https://github.com/shenggan/bccd_dataset

BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.
https://github.com/shenggan/bccd_dataset

cell-detection dataset detection medical-imaging

Last synced: 5 days ago
JSON representation

BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.

• Host: GitHub
• URL: https://github.com/shenggan/bccd_dataset
• Owner: Shenggan
• License: mit
• Created: 2017-12-07T11:54:25.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2021-09-16T17:47:24.000Z (over 3 years ago)
• Last Synced: 2025-01-23T02:06:58.954Z (12 days ago)
• Topics: cell-detection, dataset, detection, medical-imaging
• Language: Python
• Homepage:
• Size: 7.22 MB
• Stars: 386
• Watchers: 11
• Forks: 211
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# BCCD Dataset

BCCD Dataset is a small-scale dataset for blood cells detection.

Thanks the original data and annotations from [cosmicad](https://github.com/cosmicad/dataset) and [akshaylamba](https://github.com/akshaylamba/all_CELL_data). The original dataset is re-organized into VOC format. BCCD Dataset is under *[MIT licence](./LICENSE)*.

You can [download](https://github.com/Shenggan/BCCD_Dataset/releases) the `.rec` format for mxnet directly. The `.rec` file can be load by [mxnet.image.ImageDetIter](http://mxnet.incubator.apache.org/api/python/image/image.html?highlight=imagedetiter#mxnet.image.ImageDetIter).

### Data preparation

Data preparation is important to use machine learning. In this project, the Faster R-CNN algorithm from [keras-frcnn](https://github.com/kbardool/keras-frcnn) for Object Detection is used.

From this [dataset](https://github.com/Shenggan/BCCD_Dataset), [nicolaschen1](https://github.com/nicolaschen1) developed two Python scripts to make preparation data (CSV file and images) for recognition of abnormalities in blood cells on medical images.

- export.py: it creates the file "test.csv" with all data needed: filename, class_name, x1,y1,x2,y2.

- plot.py: it plots the boxes for each image and save it in a new directory.

#### Overview of dataset

* You can see a example of the labeled cell image.

  We have three kind of labels :

  * RBC (Red Blood Cell)

  * WBC (White Blood Cell)

  * Platelets (血小板)

  ![example](./example.jpg)

* The structure of the `BCCD_dataset`

  ```

  ├── BCCD

  │   ├── Annotations

  │   │       └── BloodImage_00XYZ.xml (364 items)

  │   ├── ImageSets       # Contain four Main/*.txt which split the dataset

  │   └── JPEGImages

  │       └── BloodImage_00XYZ.jpg (364 items)

  ├── dataset

  │   └── mxnet           # Some preprocess scripts for mxnet

  ├── scripts

  │   ├── split.py        # A script to generate four .txt in ImageSets

  │   └── visualize.py    # A script to generate labeled img like example.jpg

  ├── example.jpg         # A example labeled img generated by visualize.py

  ├── LICENSE

  └── README.md

  ```

* The  `JPEGImages`:

  * **Image Type** : *jpeg(JPEG)*

  * **Width** x **Height** : *640 x 480*

* The `Annotations` : The VOC format `.xml` for Object Detection, automatically generate by the label tools. Below is an example of `.xml` file.

  ```xml

  

  	JPEGImages

  	BloodImage_00000.jpg

  	/home/pi/detection_dataset/JPEGImages/BloodImage_00000.jpg

  	

  		Unknown

  	

  	

  		640

  		480

  		3

  	

  	0

  	

  		WBC

  		Unspecified

  		0

  		0

  		

  			260

  			177

  			491

  			376

  		

  	

      ...

  	

  		...

  	

  

  ```