biomedisa 2024.5.20__tar.gz → 2024.5.22__tar.gz

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biomedisa
-Version: 2024.5.20
+Version: 2024.5.22
 Summary: Segmentation of 3D volumetric image data
 Author: Philipp Lösel
 Author-email: philipp.loesel@anu.edu.au
@@ -21,36 +21,48 @@ License-File: LICENSE
 - [Installation (command-line based)](#installation-command-line-based)
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
+- [Revisions](#revisions)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Biomedisa Features](#biomedisa-features)
-- [Update Biomedisa](#update-biomedisa)
-- [Releases](#releases)
 - [Authors](#authors)
 - [FAQ](#faq)
 - [Citation](#citation)
 - [License](#license)
 
-# Overview
+## Overview
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large volumetric images, e.g. CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's semi-automated segmentation is based on a smart interpolation of sparsely pre-segmented slices, taking into account the complete underlying image data. In addition, Biomedisa enables deep learning for the fully automated segmentation of series of similar samples. It can be used in combination with segmentation tools such as Amira/Avizo, ImageJ/Fiji and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
-# Hardware Requirements
+## Hardware Requirements
 + One or more NVIDIA GPUs with compute capability 3.0 or higher or an Intel CPU.
 
-# Installation (command-line based)
+## Installation (command-line based)
 + [Ubuntu 22.04 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_cli.md)
 + [Ubuntu 22.04 + OpenCL + CPU (smart interpolation only and very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_opencl_cpu_cli.md)
 + [Windows 10 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
 + [Windows 10 + OpenCL + GPU (easy to install but lacks features like allaxis, smoothing, uncertainty, optimized GPU memory usage)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_gpu_cli.md)
 + [Windows 10 + OpenCL + CPU (very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_cpu_cli.md)
 
-# Installation (browser based)
+## Installation (browser based)
 + [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
 
-# Download Data
+## Download Data
 + Download the data from our [gallery](https://biomedisa.info/gallery/)
 
-# Smart Interpolation
+## Revisions
+2024.05.22
++ Pip is the preferred installation method
++ Commands, module names and imports have been changed to conform to the Pip standard
++ For versions <=2023.09.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
+
+## Quickstart
+Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
+```
+python -m pip install -U biomedisa
+```
+For smart interpolation and deep Learning modules, follow the [installation instructions](https://github.com/biomedisa/biomedisa#installation-command-line-based).
+
+## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)
 
 #### Python example
@@ -77,9 +89,12 @@ save_data('Downloads/final.trigonopterus.smooth.am', smooth_result, header=heade
 #### Command-line based
 ```
 python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif
+
+# if pre-segmentation is not exclusively in the XY plane
+python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif --allaxis
 ```
 
-# Deep Learning
+## Deep Learning
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/deep_learning.md)
 
 #### Python example (training)
@@ -115,10 +130,10 @@ deep_learning(img_data, label_data, train=True, batch_size=12,
 #### Command-line based (training)
 ```
 # start training with a batch size of 12
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs 12
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs=12
 
 # validation (optional)
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi C:\Users\%USERNAME%\Downloads\val_img -vl C:\Users\%USERNAME%\Downloads\val_labels
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi=C:\Users\%USERNAME%\Downloads\val_img -vl=C:\Users\%USERNAME%\Downloads\val_labels
 ```
 If running into ResourceExhaustedError due to out of memory (OOM), try to use smaller batch size.
 
