{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T12:07:59Z","timestamp":1788782879942,"version":"build-2803163510"},"reference-count":18,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T00:00:00Z","timestamp":1788566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Background: Two-stage coarse-to-fine architectures are commonly used in medical image synthesis and refinement. However, when the distributional gap between coarse inputs and high-resolution targets is large, the second-stage generator may produce unstable or weakly conditioned refinements rather than operating as a true residual corrector. Methods: We propose intentional degradation, a target-side distribution-alignment strategy that deliberately degrades high-resolution targets toward the coarse prediction space before residual learning. The degradation profile is guided by measured differences in contrast, saturation, and edge energy. We further evaluate refinement quality using two residual-space metrics: Var(\u0394), the variance of the predicted residual (target minus input), and \u0394-SSIM, the structural similarity between the predicted and true residual maps; both are designed to reveal refinement instability that conventional image-level metrics (e.g., SSIM computed on the full image) may not capture. We evaluated the approach in three medical imaging domains: wound-healing photography, retinal fundus imaging, and dermoscopy. Results: Across all three domains, intentional degradation consistently improved \u0394-SSIM and normalized residual variance recovery relative to the baseline, and predicted residuals showed substantially stronger directional correspondence with the true residual (assessed via sign-agreement and cosine-similarity metrics) than the baseline, which converged toward directionally random predictions. These findings suggest that residual-space and direction-sensitive metrics can reveal refinement instability that may not be captured by conventional image-level metrics alone. Conclusions: Intentional degradation provides a simple, architecture-agnostic-by-design strategy for stabilizing residual learning in coarse-to-fine medical image refinement, validated within a single ConvLSTM-based refinement framework; extension to other architectures remains for future validation. Rather than introducing a new network architecture, the method modifies the target-side training distribution to reduce the mismatch between coarse inputs and high-resolution targets.<\/jats:p>","DOI":"10.3390\/jimaging12090418","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T10:30:46Z","timestamp":1788777046000},"page":"418","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intentional Degradation for Stabilizing Residual Learning in Coarse-to-Fine Medical Image Refinement"],"prefix":"10.3390","volume":"12","author":[{"given":"Myongjin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Shin Ae","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Hasung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Seontai","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Jongsoo","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"}]},{"given":"Jaechul","family":"Yoon","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"}]},{"given":"Yong Suk","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Surgery, Burn Treatment Center, Pohang St. Mary\u2019s Hospital, Pohang 37661, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1402-2297","authenticated-orcid":false,"given":"Jun","family":"Hur","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9178-0599","authenticated-orcid":false,"given":"Dohern","family":"Kym","sequence":"additional","affiliation":[{"name":"Department of Burn Surgery, Hangang Sacred Heart Hospital, Hallym University College of Medicine, Seoul 07247, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., and Loy, C.C. (2018, January 8\u201314). ESRGAN: Enhanced super-resolution generative adversarial networks. Proceedings of the European Conference on Computer Vision Workshops (ECCVW), Munich, Germany.","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Burt, P.J., and Adelson, E.H. (1987). The Laplacian pyramid as a compact image code. Readings in Computer Vision, Morgan Kaufmann.","DOI":"10.1016\/B978-0-08-051581-6.50065-9"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A.P., Tejani, A., Totz, J., and Wang, Z. (2017, January 21\u201326). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., and Shan, Y. (2021, January 11\u201317). Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data. Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada.","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref_5","unstructured":"Miyato, T., Kataoka, T., Koyama, M., and Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Fei-Fei, L. (2016, January 8\u201316). Perceptual losses for real-time style transfer and super-resolution. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherland.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref_8","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, Australia."},{"key":"ref_9","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017, January 4\u20139). Improved training of Wasserstein GANs. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., and Weston, J. (2009, January 14\u201318). Curriculum learning. Proceedings of the 26th Annual International Conference on Machine Learning (ICML), Montreal, BC, Canada.","DOI":"10.1145\/1553374.1553380"},{"key":"ref_11","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive growing of GANs for improved quality, stability, and variation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., and Zhu, J.Y. (2019, January 16\u201320). Semantic image synthesis with spatially-adaptive normalization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., and Catanzaro, B. (2018, January 18\u201323). High-resolution image synthesis and semantic manipulation with conditional GANs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Nah, S., Kim, T.H., and Lee, K.M. (2017, January 21\u201326). Deep multi-scale convolutional neural network for dynamic scene deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bansal, A., Borgnia, E., Chu, H.M., Li, J.S., Kazemi, H., Huang, F., Goldblum, M., Geiping, J., and Goldstein, T. (2023, January 10\u201316). Cold diffusion: Inverting arbitrary image transforms without noise. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA.","DOI":"10.52202\/075280-1789"},{"key":"ref_16","unstructured":"Daras, G., Delbracio, M., Talebi, H., Dimakis, A.G., and Milanfar, P. (2026, April 04). Soft diffusion: Score matching for general corruptions. Trans. Mach. Learn. Res., Available online: https:\/\/openreview.net\/forum?id=W98rebBxlQ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1109\/LSP.2026.3697693","article-title":"Physics-guided self-supervised statistical residual learning for sonar despeckling with improved generalization","volume":"33","author":"Pillai","year":"2026","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1038\/s41598-025-30830-8","article-title":"A coarse-to-fine registration method for multimodal retinal images","volume":"16","author":"Xu","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/418\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T11:16:29Z","timestamp":1788779789000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/9\/418"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,5]]},"references-count":18,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["jimaging12090418"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12090418","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,5]]}}}