Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets

2026-02-03

International Conference on Medical Image Computing and Computer-Assisted Intervention

AI Summary

This study addresses the challenge of limited clinical annotations in multi-organ segmentation by systematically evaluating four cross-image data augmentation strategies—CutMix, CarveMix, ObjectAug, and AnatoMix—integrated with conventional augmentation techniques within the nnUNet framework. Despite its semantically implausible image composition, CutMix demonstrates consistently strong and robust performance improvements, outperforming more sophisticated augmentation methods. Experimental results show that CutMix, CarveMix, and AnatoMix increase the average Dice score by 4.9%, 2.0%, and 1.9%, respectively, with further gains observed when combined with traditional augmentations. These findings underscore the efficacy and practicality of simple cross-image augmentation approaches in medical image segmentation tasks.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Multi-organ segmentation is a widely applied clinical routine and automated organ segmentation tools dramatically improve the pipeline of the radiologists. Recently, deep learning (DL) based segmentation models have shown the capacity to accomplish such a task. However, the training of the segmentation networks requires large amount of data with manual annotations, which is a major concern due to the data scarcity from clinic. Working with limited data is still common for researches on novel imaging modalities. To enhance the effectiveness of DL models trained with limited data, data augmentation (DA) is a crucial regularization technique. Traditional DA (TDA) strategies focus on basic intra-image operations, i.e. generating images with different orientations and intensity distributions. In contrast, the interimage and object-level DA operations are able to create new images from separate individuals. However, such DA strategies are not well explored on the task of multi-organ segmentation. In this paper, we investigated four possible inter-image DA strategies: CutMix, CarveMix, ObjectAug and AnatoMix, on two organ segmentation datasets. The result shows that CutMix, CarveMix and AnatoMix can improve the average dice score by 4.9, 2.0 and 1.9, compared with the state-of-the-art nnUNet without DA strategies. These results can be further improved by adding TDA strategies. It is revealed in our experiments that Cut-Mix is a robust but simple DA strategy to drive up the segmentation performance for multi-organ segmentation, even when CutMix produces intuitively'wrong'images. Our implementation is publicly available for future benchmarks.

Problem

• multi-organ segmentation
• limited data
• data augmentation
• deep learning
• medical image analysis

Innovation

• CutMix
• data augmentation
• multi-organ segmentation
• limited data
• inter-image augmentation