Rethinking Perceptual Metrics for Medical Image Translation (2404.07318v1)
Abstract: 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.
- Demystifying mmd gans. In International Conference on Learning Representations, 2018.
- Contourdiff: Unpaired image translation with contour-guided diffusion models. arXiv preprint arXiv:2403.10786, 2024.
- Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, 30, 2017.
- Rethinking fid: Towards a better evaluation metric for image generation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2024.
- Structure-preserving image translation for multi-source medical image domain adaptation. Pattern Recognition, 144:109840, 2023.
- Progressive growing of gans for improved quality, stability, and variation. In International Conference on Learning Representations, 2018.
- Unpaired image-to-image translation via neural schrödinger bridge. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=uQBW7ELXfO.
- Anatomically-controllable medical image generation with segmentation-guided diffusion models. arXiv preprint arXiv:2402.05210, 2024.
- A publicly available deep learning model and dataset for segmentation of breast, fibroglandular tissue, and vessels in breast mri. Scientific Reports, 14(1):5383, 2024.
- Semantic image synthesis with spatially-adaptive normalization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.
- Structure-preserving synthesis: Maskgan for unpaired mr-ct translation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 56–65. Springer, 2023.
- A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 dce-mri features. British journal of cancer, 119(4):508–516, 2018.
- Improved techniques for training gans. Advances in neural information processing systems, 29, 2016.
- Towards annotation-efficient segmentation via image-to-image translation. Medical Image Analysis, 82:102624, 2022.
- Totalsegmentator: Robust segmentation of 104 anatomic structures in ct images. Radiology: Artificial Intelligence, 5(5), September 2023. ISSN 2638-6100. 10.1148/ryai.230024. URL http://dx.doi.org/10.1148/ryai.230024.
- Unsupervised domain adaptation via disentangled representations: Application to cross-modality liver segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22, pages 255–263. Springer, 2019.
- Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017.