Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929210923155456 |
|---|---|
| author | Chen, Jiamin Li, Xuhong Xu, Yanwu Du, Mengnan Xiong, Haoyi |
| author_facet | Chen, Jiamin Li, Xuhong Xu, Yanwu Du, Mengnan Xiong, Haoyi |
| contents | Medical image segmentation aims to identify and locate abnormal structures in medical images, such as chest radiographs, using deep neural networks. These networks require a large number of annotated images with fine-grained masks for the regions of interest, making pre-training strategies based on classification datasets essential for sample efficiency. Based on a large-scale medical image classification dataset, our work collects explanations from well-trained classifiers to generate pseudo labels of segmentation tasks. Specifically, we offer a case study on chest radiographs and train image classifiers on the CheXpert dataset to identify 14 pathological observations in radiology. We then use Integrated Gradients (IG) method to distill and boost the explanations obtained from the classifiers, generating massive diagnosis-oriented localization labels (DoLL). These DoLL-annotated images are used for pre-training the model before fine-tuning it for downstream segmentation tasks, including COVID-19 infectious areas, lungs, heart, and clavicles. Our method outperforms other baselines, showcasing significant advantages in model performance and training efficiency across various segmentation settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08469 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training Chen, Jiamin Li, Xuhong Xu, Yanwu Du, Mengnan Xiong, Haoyi Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Medical image segmentation aims to identify and locate abnormal structures in medical images, such as chest radiographs, using deep neural networks. These networks require a large number of annotated images with fine-grained masks for the regions of interest, making pre-training strategies based on classification datasets essential for sample efficiency. Based on a large-scale medical image classification dataset, our work collects explanations from well-trained classifiers to generate pseudo labels of segmentation tasks. Specifically, we offer a case study on chest radiographs and train image classifiers on the CheXpert dataset to identify 14 pathological observations in radiology. We then use Integrated Gradients (IG) method to distill and boost the explanations obtained from the classifiers, generating massive diagnosis-oriented localization labels (DoLL). These DoLL-annotated images are used for pre-training the model before fine-tuning it for downstream segmentation tasks, including COVID-19 infectious areas, lungs, heart, and clavicles. Our method outperforms other baselines, showcasing significant advantages in model performance and training efficiency across various segmentation settings. |
| title | Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.08469 |