three other sites used in this study were taken from the private `sct-testing-large` dataset from NeuroPoly. To ensure uniformity across sites, all images were initially re-oriented to RPI. Given an input image, the model is able to segment *both* the lesion and the spinal cord. -figure2_fixed +TODO: add a figure here -## Using SCIseg +## Using the model ### Install dependencies @@ -19,10 +16,10 @@ The model was trained on raw T2-weighted images of SCI patients from multiple (t - [conda](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) - Python (v3.9) -Once the dependencies are installed, download the latest SCIseg model: +Once the dependencies are installed, download the latest model: ```bash -sct_deepseg -install-task seg_sc_lesion_t2w_sci +sct_deepseg -install-task seg_sc_lesion_t2w_ms ``` ### Getting the lesion and spinal cord segmentation @@ -30,34 +27,24 @@ sct_deepseg -install-task seg_sc_lesion_t2w_sci To segment a single image, run the following command: ```bash -sct_deepseg -i -task seg_sc_lesion_t2w_sci +sct_deepseg -i -task seg_sc_lesion_t2w_ms ``` For example: ```bash -sct_deepseg -i sub-001_T2w.nii.gz -task seg_sc_lesion_t2w_sci +sct_deepseg -i sub-001_T2w.nii.gz -task seg_sc_lesion_t2w_ms ``` The outputs will be saved in the same directory as the input image, with the suffix `_lesion_seg.nii.gz` for the lesion and `_sc_seg.nii.gz` for the spinal cord. +## Analysis Pipeline + +TODO: + ## Citation Info If you find this work and/or code useful for your research, please cite our paper: -``` -@article {Naga Karthik2024.01.03.24300794, - author = {Enamundram Naga Karthik* and Jan Valosek* and Andrew C. Smith and Dario Pfyffer and Simon Schading-Sassenhausen and Lynn Farner and Kenneth A. Weber II and Patrick Freund and Julien Cohen-Adad}, - title = {SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury}, - elocation-id = {2024.01.03.24300794}, - year = {2024}, - doi = {10.1101/2024.01.03.24300794}, - publisher = {Cold Spring Harbor Laboratory Press}, - URL = {https://www.medrxiv.org/content/early/2024/04/21/2024.01.03.24300794}, - eprint = {https://www.medrxiv.org/content/early/2024/04/21/2024.01.03.24300794.full.pdf}, - journal = {medRxiv}, - note = {*Shared first authorship} -} - -``` +TODO: \ No newline at end of file