Enhancing poorly differentiated lung cancer classification with rotary position embedding and sparse attention in multiple instance learning

In clinical practice, diagnosing poorly differentiated non-small cell lung cancer (NSCLC) typically requires immunohistochemistry (IHC) to accurately distinguish between cancer subtypes. The high cost and time-consuming nature of this process significantly limit its clinical applicability. Furthermo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical signal processing and control Jg. 113; S. 108699
Hauptverfasser: Chu, Hongbo, Chang, Zhengsong, Shao, Zihan, Deng, Pengyun, Wang, Yan, Guo, Xiaojing, Wang, Yang, Yang, Jiao, Guan, Tian, Li, Xiaomei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.03.2026
Schlagworte:
ISSN:1746-8094
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In clinical practice, diagnosing poorly differentiated non-small cell lung cancer (NSCLC) typically requires immunohistochemistry (IHC) to accurately distinguish between cancer subtypes. The high cost and time-consuming nature of this process significantly limit its clinical applicability. Furthermore, the limited availability of tissue samples from advanced-stage patients poses a significant challenge for subsequent diagnosis. Consequently, leveraging novel AI technologies is critical to overcoming this challenge. Hence, we propose an innovative Multi-Instance Learning (MIL) algorithm, RoSA-MIL. This algorithm is based on a novel MIL framework that integrates relative position encoding and sparse attention mechanisms. Relative position encoding enhances the model’s comprehension of spatial relationships between samples, thereby improving its ability to capture local context. The sparse attention mechanism reduces computational overhead by eliminating redundant calculations, thereby enhancing both efficiency and scalability. Experiments conducted on diverse datasets from three independent centers demonstrate that the RoSA-MIL model outperforms existing methods, exhibiting significant improvements in diagnostic accuracy, robustness, and efficiency when processing large-scale data.
AbstractList In clinical practice, diagnosing poorly differentiated non-small cell lung cancer (NSCLC) typically requires immunohistochemistry (IHC) to accurately distinguish between cancer subtypes. The high cost and time-consuming nature of this process significantly limit its clinical applicability. Furthermore, the limited availability of tissue samples from advanced-stage patients poses a significant challenge for subsequent diagnosis. Consequently, leveraging novel AI technologies is critical to overcoming this challenge. Hence, we propose an innovative Multi-Instance Learning (MIL) algorithm, RoSA-MIL. This algorithm is based on a novel MIL framework that integrates relative position encoding and sparse attention mechanisms. Relative position encoding enhances the model’s comprehension of spatial relationships between samples, thereby improving its ability to capture local context. The sparse attention mechanism reduces computational overhead by eliminating redundant calculations, thereby enhancing both efficiency and scalability. Experiments conducted on diverse datasets from three independent centers demonstrate that the RoSA-MIL model outperforms existing methods, exhibiting significant improvements in diagnostic accuracy, robustness, and efficiency when processing large-scale data.
ArticleNumber 108699
Author Shao, Zihan
Wang, Yang
Guan, Tian
Yang, Jiao
Li, Xiaomei
Guo, Xiaojing
Chang, Zhengsong
Chu, Hongbo
Deng, Pengyun
Wang, Yan
Author_xml – sequence: 1
  givenname: Hongbo
  surname: Chu
  fullname: Chu, Hongbo
  organization: Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China
– sequence: 2
  givenname: Zhengsong
  surname: Chang
  fullname: Chang, Zhengsong
  organization: Department of Pathology, Harbin Medical University Cancer Hospital, 150 Haping road, Nangang District, Harbin 150081, China
– sequence: 3
  givenname: Zihan
  surname: Shao
  fullname: Shao, Zihan
  organization: School of Life Sciences, Anhui University, China
– sequence: 4
  givenname: Pengyun
  surname: Deng
  fullname: Deng, Pengyun
  organization: Department of Pathology, Harbin Medical University Cancer Hospital, 150 Haping road, Nangang District, Harbin 150081, China
– sequence: 5
  givenname: Yan
  surname: Wang
  fullname: Wang, Yan
  organization: Department of Pathology, Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University, the First Affiliated Hospital of Southern University of Science and Technology, Shenzhen 518001, China
