Skip to main content

High quality model for lungs segmentation.

Project description

lungs_segmentation

Automated lung segmentation in chest-x ray

https://habrastorage.org/webt/vk/jv/8r/vkjv8rjd04f1oicbczq5hyadhv0.png

Train pipeline: https://github.com/alimbekovKZ/lungs_segmentation_train

Installation

pip install lungs-segmentation

Example inference

Jupyter notebook with the example: Open In Colab

WebApp

https://lungssegmentation.herokuapp.com/

Models weights

model best dice Mb
resnet34 0.9657 103.4
densenet121 0.9655 62.8

Usage

Code example for resnet34:

from lungs_segmentation.pre_trained_models import create_model
import lungs_segmentation.inference as inference

model = create_model("resnet34")
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.to(device)

plt.figure(figsize=(20,40))
plt.subplot(1,1,1)
image, mask = inference.inference(model,'739px-Chest_Xray_PA_3-8-2010.png', 0.2)
plt.imshow(inference.img_with_masks( image, [mask[0], mask[1]], alpha = 0.1))

Results on data from the Internet

resnet34

https://habrastorage.org/webt/e3/mb/kc/e3mbkcxsmos6q4jlw5-tybudzji.png

densenet121

https://habrastorage.org/webt/ef/01/zo/ef01zo2g2qgsux8ses4keg4g8is.png

Authors

Renat Alimbekov, Ivan Vassilenko, Abylaikhan Turlassov

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

lungs_segmentation-1.1.2.tar.gz (15.1 kB view details)

Uploaded Source

Built Distribution

lungs_segmentation-1.1.2-py2.py3-none-any.whl (16.5 kB view details)

Uploaded Python 2Python 3

File details

Details for the file lungs_segmentation-1.1.2.tar.gz.

File metadata

  • Download URL: lungs_segmentation-1.1.2.tar.gz
  • Upload date:
  • Size: 15.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.28.1 CPython/3.7.3

File hashes

Hashes for lungs_segmentation-1.1.2.tar.gz
Algorithm Hash digest
SHA256 5406eafce99a60a938ab7ad900148508dac51ba269cefc938311ef814a57064f
MD5 0f0ccf07efdbfe2ffe3eab2627d47d8c
BLAKE2b-256 8057b7c4aae8ed7b19ce37bf3223f608bcf323296e618e8d2c1de3f376eaaed0

See more details on using hashes here.

File details

Details for the file lungs_segmentation-1.1.2-py2.py3-none-any.whl.

File metadata

  • Download URL: lungs_segmentation-1.1.2-py2.py3-none-any.whl
  • Upload date:
  • Size: 16.5 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.28.1 CPython/3.7.3

File hashes

Hashes for lungs_segmentation-1.1.2-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 890b8c0c3fd37d2b3e7ada13bc2fda5955ece4c004691d99cb3451fe4e527b06
MD5 ca872c89ecac23933754d2e90cd0a3a4
BLAKE2b-256 6fd7623a222151a50c2b3034c4a25fb036355b0959bdbb95e44e638dc90614e3

See more details on using hashes here.

Supported by

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