@@ -143,7 +158,7 @@ save_data('final.Head5.am', results['regular'], results['header'])
 python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\testing_axial_crop_pat13.nii.gz C:\Users\%USERNAME%\Downloads\heart.h5 -p
 ```
 
-# Biomedisa Features
+## Biomedisa Features
 
 #### Load and save data (such as Amira Mesh, TIFF, NRRD, NIfTI or DICOM)
 ```python
@@ -222,41 +237,16 @@ dice = Dice_score(ground_truth, result)
 assd = ASSD(ground_truth, result)
 ```
 
-# Update Biomedisa
-If you installed Biomedisa via Pip
-```
-pip install --upgrade biomedisa
-```
-If you used `git clone`, change to the Biomedisa directory and make a pull request
-```
-cd git/biomedisa
-git pull
-```
-
-If you installed the browser based version of Biomedisa (including MySQL database), you also need to update the database
-```
-python manage.py migrate
-```
-
-If you installed an [Apache Server](https://github.com/biomedisa/biomedisa/blob/master/README/APACHE_SERVER.md), you need to restart the server
-```
-sudo service apache2 restart
-```
-
-# Releases
-
-For the versions available, see the [list of releases](https://github.com/biomedisa/biomedisa/releases). 
-
-# Authors
+## Authors
 
 * **Philipp D. Lösel**
 
 See also the list of [contributors](https://github.com/biomedisa/biomedisa/blob/master/credits.md) who participated in this project.
 
-# FAQ
+## FAQ
 Frequently asked questions can be found at: https://biomedisa.info/faq/.
 
-# Citation
+## Citation
 
 If you use Biomedisa or the data, please cite the following paper:
 
@@ -270,7 +260,7 @@ If you use Biomedisa's Smart Interpolation, you can also cite the initial descri
 
 `Lösel, P. & Heuveline, V. Enhancing a diffusion algorithm for 4D image segmentation using local information. Proc. SPIE 9784, 97842L (2016).` https://doi.org/10.1117/12.2216202
 
-# License
+## License
 
 This project is covered under the **EUROPEAN UNION PUBLIC LICENCE v. 1.2 (EUPL)**.
 

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/README.md

@@ -5,36 +5,48 @@
 - [Installation (command-line based)](#installation-command-line-based)
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
+- [Revisions](#revisions)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Biomedisa Features](#biomedisa-features)
-- [Update Biomedisa](#update-biomedisa)
-- [Releases](#releases)
 - [Authors](#authors)
 - [FAQ](#faq)
 - [Citation](#citation)
 - [License](#license)
 
-# Overview
+## Overview
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large volumetric images, e.g. CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's semi-automated segmentation is based on a smart interpolation of sparsely pre-segmented slices, taking into account the complete underlying image data. In addition, Biomedisa enables deep learning for the fully automated segmentation of series of similar samples. It can be used in combination with segmentation tools such as Amira/Avizo, ImageJ/Fiji and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
-# Hardware Requirements
+## Hardware Requirements
 + One or more NVIDIA GPUs with compute capability 3.0 or higher or an Intel CPU.
 
-# Installation (command-line based)
+## Installation (command-line based)
 + [Ubuntu 22.04 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_cli.md)
 + [Ubuntu 22.04 + OpenCL + CPU (smart interpolation only and very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_opencl_cpu_cli.md)
 + [Windows 10 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
 + [Windows 10 + OpenCL + GPU (easy to install but lacks features like allaxis, smoothing, uncertainty, optimized GPU memory usage)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_gpu_cli.md)
 + [Windows 10 + OpenCL + CPU (very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_cpu_cli.md)
 
-# Installation (browser based)
+## Installation (browser based)
 + [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
 
-# Download Data
+## Download Data
 + Download the data from our [gallery](https://biomedisa.info/gallery/)
 
-# Smart Interpolation
+## Revisions
+2024.05.22
++ Pip is the preferred installation method
++ Commands, module names and imports have been changed to conform to the Pip standard
++ For versions <=2023.09.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
+
+## Quickstart
+Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
+```
+python -m pip install -U biomedisa
+```
+For smart interpolation and deep Learning modules, follow the [installation instructions](https://github.com/biomedisa/biomedisa#installation-command-line-based).
+
+## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)
 
 #### Python example
@@ -61,9 +73,12 @@ save_data('Downloads/final.trigonopterus.smooth.am', smooth_result, header=heade
 #### Command-line based
 ```
 python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif
+
+# if pre-segmentation is not exclusively in the XY plane
+python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif --allaxis
 ```
 
-# Deep Learning
+## Deep Learning
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/deep_learning.md)
 
 #### Python example (training)
@@ -99,10 +114,10 @@ deep_learning(img_data, label_data, train=True, batch_size=12,
 #### Command-line based (training)
 ```
 # start training with a batch size of 12
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs 12
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs=12
 
