DigiPathAI / Git / Diff of /README.md

Models:

DanielG/

DigiPathAI

Downloads: 1

Diff of /README.md [5bd30d] .. [3f3595]

Switch to unified view


[![PyPI version](https://badge.fury.io/py/DigiPathAI.svg)](https://badge.fury.io/py/DigiPathAI)
[![PyPI Downloads](https://static.pepy.tech/badge/digipathai)](https://pepy.tech/projects/digipathai)
[![arXiv](https://img.shields.io/badge/arXiv-2001.00258-<COLOR>.svg)](https://arxiv.org/abs/2001.00258)


# DigiPathAI
A software application built on top of [openslide](https://openslide.org/) for viewing [whole slide images (WSI)](https://www.ncbi.nlm.nih.gov/pubmed/30307746) and performing pathological analysis 

### Citation
If you find this reference implementation useful in your research, please consider citing:
```
@article{khened2020generalized,
  title={A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis},
  author={Khened, Mahendra and Kori, Avinash and Rajkumar, Haran and Srinivasan, Balaji and Krishnamurthi, Ganapathy},
  journal={arXiv preprint arXiv:2001.00258},
  year={2020}
}
```
# Features
- Responsive WSI image viewer 
- State of the art cancer AI pipeline to segment and display the cancerous tissue regions











# Installation
Running of the AI pipeline requires a GPU and several deep learning modules. However, you can run just the UI as well.

## Just the UI
### Requirements
- `openslide`
- `flask`

The following command will install only the dependencies listed above.
```
pip install DigiPathAI
```

## Entire AI pipeline
### Requirements
- `pytorch`
- `torchvision`
- `opencv-python`
- `imgaug`
- `matplotlib`
- `scikit-learn`
- `scikit-image`
- `tensorflow-gpu >=1.14,<2`
- `pydensecrf`
- `pandas`
- `wget`

The following command will install the dependencies mentioned
```
pip install "DigiPathAI[gpu]"
```

Both installation methods install the same package, just different dependencies. Even if you had installed using the earlier command, you can install the rest of the dependencies manually. 

# Usage 
## Local server
Traverse to the directory containing the openslide images and run the following command.
```
digipathai <host: localhost (default)> <port: 8080 (default)>
```

## Python API usage
The application also has an API which can be used within python to perform the segmentation. 
```
from DigiPathAI.Segmentation import getSegmentation

prediction = getSegmentation(img_path, 
            patch_size  = 256, 
            stride_size = 128,
            batch_size  = 32,
            quick       = True,
            tta_list    = None,
            crf         = False,
            save_path   = None,
            status      = None)
```

# Contact
- Avinash Kori (koriavinash1@gmail.com)
- Haran Rajkumar (haranrajkumar97@gmail.com)

[![ko-fi](https://www.ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/M4M132RPG)


