Skip to main content

A package to compute different segmentation metrics for Medical images.

Project description

Segmentaion Metrics Package DOI

GitHub release (latest SemVer) publish workflow status codecov test workflow status

This is a simple package to compute different metrics for Medical image segmentation(images with suffix .mhd, .mha, .nii, .nii.gz or .nrrd), and write them to csv file.

Summary

To assess the segmentation performance, there are several different methods. Two main methods are volume-based metrics and distance-based metrics.

Metrics included

This library computes the following performance metrics for segmentation:

Voxel based metrics

  • Dice (F-1)
  • Jaccard
  • Precision
  • Recall
  • False positive rate
  • False negtive rate
  • Volume similarity

Surface Distance based metrics (with spacing as default)

  • Hausdorff distance
  • Hausdorff distance 95% percentile
  • Mean (Average) surface distance
  • Median surface distance
  • Std surface distance

Installation

$ pip install seg-metrics

Usage

At first, import the package:

import seg_metrics.seg_metrics as sg

Evaluate two batch of images with same filenames from two different folders

labels = [0, 4, 5 ,6 ,7 , 8]
gdth_path = 'data/gdth'  # this folder saves a batch of ground truth images
pred_path = 'data/pred'  # this folder saves the same number of prediction images
csv_file = 'metrics.csv'  # results will be saved to this file and prented on terminal as well. If not set, results 
# will only be shown on terminal.

metrics = sg.write_metrics(labels=labels[1:],  # exclude background
                  gdth_path=gdth_path,
                  pred_path=pred_path,
                  csv_file=csv_file)
print(metrics)

After runing the above codes, you can get a dict metrics which contains all the metrics. Also you can find a .csv file containing all metrics in the same directory.

Evaluate two images

labels = [0, 4, 5 ,6 ,7 , 8]
gdth_file = 'data/gdth.mhd'  # ground truth image full path
pred_file = 'data/pred.mhd'  # prediction image full path
csv_file = 'metrics.csv'

metrics = sg.write_metrics(labels=labels[1:],  # exclude background
                  gdth_path=gdth_file,
                  pred_path=pred_file,
                  csv_file=csv_file)

Evaluate two images with specific metrics

labels = [0, 4, 5 ,6 ,7 , 8]
gdth_file = 'data/gdth.mhd'
pred_file = 'data/pred.mhd'
csv_file = 'metrics.csv'

metrics = sg.write_metrics(labels=labels[1:],  # exclude background if needed
                  gdth_path=gdth_file,
                  pred_path=pred_file,
                  csv_file=csv_file,
                  metrics=['dice', 'hd'])
# for only one metric
metrics = sg.write_metrics(labels=labels[1:],  # exclude background if needed
                  gdth_path=gdth_file,
                  pred_path=pred_file,
                  csv_file=csv_file,
                  metrics='msd')  

By passing the following parameters to select specific metrics.

- dice:     Dice (F-1)
- jaccard:  Jaccard
- precision:    Precision
- recall:   Recall
- fpr:      False positive rate
- fnr:      False negtive rate
- vs:       Volume similarity

- hd:       Hausdorff distance
- hd95:     Hausdorff distance 95% percentile
- msd:      Mean (Average) surface distance
- mdsd:     Median surface distance
- stdsd:    Std surface distance

For example:

labels = [1]
gdth_file = 'data/gdth.mhd'
pred_file = 'data/pred.mhd'
csv_file = 'metrics.csv'

metrics = sg.write_metrics(labels, gdth_file, pred_file, csv_file, metrics=['dice', 'hd95'])
dice = metrics['dice']
hd95 = metrics['hd95']

Evaluate two images in memory instead of in disk

Note:

  1. The two images must be both numpy.ndarray or SimpleITK.Image.
  2. Input arguments are different. Please use gdth_img and pred_img instead of gdth_path and pred_path.
  3. If evaluating numpy.ndarray, the default spacing for all dimensions would be 1.0 for distance based metrics.
  4. If you want to evaluate numpy.ndarray with specific spacing, please convert numpy array to SimpleITK.Image manually at first.
labels = [0, 1, 2]
gdth_img = np.array([0,0,1,1,2])
pred_img = np.array([0,0,1,2,2])
csv_file = 'metrics.csv'

metrics = sg.write_metrics(labels=labels[1:],  # exclude background if needed
                  gdth_img=gdth_img,
                  pred_img=pred_img,
                  csv_file=csv_file,
                  metrics=['dice', 'hd'])
# for only one metrics
metrics = sg.write_metrics(labels=labels[1:],  # exclude background if needed
                  gdth_img=gdth_img,
                  pred_img=pred_img,
                  csv_file=csv_file,
                  metrics='msd')  

If this repository helps you in anyway, show your love ❤️ by putting a ⭐ on this project. I would also appreciate it if you cite the package in your publication.

#Bibtex

@misc{Jingnan,
    title  = {A package to compute segmentation metrics: seg-metrics},
    author = {Jingnan Jia},
    url    = {https://github.com/Ordgod/segmentation_metrics}, 
    year   = {2020}, 
    doi = {10.5281/zenodo.3995075}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

seg_metrics-1.0.13.tar.gz (7.9 kB view hashes)

Uploaded Source

Built Distribution

seg_metrics-1.0.13-py3-none-any.whl (8.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page