 # validation (optional)
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi C:\Users\%USERNAME%\Downloads\val_img -vl C:\Users\%USERNAME%\Downloads\val_labels
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi=C:\Users\%USERNAME%\Downloads\val_img -vl=C:\Users\%USERNAME%\Downloads\val_labels
 ```
 If running into ResourceExhaustedError due to out of memory (OOM), try to use smaller batch size.
 
@@ -127,7 +142,7 @@ save_data('final.Head5.am', results['regular'], results['header'])
 python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\testing_axial_crop_pat13.nii.gz C:\Users\%USERNAME%\Downloads\heart.h5 -p
 ```
 
-# Biomedisa Features
+## Biomedisa Features
 
 #### Load and save data (such as Amira Mesh, TIFF, NRRD, NIfTI or DICOM)
 ```python
@@ -206,41 +221,16 @@ dice = Dice_score(ground_truth, result)
 assd = ASSD(ground_truth, result)
 ```
 
-# Update Biomedisa
-If you installed Biomedisa via Pip
-```
-pip install --upgrade biomedisa
-```
-If you used `git clone`, change to the Biomedisa directory and make a pull request
-```
-cd git/biomedisa
-git pull
-```
-
-If you installed the browser based version of Biomedisa (including MySQL database), you also need to update the database
-```
-python manage.py migrate
-```
-
-If you installed an [Apache Server](https://github.com/biomedisa/biomedisa/blob/master/README/APACHE_SERVER.md), you need to restart the server
-```
-sudo service apache2 restart
-```
-
-# Releases
-
-For the versions available, see the [list of releases](https://github.com/biomedisa/biomedisa/releases). 
-
-# Authors
+## Authors
 
 * **Philipp D. Lösel**
 
 See also the list of [contributors](https://github.com/biomedisa/biomedisa/blob/master/credits.md) who participated in this project.
 
-# FAQ
+## FAQ
 Frequently asked questions can be found at: https://biomedisa.info/faq/.
 
-# Citation
+## Citation
 
 If you use Biomedisa or the data, please cite the following paper:
 
@@ -254,7 +244,7 @@ If you use Biomedisa's Smart Interpolation, you can also cite the initial descri
 
 `Lösel, P. & Heuveline, V. Enhancing a diffusion algorithm for 4D image segmentation using local information. Proc. SPIE 9784, 97842L (2016).` https://doi.org/10.1117/12.2216202
 
-# License
+## License
 
 This project is covered under the **EUROPEAN UNION PUBLIC LICENCE v. 1.2 (EUPL)**.
 

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "biomedisa"
-version = "2024.5.20"
+version = "2024.5.22"
 authors = [
   { name="Philipp Lösel"}, {email="philipp.loesel@anu.edu.au" },
 ]

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/src/biomedisa/__init__.py

@@ -1,7 +1,7 @@
 import os
 import subprocess
 
-# from source base directory
+# base directory
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
 # pip installation

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/src/biomedisa/deeplearning.py

@@ -42,6 +42,7 @@ import time
 import subprocess
 import glob
 import tempfile
+import tifffile
 
 class Biomedisa(object):
      pass
@@ -55,6 +56,11 @@ def get_gpu_memory():
     except:
         return None
 
+def number_of_slices(file_path):
+    with tifffile.TiffFile(file_path) as tiff:
+        z_dim = len(tiff.pages)
+    return z_dim
+
 def deep_learning(img_data, label_data=None, val_img_data=None, val_label_data=None,
     path_to_images=None, path_to_labels=None, val_images=None, val_labels=None,
     path_to_model=None, predict=False, train=False, header_file=None,
@@ -248,8 +254,16 @@ def deep_learning(img_data, label_data=None, val_img_data=None, val_label_data=N
             # list of images
             path_to_finals = []
             if bm.path_to_images is not None and os.path.isdir(bm.path_to_images):
-                files = glob.glob(bm.path_to_images+'/**/*', recursive=True)
-                bm.path_to_images = [f for f in files if os.path.isfile(f)]
+                # load list of volumetric image files
+                files = []
+                for data_type in ['.am','.hdr','.mhd','.mha','.nrrd','.nii','.nii.gz','.zip','.mrc']:
+                    files += [file for file in glob.glob(bm.path_to_images+'/**/*'+data_type, recursive=True) if not os.path.basename(file).startswith('.')]
+                for data_type in ['.tif','.tiff']:
+                    files += [file for file in glob.glob(bm.path_to_images+'/**/*'+data_type, recursive=True) if not os.path.basename(file).startswith('.') and number_of_slices(file)>1]
+                if len(files)==0: # assume directory of 2D slices
+                    bm.path_to_images = [bm.path_to_images]
+                else:
+                    bm.path_to_images = files
             else:
                 bm.path_to_images = [bm.path_to_images]
 

