mlarray 0.0.26

Array format specialized for Machine Learning with Blosc2 backend and standardized metadata.

tl;dr: Working with large medical or scientific images for machine learning? -> Use MLArray.

MLArray is a purpose-built file format for N-dimensional medical and scientific array data in machine learning workflows. It replaces the usual patchwork of source formats and late-stage conversions to NumPy/Zarr/Blosc2 by layering standardized metadata on top of a Blosc2-backed storage layout, so the same files work reliably across training, analysis, and visualization tools (including Napari and MITK).

Installation

You can install mlarray via pip:

pip install mlarray

To enable the mlarray_convert CLI command, install MLArray with the necessary extra dependencies:

pip install mlarray[all]

Documentaion

See the documentation for the API reference, the metadata schema, usage examples or CLI usage.

Usage

Below are common usage patterns for loading, saving, and working with metadata.

Default usage

import numpy as np
from mlarray import MLArray

array = np.random.random((128, 256, 256))
image = MLArray(array)  # Create MLArray image
image.save("sample.mla")

image = MLArray("sample.mla")  # Loads image

Memory-mapped usage

from mlarray import MLArray
import numpy as np

# read-only, partial access (default)
image = MLArray().open("sample.mla", mmap='r')  
crop = image[10:20, 50:60]  # Read crop

# read/write, partial access
image = MLArray().open("sample.mla", mmap='r+')  
image[10:20, 50:60] *= 5  # Modify crop in memory and disk

# read/write, partial access, create/overwrite
array = np.random.random((128, 256, 256))
image = MLArray().open("sample.mla", shape=array.shape, dtype=array.dtype, mmap='w+')  
image[...] = array  # Modify image in memory and disk

Metadata inspection and manipulation

import numpy as np
from mlarray import MLArray

array = np.random.random((64, 128, 128))
image = MLArray(
    array,
    spacing=(1.0, 1.0, 1.5),
    origin=(10.0, 10.0, 30.0),
    direction=[[1, 0, 0], [0, 1, 0], [0, 0, 1]],
    meta={"patient_id": "123", "modality": "CT"},  # Any image metadata (for example raw DICOM metadata)
)

print(image.spacing)  # [1.0, 1.0, 1.5]
print(image.origin)  # [10.0, 10.0, 30.0]
print(image.meta.image)  # {"patient_id": "123", "modality": "CT"}

image.spacing[1] = 5.3
image.meta.image["study_id"] = "study-001"
image.save("with-metadata.mla")

# Open memory-mapped
image = MLArray().open("with-metadata.mla", mmap='r+')  
image.meta.image["study_id"] = "new-study"  # Modify metadata
image.close()  # Close and save metadata, only necessary to save modified metadata

Copy metadata with overrides

import numpy as np
from mlarray import MLArray

base = MLArray("sample.mla")
array = np.random.random(base.shape)

image = MLArray(
    array,
    spacing=(0.8, 0.8, 1.0),
    copy=base,  # Copies all non-explicitly set arguments from base
)

image.save("copied-metadata.mla")

Standardized metadata usage

import numpy as np
from mlarray import MLArray, Meta

array = np.random.random((64, 128, 128))
image = MLArray(
    array,
    meta=Meta(image={"patient_id": "123", "modality": "CT"}, is_seg=True),  # Add metadata in a pre-defined format
)

print(image.meta.image)  # {"patient_id": "123", "modality": "CT"}
print(image.meta.is_seg)  # True

image.meta.image["study_id"] = "study-001"
image.meta.is_seg = False
image.save("with-metadata.mla")

Patch size variants

Default patch size (192):

from mlarray import MLArray

image = MLArray("sample.mla")
image.save("default-patch.mla")  # Default patch_size is 'default' -> Isotropic patch size of 192 pixels
image.save("default-patch.mla", patch_size='default')

Custom isotropic patch size (512):

from mlarray import MLArray

image = MLArray("sample.mla")
image.save("patch-512.mla", patch_size=512)

Custom non-isotropic patch size:

from mlarray import MLArray

image = MLArray("sample.mla")
image.save("patch-non-iso.mla", patch_size=(128, 192, 256))

Manual chunk/block size:

from mlarray import MLArray

image = MLArray("sample.mla")
image.save("manual-chunk-block.mla", chunk_size=(1, 128, 128), block_size=(1, 32, 32))

Let Blosc2 itself configure chunk/block size:

from mlarray import MLArray

image = MLArray("sample.mla")
# If patch_size, chunk_size and block_size are all None, Blosc2 will auto-configure chunk and block size
image.save("manual-chunk-block.mla", patch_size=None)

CLI

mlarray_header

Print the metadata header from a .mla or .b2nd file.

mlarray_header sample.mla

mlarray_convert

Convert a NIfTI or NRRD file to MLArray and copy metadata.

mlarray_convert sample.nii.gz output.mla

Contributing

Contributions are welcome! Please open a pull request with clear changes and add tests when appropriate.

Acknowledgments

    

This repository is developed and maintained by the Applied Computer Vision Lab (ACVL) of Helmholtz Imaging and the Division of Medical Image Computing at DKFZ.