Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions
Not on the map. Why?
Abstract (arXiv)
The medical datasets are usually faced with the problem of scarcity and data imbalance. Moreover, annotating large datasets for semantic segmentation of medical lesions is domain-knowledge and time-consuming. In this paper, we propose a new object-blend method(short in soft-CP) that combines the Copy-Paste augmentation method for semantic segmentation of medical lesions offline, ensuring the correct edge information around the lession to solve the issue above-mentioned. We proved the method's validity with several datasets in different imaging modalities. In our experiments on the KiTS19[2] dataset, Soft-CP outperforms existing medical lesions synthesis approaches. The Soft-CP augementation provides gains of +26.5% DSC in the low data regime(10% of data) and +10.2% DSC in the high data regime(all of data), In offline training data, the ratio of real images to synthetic images is 3:1.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 42 of its 64 references that are in the map. First posted on arXiv 20 Mar 2022.
Builds on
42 of 64 references.
References · 42
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
- 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
- 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
30 more
- 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
- 2019Kvasir-SEG: A Segmented Polyp Datasetcited by 588
- 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
- 2017Tversky loss function for image segmentation using 3D fully convolutional deep networkscited by 228
- 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 219
- 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
- 2016Gland Segmentation in Colon Histology Images: The GlaS Challenge Contestcited by 203
- 2019The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challengecited by 188
- 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
- 2019Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentationcited by 121
- 2018Modeling Visual Context is Key to Augmenting Object Detection Datasetscited by 106
- 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
- 2018Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentationcited by 76
- 2020Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representationscited by 69
- 2021Semi-supervised Contrastive Learning for Label-efficient Medical Image Segmentationcited by 52
- 2020What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentationcited by 50
- 2017Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networkscited by 42
- 2019Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learningcited by 41
- 2021Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentationcited by 39
- 2020Synthetic Learning: Learn From Distributed Asynchronized Discriminator GAN Without Sharing Medical Image Datacited by 38
- 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
- 2020Vox2Vox: 3D-GAN for Brain Tumour Segmentationcited by 30
- 2019Automated Design of Deep Learning Methods for Biomedical Image Segmentationcited by 27
- 2020Unsupervised Domain Adaptation via CycleGAN for White Matter Hyperintensity Segmentation in Multicenter MR Imagescited by 15
- 2020Medico Multimedia Task at MediaEval 2020: Automatic Polyp Segmentationcited by 14
- 2018A Novel Domain Adaptation Framework for Medical Image Segmentationcited by 9
- 2020Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADEcited by 9
- 2021TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentationcited by 9
- 2017Learning Based Segmentation of CT Brain Images: Application to Post-Operative Hydrocephalic Scanscited by 7
- 2019Healthy versus pathological learning transferability in shoulder muscle MRI segmentation using deep convolutional encoder-decoderscited by 6
Built on by
Citing papers per year: 2022: 2.
2 papers.