CAMIL: channel attention-based multiple instance learning for whole slide image classification
Motivation The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically...
Uložené v:
| Vydané v: | Bioinformatics (Oxford, England) Ročník 41; číslo 2 |
|---|---|
| Hlavní autori: | , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
England
Oxford University Press
04.02.2025
|
| Predmet: | |
| ISSN: | 1367-4811, 1367-4811 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Motivation
The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension.
Results
To address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics.
Availability and implementation
All implementation code is available at https://github.com/maojy0914/CAMIL. |
|---|---|
| AbstractList | The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension.
To address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics.
All implementation code is available at https://github.com/maojy0914/CAMIL. Motivation The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension. Results To address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics. Availability and implementation All implementation code is available at https://github.com/maojy0914/CAMIL. The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension.MOTIVATIONThe classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension.To address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics.RESULTSTo address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics.All implementation code is available at https://github.com/maojy0914/CAMIL.AVAILABILITY AND IMPLEMENTATIONAll implementation code is available at https://github.com/maojy0914/CAMIL. |
| Author | Liu, Yongjin Xu, Junlin Yang, Jialiang Mao, Jinyang Tang, Xianfang Tian, Geng Zhao, Heaven |
| Author_xml | – sequence: 1 givenname: Jinyang orcidid: 0009-0009-7264-2225 surname: Mao fullname: Mao, Jinyang – sequence: 2 givenname: Junlin orcidid: 0000-0003-1057-1504 surname: Xu fullname: Xu, Junlin email: xjl@hnu.edu.cn – sequence: 3 givenname: Xianfang surname: Tang fullname: Tang, Xianfang – sequence: 4 givenname: Yongjin surname: Liu fullname: Liu, Yongjin email: yjliu@fzu.edu.cn – sequence: 5 givenname: Heaven surname: Zhao fullname: Zhao, Heaven – sequence: 6 givenname: Geng surname: Tian fullname: Tian, Geng – sequence: 7 givenname: Jialiang surname: Yang fullname: Yang, Jialiang email: yangjl@geneis.cn |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/39820310$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkMtOwzAQRS1URB_wC1WWbELHeQexQRWPSkVsYEvkOOPWyLFL7Ajx97i0IGADK4_sc2c8Z0wG2mgkZErhjEIZz2pppBama5mT3M5qxwREyQEZ0TjLw6SgdPCtHpKxtc8AkEKaHZFhXBYRxBRG5Gl-ebdYngd8zbRGFTDnUDtpdFgzi03Q9srJjcJAauuY5hgoZJ2WehX46cHr2vg3q2TjiZatMOCKWSuF5Gzb5ZgcCqYsnuzPCXm8vnqY34bL-5vF_HIZ8gSoC0UWAa1pk1PIaVpimmSAOYjtZVkD-o0zZAUA4zxiTR5HUSnKrIBGYMEbGk_I6a7vpjMvPVpXtdJyVIppNL2tYpp6GtK09Oh0j_Z1i0216fzHu7fq04kHsh3AO2Nth-ILoVBt5Vc_5Vd7-T548SvIpfvQ4Dom1d9xuoubfvPfke-n4KT0 |
| CitedBy_id | crossref_primary_10_1002_jemt_70069 |
| Cites_doi | 10.1016/j.media.2020.101814 10.1016/j.media.2020.101813 10.1038/s41591-018-0177-5 10.1016/j.ccell.2023.08.002 10.1001/jama.2017.14585 10.1016/j.bspc.2021.103406 10.48550/arXiv.2404.00351 10.1016/j.cmpb.2011.12.007 10.1016/j.compbiomed.2022.106199 10.1038/s41551-020-00682-w 10.1038/s41586-021-03512-4 10.1038/s41587-021-01094-0 10.1109/TMI.2021.3077079 10.1016/j.media.2022.102559 10.1093/bioinformatics/btac641 10.48550/arXiv.1612.03217, 10.1016/j.patcog.2022.108785 10.1038/s41591-024-02857-3 10.1609/aaai.v35i16.17664 10.1109/TCYB.2019.2935141 10.1016/j.compbiomed.2020.103639 10.1093/bib/bbac448 10.1016/j.media.2019.101563 10.1016/j.compbiomed.2024.107938 10.1109/TMM.2020.2997192 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2025. Published by Oxford University Press. 2025 The Author(s) 2025. Published by Oxford University Press. |
