CheXseg: Combining Expert Annotations with DNN-generated Saliency Maps for X-ray Segmentation
Not on the map. Why?
Abstract (arXiv)
Medical image segmentation models are typically supervised by expert annotations at the pixel-level, which can be expensive to acquire. In this work, we propose a method that combines the high quality of pixel-level expert annotations with the scale of coarse DNN-generated saliency maps for training multi-label semantic segmentation models. We demonstrate the application of our semi-supervised method, which we call CheXseg, on multi-label chest X-ray interpretation. We find that CheXseg improves upon the performance (mIoU) of fully-supervised methods that use only pixel-level expert annotations by 9.7% and weakly-supervised methods that use only DNN-generated saliency maps by 73.1%. Our best method is able to match radiologist agreement on three out of ten pathologies and reduces the overall performance gap by 57.2% as compared to weakly-supervised methods.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 21 Feb 2021.
Builds on
22 of 32 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2016Densely Connected Convolutional Networkscited by 6,691
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
- 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
- 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 312
10 more
- 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
- 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
- 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
- 2019A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domainscited by 33
- 2020Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imagingcited by 32
- 2019Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentationcited by 28
- 2019Testing the robustness of attribution methods for convolutional neural networks in MRI-based Alzheimer's disease classificationcited by 25
- 2019Deep neural network or dermatologist?cited by 20
- 2020Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Imagescited by 15
- 2019Learning to segment images with classification labelscited by 5
Built on by
Citing papers per year: 2021: 2.
2 papers.