Cross-Attention-Based Saliency Inference for Predicting Cancer Metastasis on Whole Slide Images
Open accessAbstract
Although multiple instance learning (MIL) methods are widely used for automatic tumor detection on whole slide images (WSI), they suffer from the extreme class imbalance WSIs containing small tumors where the tumor may include only a few isolated cells. For early detection, it is important that MIL algorithms can identify small tumors. Existing studies have attempted to address this issue using attention-based architectures and instance selection-based methodologies but have not produced significant improvements. This paper proposes cross-attention-based salient instance inference MIL (CASiiMIL), which involves a novel saliency-informed attention mechanism to identify small tumors (e.g., breast cancer lymph node micro-metastasis) on WSIs without needing any annotations. In addition to this new attention mechanism, we introduce a negative representation learning algorithm to facilitate the learning of saliency-informed attention weights for improved sensitivity on tumor WSIs. The proposed model outperforms the state-of-the-art MIL methods on two popular tumor metastasis detection datasets. The proposed approach demonstrates great cross-center generalizability, high accuracy in classifying WSIs with small tumor lesions, and excellent interpretability attributed to the saliency-informed attention weights. We expect that the proposed method will pave the way for training algorithms for early tumor detection on large datasets where acquiring fine-grained annotations is is not practical.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Current hotspot detection methods rely on attention-based multiple instance learning and transformers, saliency-inference techniques for small lesions, and uncertainty-aware heatmaps that flag areas requiring human verification.
“Current methods rely on attention-based multiple instance learning (MIL) and transformers, saliency-inference techniques for small lesions, and uncertainty-aware heatmaps that flag areas requiring human verification [33,34].”
From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [33]
The Introduction (page not specified) describes a transformer-inspired, cross-attention MIL method for identifying small tumor lesions. Results > Interpretability (page not specified) shows attention heatmaps and reports that a pathologist examined false-positive patches. The paper does not describe uncertainty-aware heatmaps that flag areas requiring human verification. (LLM, conf=0.88)
Experimental — accuracy not yet measuredHotspot detection approaches can reduce review time and improve safety but face challenges such as spurious attention to artifacts, sensitivity-specificity trade-offs in small-lesion detection, and overconfidence on out-of-distribution detection.
“These approaches can reduce review time and improve safety but face challenges such as spurious attention to artifacts, sensitivity-specificity trade-offs in small-lesion detection, and overconfidence on out-of-distribution detection [33,35,36].”
From Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature (2026) · cites this paper as [33]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513 · see citing works
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · see citing works
Amin, M. B., Greene, F. L., Edge, S. B., Compton, C. C., Gershenwald, J. E., Brookland, R. K., Meyer, L., Gress, D. M., Byrd, D. R., & Winchester, D. P. (2017) · CA A Cancer Journal for Clinicians · doi:10.3322/caac.21388 · Cited by 6,531 · see citing works
Waks, A. G., & Winer, E. P. (2019) · JAMA · doi:10.1001/jama.2018.19323 · Cited by 4,913 · see citing works
Ehteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293 · see citing works
Clinical-grade computational pathology using weakly supervised deep learning on whole slide images
Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019) · Nature Medicine · doi:10.1038/s41591-019-0508-1 · Cited by 2,799 · see citing works
Data-efficient and weakly supervised computational pathology on whole-slide images
Lu, M. Y., Williamson, D. F. K., Chen, T. Y., Chen, R. J., Barbieri, M., & Mahmood, F. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-020-00682-w · Cited by 2,282 · see citing works
Attention-based Deep Multiple Instance LearningPreprint
Ilse, M., Tomczak, J. M., & Welling, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04712 · Cited by 1,235 · see citing works
Digital pathology and artificial intelligence
Niazi, M. K. K., Parwani, A. V., & Gurcan, M. N. (2019) · The Lancet Oncology · doi:10.1016/s1470-2045(19)30154-8 · Cited by 1,232 · see citing works
Self-citationLi, B., Li, Y., & Eliceiri, K. W. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01409 · Cited by 957 · see citing works
CUR matrix decompositions for improved data analysis
Mahoney, M. W., & Drineas, P. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0803205106 · Cited by 799 · see citing works
Transformer-based unsupervised contrastive learning for histopathological image classification
Wang, X., Yang, S., Zhang, J., Wang, M., Zhang, J., Yang, W., Huang, J., & Han, X. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102559 · Cited by 751 · see citing works
Bandi, P., Geessink, O., Manson, Q., Van Dijk, M., Balkenhol, M., Hermsen, M., Ehteshami Bejnordi, B., Lee, B., Paeng, K., Zhong, A., et al. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2018.2867350 · Cited by 569 · see citing works
