High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing
Histopathological Whole Slide Images (WSIs) play a crucial role in cancer diagnosis. It is of significant importance for pathologists to search for images sharing similar content with the query WSI, especially in the case-based diagnosis. While slide-level retrieval could be more intuitive and practical in clinical applications, most methods are designed for patch-level retrieval. A few recently unsupervised slide-level methods only focus on integrating patch features directly, without perceiving slide-level information, and thus severely limits the performance of WSI retrieval. To tackle the issue, we propose a High-Order Correlation-Guided Self-Supervised Hashing-Encoding Retrieval (HSHR) method. Specifically, we train an attention-based hash encoder with slide-level representation in a self-supervised manner, enabling it to generate more representative slide-level hash codes of cluster centers and assign weights for each. These optimized and weighted codes are leveraged to establish a similarity-based hypergraph, in which a hypergraph-guided retrieval module is adopted to explore high-order correlations in the multi-pairwise manifold to conduct WSI retrieval. Extensive experiments on multiple TCGA datasets with over 24,000 WSIs spanning 30 cancer subtypes demonstrate that HSHR achieves state-of-the-art performance compared with other unsupervised histology WSI retrieval methods.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:45 |
|---|---|
| Enthalten in: |
IEEE transactions on pattern analysis and machine intelligence - 45(2023), 9 vom: 25. Sept., Seite 11008-11023 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Shengrui [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 04.10.2023 Date Revised 04.10.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TPAMI.2023.3269810 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM356014568 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM356014568 | ||
| 003 | DE-627 | ||
| 005 | 20231226065548.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TPAMI.2023.3269810 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1186.xml |
| 035 | |a (DE-627)NLM356014568 | ||
| 035 | |a (NLM)37097802 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Shengrui |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a High-Order Correlation-Guided Slide-Level Histology Retrieval With Self-Supervised Hashing |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 04.10.2023 | ||
| 500 | |a Date Revised 04.10.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Histopathological Whole Slide Images (WSIs) play a crucial role in cancer diagnosis. It is of significant importance for pathologists to search for images sharing similar content with the query WSI, especially in the case-based diagnosis. While slide-level retrieval could be more intuitive and practical in clinical applications, most methods are designed for patch-level retrieval. A few recently unsupervised slide-level methods only focus on integrating patch features directly, without perceiving slide-level information, and thus severely limits the performance of WSI retrieval. To tackle the issue, we propose a High-Order Correlation-Guided Self-Supervised Hashing-Encoding Retrieval (HSHR) method. Specifically, we train an attention-based hash encoder with slide-level representation in a self-supervised manner, enabling it to generate more representative slide-level hash codes of cluster centers and assign weights for each. These optimized and weighted codes are leveraged to establish a similarity-based hypergraph, in which a hypergraph-guided retrieval module is adopted to explore high-order correlations in the multi-pairwise manifold to conduct WSI retrieval. Extensive experiments on multiple TCGA datasets with over 24,000 WSIs spanning 30 cancer subtypes demonstrate that HSHR achieves state-of-the-art performance compared with other unsupervised histology WSI retrieval methods | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Zhao, Yining |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Jun |e verfasserin |4 aut | |
| 700 | 1 | |a Yu, Ting |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Ji |e verfasserin |4 aut | |
| 700 | 1 | |a Gao, Yue |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on pattern analysis and machine intelligence |d 1979 |g 45(2023), 9 vom: 25. Sept., Seite 11008-11023 |w (DE-627)NLM098212257 |x 1939-3539 |7 nnns |
| 773 | 1 | 8 | |g volume:45 |g year:2023 |g number:9 |g day:25 |g month:09 |g pages:11008-11023 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TPAMI.2023.3269810 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 45 |j 2023 |e 9 |b 25 |c 09 |h 11008-11023 | ||