Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.04828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917859464052736 |
|---|---|
| author | Jin, Ying Zhou, Zhuoran Fang, Haoquan Hwang, Jenq-Neng |
| author_facet | Jin, Ying Zhou, Zhuoran Fang, Haoquan Hwang, Jenq-Neng |
| contents | Medical image understanding requires meticulous examination of fine visual details, with particular regions requiring additional attention. While radiologists build such expertise over years of experience, it is challenging for AI models to learn where to look with limited amounts of training data. This limitation results in unsatisfying robustness in medical image understanding. To address this issue, we propose Diffusion-based Feature Augmentation (DAug), a portable method that improves a perception model's performance with a generative model's output. Specifically, we extend a radiology image to multiple channels, with the additional channels being the heatmaps of regions where diseases tend to develop. A diffusion-based image-to-image translation model was used to generate such heatmaps conditioned on selected disease classes. Our method is motivated by the fact that generative models learn the distribution of normal and abnormal images, and such knowledge is complementary to image understanding tasks. In addition, we propose the Image-Text-Class Hybrid Contrastive learning to utilize both text and class labels. With two novel approaches combined, our method surpasses baseline models without changing the model architecture, and achieves state-of-the-art performance on both medical image retrieval and classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04828 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DAug: Diffusion-based Channel Augmentation for Radiology Image Retrieval and Classification Jin, Ying Zhou, Zhuoran Fang, Haoquan Hwang, Jenq-Neng Computer Vision and Pattern Recognition Medical image understanding requires meticulous examination of fine visual details, with particular regions requiring additional attention. While radiologists build such expertise over years of experience, it is challenging for AI models to learn where to look with limited amounts of training data. This limitation results in unsatisfying robustness in medical image understanding. To address this issue, we propose Diffusion-based Feature Augmentation (DAug), a portable method that improves a perception model's performance with a generative model's output. Specifically, we extend a radiology image to multiple channels, with the additional channels being the heatmaps of regions where diseases tend to develop. A diffusion-based image-to-image translation model was used to generate such heatmaps conditioned on selected disease classes. Our method is motivated by the fact that generative models learn the distribution of normal and abnormal images, and such knowledge is complementary to image understanding tasks. In addition, we propose the Image-Text-Class Hybrid Contrastive learning to utilize both text and class labels. With two novel approaches combined, our method surpasses baseline models without changing the model architecture, and achieves state-of-the-art performance on both medical image retrieval and classification tasks. |
| title | DAug: Diffusion-based Channel Augmentation for Radiology Image Retrieval and Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.04828 |