– sequence: 6
  givenname: Xiaojing
  surname: Guo
  fullname: Guo, Xiaojing
  organization: Department of Pathology, Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University, the First Affiliated Hospital of Southern University of Science and Technology, Shenzhen 518001, China
– sequence: 7
  givenname: Yang
  surname: Wang
  fullname: Wang, Yang
  organization: Department of Pathology, Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University, the First Affiliated Hospital of Southern University of Science and Technology, Shenzhen 518001, China
– sequence: 8
  givenname: Jiao
  surname: Yang
  fullname: Yang, Jiao
  organization: Department of Pathology, Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University, the First Affiliated Hospital of Southern University of Science and Technology, Shenzhen 518001, China
– sequence: 9
  givenname: Tian
  surname: Guan
  fullname: Guan, Tian
  email: guantian@sz.tsinghua.edu.cn
  organization: Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School, Shenzhen 518055, China
– sequence: 10
  givenname: Xiaomei
  surname: Li
  fullname: Li, Xiaomei
  email: lijingfmmu@fmmu.edu.cn
  organization: Department of Pathology, Shenzhen People’s Hospital, The Second Clinical Medical College of Jinan University, the First Affiliated Hospital of Southern University of Science and Technology, Shenzhen 518001, China
BookMark eNp9kE1OwzAQhb0oEm3hAqx8gRYncRJbYoOq8iNVYgNry7HHdKrUiWwD6h04NA5lzWpGM_M9vXkLMvODB0JuCrYuWNHcHtZdHM26ZGWdB6KRckbmRcublWCSX5JFjAfGuGgLPiffW7_X3qB_p-MwhP5ELToHAXxCncDS_iOvTD6BQE2vY0SHRiccPP3CtKdhSDqcMhzxdwjHDqyd9LS3NI46RKA6pUkwr9HT40efcOwh9zFNwrQHHXxGrsiF032E67-6JG8P29fN02r38vi8ud-tTFlXaeVA1FYyaXmjWy0ArDYtL0AY7srGCpm_q40TVdk1DHjVycrULe9KwY2stKiWpDzrmjDEGMCpMeAxv6EKpqYM1UFNGaopQ3XOMEN3Zwiys0-EoKJByPYtBjBJ2QH_w38AD1iDZg
Cites_doi 10.1109/CVPR52688.2022.01825
10.1038/s41746-024-01003-0
10.4103/2153-3539.119005
10.1016/j.neucom.2023.127063
10.1109/ICCVW54120.2021.00081
10.1038/s41591-024-02857-3
10.1145/3664647.3681425
10.1109/ICCV48922.2021.00986
10.1109/CVPR52688.2022.01824
10.1109/CVPR52733.2024.01076
10.1109/CVPR46437.2021.01409
10.1038/s41591-024-02856-4
10.1109/CVPR52729.2023.00720
10.1109/CVPR52729.2023.01503
10.1038/s41551-020-00682-w
10.1609/aaai.v35i16.17664
10.6004/jnccn.2022.0025
ContentType Journal Article
Copyright 2025
Copyright_xml – notice: 2025
DBID AAYXX
CITATION
DOI 10.1016/j.bspc.2025.108699
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
ExternalDocumentID 10_1016_j_bspc_2025_108699
S1746809425012108
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9DU
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACLOT
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
ADTZH
AEBSH
AECPX
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
UNMZH
~G-
~HD
AAYXX
CITATION
ID FETCH-LOGICAL-c253t-fe85d909d46a7a8eedac741e8c4f26d890045cf832b60e43b93c574b284c93a83
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001607666900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1746-8094
IngestDate Sat Nov 29 06:50:25 EST 2025
Sat Nov 29 17:03:55 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Transformer
Histopathological classification
Poorly differentiated lung cancer
Multiple instance learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c253t-fe85d909d46a7a8eedac741e8c4f26d890045cf832b60e43b93c574b284c93a83
ParticipantIDs crossref_primary_10_1016_j_bspc_2025_108699
elsevier_sciencedirect_doi_10_1016_j_bspc_2025_108699
PublicationCentury 2000
PublicationDate March 2026
2026-03-00
PublicationDateYYYYMMDD 2026-03-01
PublicationDate_xml – month: 03
  year: 2026
  text: March 2026
PublicationDecade 2020
PublicationTitle Biomedical signal processing and control
PublicationYear 2026
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Zhang, Yang, Chen, Zhu, Liu, Dong, Zhang, Sun, Ying, Lin (b9) 2024; 7
Yang (b40) 2019
Raffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, Liu (b21) 2020; 21
Xu, Usuyama, Bagga, Zhang, Rao, Naumann, Wong, Gero, González, Gu (b10) 2024
Fourkioti, De Vries, Jin, Alexander, Bakal (b36) 2023
Devlin (b41) 2018
Dosovitskiy (b42) 2020
Sung, Ferlay, Siegel, Laversanne, Soerjomataram, Jemal, Bray (b1) 2021; 71
Ettinger, Wood, Aisner, Akerley, Bauman, Bharat, Bruno, Chang, Chirieac, D’Amico (b2) 2022; 20
Lu, Williamson, Chen, Chen, Barbieri, Mahmood (b5) 2021; 5
Shao, Bian, Chen, Wang, Zhang, Ji (b7) 2021; 34
Xitong Ling, Minxi Ouyang, Yizhi Wang, Xinrui Chen, Renao Yan, Hongbo Chu, Junru Cheng, Tian Guan, Sufang Tian, Xiaoping Liu, et al., Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 2795–2803.
