Step-Calibrated Diffusion for Biomedical Optical Image Restoration
Guardado en:
| 發表在: | arXiv.org (Dec 17, 2024), p. n/a |
|---|---|
| 主要作者: | |
| 其他作者: | , , , , , , , , |
| 出版: |
Cornell University Library, arXiv.org
|
| 主題: | |
| 在線閱讀: | Citation/Abstract Full text outside of ProQuest |
| 標簽: |
沒有標簽, 成為第一個標記此記錄!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 2972951255 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 2972951255 | ||
| 045 | 0 | |b d20241217 | |
| 100 | 1 | |a Lyu, Yiwei | |
| 245 | 1 | |a Step-Calibrated Diffusion for Biomedical Optical Image Restoration | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 17, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a High-quality, high-resolution medical imaging is essential for clinical care. Raman-based biomedical optical imaging uses non-ionizing infrared radiation to evaluate human tissues in real time and is used for early cancer detection, brain tumor diagnosis, and intraoperative tissue analysis. Unfortunately, optical imaging is vulnerable to image degradation due to laser scattering and absorption, which can result in diagnostic errors and misguided treatment. Restoration of optical images is a challenging computer vision task because the sources of image degradation are multi-factorial, stochastic, and tissue-dependent, preventing a straightforward method to obtain paired low-quality/high-quality data. Here, we present Restorative Step-Calibrated Diffusion (RSCD), an unpaired diffusion-based image restoration method that uses a step calibrator model to dynamically determine the number of steps required to complete the reverse diffusion process for image restoration. RSCD outperforms other widely used unpaired image restoration methods on both image quality and perceptual evaluation metrics for restoring optical images. Medical imaging experts consistently prefer images restored using RSCD in blinded comparison experiments and report minimal to no hallucinations. Finally, we show that RSCD improves performance on downstream clinical imaging tasks, including automated brain tumor diagnosis and deep tissue imaging. Our code is available at https://github.com/MLNeurosurg/restorative_step-calibrated_diffusion. | |
| 653 | |a Tumors | ||
| 653 | |a Human tissues | ||
| 653 | |a Image resolution | ||
| 653 | |a Brain cancer | ||
| 653 | |a Medical imaging | ||
| 653 | |a Calibration | ||
| 653 | |a Image degradation | ||
| 653 | |a Diagnosis | ||
| 653 | |a Brain | ||
| 653 | |a Image restoration | ||
| 653 | |a Computer vision | ||
| 653 | |a Image quality | ||
| 653 | |a Infrared imaging | ||
| 653 | |a Image processing | ||
| 700 | 1 | |a Cha, Sung Jik | |
| 700 | 1 | |a Cheng, Jiang | |
| 700 | 1 | |a Chowdury, Asadur | |
| 700 | 1 | |a Hou, Xinhai | |
| 700 | 1 | |a Harake, Edward | |
| 700 | 1 | |a Kondepudi, Akhil | |
| 700 | 1 | |a Freudiger, Christian | |
| 700 | 1 | |a Lee, Honglak | |
| 700 | 1 | |a Hollon, Todd C | |
| 773 | 0 | |t arXiv.org |g (Dec 17, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/2972951255/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2403.13680 |