Cross Attention Network for Few-shot ClassificationPreprint
Hou, R., Chang, H., Ma, B., Shan, S., & Chen, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.07677 · Cited by 565 · see citing works
Zhang, H., Meng, Y., Zhao, Y., Qiao, Y., Yang, X., Coupland, S. E., & Zheng, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01824 · Cited by 509 · see citing works
Revisiting multiple instance neural networks
Wang, X., Yan, Y., Tang, P., Bai, X., & Liu, W. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.08.026 · Cited by 502 · see citing works
Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images
Chen, R. J., Lu, M. Y., Weng, W.-H., Chen, T. Y., Williamson, D. F., Manz, T., Shady, M., & Mahmood, F. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00398 · Cited by 398 · see citing works
U-Net Transformer: Self and Cross Attention for Medical Image Segmentation
Petit, O., Thome, N., Rambour, C., Themyr, L., Collins, T., & Soler, L. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87589-3_28 · Cited by 349 · see citing works
Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
Ding, C., Pang, G., & Shen, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00724 · Cited by 197 · see citing works
Multiple Instance Learning with Center Embeddings for Histopathology Classification
Chikontwe, P., Kim, M., Nam, S. J., Go, H., & Park, S. H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59722-1_50 · Cited by 144 · see citing works
Nottegar, A., Veronese, N., Senthil, M., Roumen, R. M. H., Stubbs, B., Choi, A. H., Verheuvel, N. C., Solmi, M., Pea, A., Capelli, P., et al. (2016) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2016.02.259 · Cited by 129 · see citing works
CASF-Net: Cross-attention and cross-scale fusion network for medical image segmentation
Zheng, J., Liu, H., Feng, Y., Xu, J., & Zhao, L. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.107307 · Cited by 126 · see citing works
Tang, W., Huang, S., Zhang, X., Zhou, F., Zhang, Y., & Liu, B. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00377 · Cited by 126 · see citing works
Med-Flamingo: a Multimodal Medical Few-shot LearnerPreprint
Moor, M., Huang, Q., Wu, S., Yasunaga, M., Zakka, C., Dalmia, Y., Reis, E. P., Rajpurkar, P., & Leskovec, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.15189 · Cited by 111 · see citing works
Courtiol, P., Tramel, E. W., Sanselme, M., & Wainrib, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.02212 · Cited by 99 · see citing works
van la Parra, R. F. D., Peer, P. G. M., Ernst, M. F., & Bosscha, K. P. (2011) · European Journal of Surgical Oncology · doi:10.1016/j.ejso.2011.01.006 · Cited by 96 · see citing works
Open-World Semi-Supervised LearningPreprint
Cao, K., Brbić, M., & Leskovec, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.03526 · Cited by 92 · see citing works
Multimodal Triplet Attention Network for Brain Disease Diagnosis
Zhu, Q., Wang, H., Xu, B., Zhang, Z., Shao, W., & Zhang, D. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3199032 · Cited by 82 · see citing works
Yu, J.-G., Wu, Z., Ming, Y., Deng, S., Li, Y., Ou, C., He, C., Wang, B., Zhang, P., & Wang, Y. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102748 · Cited by 69 · see citing works
Bi-Directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification
Qu, L., Luo, X., Wang, M., & Song, Z. (2022) · neural information processing systems · doi:10.52202/068431-1118 · Cited by 58 · see citing works
Myronenko, A., Xu, Z., Yang, D., Roth, H. R., & Xu, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87237-3_32 · Cited by 55 · see citing works
Su, Z., Tavolara, T. E., Carreno-Galeano, G. L., Lee, S. J., Gürcan, M. N., & Niazi, M. K. K. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102462 · Cited by 55 · see citing works
Structured State Space Models for Multiple Instance Learning in Digital Pathology
Fillioux, L., Boyd, J., Vakalopoulou, M., Cournède, P.-H., & Christodoulidis, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43907-0_57 · Cited by 46 · see citing works
Tavolara, T. E., Niazi, M. K. K., Gower, A. C., Ginese, M. L., Beamer, G., & Gürcan, M. N. (2021) · EBioMedicine · doi:10.1016/j.ebiom.2021.103388 · Cited by 39 · see citing works
(2021) · arXiv (Cornell University) · Cited by 31 · see citing works
One label is all you need: Interpretable AI-enhanced histopathology for oncology
Tavolara, T. E., Su, Z., Gurcan, M. N., & Niazi, M. K. K. (2023) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2023.09.006 · Cited by 28 · see citing works
SeATrans: Learning Segmentation-Assisted Diagnosis Model via Transformer
Wu, J., Fang, H., Shang, F., Yang, D., Wang, Z., Gao, J., Yang, Y., & Xu, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16434-7_65 · Cited by 26 · see citing works
Synthetic Augmentation with Large-Scale Unconditional Pre-training
Ye, J., Ni, H., Jin, P., Huang, X., & Xue, Y. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43895-0_71 · Cited by 22 · see citing works
Location-Aware Transformer Network for Few-Shot Medical Image Segmentation
Huang, W., Xiao, B., Hu, J., & Bi, X. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385286 · Cited by 16 · see citing works
Flagged first, then by citations
1 of the 44 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- [26]Wen Y, Liu W, Weller A, Raj B, and Singh R, “ SphereFace2: Binary classification is all you need for deep face recognition,” in Proc. Int. Conf. Learn. Representations, 2021.
