# SenNet + HOA - Hacking the Human Vasculature in 3D — Data

来源：https://www.kaggle.com/competitions/blood-vessel-segmentation/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

This competition dataset comprises high-resolution 3D images of several kidneys together with 3D segmentation masks of their vasculature. Your task is to create segmentation masks for the kidney datasets in the test set.

The kidney images were obtained through Hierarchical Phase-Contrast Tomography (HiP-CT) imaging. HiP-CT is an imaging technique that obtains high-resolution (from 1.4 micrometers - 50 micrometers resolution) 3D data from ex vivo organs. See this [Nature Methods](https://www.nature.com/articles/s41592-021-01317-x) article for more information. 


# File and Field Information #

- **train/{dataset}/images** - Contains TIFF scans from several kidney datasets. Each image represents a 2D slice of a 3D volume. The slices run along the z-axis, with files enumerated from top to bottom. (The slices should be stacked vertically or depth-wise, in other words.)
- **train/{dataset}/labels** - Contains blood vessel segmentation masks in TIFF format for the images.
    The **{dataset}** folders comprise the following:
    - `kidney_1_dense` - The whole of a right kidney at 50um resolution. The entire 3D arterial vascular tree has been densely segmented, down to two generations from the glomeruli (i.e. the capillary bed). Uses beamline BM05.
    - `kidney_1_voi` - A high-resolution subset of `kidney_1`, at 5.2um resolution.
    - `kidney_2` - The whole of a kidney from another donor, at 50um resolution. Sparsely segmented (about 65%).
    - `kidney_3_dense` - A portion (500 slices) of a kidney at 50.16um resolution using BM05. Densely segmented. Note that we provide all of the images for `kidney_3` in the `kidney_3_sparse/images` folder. This dataset accordingly has only a `labels` folder.
    - `kidney_3_sparse` - The remainder of the segmentation masks for `kidney_3`. Sparsely segmented (about 85%).
- **test/{dataset}/images** - Contains the TIFF scans for the test set. These scans may or may not use a different beamline or resolution from the scans used in the training set. The names of the datasets are `kidney_5` and `kidney_6`.

- **train_rles.csv** - The run length encoded segmentation masks for images in the training set.
  - `id` - A unique identifier for each slice, in the form `{dataset}_{slice}`.
  - `rle` - The run length encoded mask for this slice.

- **sample_submission.csv** - A sample submission file in the correct format. See the [Evaluation](https://www.kaggle.com/competitions/blood-vessel-segmentation/overview/evaluation) page for more details.

You may find functions to encode and decode the segmentation masks in [this notebook](https://www.kaggle.com/code/paulorzp/run-length-encode-and-decode/script).

Please note that this is a [**Code Competition**](https://www.kaggle.com/competitions/blood-vessel-segmentation/overview/code-requirements). We give a few example images in the `test/` folder to help you author your submissions. These example images are not meant to be representative of the test set with regard to scan resolution, beamline, or other such qualities. When your submission is scored, this example test data will be replaced with the full test set. The full test set contains about 1500 TIFF images.


## **UPDATE ON DATA 11th DEC**

Hi All Kagglers,
It's been great watching the progress these last few weeks. Seeing a few things in the competition and also following the discussion carefully we decided that it makes sense to give some more information about the two hidden datasets i.e. the Public and Private test datasets:

**Public Test:**
Continuous 3D part of a whole human kidney imaged with HiP-CT - Originally scanned at 25.14um/voxel and binned to 50.28um/voxel (bin x2) before segmentation.

**Private Test:**
Continuous 3D part of a whole human kidney imaged with HiP-CT - Originally scanned at 15.77um/voxel binned to 63.08um/voxel (bin x4) before segmentation.

Neither of these kidneys are different parts of ones already in the public dataset, i.e. they are physically different samples. The scanning and reconstruction procedures follow the method described in the original HiP-CT Methods paper (you should read this paper for background), and the manual annotation process is the same as in the benchmark review paper.

We provided the higher resolution 5.2um/voxel VOI, to give some example data of different resolutions as we thought this might be useful.