T. Lin, L. Zhao, Efficient Attention with Sliding Window for Visual Transformers, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020.
Goode, Gilbert, Harkes, Jukic, Satyanarayanan (b43) 2013; 4
Zhang, Kapse, Ma, Prasanna, Saltz, Vakalopoulou, Samaras (b15) 2023
Bin Li, Yin Li, Kevin W. Eliceiri, Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14318–14328.
Press, Smith, Lewis (b24) 2021
Tsai Hor Chan, Fernando Julio Cendra, Lan Ma, Guosheng Yin, Lequan Yu, Histopathology whole slide image analysis with heterogeneous graph representation learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15661–15670.
Ketkar, Moolayil, Ketkar, Moolayil (b45) 2021
Honglin Li, Chenglu Zhu, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui, Wenwei Kuang, Sunyi Zheng, Lin Yang, Task-specific fine-tuning via variational information bottleneck for weakly-supervised pathology whole slide image classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7454–7463.
Dai (b22) 2019
Su, Ahmed, Lu, Pan, Bo, Liu (b25) 2024; 568
Gil, Dick, Harrow, Murray, March, Marshall (b4) 2023
Zhu, Chen, Qiu, Sotiras, Razi, Wang (b29) 2025
He, Liu, Gao, Chen (b20) 2020
Lu, Chen, Williamson, Chen, Liang, Ding, Jaume, Odintsov, Le, Gerber (b12) 2024; 30
Yonghang Guan, Jun Zhang, Kuan Tian, Sen Yang, Pei Dong, Jinxi Xiang, Wei Yang, Junzhou Huang, Yuyao Zhang, Xiao Han, Node-aligned graph convolutional network for whole-slide image representation and classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18813–18823.
Wang, Li, Khabsa, Fang, Ma (b18) 2020
Jiawen Li, Yuxuan Chen, Hongbo Chu, Qiehe Sun, Tian Guan, Anjia Han, Yonghong He, Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 11323–11332.
Chen, Ding, Lu, Williamson, Jaume, Song, Chen, Zhang, Shao, Shaban (b11) 2024; 30
Richard J Chen, Chengkuan Chen, Yicong Li, Tiffany Y Chen, Andrew D Trister, Rahul G Krishnan, Faisal Mahmood, Scaling vision transformers to gigapixel images via hierarchical self-supervised learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16144–16155.
Beltagy, Peters, Cohan (b28) 2020
Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh, Nyströmformer: A nyström-based algorithm for approximating self-attention, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 14138–14148.
Chikontwe, Kim, Jeong, Sung, Go, Nam, Park (b30) 2024
Li, Yao, Zhu, Li, Huang (b34) 2018
Ilse, Tomczak, Welling (b6) 2018
Chen, Lu, Shaban, Chen, Chen, Williamson, Mahmood (b33) 2021
Hongrun Zhang, Yanda Meng, Yitian Zhao, Yihong Qiao, Xiaoyun Yang, Sarah E Coupland, Yalin Zheng, Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18802–18812.
