Skip to content

Using basic image segmentation and Mask-RCNN to segment nuclei in the Kaggle Data Science Bowl 2018.

Notifications You must be signed in to change notification settings

sdw95927/kaggle_data_science_bowl_2018

Repository files navigation

kaggle_data_science_bowl_2018

This contains our solutions for 2018 data science bowl hold by Kaggle. The task is to do nuclei segmentation across multiple kinds of cell images.

Nuclei Segmentation Summary

Our team ranked 407 out of ~3800 teams, with final score 0.436. We first tried basic image segmentation without any deep learning. Then tried "semantic segmentation" SegNet, a Fully-Convolutional Neural Network. Finally we implemented Mask-RCNN, and got the best score among our tryings. We did not try Unet, which may yield a higher score.

Tryings

The repository includes:

  • Basic image processing method using watershed (Visualize_data_and_basic_segmentation.ipynb)
  • Implementation of Mask-RCNN (Mask_RCNN.ipynb)
  • Source code of segmentation functions (segmentationFunctions.py)

Requirements:

About

Using basic image segmentation and Mask-RCNN to segment nuclei in the Kaggle Data Science Bowl 2018.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published