Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis
<p>Damage to cartilage is an important indicator of osteoarthritis progression, but manual extraction of cartilage morphology is time-consuming and prone to error. To address this, we hypothesize that automatic labeling of cartilage can be achieved through the comparison of contrasted and non-...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Elsevier
2023
|
| _version_ | 1797109936480583680 |
|---|---|
| author | Zheng, J-Q Lim, NH Papież, BW |
| author_facet | Zheng, J-Q Lim, NH Papież, BW |
| author_sort | Zheng, J-Q |
| collection | OXFORD |
| description | <p>Damage to cartilage is an important indicator of osteoarthritis progression, but manual extraction of cartilage morphology is time-consuming and prone to error. To address this, we hypothesize that automatic labeling of cartilage can be achieved through the comparison of contrasted and non-contrasted Computer Tomography (CT). However, this is non-trivial as the pre-clinical volumes are at arbitrary starting poses due to the lack of standardized acquisition protocols. Thus, we propose an annotation-free deep learning method, D-net, for accurate and automatic alignment of pre- and post-contrasted cartilage CT volumes. D-Net is based on a novel mutual attention network structure to capture large-range translation and full-range rotation without the need for a prior pose template. CT volumes of mice tibiae are used for validation, with synthetic transformation for training and tested with real pre- and post-contrasted CT volumes. Analysis of Variance (ANOVA) was used to compare the different network structures. Our proposed method, D-net, achieves a Dice coefficient of 0.87, and significantly outperforms other state-of-the-art deep learning models, in the real-world alignment of 50 pairs of pre- and post-contrasted CT volumes when cascaded as a multi-stage network.<p/> |
| first_indexed | 2024-03-07T07:48:09Z |
| format | Journal article |
| id | oxford-uuid:3a85a172-f9a2-4285-b660-78b41c1f1406 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:48:09Z |
| publishDate | 2023 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:3a85a172-f9a2-4285-b660-78b41c1f14062023-06-22T11:18:58ZAccurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysisJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:3a85a172-f9a2-4285-b660-78b41c1f1406EnglishSymplectic ElementsElsevier 2023Zheng, J-QLim, NHPapież, BW<p>Damage to cartilage is an important indicator of osteoarthritis progression, but manual extraction of cartilage morphology is time-consuming and prone to error. To address this, we hypothesize that automatic labeling of cartilage can be achieved through the comparison of contrasted and non-contrasted Computer Tomography (CT). However, this is non-trivial as the pre-clinical volumes are at arbitrary starting poses due to the lack of standardized acquisition protocols. Thus, we propose an annotation-free deep learning method, D-net, for accurate and automatic alignment of pre- and post-contrasted cartilage CT volumes. D-Net is based on a novel mutual attention network structure to capture large-range translation and full-range rotation without the need for a prior pose template. CT volumes of mice tibiae are used for validation, with synthetic transformation for training and tested with real pre- and post-contrasted CT volumes. Analysis of Variance (ANOVA) was used to compare the different network structures. Our proposed method, D-net, achieves a Dice coefficient of 0.87, and significantly outperforms other state-of-the-art deep learning models, in the real-world alignment of 50 pairs of pre- and post-contrasted CT volumes when cascaded as a multi-stage network.<p/> |
| spellingShingle | Zheng, J-Q Lim, NH Papież, BW Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title | Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title_full | Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title_fullStr | Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title_full_unstemmed | Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title_short | Accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| title_sort | accurate volume alignment of arbitrarily oriented tibiae based on a mutual attention network for osteoarthritis analysis |
| work_keys_str_mv | AT zhengjq accuratevolumealignmentofarbitrarilyorientedtibiaebasedonamutualattentionnetworkforosteoarthritisanalysis AT limnh accuratevolumealignmentofarbitrarilyorientedtibiaebasedonamutualattentionnetworkforosteoarthritisanalysis AT papiezbw accuratevolumealignmentofarbitrarilyorientedtibiaebasedonamutualattentionnetworkforosteoarthritisanalysis |