Kitaev, Kaiser, Levskaya (b23) 2020
Mostafa Jahanifar, Neda Zamani Tajeddin, Navid Alemi Koohbanani, Nasir M Rajpoot, Robust interactive semantic segmentation of pathology images with minimal user input, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 674–683.
Ainslie, Ontanon, Alberti, Cvicek, Fisher, Pham, Ravula, Sanghai, Wang, Yang (b27) 2020
Culjak, Abram, Pribanic, Dzapo, Cifrek (b44) 2012
Vaswani (b32) 2017
Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10012–10022.
Zaheer, Guruganesh, Dubey, Ainslie, Alberti, Ontanon, Pham, Ravula, Wang, Yang (b26) 2020; 33
Zhang (10.1016/j.bspc.2025.108699_b9) 2024; 7
Ketkar (10.1016/j.bspc.2025.108699_b45) 2021
Press (10.1016/j.bspc.2025.108699_b24) 2021
10.1016/j.bspc.2025.108699_b16
Ainslie (10.1016/j.bspc.2025.108699_b27) 2020
Beltagy (10.1016/j.bspc.2025.108699_b28) 2020
10.1016/j.bspc.2025.108699_b38
10.1016/j.bspc.2025.108699_b17
10.1016/j.bspc.2025.108699_b39
Gil (10.1016/j.bspc.2025.108699_b4) 2023
Chikontwe (10.1016/j.bspc.2025.108699_b30) 2024
Devlin (10.1016/j.bspc.2025.108699_b41) 2018
Lu (10.1016/j.bspc.2025.108699_b12) 2024; 30
10.1016/j.bspc.2025.108699_b19
Culjak (10.1016/j.bspc.2025.108699_b44) 2012
10.1016/j.bspc.2025.108699_b13
Zhu (10.1016/j.bspc.2025.108699_b29) 2025
10.1016/j.bspc.2025.108699_b35
10.1016/j.bspc.2025.108699_b14
Kitaev (10.1016/j.bspc.2025.108699_b23) 2020
10.1016/j.bspc.2025.108699_b37
10.1016/j.bspc.2025.108699_b31
Vaswani (10.1016/j.bspc.2025.108699_b32) 2017
Raffel (10.1016/j.bspc.2025.108699_b21) 2020; 21
Zaheer (10.1016/j.bspc.2025.108699_b26) 2020; 33
Ilse (10.1016/j.bspc.2025.108699_b6) 2018
Zhang (10.1016/j.bspc.2025.108699_b15) 2023
Wang (10.1016/j.bspc.2025.108699_b18) 2020
Su (10.1016/j.bspc.2025.108699_b25) 2024; 568
Dai (10.1016/j.bspc.2025.108699_b22) 2019
Goode (10.1016/j.bspc.2025.108699_b43) 2013; 4
He (10.1016/j.bspc.2025.108699_b20) 2020
Sung (10.1016/j.bspc.2025.108699_b1) 2021; 71
Chen (10.1016/j.bspc.2025.108699_b11) 2024; 30
Fourkioti (10.1016/j.bspc.2025.108699_b36) 2023
Li (10.1016/j.bspc.2025.108699_b34) 2018
Yang (10.1016/j.bspc.2025.108699_b40) 2019
Chen (10.1016/j.bspc.2025.108699_b33) 2021
Ettinger (10.1016/j.bspc.2025.108699_b2) 2022; 20
Xu (10.1016/j.bspc.2025.108699_b10) 2024
Lu (10.1016/j.bspc.2025.108699_b5) 2021; 5
Shao (10.1016/j.bspc.2025.108699_b7) 2021; 34
10.1016/j.bspc.2025.108699_b3
Dosovitskiy (10.1016/j.bspc.2025.108699_b42) 2020
10.1016/j.bspc.2025.108699_b8
References_xml – reference: Honglin Li, Chenglu Zhu, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui, Wenwei Kuang, Sunyi Zheng, Lin Yang, Task-specific fine-tuning via variational information bottleneck for weakly-supervised pathology whole slide image classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7454–7463.