	a/README.md		b/README.md
1	[![PyPI version](https://badge.fury.io/py/DigiPathAI.svg)](https://badge.fury.io/py/DigiPathAI)	1	[![PyPI version](https://badge.fury.io/py/DigiPathAI.svg)](https://badge.fury.io/py/DigiPathAI)
2	[![PyPI Downloads](https://static.pepy.tech/badge/digipathai)](https://pepy.tech/projects/digipathai)	2	[![PyPI Downloads](https://static.pepy.tech/badge/digipathai)](https://pepy.tech/projects/digipathai)
3	[![arXiv](https://img.shields.io/badge/arXiv-2001.00258-<COLOR>.svg)](https://arxiv.org/abs/2001.00258)	3	[![arXiv](https://img.shields.io/badge/arXiv-2001.00258-<COLOR>.svg)](https://arxiv.org/abs/2001.00258)
4		4
5		5
6	# DigiPathAI	6	# DigiPathAI
7	A software application built on top of [openslide](https://openslide.org/) for viewing [whole slide images (WSI)](https://www.ncbi.nlm.nih.gov/pubmed/30307746) and performing pathological analysis	7	A software application built on top of [openslide](https://openslide.org/) for viewing [whole slide images (WSI)](https://www.ncbi.nlm.nih.gov/pubmed/30307746) and performing pathological analysis
8		8
9	### Citation	9	### Citation
10	If you find this reference implementation useful in your research, please consider citing:	10	If you find this reference implementation useful in your research, please consider citing:
11	```	11	```
12	@article{khened2020generalized,	12	@article{khened2020generalized,
13	title={A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis},	13	title={A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis},
14	author={Khened, Mahendra and Kori, Avinash and Rajkumar, Haran and Srinivasan, Balaji and Krishnamurthi, Ganapathy},	14	author={Khened, Mahendra and Kori, Avinash and Rajkumar, Haran and Srinivasan, Balaji and Krishnamurthi, Ganapathy},
15	journal={arXiv preprint arXiv:2001.00258},	15	journal={arXiv preprint arXiv:2001.00258},
16	year={2020}	16	year={2020}
17	}	17	}
18	```	18	```
19	# Features	19	# Features
20	- Responsive WSI image viewer	20	- Responsive WSI image viewer
21	- State of the art cancer AI pipeline to segment and display the cancerous tissue regions	21	- State of the art cancer AI pipeline to segment and display the cancerous tissue regions
22		22
23	# Application Overview
24	<p align="center">
25	<img src="imgs/demo.gif">
26	</p>
27
28	# Results
29	<p align="center">
30	<img width="460" height="300" src="imgs/results_1.png">
31	</p>
32
33	# Installation	23	# Installation
34	Running of the AI pipeline requires a GPU and several deep learning modules. However, you can run just the UI as well.	24	Running of the AI pipeline requires a GPU and several deep learning modules. However, you can run just the UI as well.
35		25
36	## Just the UI	26	## Just the UI
37	### Requirements	27	### Requirements
38	- `openslide`	28	- `openslide`
39	- `flask`	29	- `flask`
40		30
41	The following command will install only the dependencies listed above.	31	The following command will install only the dependencies listed above.
42	```	32	```
43	pip install DigiPathAI	33	pip install DigiPathAI
44	```	34	```
45		35
46	## Entire AI pipeline	36	## Entire AI pipeline
47	### Requirements	37	### Requirements
48	- `pytorch`	38	- `pytorch`
49	- `torchvision`	39	- `torchvision`
50	- `opencv-python`	40	- `opencv-python`
51	- `imgaug`	41	- `imgaug`
52	- `matplotlib`	42	- `matplotlib`
53	- `scikit-learn`	43	- `scikit-learn`
54	- `scikit-image`	44	- `scikit-image`
55	- `tensorflow-gpu >=1.14,<2`	45	- `tensorflow-gpu >=1.14,<2`
56	- `pydensecrf`	46	- `pydensecrf`
57	- `pandas`	47	- `pandas`
58	- `wget`	48	- `wget`
59		49
60	The following command will install the dependencies mentioned	50	The following command will install the dependencies mentioned
61	```	51	```
62	pip install "DigiPathAI[gpu]"	52	pip install "DigiPathAI[gpu]"
63	```	53	```
64		54
65	Both installation methods install the same package, just different dependencies. Even if you had installed using the earlier command, you can install the rest of the dependencies manually.	55	Both installation methods install the same package, just different dependencies. Even if you had installed using the earlier command, you can install the rest of the dependencies manually.
66		56
67	# Usage	57	# Usage
68	## Local server	58	## Local server
69	Traverse to the directory containing the openslide images and run the following command.	59	Traverse to the directory containing the openslide images and run the following command.
70	```	60	```
71	digipathai <host: localhost (default)> <port: 8080 (default)>	61	digipathai <host: localhost (default)> <port: 8080 (default)>
72	```	62	```
73		63
74	## Python API usage	64	## Python API usage
75	The application also has an API which can be used within python to perform the segmentation.	65	The application also has an API which can be used within python to perform the segmentation.
76	```	66	```
77	from DigiPathAI.Segmentation import getSegmentation	67	from DigiPathAI.Segmentation import getSegmentation
78		68
79	prediction = getSegmentation(img_path,	69	prediction = getSegmentation(img_path,
80	patch_size = 256,	70	patch_size = 256,
81	stride_size = 128,	71	stride_size = 128,
82	batch_size = 32,	72	batch_size = 32,
83	quick = True,	73	quick = True,
84	tta_list = None,	74	tta_list = None,
85	crf = False,	75	crf = False,
86	save_path = None,	76	save_path = None,
87	status = None)	77	status = None)
88	```	78	```
89		79
90	# Contact	80	# Contact
91	- Avinash Kori (koriavinash1@gmail.com)	81	- Avinash Kori (koriavinash1@gmail.com)
92	- Haran Rajkumar (haranrajkumar97@gmail.com)	82	- Haran Rajkumar (haranrajkumar97@gmail.com)
93		83
94	[![ko-fi](https://www.ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/M4M132RPG)	84	[![ko-fi](https://www.ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/M4M132RPG)
95		85