File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ISBI53787.2023.10230389
- Scopus: eid_2-s2.0-85172120094
- WOS: WOS:001062050500067
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: PCT-GAN: A Real CT Image Super-Resolution Model for Trabecular Bone Restoration
Title | PCT-GAN: A Real CT Image Super-Resolution Model for Trabecular Bone Restoration |
---|---|
Authors | |
Keywords | computed tomography image enhancement generative adversarial network Real-world medical image super-resolution |
Issue Date | 18-Apr-2023 |
Abstract | We consider the real-world super-resolution (SR) problem for medical images with two distinct imaging modalities. Most previous attempts either focused on image enhancement between similar imaging modalities or used the down-sampled or simulated low-resolution images as input to train their model, which reduces the clinical significance of the work. We, therefore, collect a dataset with paired clinical computed tomography (CT) and microcomputed tomography (µCT) of vertebra specimens and develop the progressive CT generative adversarial network (PCT-GAN) model to generate high-resolution images. PCT-GAN is designed using the progressive strategy by first denoising the input clinical CT image and then increasing its spatial resolution. To encourage our model to generate trabecular bone details from clinical CTs, we propose to combine wavelet and edge losses with the L1 and adversarial losses for model training. Experimental results show that the proposed method outperforms the state-of-the-art methods in terms of quantitative measurements and visual results. |
Persistent Identifier | http://hdl.handle.net/10722/335645 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Moxin | - |
dc.contributor.author | Meng, Nan | - |
dc.contributor.author | Cheung, Jason Pui Yin | - |
dc.contributor.author | Zhang, Teng | - |
dc.date.accessioned | 2023-12-04T09:37:21Z | - |
dc.date.available | 2023-12-04T09:37:21Z | - |
dc.date.issued | 2023-04-18 | - |
dc.identifier.uri | http://hdl.handle.net/10722/335645 | - |
dc.description.abstract | <p>We consider the real-world super-resolution (SR) problem for medical images with two distinct imaging modalities. Most previous attempts either focused on image enhancement between similar imaging modalities or used the down-sampled or simulated low-resolution images as input to train their model, which reduces the clinical significance of the work. We, therefore, collect a dataset with paired clinical computed tomography (CT) and microcomputed tomography (µCT) of vertebra specimens and develop the progressive CT generative adversarial network (PCT-GAN) model to generate high-resolution images. PCT-GAN is designed using the progressive strategy by first denoising the input clinical CT image and then increasing its spatial resolution. To encourage our model to generate trabecular bone details from clinical CTs, we propose to combine wavelet and edge losses with the L1 and adversarial losses for model training. Experimental results show that the proposed method outperforms the state-of-the-art methods in terms of quantitative measurements and visual results.<br></p> | - |
dc.language | eng | - |
dc.relation.ispartof | 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, 2023 (18/04/2023-21/04/2023, Cartagena, Colombia) | - |
dc.subject | computed tomography image enhancement | - |
dc.subject | generative adversarial network | - |
dc.subject | Real-world medical image super-resolution | - |
dc.title | PCT-GAN: A Real CT Image Super-Resolution Model for Trabecular Bone Restoration | - |
dc.type | Conference_Paper | - |
dc.identifier.doi | 10.1109/ISBI53787.2023.10230389 | - |
dc.identifier.scopus | eid_2-s2.0-85172120094 | - |
dc.identifier.volume | 2023-April | - |
dc.identifier.isi | WOS:001062050500067 | - |