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/src/biomedisa/features/split_volume.py

@@ -28,7 +28,7 @@
 
 import os
 from biomedisa.features.biomedisa_helper import load_data, save_data
-from biomedisa.features.interpolation import smart_interpolation
+from biomedisa.interpolation import smart_interpolation
 from tifffile import imread, imwrite, TiffFile
 import numpy as np
 import argparse

{biomedisa-2024.5.20 → biomedisa-2024.5.22}/src/biomedisa.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: biomedisa
-Version: 2024.5.20
+Version: 2024.5.22
 Summary: Segmentation of 3D volumetric image data
 Author: Philipp Lösel
 Author-email: philipp.loesel@anu.edu.au
@@ -21,36 +21,48 @@ License-File: LICENSE
 - [Installation (command-line based)](#installation-command-line-based)
 - [Installation (browser based)](#installation-browser-based)
 - [Download Data](#download-data)
+- [Revisions](#revisions)
 - [Smart Interpolation](#smart-interpolation)
 - [Deep Learning](#deep-learning)
 - [Biomedisa Features](#biomedisa-features)
-- [Update Biomedisa](#update-biomedisa)
-- [Releases](#releases)
 - [Authors](#authors)
 - [FAQ](#faq)
 - [Citation](#citation)
 - [License](#license)
 
-# Overview
+## Overview
 Biomedisa (https://biomedisa.info) is a free and easy-to-use open-source application for segmenting large volumetric images, e.g. CT and MRI scans, developed at [The Australian National University CTLab](https://ctlab.anu.edu.au/). Biomedisa's semi-automated segmentation is based on a smart interpolation of sparsely pre-segmented slices, taking into account the complete underlying image data. In addition, Biomedisa enables deep learning for the fully automated segmentation of series of similar samples. It can be used in combination with segmentation tools such as Amira/Avizo, ImageJ/Fiji and 3D Slicer. If you are using Biomedisa or the data for your research please cite: Lösel, P.D. et al. [Introducing Biomedisa as an open-source online platform for biomedical image segmentation.](https://www.nature.com/articles/s41467-020-19303-w) *Nat. Commun.* **11**, 5577 (2020).
 
-# Hardware Requirements
+## Hardware Requirements
 + One or more NVIDIA GPUs with compute capability 3.0 or higher or an Intel CPU.
 
-# Installation (command-line based)
+## Installation (command-line based)
 + [Ubuntu 22.04 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8_gpu_cli.md)
 + [Ubuntu 22.04 + OpenCL + CPU (smart interpolation only and very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_opencl_cpu_cli.md)
 + [Windows 10 + CUDA + GPU (recommended)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_cuda_gpu_cli.md)
 + [Windows 10 + OpenCL + GPU (easy to install but lacks features like allaxis, smoothing, uncertainty, optimized GPU memory usage)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_gpu_cli.md)
 + [Windows 10 + OpenCL + CPU (very slow)](https://github.com/biomedisa/biomedisa/blob/master/README/windows10_opencl_cpu_cli.md)
 
-# Installation (browser based)
+## Installation (browser based)
 + [Ubuntu 22.04](https://github.com/biomedisa/biomedisa/blob/master/README/ubuntu2204_cuda11.8.md)
 
-# Download Data
+## Download Data
 + Download the data from our [gallery](https://biomedisa.info/gallery/)
 