– year: 2020
  ident: b20
  article-title: Deberta: Decoding-enhanced bert with disentangled attention
– year: 2020
  ident: b27
  article-title: ETC: Encoding long and structured inputs in transformers
– year: 2018
  ident: b41
  article-title: Bert: Pre-training of deep bidirectional transformers for language understanding
– start-page: 1725
  year: 2012
  end-page: 1730
  ident: b44
  article-title: A brief introduction to opencv
  publication-title: 2012 Proceedings of the 35th International Convention MIPRO
– reference: Jiawen Li, Yuxuan Chen, Hongbo Chu, Qiehe Sun, Tian Guan, Anjia Han, Yonghong He, Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 11323–11332.
– year: 2020
  ident: b23
  article-title: Reformer: The efficient transformer
– year: 2020
  ident: b18
  article-title: Linformer: Self-attention with linear complexity
– start-page: 333
  year: 2025
  end-page: 351
  ident: b29
  article-title: DGR-MIL: Exploring diverse global representation in multiple instance learning for whole slide image classification
  publication-title: European Conference on Computer Vision
– reference: Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty, Mingxing Tan, Glenn Fung, Yin Li, Vikas Singh, Nyströmformer: A nyström-based algorithm for approximating self-attention, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 14138–14148.
– reference: Tsai Hor Chan, Fernando Julio Cendra, Lan Ma, Guosheng Yin, Lequan Yu, Histopathology whole slide image analysis with heterogeneous graph representation learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 15661–15670.
– volume: 568
  year: 2024
  ident: b25
  article-title: Roformer: Enhanced transformer with rotary position embedding
  publication-title: Neurocomputing
– year: 2019
  ident: b40
  article-title: XLNet: Generalized autoregressive pretraining for language understanding
– volume: 71
  start-page: 209
  year: 2021
  end-page: 249
  ident: b1
  article-title: Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
  publication-title: CA: Cancer J. Clin.
– volume: 4
  start-page: 27
  year: 2013
  ident: b43
  article-title: OpenSlide: A vendor-neutral software foundation for digital pathology
  publication-title: J. Pathol. Inform.
– year: 2019
  ident: b22
  article-title: Transformer-xl: Attentive language models beyond a fixed-length context
– volume: 33
  start-page: 17283
  year: 2020
  end-page: 17297
  ident: b26
  article-title: Big bird: Transformers for longer sequences
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 1
  year: 2024
  end-page: 8
  ident: b10
  article-title: A whole-slide foundation model for digital pathology from real-world data
  publication-title: Nat.
– start-page: 339
  year: 2021
  end-page: 349
  ident: b33
  article-title: Whole slide images are 2d point clouds: Context-aware survival prediction using patch-based graph convolutional networks
  publication-title: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VIII 24
– reference: Yonghang Guan, Jun Zhang, Kuan Tian, Sen Yang, Pei Dong, Jinxi Xiang, Wei Yang, Junzhou Huang, Yuyao Zhang, Xiao Han, Node-aligned graph convolutional network for whole-slide image representation and classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18813–18823.
– start-page: 174
  year: 2018
  end-page: 182
  ident: b34
  article-title: Graph CNN for survival analysis on whole slide pathological images
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– year: 2023
  ident: b36
  article-title: CAMIL: Context-aware multiple instance learning for cancer detection and subtyping in whole slide images
– reference: Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, Baining Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10012–10022.
– start-page: 2127
  year: 2018
  end-page: 2136
  ident: b6
  article-title: Attention-based deep multiple instance learning
  publication-title: International Conference on Machine Learning
– reference: Bin Li, Yin Li, Kevin W. Eliceiri, Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14318–14328.
– reference: Xitong Ling, Minxi Ouyang, Yizhi Wang, Xinrui Chen, Renao Yan, Hongbo Chu, Junru Cheng, Tian Guan, Sufang Tian, Xiaoping Liu, et al., Agent Aggregator with Mask Denoise Mechanism for Histopathology Whole Slide Image Analysis, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 2795–2803.
– year: 2024
  ident: b30
  article-title: FR-MIL: Distribution re-calibration based multiple instance learning with transformer for whole slide image classification
  publication-title: IEEE Trans. Med. Imaging
– volume: 5
  start-page: 555
  year: 2021
  end-page: 570
  ident: b5
  article-title: Data-efficient and weakly supervised computational pathology on whole-slide images
  publication-title: Nat. Biomed. Eng.
