Background and objective

Processing of medical images such as MRI or CT presents different challenges compared to RGB images typically used in computer vision. These include a lack of labels for large datasets, high computational costs, and the need of metadata to describe the physical properties of voxels. Data augmentation is used to artificially increase the size of the training datasets. Training with image subvolumes or patches decreases the need for computational power. Spatial metadata needs to be carefully taken into account in order to ensure a correct alignment and orientation of volumes.

Methods

We present TorchIO, an open-source Python library to enable efficient loading, preprocessing, augmentation and patch-based sampling of medical images for deep learning. TorchIO follows the style of PyTorch and integrates standard medical image processing libraries to efficiently process images during training of neural networks. TorchIO transforms can be easily composed, reproduced, traced and extended. Most transforms can be inverted, making the library suitable for test-time augmentation and estimation of aleatoric uncertainty in the context of segmentation. We provide multiple generic preprocessing and augmentation operations as well as simulation of MRI-specific artifacts.

Results

Source code, comprehensive tutorials and extensive documentation for TorchIO can be found at http://torchio.rtfd.io/. The package can be installed from the Python Package Index (PyPI) running pip install torchio. It includes a command-line interface which allows users to apply transforms to image files without using Python. Additionally, we provide a graphical user interface within a TorchIO extension in 3D Slicer to visualize the effects of transforms.

Conclusion

TorchIO was developed to help researchers standardize medical image processing pipelines and allow them to focus on the deep learning experiments. It encourages good open-science practices, as it supports experiment reproducibility and is version-controlled so that the software can be cited precisely. Due to its modularity, the library is compatible with other frameworks for deep learning with medical images.

中文翻译：

---

TorchIO：一个 Python 库，用于在深度学习中高效加载、预处理、增强和基于补丁的医学图像采样

背景和目的

与计算机视觉中通常使用的 RGB 图像相比，处理 MRI 或 CT 等医学图像提出了不同的挑战。这些包括缺乏大型数据集的标签、高计算成本以及需要元数据来描述体素的物理特性。数据增强用于人为地增加训练数据集的大小。使用图像子卷或补丁进行训练减少了对计算能力的需求。需要仔细考虑空间元数据，以确保卷的正确对齐和方向。

方法

我们介绍 TorchIO，这是一个开源 Python 库，可以为深度学习实现医学图像的高效加载、预处理、增强和基于补丁的采样。TorchIO 沿用了 PyTorch 的风格，集成了标准的医学图像处理库，可以在神经网络的训练过程中高效处理图像。TorchIO 转换可以轻松组合、复制、跟踪和扩展。大多数变换都可以反转，使库适用于测试时间增强和分割上下文中任意不确定性的估计。我们提供多种通用预处理和增强操作以及 MRI 特定伪影的模拟。

结果

TorchIO 的源代码、综合教程和大量文档可以在 http://torchio.rtfd.io/ 上找到。该包可以从运行pip install torchio的 Python Package Index (PyPI)安装。它包括一个命令行界面，允许用户在不使用 Python 的情况下将转换应用于图像文件。此外，我们在 3D Slicer 中的 TorchIO 扩展中提供了一个图形用户界面，以可视化变换的效果。

结论

TorchIO 的开发旨在帮助研究人员标准化医学图像处理流程，并使他们能够专注于深度学习实验。它鼓励良好的开放科学实践，因为它支持实验可重复性并且受版本控制，因此可以准确地引用软件。由于其模块化，该库与其他医学图像深度学习框架兼容。