Rethinking Perceptual Metrics for Medical Image Translation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911835580530688 |
|---|---|
| author | Konz, Nicholas Chen, Yuwen Gu, Hanxue Dong, Haoyu Mazurowski, Maciej A. |
| author_facet | Konz, Nicholas Chen, Yuwen Gu, Hanxue Dong, Haoyu Mazurowski, Maciej A. |
| contents | Modern medical image translation methods use generative models for tasks such as the conversion of CT images to MRI. Evaluating these methods typically relies on some chosen downstream task in the target domain, such as segmentation. On the other hand, task-agnostic metrics are attractive, such as the network feature-based perceptual metrics (e.g., FID) that are common to image translation in general computer vision. In this paper, we investigate evaluation metrics for medical image translation on two medical image translation tasks (GE breast MRI to Siemens breast MRI and lumbar spine MRI to CT), tested on various state-of-the-art translation methods. We show that perceptual metrics do not generally correlate with segmentation metrics due to them extending poorly to the anatomical constraints of this sub-field, with FID being especially inconsistent. However, we find that the lesser-used pixel-level SWD metric may be useful for subtle intra-modality translation. Our results demonstrate the need for further research into helpful metrics for medical image translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07318 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Perceptual Metrics for Medical Image Translation Konz, Nicholas Chen, Yuwen Gu, Hanxue Dong, Haoyu Mazurowski, Maciej A. Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Modern medical image translation methods use generative models for tasks such as the conversion of CT images to MRI. Evaluating these methods typically relies on some chosen downstream task in the target domain, such as segmentation. On the other hand, task-agnostic metrics are attractive, such as the network feature-based perceptual metrics (e.g., FID) that are common to image translation in general computer vision. In this paper, we investigate evaluation metrics for medical image translation on two medical image translation tasks (GE breast MRI to Siemens breast MRI and lumbar spine MRI to CT), tested on various state-of-the-art translation methods. We show that perceptual metrics do not generally correlate with segmentation metrics due to them extending poorly to the anatomical constraints of this sub-field, with FID being especially inconsistent. However, we find that the lesser-used pixel-level SWD metric may be useful for subtle intra-modality translation. Our results demonstrate the need for further research into helpful metrics for medical image translation. |
| title | Rethinking Perceptual Metrics for Medical Image Translation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.07318 |