– volume: 7
  start-page: 15
  year: 2024
  ident: b9
  article-title: Histopathology images-based deep learning prediction of prognosis and therapeutic response in small cell lung cancer
  publication-title: NPJ Digit. Med.
– reference: Hongrun Zhang, Yanda Meng, Yitian Zhao, Yihong Qiao, Xiaoyun Yang, Sarah E Coupland, Yalin Zheng, Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 18802–18812.
– start-page: 18
  year: 2023
  end-page: 32
  ident: b4
  article-title: A deep learning based approach to semantic segmentation of lung tumour areas in gross pathology images
  publication-title: Annual Conference on Medical Image Understanding and Analysis
– year: 2020
  ident: b42
  article-title: An image is worth 16x16 words: Transformers for image recognition at scale
– volume: 30
  start-page: 863
  year: 2024
  end-page: 874
  ident: b12
  article-title: A visual-language foundation model for computational pathology
  publication-title: Nature Med.
– year: 2021
  ident: b24
  article-title: Train short, test long: Attention with linear biases enables input length extrapolation
– volume: 21
  start-page: 1
  year: 2020
  end-page: 67
  ident: b21
  article-title: Exploring the limits of transfer learning with a unified text-to-text transformer
  publication-title: J. Mach. Learn. Res.
– volume: 20
  start-page: 497
  year: 2022
  end-page: 530
  ident: b2
  article-title: Non–small cell lung cancer, version 3.2022, NCCN clinical practice guidelines in oncology
  publication-title: J. Natl. Compr. Cancer Netw.
– reference: T. Lin, L. Zhao, Efficient Attention with Sliding Window for Visual Transformers, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2020.
– start-page: 624
  year: 2023
  end-page: 634
  ident: b15
  article-title: Prompt-mil: Boosting multi-instance learning schemes via task-specific prompt tuning
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– volume: 34
  start-page: 2136
  year: 2021
  end-page: 2147
  ident: b7
  article-title: Transmil: Transformer based correlated multiple instance learning for whole slide image classification
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 27
  year: 2021
  end-page: 91
  ident: b45
  article-title: Introduction to pytorch
  publication-title: Deep Learning with Python: Learn Best Practices of Deep Learning Models with Pytorch
– reference: Mostafa Jahanifar, Neda Zamani Tajeddin, Navid Alemi Koohbanani, Nasir M Rajpoot, Robust interactive semantic segmentation of pathology images with minimal user input, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 674–683.
– reference: Richard J Chen, Chengkuan Chen, Yicong Li, Tiffany Y Chen, Andrew D Trister, Rahul G Krishnan, Faisal Mahmood, Scaling vision transformers to gigapixel images via hierarchical self-supervised learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16144–16155.
– volume: 30
  start-page: 850
  year: 2024
  end-page: 862
  ident: b11
  article-title: Towards a general-purpose foundation model for computational pathology
  publication-title: Nature Med.
– year: 2017
  ident: b32
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2020
  ident: b28
  article-title: Longformer: The long-document transformer
– start-page: 18
  year: 2023
  ident: 10.1016/j.bspc.2025.108699_b4
  article-title: A deep learning based approach to semantic segmentation of lung tumour areas in gross pathology images
– year: 2018
  ident: 10.1016/j.bspc.2025.108699_b41
– ident: 10.1016/j.bspc.2025.108699_b38
– ident: 10.1016/j.bspc.2025.108699_b19
– year: 2024
  ident: 10.1016/j.bspc.2025.108699_b30
  article-title: FR-MIL: Distribution re-calibration based multiple instance learning with transformer for whole slide image classification
  publication-title: IEEE Trans. Med. Imaging
– start-page: 333
  year: 2025
  ident: 10.1016/j.bspc.2025.108699_b29
  article-title: DGR-MIL: Exploring diverse global representation in multiple instance learning for whole slide image classification
– ident: 10.1016/j.bspc.2025.108699_b37
  doi: 10.1109/CVPR52688.2022.01825
– volume: 7
  start-page: 15
  issue: 1
  year: 2024
  ident: 10.1016/j.bspc.2025.108699_b9
  article-title: Histopathology images-based deep learning prediction of prognosis and therapeutic response in small cell lung cancer
  publication-title: NPJ Digit. Med.
  doi: 10.1038/s41746-024-01003-0
– volume: 71
  start-page: 209
  issue: 3
  year: 2021
  ident: 10.1016/j.bspc.2025.108699_b1
  article-title: Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
  publication-title: CA: Cancer J. Clin.
