Lightening Anything in Medical Images
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917694886903808 |
|---|---|
| author | Fei, Ben Li, Yixuan Yang, Weidong Gao, Hengjun Xu, Jingyi Ma, Lipeng Yang, Yatian Zhou, Pinghong |
| author_facet | Fei, Ben Li, Yixuan Yang, Weidong Gao, Hengjun Xu, Jingyi Ma, Lipeng Yang, Yatian Zhou, Pinghong |
| contents | The development of medical imaging techniques has made a significant contribution to clinical decision-making. However, the existence of suboptimal imaging quality, as indicated by irregular illumination or imbalanced intensity, presents significant obstacles in automating disease screening, analysis, and diagnosis. Existing approaches for natural image enhancement are mostly trained with numerous paired images, presenting challenges in data collection and training costs, all while lacking the ability to generalize effectively. Here, we introduce a pioneering training-free Diffusion Model for Universal Medical Image Enhancement, named UniMIE. UniMIE demonstrates its unsupervised enhancement capabilities across various medical image modalities without the need for any fine-tuning. It accomplishes this by relying solely on a single pre-trained model from ImageNet. We conduct a comprehensive evaluation on 13 imaging modalities and over 15 medical types, demonstrating better qualities, robustness, and accuracy than other modality-specific and data-inefficient models. By delivering high-quality enhancement and corresponding accuracy downstream tasks across a wide range of tasks, UniMIE exhibits considerable potential to accelerate the advancement of diagnostic tools and customized treatment plans. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10236 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Lightening Anything in Medical Images Fei, Ben Li, Yixuan Yang, Weidong Gao, Hengjun Xu, Jingyi Ma, Lipeng Yang, Yatian Zhou, Pinghong Image and Video Processing Artificial Intelligence The development of medical imaging techniques has made a significant contribution to clinical decision-making. However, the existence of suboptimal imaging quality, as indicated by irregular illumination or imbalanced intensity, presents significant obstacles in automating disease screening, analysis, and diagnosis. Existing approaches for natural image enhancement are mostly trained with numerous paired images, presenting challenges in data collection and training costs, all while lacking the ability to generalize effectively. Here, we introduce a pioneering training-free Diffusion Model for Universal Medical Image Enhancement, named UniMIE. UniMIE demonstrates its unsupervised enhancement capabilities across various medical image modalities without the need for any fine-tuning. It accomplishes this by relying solely on a single pre-trained model from ImageNet. We conduct a comprehensive evaluation on 13 imaging modalities and over 15 medical types, demonstrating better qualities, robustness, and accuracy than other modality-specific and data-inefficient models. By delivering high-quality enhancement and corresponding accuracy downstream tasks across a wide range of tasks, UniMIE exhibits considerable potential to accelerate the advancement of diagnostic tools and customized treatment plans. |
| title | Lightening Anything in Medical Images |
| topic | Image and Video Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2406.10236 |