| Copyright_xml | – notice: The Author(s) 2025. Published by Oxford University Press. 2025 – notice: The Author(s) 2025. Published by Oxford University Press. |
| DBID | TOX AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1093/bioinformatics/btaf024 |
| DatabaseName | Oxford Journals Open Access Collection CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: TOX name: Oxford Journals Open Access Collection url: https://academic.oup.com/journals/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 1367-4811 |
| ExternalDocumentID | 39820310 10_1093_bioinformatics_btaf024 10.1093/bioinformatics/btaf024 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: Natural Science Foundation of Hunan Province grantid: 2023JJ40180 – fundername: Wuhan Textile University Foundation grantid: 20230612 |
| GroupedDBID | --- -E4 -~X .-4 .2P .DC .GJ .I3 0R~ 1TH 23N 2WC 4.4 48X 53G 5GY 5WA 70D AAIJN AAIMJ AAJKP AAJQQ AAKPC AAMDB AAMVS AAOGV AAPQZ AAPXW AAUQX AAVAP AAVLN ABEFU ABEJV ABEUO ABGNP ABIXL ABNGD ABNKS ABPQP ABPTD ABQLI ABWST ABXVV ABZBJ ACGFS ACIWK ACPRK ACUFI ACUKT ACUXJ ACYTK ADBBV ADEYI ADEZT ADFTL ADGKP ADGZP ADHKW ADHZD ADMLS ADOCK ADPDF ADRDM ADRTK ADVEK ADYVW ADZTZ ADZXQ AECKG AEGPL AEJOX AEKKA AEKSI AELWJ AEMDU AENEX AENZO AEPUE AETBJ AEWNT AFFNX AFFZL AFGWE AFIYH AFOFC AFRAH AGINJ AGKEF AGQPQ AGQXC AGSYK AHMBA AHXPO AI. AIJHB AJEEA AJEUX AKHUL AKWXX ALMA_UNASSIGNED_HOLDINGS ALTZX ALUQC AMNDL APIBT APWMN AQDSO ARIXL ASPBG ATTQO AVWKF AXUDD AYOIW AZFZN AZVOD BAWUL BAYMD BHONS BQDIO BQUQU BSWAC BTQHN C1A C45 CAG CDBKE COF CS3 CZ4 DAKXR DIK DILTD DU5 D~K EBD EBS EE~ EJD ELUNK EMOBN F5P F9B FEDTE FHSFR FLIZI FLUFQ FOEOM FQBLK GAUVT GJXCC GROUPED_DOAJ GX1 H13 H5~ HAR HVGLF HW0 HZ~ IOX J21 JXSIZ KAQDR KOP KQ8 KSI KSN M-Z MK~ ML0 N9A NGC NLBLG NMDNZ NOMLY NTWIH NU- NVLIB O0~ O9- OAWHX ODMLO OJQWA OK1 OVD OVEED O~Y P2P PAFKI PB- PEELM PQQKQ Q1. Q5Y R44 RD5 RIG RNI RNS ROL RPM RUSNO RW1 RXO RZF RZO SV3 TEORI TJP TLC TOX TR2 VH1 W8F WOQ X7H YAYTL YKOAZ YXANX ZGI ZKX ~91 ~KM AAYXX CITATION ROX CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c401t-f6201b1d7107159e5460e70f01b19b0e0936ea800acc2ad73229f9680dfe8cd13 |
| IEDL.DBID | TOX |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001414845800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1367-4811 |
| IngestDate | Sun Nov 09 12:46:34 EST 2025 Thu May 29 04:59:34 EDT 2025 Sat Nov 29 08:13:42 EST 2025 Tue Nov 18 21:21:01 EST 2025 Mon Jun 30 08:34:51 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. https://creativecommons.org/licenses/by/4.0 The Author(s) 2025. Published by Oxford University Press. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c401t-f6201b1d7107159e5460e70f01b19b0e0936ea800acc2ad73229f9680dfe8cd13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0009-0009-7264-2225 0000-0003-1057-1504 |
| OpenAccessLink | https://dx.doi.org/10.1093/bioinformatics/btaf024 |
| PMID | 39820310 |
| PQID | 3156800559 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_3156800559 pubmed_primary_39820310 crossref_primary_10_1093_bioinformatics_btaf024 crossref_citationtrail_10_1093_bioinformatics_btaf024 oup_primary_10_1093_bioinformatics_btaf024 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-Feb-04 |
| PublicationDateYYYYMMDD | 2025-02-04 |
| PublicationDate_xml | – month: 02 year: 2025 text: 2025-Feb-04 day: 04 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | Bioinformatics (Oxford, England) |
| PublicationTitleAlternate | Bioinformatics |
| PublicationYear | 2025 |
| Publisher | Oxford University Press |
| Publisher_xml | – name: Oxford University Press |
