Skip to content
Snippets Groups Projects
Commit 53ed2360 authored by Nassim Bouteldja's avatar Nassim Bouteldja
Browse files

Update README.md

parent dcbbc7b2
Branches
No related tags found
1 merge request!1Update README.md
...@@ -4,7 +4,7 @@ ...@@ -4,7 +4,7 @@
# **FLASH**: **F**ramework for **LA**rge-**S**cale **H**istomorphometry # **FLASH**: **F**ramework for **LA**rge-**S**cale **H**istomorphometry
This repository represents a python framework to train, evaluate and apply segmentation networks for renal histological analysis. In particular, we trained a neural network based on the [U-net architecture](https://arxiv.org/pdf/1505.04597.pdf) to segment several renal structures including ![#ff0000](https://via.placeholder.com/15/ff0000/000000?text=+) tubulus, ![#00ff00](https://via.placeholder.com/15/00ff00/000000?text=+) glomerulus, ![#0000ff](https://via.placeholder.com/15/0000ff/000000?text=+) glomerular tuft, ![#00ffff](https://via.placeholder.com/15/00ffff/000000?text=+) non-tissue background (including veins, renal pelvis), ![#ff00ff](https://via.placeholder.com/15/ff00ff/000000?text=+) artery, and ![#ffff00](https://via.placeholder.com/15/ffff00/000000?text=+) arterial lumen from histopathology data. In our experiments, we utilized human tissue data sampled from different cohorts including inhouse biopsies (UKA_B) and nephrectomies (UKA_N), HuBMAP, KPMP, and VALIGA. This repository represents a python framework to train, evaluate and apply segmentation networks for renal histological analysis. In particular, we trained a neural network based on the [U-net architecture](https://arxiv.org/pdf/1505.04597.pdf) to segment several renal structures including ![#ff0000](https://via.placeholder.com/15/ff0000/000000?text=+) tubulus, ![#00ff00](https://via.placeholder.com/15/00ff00/000000?text=+) glomerulus, ![#0000ff](https://via.placeholder.com/15/0000ff/000000?text=+) glomerular tuft, ![#00ffff](https://via.placeholder.com/15/00ffff/000000?text=+) non-tissue background (including veins, renal pelvis), ![#ff00ff](https://via.placeholder.com/15/ff00ff/000000?text=+) artery, and ![#ffff00](https://via.placeholder.com/15/ffff00/000000?text=+) arterial lumen from PAS-stained histopathology data. In our experiments, we utilized human tissue data sampled from different cohorts including inhouse biopsies (UKA_B) and nephrectomies (UKA_N), the Human BioMolecular Atlas Program cohort (HuBMAP), the Kidney Precision Medicine Project cohort (KPMP), and the Validation of the Oxford classification of IgA Nephropathy cohort (VALIGA).
# Installation # Installation
1. Clone this repo using [git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git):<br> 1. Clone this repo using [git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git):<br>
...@@ -46,17 +46,14 @@ You can also apply the trained network to our provided exemplary image patches c ...@@ -46,17 +46,14 @@ You can also apply the trained network to our provided exemplary image patches c
<br> <br>
| Cohort | Annotation | | Cohort | Annotation |
|:--:|:--:| |:--:|:--:|
| <img src="/exemplaryImages/AC_B_Aachen_KiBiDatabase_KiBiAcZRMP870_01_018_PAS.svs__1_33_26832_15824_640_640_.png" width="400">| <img src="/exemplaryImages/AC_B_Aachen_KiBiDatabase_KiBiAcZRMP870_01_018_PAS.svs__1_33_26832_15824_640_640_-labels.png" width="324"> |
| UKA_B | Annotation | | UKA_B | Annotation |
| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/UUO.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/UUO-labels.png?raw=true" width="324"> | | <img src="/exemplaryImages/UKA_Biopsies.png" width="400">| <img src="/exemplaryImages/UKA_Biopsies_Annotation.png" width="324"> |
| UKA_N | Annotation | | UKA_N | Annotation |
| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/Adenine.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/Adenine-labels.png?raw=true" width="324"> | | <img src="/exemplaryImages/UKA_Nephrectomies.png" width="400">| <img src="/exemplaryImages/UKA_Nephrectomies_Annotation.png" width="324"> |
| HuBMAP | Annotation | | HuBMAP | Annotation |
| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/Alport.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/Alport-labels.png?raw=true" width="324"> | | <img src="/exemplaryImages/HuBMAP.png" width="400">| <img src="/exemplaryImages/HuBMAP_Annotation.png" width="324"> |
| KPMP | Annotation | | KPMP | Annotation |
| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/IRI.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/IRI-labels.png?raw=true" width="324"> | | <img src="/exemplaryImages/KPMP.png" width="400">| <img src="/exemplaryImages/KPMP_Annotation.png" width="324"> |
| VALIGA | Annotation |
| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/NTN.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneySegmentation_Histology/blob/master/exemplaryData/NTN-labels.png?raw=true" width="324"> |
# Contact # Contact
Peter Boor, MD, PhD<br> Peter Boor, MD, PhD<br>
...@@ -72,13 +69,13 @@ E-mail: pboor@ukaachen.de<br> ...@@ -72,13 +69,13 @@ E-mail: pboor@ukaachen.de<br>
# #
/************************************************************************** /**************************************************************************
* * * *
* Copyright (C) 2020 by RWTH Aachen University * * Copyright (C) 2022 by RWTH Aachen University *
* http://www.rwth-aachen.de * * http://www.rwth-aachen.de *
* * * *
* License: * * License: *
* * * *
* This software is dual-licensed under: * * This software is dual-licensed under: *
* • Commercial license (please contact: lfb@lfb.rwth-aachen.de) * * • Commercial license (please contact: pboor@ukaachen.de) *
* • AGPL (GNU Affero General Public License) open source license * * • AGPL (GNU Affero General Public License) open source license *
* * * *
***************************************************************************/ ***************************************************************************/
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment