S³-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation

2023/10/25 by Kangxian Xie, Xie, Kangxian, Siyu Huang +7
Computer Science · Medicine · #AI in cancer detection #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Radiomics and Machine Learning in Medical Imaging

paper · pdf · doi:10.48550/arxiv.2310.16783

openalex publication_date 2023/10/25 · openalex created_date 2023/10/28 · openalex updated_date 2026/07/28

Abstract

Deep-learning models have been successful in biomedical image segmentation. To generalize for real-world deployment, test-time augmentation (TTA) methods are often used to transform the test image into different versions that are hopefully closer to the training domain. Unfortunately, due to the vast diversity of instance scale and image styles, many augmented test images produce undesirable results, thus lowering the overall performance. This work proposes a new TTA framework, S³-TTA, which selects the suitable image scale and style for each test image based on a transformation consistency metric. In addition, S³-TTA constructs an end-to-end augmentation-segmentation joint-training pipeline to ensure a task-oriented augmentation. On public benchmarks for cell and lung segmentation, S³-TTA demonstrates improvements over the prior art by 3.4% and 1.3%, respectively, by simply augmenting the input data in testing phase.

Related

• TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation
• Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentation
• Towards Clinician-Preferred Segmentation: Leveraging Human-in-the-Loop for Test Time Adaptation in Medical Image Segmentation
• Test-time generative augmentation for medical image segmentation
• PASS:Test-Time Prompting to Adapt Styles and Semantic Shapes in Medical Image Segmentation