Cited by
Sorted by citations
Employing machine learning to enhance fracture recovery insights through gait analysis
Rezapour, M., Seymour, R. B., Sims, S. H., Karunakar, M. A., Habet, N. A., & Gürcan, M. N. (2024) · Journal of Orthopaedic Research® · doi:10.1002/jor.25837 · Cited by 10 · see citing works
Artificial Intelligence in Dermatopathology: An Update and Review of the Current Literature
Abu-Dayeh, A., Cazzato, G., & Giubellino, A. (2026) · Diagnostics · doi:10.3390/diagnostics16111702 · Cited by 1 · see citing works
“Current methods rely on attention-based multiple instance learning (MIL) and transformers, saliency-inference techniques for small lesions, and uncertainty-aware heatmaps that flag areas requiring human verification [33,34].”
Sajjad, U., Niazi, K. K., Beamer, G., & Gürcan, M. N. (2025) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.3047288 · Cited by 1 · see citing works
Guo, Y., Su, Z., Koyun, O. C., Lü, H., Wesolowski, R., Tozbikian, G. H., Niazi, M. K. K., & Gürcan, M. N. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.109039 · Cited by 3 · see citing works
H&E to Oncotype DX: Predicting recurrence risk in HR+/HER2- breast cancer
Koyun, O. C., Guo, Y., Su, Z., Lü, H., Rezapour, M., Wesolowski, R., Tozbikian, G. H., Niazi, M. K. K., & Gürcan, M. N. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130469 · Cited by 1 · see citing works
Sajjad, U., Akbar, A., Su, Z., Leyva, A., Knight, D. A., Frankel, W. L., Gürcan, M. N., Chen, W., & Niazi, M. K. K. (2026) · Cancers · doi:10.3390/cancers18071150 · Cited by 1 · see citing works
Ramkumar, M., Kumar, R. S., Padmapriya, R., & Mahandiran, S. B. (2024) · International Journal of Medical Robotics and Computer Assisted Surgery · doi:10.1002/rcs.70009 · Cited by 1 · see citing works
Alrahhal, M., Hamid, A.-K., Bonny, T., & Mouti, S. (2025) · Advances in Science and Engineering Technology International Conferences (ASET) · doi:10.1109/aset66891.2025.11427916
CSFMIL: Whole slide image classification with two-stage cross-scale fusion
Li, S., Luo, Y., Chen, Z.-N., Chen, F.-J., Hu, K., & Gao, X.-P. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134807
Artificial intelligence (imaging analysis) fundamentals
Akbar, A., & Niazi, M. K. K. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-40383-5.00006-6
- Authors
- Su, Z., Rezapour, M., Sajjad, U., Niu, S., Gurcan, M. N., & Niazi, M. K. K.
- Affiliations
- Wake Forest University Health Sciences (US)
- Center for Artificial Intelligence Research, Wake Forest University School of Medicine, Winston-Salem, NC, USA
- Venue
- IEEE Journal of Biomedical and Health Informatics
- Published
- 2024-12
- Volume
- 28
- Issue
- 12
- Pages
- 7206-7216
- ISSN
- 2168-2194 (ISSN-L)
- 2168-2208
- PMC
- PMC11863751
- OpenAlex
- W4401358069
- Cited by
- 10
- References
- 44
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 2
- FWCI
- 1.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- IEEE Journal of Biomedical and Health Informatics (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Cancer Institute Gurcan (R21 CA273665)
- National Cancer Institute Niazi, Chen (R01 CA276301)
- National Institute of Biomedical Imaging and Bioengineering Niazi, Segal (R21 EB029493)
- Alliance Clinical Trials in Oncology Frankel, Niazi (GR125886)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Imaging for Blood Diseases
- Keywords
- cancer metastasis detection, whole slide images, multiple instance learning, cross-attention, small tumor detection, attention mechanism, class imbalance, interpretability, early cancer detection
- MeSH terms
- Machine Learning, Algorithms, Breast Neoplasms, Female, Humans, Image Interpretation, Computer-Assisted, Neoplasm Metastasis, Neoplasms, Databases, Factual
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
