ZIPLIDC-IDRI预处理项目 362.04KB

qq_67696694

资源文件列表:

LIDC-IDRI-Preprocessing-master.zip 大约有30个文件
  1. LIDC-IDRI-Preprocessing-master/
  2. LIDC-IDRI-Preprocessing-master/LIDC-IDRI/
  3. LIDC-IDRI-Preprocessing-master/LIDC-IDRI/.gitignore
  4. LIDC-IDRI-Preprocessing-master/README.md 5.31KB
  5. LIDC-IDRI-Preprocessing-master/config_file_create.py 1.49KB
  6. LIDC-IDRI-Preprocessing-master/data/
  7. LIDC-IDRI-Preprocessing-master/data/Clean/
  8. LIDC-IDRI-Preprocessing-master/data/Clean/.gitkeep
  9. LIDC-IDRI-Preprocessing-master/data/Clean/Image/
  10. LIDC-IDRI-Preprocessing-master/data/Clean/Image/.gitkeep
  11. LIDC-IDRI-Preprocessing-master/data/Clean/Mask/
  12. LIDC-IDRI-Preprocessing-master/data/Clean/Mask/.gitkeep
  13. LIDC-IDRI-Preprocessing-master/data/Image/
  14. LIDC-IDRI-Preprocessing-master/data/Image/.gitkeep
  15. LIDC-IDRI-Preprocessing-master/data/Mask/
  16. LIDC-IDRI-Preprocessing-master/data/Mask/.gitkeep
  17. LIDC-IDRI-Preprocessing-master/data/Meta/
  18. LIDC-IDRI-Preprocessing-master/data/Meta/.gitkeep
  19. LIDC-IDRI-Preprocessing-master/data/Meta/meta_info.csv 86B
  20. LIDC-IDRI-Preprocessing-master/figures/
  21. LIDC-IDRI-Preprocessing-master/figures/output_segment.png 185.5KB
  22. LIDC-IDRI-Preprocessing-master/lung.conf 269B
  23. LIDC-IDRI-Preprocessing-master/meta_info.csv 1.54MB
  24. LIDC-IDRI-Preprocessing-master/notebook/
  25. LIDC-IDRI-Preprocessing-master/notebook/.ipynb_checkpoints/
  26. LIDC-IDRI-Preprocessing-master/notebook/.ipynb_checkpoints/make_label-checkpoint.ipynb 23.81KB
  27. LIDC-IDRI-Preprocessing-master/notebook/make_label.ipynb 23.81KB
  28. LIDC-IDRI-Preprocessing-master/prepare_dataset.py 8.18KB
  29. LIDC-IDRI-Preprocessing-master/requirements.txt 39B
  30. LIDC-IDRI-Preprocessing-master/utils.py 2.3KB

资源介绍:

