# Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentation

arXiv: https://arxiv.org/abs/2510.23241 · HTML: https://mlsanity.com/paper/2510.23241/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 50 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 30 of 40)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation](https://mlsanity.com/paper/2206.08023/) (2022)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation](https://mlsanity.com/paper/2303.09975/) (2023)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)
- [HeMIS: Hetero-Modal Image Segmentation](https://mlsanity.com/paper/1607.05194/) (2016)
- [Shortformer: Better Language Modeling using Shorter Inputs](https://mlsanity.com/paper/2012.15832/) (2020)
- [MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation](https://mlsanity.com/paper/2303.14444/) (2023)
- [Is segmentation uncertainty useful?](https://mlsanity.com/paper/2103.16265/) (2021)
- [The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models](https://mlsanity.com/paper/2108.06084/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classification](https://mlsanity.com/paper/2009.13698/) (2020)
- [Extending nnU-Net is all you need](https://mlsanity.com/paper/2208.10791/) (2022)
- [Medical-based Deep Curriculum Learning for Improved Fracture Classification](https://mlsanity.com/paper/2004.00482/) (2020)
- [Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis](https://mlsanity.com/paper/2203.02202/) (2022)
- [EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training](https://mlsanity.com/paper/2405.08768/) (2024)
- [CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance](https://mlsanity.com/paper/1807.10819/) (2018)
- [RECLIP: Resource-efficient CLIP by Training with Small Images](https://mlsanity.com/paper/2304.06028/) (2023)

## Built on by (most cited first, 1 of 1)

- [NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Multi-Exposure Image Fusion in Dynamic Scenes (Track 2)](https://mlsanity.com/paper/2604.09030/) (2026)

## Abstract (arXiv)

In this work, we introduce Progressive Growing of Patch Size, an automatic curriculum learning approach for 3D medical image segmentation. Our approach progressively increases the patch size during model training, resulting in an improved class balance for smaller patch sizes and accelerated convergence of the training process. We evaluate our curriculum approach in two settings: a resource-efficient mode and a performance mode, both regarding Dice score performance and computational costs across 15 diverse and popular 3D medical image segmentation tasks. The resource-efficient mode matches the Dice score performance of the conventional constant patch size sampling baseline with a notable reduction in training time to only 44%. The performance mode improves upon constant patch size segmentation results, achieving a statistically significant relative mean performance gain of 1.28% in Dice Score. Remarkably, across all 15 tasks, our proposed performance mode manages to surpass the constant patch size baseline in Dice Score performance, while simultaneously reducing training time to only 89%. The benefits are particularly pronounced for highly imbalanced tasks such as lesion segmentation tasks. Rigorous experiments demonstrate that our performance mode not only improves mean segmentation performance but also reduces performance variance, yielding more trustworthy model comparison. Furthermore, our findings reveal that the proposed curriculum sampling is not tied to a specific architecture but represents a broadly applicable strategy that consistently boosts performance across diverse segmentation models, including UNet, UNETR, and SwinUNETR. In summary, we show that this simple yet elegant transformation on input data substantially improves both Dice Score performance and training runtime, while being compatible across diverse segmentation backbones.