– start-page: 2127
  year: 2018
  ident: 10.1016/j.bspc.2025.108699_b6
  article-title: Attention-based deep multiple instance learning
– year: 2021
  ident: 10.1016/j.bspc.2025.108699_b24
– volume: 4
  start-page: 27
  issue: 1
  year: 2013
  ident: 10.1016/j.bspc.2025.108699_b43
  article-title: OpenSlide: A vendor-neutral software foundation for digital pathology
  publication-title: J. Pathol. Inform.
  doi: 10.4103/2153-3539.119005
– start-page: 174
  year: 2018
  ident: 10.1016/j.bspc.2025.108699_b34
  article-title: Graph CNN for survival analysis on whole slide pathological images
– volume: 568
  year: 2024
  ident: 10.1016/j.bspc.2025.108699_b25
  article-title: Roformer: Enhanced transformer with rotary position embedding
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2023.127063
– volume: 34
  start-page: 2136
  year: 2021
  ident: 10.1016/j.bspc.2025.108699_b7
  article-title: Transmil: Transformer based correlated multiple instance learning for whole slide image classification
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2019
  ident: 10.1016/j.bspc.2025.108699_b22
– start-page: 339
  year: 2021
  ident: 10.1016/j.bspc.2025.108699_b33
  article-title: Whole slide images are 2d point clouds: Context-aware survival prediction using patch-based graph convolutional networks
– ident: 10.1016/j.bspc.2025.108699_b3
  doi: 10.1109/ICCVW54120.2021.00081
– volume: 30
  start-page: 850
  issue: 3
  year: 2024
  ident: 10.1016/j.bspc.2025.108699_b11
  article-title: Towards a general-purpose foundation model for computational pathology
  publication-title: Nature Med.
  doi: 10.1038/s41591-024-02857-3
– ident: 10.1016/j.bspc.2025.108699_b13
  doi: 10.1145/3664647.3681425
– start-page: 624
  year: 2023
  ident: 10.1016/j.bspc.2025.108699_b15
  article-title: Prompt-mil: Boosting multi-instance learning schemes via task-specific prompt tuning
– year: 2017
  ident: 10.1016/j.bspc.2025.108699_b32
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.bspc.2025.108699_b39
  doi: 10.1109/ICCV48922.2021.00986
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b23
– ident: 10.1016/j.bspc.2025.108699_b31
  doi: 10.1109/CVPR52688.2022.01824
– start-page: 1
  year: 2024
  ident: 10.1016/j.bspc.2025.108699_b10
  article-title: A whole-slide foundation model for digital pathology from real-world data
  publication-title: Nat.
– ident: 10.1016/j.bspc.2025.108699_b8
  doi: 10.1109/CVPR52733.2024.01076
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b42
– ident: 10.1016/j.bspc.2025.108699_b16
  doi: 10.1109/CVPR46437.2021.01409
– volume: 30
  start-page: 863
  issue: 3
  year: 2024
  ident: 10.1016/j.bspc.2025.108699_b12
  article-title: A visual-language foundation model for computational pathology
  publication-title: Nature Med.
  doi: 10.1038/s41591-024-02856-4
– volume: 21
  start-page: 1
  issue: 140
  year: 2020
  ident: 10.1016/j.bspc.2025.108699_b21
  article-title: Exploring the limits of transfer learning with a unified text-to-text transformer
  publication-title: J. Mach. Learn. Res.