该项目是基于LIDC-IDRI数据集，用于图像分割的数据预处理项目代码
# LIDC Preprocessing with Pylidc library [Medium Link](https://medium.com/@jaeho3690/how-to-start-your-very-first-lung-cancer-detection-project-using-python-part-1-3ab490964aae) This repository would preprocess the LIDC-IDRI dataset. We use pylidc library to save nodule images into an .npy file format. The code file structure is as below ``` +-- LIDC-IDRI | # This file should contain the original LIDC dataset +-- data | # This file contains the preprocessed data | |-- _Clean | +-- Image | +-- Mask | |-- Image | +-- LIDC-IDRI-0001 | +-- LIDC-IDRI-0002 | +-- ... | |-- Mask | +-- LIDC-IDRI-0001 | +-- LIDC-IDRI-0002 | +-- ... | |-- Meta | +-- meta.csv +-- figures | # Save figures here +-- notebook | # This notebook file edits the meta.csv file to make indexing easier +-- config_file_create.py | # Creates configuration file. You can edit the hyperparameters of the Pylidc library here +-- prepare_dataset.py | # Run this file to preprocess the LIDC-IDRI dicom files. Results would be saved in the data folder +-- utils.py # Utility script ``` ![Segmented Image](/figures/output_segment.png) ## 1.Download LIDC-IDRI dataset First you would have to download the whole LIDC-IDRI [dataset](https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI). On the website, you will see the Data Acess section. You would need to click Search button to specify the images modality. I clicked on CT only and downloaded total of 1010 patients. ## 2. Set up pylidc library You would need to set up the pylidc library for preprocessing. There is an instruction in the [documentation](https://pylidc.github.io/install.html). Make sure to create the configuration file as stated in the instruction. Right now I am using library version 0.2.1 ## 3. Explanation for each python file ```bash python config_file_create.py ``` This python script contains the configuration setting for the directories. Change the directories settings to where you want to save your output files. Without modification, it will automatically save the preprocessed file in the data folder. Running this script will create a configuration file 'lung.conf' This utils.py script contains function to segment the lung. Segmenting the lung and nodule are two different things. Segmenting the lung leaves the lung region only, while segmenting the nodule is finding prosepctive lung nodule regions in the lung. Don't get confused. ```bash python prepare_dataset.py ``` This python script will create the image, mask files and save them to the data folder. The script will also create a meta_info.csv file containing information about whether the nodule is cancerous. In the LIDC Dataset, each nodule is annotated at a maximum of 4 doctors. Each doctors have annotated the malignancy of each nodule in the scale of 1 to 5. I have chosed the median high label for each nodule as the final malignancy. The meta_csv data contains all the information and will be used later in the classification stage. This prepare_dataset.py looks for the lung.conf file. The configuration file should be in the same directory. Running this script will output .npy files for each slice with a size of 512*512 To make a train/ val/ test split run the jupyter file in notebook folder. This will create an additional clean_meta.csv, meta.csv containing information about the nodules, train/val/test split. A nodule may contain several slices of images. Some researches have taken each of these slices indpendent from one another. However, I believe that these image slices should not be seen as independent from adjacent slice image. Thus, I have tried to maintain a same set of nodule images to be included in the same split. Although this apporach reduces the accuracy of test results, it seems to be the honest approach. ## 4. Data folder the data folder stores all the output images,masks. inside the data folder there are 3 subfolders. ### 1. Clean The Clean folder contains two subfolders. Image and Mask folders. Some patients don't have nodules. In the actual implementation, a person will have more slices of image without a nodule. To evaluate our generalization on real world application, we save lung images without nodules for testing purpose. These images will be used in the test set. ### 2. Image The Image folder contains the segmented lung .npy folders for each patient's folder ### 3. Mask The Mask folder contains the mask files for the nodule. ### 4. Meta The Meta folder contains the meta.csv file. The csv file contains information of each slice of image: Malignancy, whether the image should be used in train/val/test for the whole process, etc. ## 5. Contributing and Acknowledgement I started this Lung cancer detection project a year ago. I was really a newbie to python. I didn't even understand what a directory setting is at the time! However, I had to complete this project for some personal reasons. I looked through google and other githubs. But most of them were too hard to understand and the code itself lacked information. I hope my codes here could help other researchers first starting to do lung cancer detection projects. Please give a star if you found this repository useful. here is the link of github where I learned a lot from. Some of the codes are sourced from below. 1. https://github.com/mikejhuang/LungNoduleDetectionClassification
100+评论
captcha
    相关资源
    类型标题大小时间
    ZIPWin11可用的鼠标模拟多点触摸软件4.28MB9月前
    ZIP基于Java的游泳馆管理系统12.17MB9月前
    ZIP“爱听”音乐网站(编号：54580356)java后端+vue前端+数据库sql15.2MB9月前
    ZIP深海王国小学生都能做的APP？AI伴侣2.65版本16.52MB9月前
    ZIPCityEngine CE规则 高架导轨39.26KB9月前
    ZIPWeChatAuto,电脑微信辅助，微信自动发消息764.83KB9月前
    ZIPvue3大屏展示炫酷效果4.82MB9月前
    ZIPQT仿PVZ植物大战僵尸5.05MB9月前