| References | Li (2025030422283808300_btaf024-B22) 2021; 23 Zhang (2025030422283808300_btaf024-B42) 2022 Pan (2025030422283808300_btaf024-B29) 2022; 150 Qu (2025030422283808300_btaf024-B31) 2022 Srinidhi (2025030422283808300_btaf024-B33) 2021; 67 Wang (2025030422283808300_btaf024-B37) 2020 Wang (2025030422283808300_btaf024-B39) 2020; 50 Fu (2025030422283808300_btaf024-B11) 2024; 170 Woo (2025030422283808300_btaf024-B40) 2018 Yao (2025030422283808300_btaf024-B41) 2022; 23 Tang (2025030422283808300_btaf024-B34) 2024 Fang (2025030422283808300_btaf024-B10) Greenwald (2025030422283808300_btaf024-B13) 2022; 40 Shao (2025030422283808300_btaf024-B32) 2021 Coudray (2025030422283808300_btaf024-B7) 2018; 24 Ilse (2025030422283808300_btaf024-B18) 2018 Javed (2025030422283808300_btaf024-B19) 2022 Karthik (2025030422283808300_btaf024-B20) 2022; 73 Chollet (2025030422283808300_btaf024-B6) 2017 He (2025030422283808300_btaf024-B14) 2012; 107 Zhu (2025030422283808300_btaf024-B43) 2021; 40 Huang (2025030422283808300_btaf024-B16) Maron (2025030422283808300_btaf024-B26) 1997 Li (2025030422283808300_btaf024-B21) 2021 Lu (2025030422283808300_btaf024-B25) 2021; 5 Chi (2025030422283808300_btaf024-B5) 2023 Mou (2025030422283808300_btaf024-B27) 2019 Cai (2025030422283808300_btaf024-B1) Chen (2025030422283808300_btaf024-B4) 2024; 30 Xiong (2025030422283808300_btaf024-B52499774) 2021; 35 Li (2025030422283808300_btaf024-B23) 2022; 129 Graham (2025030422283808300_btaf024-B12) 2019; 58 Vaswani (2025030422283808300_btaf024-B35) 2017 Chen (2025030422283808300_btaf024-B3) 2022 Chen (2025030422283808300_btaf024-B2) Huang (2025030422283808300_btaf024-B17) 2022; 38 Ni (2025030422283808300_btaf024-B28) 2020; 118 Wagner (2025030422283808300_btaf024-B36) 2023; 41 Dov (2025030422283808300_btaf024-B8) 2021; 67 Ehteshami Bejnordi (2025030422283808300_btaf024-B9) 2017; 318 Qin (2025030422283808300_btaf024-B30) 2021 Lu (2025030422283808300_btaf024-B24) 2021; 594 Hu (2025030422283808300_btaf024-B15) 2018 Wang (2025030422283808300_btaf024-B38) 2022; 81 |
| References_xml | – start-page: 721 volume-title: Medical Image Computing and Computer Assisted Intervention—MICCAI 2019, Lecture Notes in Computer Science year: 2019 ident: 2025030422283808300_btaf024-B27 – year: 2018 ident: 2025030422283808300_btaf024-B40 – volume: 67 start-page: 101814 year: 2021 ident: 2025030422283808300_btaf024-B8 article-title: Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images publication-title: Med Image Anal doi: 10.1016/j.media.2020.101814 – volume: 67 start-page: 101813 year: 2021 ident: 2025030422283808300_btaf024-B33 article-title: Deep neural network models for computational histopathology: a survey publication-title: Med Image Anal doi: 10.1016/j.media.2020.101813 – volume: 24 start-page: 1559 year: 2018 ident: 2025030422283808300_btaf024-B7 article-title: Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning publication-title: Nat Med doi: 10.1038/s41591-018-0177-5 – year: 1997 ident: 2025030422283808300_btaf024-B26 – volume: 41 start-page: 1650 year: 2023 ident: 2025030422283808300_btaf024-B36 article-title: Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study publication-title: Cancer Cell doi: 10.1016/j.ccell.2023.08.002 – volume: 318 start-page: 2199 year: 2017 ident: 2025030422283808300_btaf024-B9 article-title: Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer publication-title: JAMA doi: 10.1001/jama.2017.14585 – volume: 73 start-page: 103406 year: 2022 ident: 2025030422283808300_btaf024-B20 article-title: Eff2Net: an efficient channel attention-based convolutional neural network for skin disease classification publication-title: Biomed Signal Process Control doi: 10.1016/j.bspc.2021.103406 – start-page: 763 year: 2021 ident: 2025030422283808300_btaf024-B30 – ident: 2025030422283808300_btaf024-B1 doi: 10.48550/arXiv.2404.00351 – volume: 107 start-page: 538 year: 2012 ident: 2025030422283808300_btaf024-B14 article-title: Histology image analysis for carcinoma detection and grading publication-title: Comput Methods Programs Biomed doi: 10.1016/j.cmpb.2011.12.007 – year: 2018 ident: 2025030422283808300_btaf024-B15 – start-page: 24 volume-title: Medical Image Computing and Computer Assisted Intervention—MICCAI 2022, Lecture Notes in Computer Science year: 2022 ident: 2025030422283808300_btaf024-B31 – start-page: 18780 year: 2022 ident: 2025030422283808300_btaf024-B42 – start-page: 11531 year: 2020 ident: 2025030422283808300_btaf024-B37 – start-page: 16123 year: 2022 ident: 2025030422283808300_btaf024-B3 – volume: 150 start-page: 106199 year: 2022 ident: 2025030422283808300_btaf024-B29 article-title: MCA-net: a multi-task channel attention network for Myocardial infarction detection and location using 12-lead ECGs publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2022.106199 – start-page: 20689 volume-title: Advances in Neural Information Processing Systems year: 2022 ident: 2025030422283808300_btaf024-B19 – volume: 5 start-page: 555 year: 2021 ident: 2025030422283808300_btaf024-B25 article-title: Data-efficient and weakly supervised computational pathology on whole-slide images publication-title: Nat Biomed Eng doi: 10.1038/s41551-020-00682-w – volume: 594 start-page: 106 year: 2021 ident: 2025030422283808300_btaf024-B24 article-title: AI-based pathology predicts origins for cancers of unknown primary publication-title: Nature doi: 10.1038/s41586-021-03512-4 – volume: 40 start-page: 555 year: 2022 ident: 2025030422283808300_btaf024-B13 article-title: Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning publication-title: Nat Biotechnol doi: 10.1038/s41587-021-01094-0 – volume: 40 start-page: 2354 year: 2021 ident: 2025030422283808300_btaf024-B43 article-title: Dual attention multi-instance deep learning for Alzheimer’s disease diagnosis with structural MRI publication-title: IEEE Trans Med Imaging doi: 10.1109/TMI.2021.3077079 – volume: 81 start-page: 102559 year: 2022 ident: 2025030422283808300_btaf024-B38 article-title: Transformer-based unsupervised contrastive learning for histopathological image classification publication-title: Med Image Anal doi: 10.1016/j.media.2022.102559 – start-page: 2136 volume-title: Advances in Neural Information Processing Systems year: 2021 ident: 2025030422283808300_btaf024-B32 – start-page: 98 volume-title: Medical Image Computing and Computer Assisted Intervention—MICCAI 2023, Lecture Notes in Computer Science year: 2023 ident: 2025030422283808300_btaf024-B5 – volume: 38 start-page: 5108 year: 2022 ident: 2025030422283808300_btaf024-B17 article-title: Predicting colorectal cancer tumor mutational burden from histopathological images and clinical information using multi-modal deep learning publication-title: Bioinformatics doi: 10.1093/bioinformatics/btac641 – ident: 2025030422283808300_btaf024-B2 doi: 10.48550/arXiv.1612.03217, – ident: 2025030422283808300_btaf024-B16 – volume: 129 start-page: 108785 year: 2022 ident: 2025030422283808300_btaf024-B23 article-title: HAM: hybrid attention module in deep convolutional neural networks for image classification publication-title: Pattern Recognit doi: 10.1016/j.patcog.2022.108785 – start-page: 11343 year: 2024 ident: 2025030422283808300_btaf024-B34 – volume: 30 start-page: 850 year: 2024 ident: 2025030422283808300_btaf024-B4 article-title: Towards a general-purpose foundation model for computational pathology publication-title: Nat Med doi: 10.1038/s41591-024-02857-3 – start-page: 14313 year: 2021 ident: 2025030422283808300_btaf024-B21 – volume: 35 start-page: 14138 year: 2021 ident: 2025030422283808300_btaf024-B52499774 article-title: Nyströmformer: A nyström-based algorithm for approximating self-attention publication-title: AAAI doi: 10.1609/aaai.v35i16.17664 – volume-title: Advances in Neural Information Processing Systems year: 2017 ident: 2025030422283808300_btaf024-B35 – start-page: 1800 year: 2017 ident: 2025030422283808300_btaf024-B6 – start-page: 2127 volume-title: Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research year: 2018 ident: 2025030422283808300_btaf024-B18 – volume: 50 start-page: 3950 year: 2020 ident: 2025030422283808300_btaf024-B39 article-title: Weakly supervised deep learning for whole slide lung cancer image analysis publication-title: IEEE Trans Cybern doi: 10.1109/TCYB.2019.2935141 – volume: 118 start-page: 103639 year: 2020 ident: 2025030422283808300_btaf024-B28 article-title: Global channel attention networks for intracranial vessel segmentation publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2020.103639 – volume: 23 start-page: bbac448 year: 2022 ident: 2025030422283808300_btaf024-B41 article-title: ICSDA: a multi-modal deep learning model to predict breast cancer recurrence and metastasis risk by integrating pathological, clinical and gene expression data publication-title: Brief Bioinform doi: 10.1093/bib/bbac448 – volume: 58 start-page: 101563 year: 2019 ident: 2025030422283808300_btaf024-B12 article-title: Hover-net: simultaneous segmentation and classification of nuclei in multi-tissue histology images publication-title: Med Image Anal doi: 10.1016/j.media.2019.101563 – ident: 2025030422283808300_btaf024-B10 – volume: 170 start-page: 107938 year: 2024 ident: 2025030422283808300_btaf024-B11 article-title: TSCA-Net: transformer based spatial-channel attention segmentation network for medical images publication-title: Comput Biol Med doi: 10.1016/j.compbiomed.2024.107938 – volume: 23 start-page: 1397 year: 2021 ident: 2025030422283808300_btaf024-B22 article-title: Stacked U-shape network with channel-wise attention for salient object detection publication-title: IEEE Trans Multimedia doi: 10.1109/TMM.2020.2997192 |
| SSID | ssj0005056 |
| Score | 2.4937341 |
| Snippet | Motivation
The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL)... The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust... |
| SourceID | proquest pubmed crossref oup |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| SubjectTerms | Algorithms Computational Biology - methods Humans Image Processing, Computer-Assisted - methods Multiple-Instance Learning Algorithms |
| Title | CAMIL: channel attention-based multiple instance learning for whole slide image classification |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/39820310 https://www.proquest.com/docview/3156800559 |
| Volume | 41 |
| WOSCitedRecordID | wos001414845800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: Directory of Open Access Journals (DOAJ) customDbUrl: eissn: 1367-4811 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0005056 issn: 1367-4811 databaseCode: DOA dateStart: 20230101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVASL databaseName: Oxford Journals Open Access Collection customDbUrl: eissn: 1367-4811 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0005056 issn: 1367-4811 databaseCode: TOX dateStart: 19850101 isFulltext: true titleUrlDefault: https://academic.oup.com/journals/ providerName: Oxford University Press |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ZSwMxEB5qUfDF-6hHieCTsHTb7BXfSlEUtPqg0CeXJJtIQbdit4r_3pk9KlXE43VJ9kgmmS87M98HcKgsWoXS2uFJRGFGPLOKRFAWofCt5Ny6vs3FJsJ-PxoMxHUN2lUtzOcQvuAtNRyVJKJEXNxSmbToWHDXbfsRaRbcXA0-kjrQn1d1wN92nXFBM2VtX9Bl7mVOl__xfiuwVEJK1i1sYBVqJl2DhUJk8m0d7nrdy_OLY0Ylvql5YESomac4OuTBElalFLJhjhS1YaWSxD3Dx7FXEtBliEYTbPGIuw_TBLgpwyif1A24PT256Z05paqCo_EslTk2QJ-v2glCixCxjPG9wDWha-miUK7BTwqMRBwpte7IJMQVL6wIIjexJtJJm29CPR2lZhuY4h1LfIYisNLjnlY8VL4UXge3ET9UsgF-NdCxLinHSfniIS5C3zyeHbu4HLsGtKb9ngrSjR97HOE8_rrxQTXdMS4mipDI1Iwm45jjaTYiWjLRgK3CDqb35ALBEoLhnb88ahcWOyQYTGne3h7Us-eJ2Yd5_ZINx89NmAsHUTP_DdDM7fgdkiH53g |
| linkProvider | Oxford University Press |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=CAMIL%3A+channel+attention-based+multiple+instance+learning+for+whole+slide+image+classification&rft.jtitle=Bioinformatics+%28Oxford%2C+England%29&rft.au=Mao%2C+Jinyang&rft.au=Xu%2C+Junlin&rft.au=Tang%2C+Xianfang&rft.au=Liu%2C+Yongjin&rft.date=2025-02-04&rft.eissn=1367-4811&rft.volume=41&rft.issue=2&rft_id=info:doi/10.1093%2Fbioinformatics%2Fbtaf024&rft_id=info%3Apmid%2F39820310&rft.externalDocID=39820310 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1367-4811&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1367-4811&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1367-4811&client=summon |