– volume: 33
  start-page: 17283
  year: 2020
  ident: 10.1016/j.bspc.2025.108699_b26
  article-title: Big bird: Transformers for longer sequences
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b18
– ident: 10.1016/j.bspc.2025.108699_b14
  doi: 10.1109/CVPR52729.2023.00720
– year: 2019
  ident: 10.1016/j.bspc.2025.108699_b40
– ident: 10.1016/j.bspc.2025.108699_b35
  doi: 10.1109/CVPR52729.2023.01503
– start-page: 27
  year: 2021
  ident: 10.1016/j.bspc.2025.108699_b45
  article-title: Introduction to pytorch
– volume: 5
  start-page: 555
  issue: 6
  year: 2021
  ident: 10.1016/j.bspc.2025.108699_b5
  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
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b27
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b28
– year: 2020
  ident: 10.1016/j.bspc.2025.108699_b20
– ident: 10.1016/j.bspc.2025.108699_b17
  doi: 10.1609/aaai.v35i16.17664
– start-page: 1725
  year: 2012
  ident: 10.1016/j.bspc.2025.108699_b44
  article-title: A brief introduction to opencv
– volume: 20
  start-page: 497
  issue: 5
  year: 2022
  ident: 10.1016/j.bspc.2025.108699_b2
  article-title: Non–small cell lung cancer, version 3.2022, NCCN clinical practice guidelines in oncology
  publication-title: J. Natl. Compr. Cancer Netw.
  doi: 10.6004/jnccn.2022.0025
– year: 2023
  ident: 10.1016/j.bspc.2025.108699_b36
SSID ssj0048714
Score 2.3935938
Snippet In clinical practice, diagnosing poorly differentiated non-small cell lung cancer (NSCLC) typically requires immunohistochemistry (IHC) to accurately...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 108699
SubjectTerms Deep learning
Histopathological classification
Multiple instance learning
Poorly differentiated lung cancer
Transformer
Title Enhancing poorly differentiated lung cancer classification with rotary position embedding and sparse attention in multiple instance learning
URI https://dx.doi.org/10.1016/j.bspc.2025.108699
Volume 113
WOSCitedRecordID wos001607666900005&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 1746-8094
  databaseCode: AIEXJ
  dateStart: 20060101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0048714
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELZKlwMcEE-xvOQDtyqrbpw49nEFRYDQag8LqvYS2Y6TdrU4Vdqulv_A_-HvMY5jJ10eYg9c0ipK3SjzdfzN9JsZhF7rVNJDkbKIyERHiVY0EllZRFSUNFHZVLK2XdOXT9nxMZvP-clo9MPXwlxeZMawqyu--q-mhnNgbFs6ewNzh0XhBLwHo8MRzA7HfzL8zCxsDw1bZF7Xtnuxn4ECv2VLLy-2tszWGruZKMudrVjIwaBNyjb1xirpvJpror9KXRS-lhEcULPWE9uVM-gkgyhx2XJN8BTdLIpq5y_jttDfVWEuK0uCV65IwS_dqeZ7wcG23RdrU8l6oEJwzulsoU0FsUIVUkQL0WZ9z5aLHvBvtbv6BF6_bc0wxRHTXuPVeeUssV2T3TTk4LYPycDx2oFRbtLSL3uCS0-cH8j1yvasjNOD_uLdBtzXNsYgV_RKuPPcrpHbNXK3xi20F2cpZ2O0d_RhNv_oSQCEgW1b-XDnXb2WkxZev5Pfc6IBzzm9j-51AQo-csB6gEbaPER3B20rH6HvAWLYQQzvQgxbiGEHMbwLMWwhhh3EsIcYDhDDgAPsIIYDxPDSYA8x7CGGPcQeo8_vZqdv3kfdVI9IxSnZRKVmacGnvEioyAQDjiYU0FrNVFLGtGDcRhmqhJ1G0qlOiOREpVkigUcpTgQjT9DY1EY_RThjuiy4oiUhEBUTIhQENKXgFMKCmEq9jyb-ueYr17wl_7Mt91HqH33e0U9HK3NA0l8-9-xG3_Ic3ekh_gKNN81Wv0S31eVmuW5edTD6CSPbsMA
linkProvider Elsevier
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=Enhancing+poorly+differentiated+lung+cancer+classification+with+rotary+position+embedding+and+sparse+attention+in+multiple+instance+learning&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Chu%2C+Hongbo&rft.au=Chang%2C+Zhengsong&rft.au=Shao%2C+Zihan&rft.au=Deng%2C+Pengyun&rft.date=2026-03-01&rft.issn=1746-8094&rft.volume=113&rft.spage=108699&rft_id=info:doi/10.1016%2Fj.bspc.2025.108699&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_bspc_2025_108699
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon