# High Resolution Medical Image Analysis with Spatial Partitioning

arXiv: https://arxiv.org/abs/1909.03108 · HTML: https://mlsanity.com/paper/1909.03108/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Sequence Parallelism: Long Sequence Training from System Perspective](https://mlsanity.com/paper/2105.13120/) (2021)
- [PartIR: Composing SPMD Partitioning Strategies for Machine Learning](https://mlsanity.com/paper/2401.11202/) (2024)
- [UltraMNIST Classification: A Benchmark to Train CNNs for Very Large Images](https://mlsanity.com/paper/2206.12681/) (2022)
- [Distributing Deep Learning Hyperparameter Tuning for 3D Medical Image Segmentation](https://mlsanity.com/paper/2110.15884/) (2021)
- [Deep Learning-Based Prediction of Molecular Tumor Biomarkers from H&E: A Practical Review](https://mlsanity.com/paper/2211.14847/) (2022)
- [Scalable Artificial Intelligence for Science: Perspectives, Methods and Exemplars](https://mlsanity.com/paper/2406.17812/) (2024)
- [DDU-Net: A Domain Decomposition-Based CNN for High-Resolution Image Segmentation on Multiple GPUs](https://mlsanity.com/paper/2407.21266/) (2024)
- [L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training](https://mlsanity.com/paper/2208.08711/) (2022)
- [TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling](https://mlsanity.com/paper/2608.15211/) (2026)

## Abstract (arXiv)

Medical images such as 3D computerized tomography (CT) scans and pathology images, have hundreds of millions or billions of voxels/pixels. It is infeasible to train CNN models directly on such high resolution images, because neural activations of a single image do not fit in the memory of a single GPU/TPU, and naive data and model parallelism approaches do not work. Existing image analysis approaches alleviate this problem by cropping or down-sampling input images, which leads to complicated implementation and sub-optimal performance due to information loss. In this paper, we implement spatial partitioning, which internally distributes the input and output of convolutional layers across GPUs/TPUs. Our implementation is based on the Mesh-TensorFlow framework and the computation distribution is transparent to end users. With this technique, we train a 3D Unet on up to 512 by 512 by 512 resolution data. To the best of our knowledge, this is the first work for handling such high resolution images end-to-end.