Sample notebook + README file for contributing SUPER IVIM DC package

src/original/TCML_TechnionIIT/SUPER-IVIM-DC/README.md

@@ -0,0 +1,21 @@
+# SUPER-IVIM-DC
+
+Provided here is a sample Jupyter notebook for the SUPER-IVIM-DC package.
+
+Full README and usage instructions can be found here: https://github.com/TechnionComputationalMRILab/SUPER-IVIM-DC or https://pypi.org/project/super-ivim-dc/0.4.0/
+
+Citation: 
+
+```
+@article{
+  Korngut_Rotman_Afacan_Kurugol_Zaffrani-Reznikov_Nemirovsky-Rotman_Warfield_Freiman_2022,
+  title={SUPER-IVIM-DC: Intra-voxel incoherent motion based fetal lung maturity assessment from limited DWI data using supervised learning coupled with data-consistency},
+  volume={13432}, DOI={10.1007/978-3-031-16434-7_71},
+  journal={Lecture Notes in Computer Science},
+  author={Korngut, Noam and Rotman, Elad and Afacan, Onur and Kurugol, Sila and Zaffrani-Reznikov, Yael and Nemirovsky-Rotman, Shira and Warfield, Simon and Freiman, Moti},
+  year={2022},
+  pages={743–752}
+}
+```
+
+[The paper is also available on ArXiv](https://arxiv.org/abs/2206.03820).

src/original/TCML_TechnionIIT/SUPER-IVIM-DC/sample.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "working_dir: str = './working_dir'\n",
+    "super_ivim_dc_filename: str = 'super_ivim_dc'  # do not include .pt\n",
+    "ivimnet_filename: str = 'ivimnet'  # do not include .pt\n",
+    "\n",
+    "bvalues = np.array([0,15,30,45,60,75,90,105,120,135,150,175,200,400,600,800])\n",
+    "snr = 10\n",
+    "sample_size = 100"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Simulate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Run training, generate .pt files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from super_ivim_dc.train import train\n",
+    "\n",
+    "train(\n",
+    "    SNR=snr, \n",
+    "    bvalues=bvalues, \n",
+    "    super_ivim_dc=True,\n",
+    "    ivimnet=True,\n",
+    "    work_dir=working_dir,\n",
+    "    super_ivim_dc_filename=super_ivim_dc_filename,\n",
+    "    ivimnet_filename=ivimnet_filename,\n",
+    "    verbose=False\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Files that will be created:\n",
+    "\n",
+    "- **super_ivim_dc_init.json** - contains the initial values used in the training\n",
+    "- **super_ivim_dc_init_NRMSE.csv** - ???\n",
+    "- **super_ivim_dc_init.pt** - the pytorch model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test\n",
+    "\n",
+    "Generate a simulated signal + ..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from super_ivim_dc.infer import test_infer\n",
+    "\n",
+    "test_infer(\n",
+    "    SNR=snr,\n",
+    "    bvalues=bvalues,\n",
+    "    work_dir=working_dir,\n",
+    "    super_ivim_dc_filename=super_ivim_dc_filename,\n",
+    "    ivimnet_filename=ivimnet_filename,\n",
+    "    save_figure_to=None,  # if set to None, the figure will be shown in the notebook\n",
+    "    sample_size=sample_size,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate simulated signal"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from super_ivim_dc.IVIMNET import simulations\n",
+    "\n",
+    "IVIM_signal_noisy, Dt, f, Dp = simulations.sim_signal(\n",
+    "    SNR=snr, \n",
+    "    bvalues=bvalues, \n",
+    "    sims=sample_size\n",
+    ")\n",
+    "\n",
+    "Dt, f, Dp = np.squeeze(Dt), np.squeeze(f), np.squeeze(Dp)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Run inference on the simulated signal"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from super_ivim_dc.infer import infer_from_signal\n",
+    "\n",
+    "Dp_ivimnet, Dt_ivimnet, Fp_ivimnet, S0_ivimnet = infer_from_signal(\n",
+    "    signal=IVIM_signal_noisy, \n",
+    "    bvalues=bvalues,\n",
+    "    model_path=f\"{working_dir}/{ivimnet_filename}.pt\",\n",
+    ")\n",
+    "\n",
+    "Dp_superivimdc, Dt_superivimdc, Fp_superivimdc, S0_superivimdc = infer_from_signal(\n",
+    "    signal=IVIM_signal_noisy, \n",
+    "    bvalues=bvalues,\n",
+    "    model_path=f\"{working_dir}/{super_ivim_dc_filename}.pt\",\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "super_ivim_dc",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}