-# Smart Interpolation
+## Revisions
+2024.05.22
++ Pip is the preferred installation method
++ Commands, module names and imports have been changed to conform to the Pip standard
++ For versions <=2023.09.1 please check [README](https://github.com/biomedisa/biomedisa/blob/master/README/deprecated/README_2023.09.1.md)
+
+## Quickstart
+Install the Biomedisa package from the [Python Package Index](https://pypi.org/project/biomedisa/):
+```
+python -m pip install -U biomedisa
+```
+For smart interpolation and deep Learning modules, follow the [installation instructions](https://github.com/biomedisa/biomedisa#installation-command-line-based).
+
+## Smart Interpolation
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/smart_interpolation.md)
 
 #### Python example
@@ -77,9 +89,12 @@ save_data('Downloads/final.trigonopterus.smooth.am', smooth_result, header=heade
 #### Command-line based
 ```
 python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif
+
+# if pre-segmentation is not exclusively in the XY plane
+python -m biomedisa.interpolation C:\Users\%USERNAME%\Downloads\tumor.tif C:\Users\%USERNAME%\Downloads\labels.tumor.tif --allaxis
 ```
 
-# Deep Learning
+## Deep Learning
 + [Parameters and Examples](https://github.com/biomedisa/biomedisa/blob/master/README/deep_learning.md)
 
 #### Python example (training)
@@ -115,10 +130,10 @@ deep_learning(img_data, label_data, train=True, batch_size=12,
 #### Command-line based (training)
 ```
 # start training with a batch size of 12
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs 12
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -bs=12
 
 # validation (optional)
-python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi C:\Users\%USERNAME%\Downloads\val_img -vl C:\Users\%USERNAME%\Downloads\val_labels
+python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\training_heart C:\Users\%USERNAME%\Downloads\training_heart_labels -t -vi=C:\Users\%USERNAME%\Downloads\val_img -vl=C:\Users\%USERNAME%\Downloads\val_labels
 ```
 If running into ResourceExhaustedError due to out of memory (OOM), try to use smaller batch size.
 
@@ -143,7 +158,7 @@ save_data('final.Head5.am', results['regular'], results['header'])
 python -m biomedisa.deeplearning C:\Users\%USERNAME%\Downloads\testing_axial_crop_pat13.nii.gz C:\Users\%USERNAME%\Downloads\heart.h5 -p
 ```
 
-# Biomedisa Features
+## Biomedisa Features
 
 #### Load and save data (such as Amira Mesh, TIFF, NRRD, NIfTI or DICOM)
 ```python
@@ -222,41 +237,16 @@ dice = Dice_score(ground_truth, result)
 assd = ASSD(ground_truth, result)
 ```
 
-# Update Biomedisa
-If you installed Biomedisa via Pip
-```
-pip install --upgrade biomedisa
-```
-If you used `git clone`, change to the Biomedisa directory and make a pull request
-```
-cd git/biomedisa
-git pull
-```
-
-If you installed the browser based version of Biomedisa (including MySQL database), you also need to update the database
-```
-python manage.py migrate
-```
-
-If you installed an [Apache Server](https://github.com/biomedisa/biomedisa/blob/master/README/APACHE_SERVER.md), you need to restart the server
-```
-sudo service apache2 restart
-```
-
-# Releases
-
-For the versions available, see the [list of releases](https://github.com/biomedisa/biomedisa/releases). 
-
-# Authors
+## Authors
 
 * **Philipp D. Lösel**
 
 See also the list of [contributors](https://github.com/biomedisa/biomedisa/blob/master/credits.md) who participated in this project.
 
-# FAQ
+## FAQ
 Frequently asked questions can be found at: https://biomedisa.info/faq/.
 
-# Citation
+## Citation
 
 If you use Biomedisa or the data, please cite the following paper:
 
@@ -270,7 +260,7 @@ If you use Biomedisa's Smart Interpolation, you can also cite the initial descri
 
 `Lösel, P. & Heuveline, V. Enhancing a diffusion algorithm for 4D image segmentation using local information. Proc. SPIE 9784, 97842L (2016).` https://doi.org/10.1117/12.2216202
 
-# License
+## License
 
 This project is covered under the **EUROPEAN UNION PUBLIC LICENCE v. 1.2 (EUPL)**.