mednet.data.classify.visceral¶
VISCERAL dataset for 3D organ classification (only lungs and bladders).
Database reference: [JdTMK+16]
Data specifications:
Raw data input (on disk):
NIfTI volumes
resolution: 16x16x16 pixels - Loaded samples are not full scans but 16x16x16 volumes of organs.
Output image:
Transforms:
Load raw NIfTI with torchio
Clamp and Rescale intensity
Convert to torch tensor
Final specifications
32-bit floats, cubes 16x16x16 pixels
targets: 0 (bladder), 1 (lung)
This module contains the base declaration of common data modules and raw-data loaders for this database. All configured splits inherit from this definition.
Module Attributes
Pythonic name of this database. |
|
Key to search for in the configuration file for the root directory of this database. |
Classes
|
VISCERAL DataModule for 3D organ binary classification. |
A specialized raw-data-loader for the VISCERAL database. |
- mednet.data.classify.visceral.DATABASE_SLUG = 'visceral'¶
Pythonic name of this database.
- mednet.data.classify.visceral.CONFIGURATION_KEY_DATADIR = 'datadir.visceral'¶
Key to search for in the configuration file for the root directory of this database.
- class mednet.data.classify.visceral.RawDataLoader[source]¶
Bases:
RawDataLoader
A specialized raw-data-loader for the VISCERAL database.
- class mednet.data.classify.visceral.DataModule(split_path)[source]¶
Bases:
CachingDataModule
VISCERAL DataModule for 3D organ binary classification.
- Parameters:
split_path (
Path
|Traversable
) – Path or traversable (resource) with the JSON split description to load.