Cited by 255AI in cancer detectionRadiomics and Machine Learning in Medical ImagingAdvanced Neural Network Applications

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

A Graph-Transformer for Whole Slide Image Classification

Open access

Zheng, Yi, Gindra, Rushin H., Green, Emily J., Burks, Eric J., Betke, Margrit, Beane, Jennifer E., Kolachalama, Vijaya B.·2022·IEEE Transactions on Medical Imaging

DOI 10.1109/tmi.2022.3176598PMC PMC9670036

Published version of a preprint

Open this paper in CoChat — free account Open PDF

Abstract

Deep learning is a powerful tool for whole slide image (WSI) analysis. Typically, when performing supervised deep learning, a WSI is divided into small patches, trained and the outcomes are aggregated to estimate disease grade. However, patch-based methods introduce label noise during training by assuming that each patch is independent with the same label as the WSI and neglect overall WSI-level information that is significant in disease grading. Here we present a Graph-Transformer (GT) that fuses a graph-based representation of an WSI and a vision transformer for processing pathology images, called GTP, to predict disease grade. We selected 4,818 WSIs from the Clinical Proteomic Tumor Analysis Consortium (CPTAC), the National Lung Screening Trial (NLST), and The Cancer Genome Atlas (TCGA), and used GTP to distinguish adenocarcinoma (LUAD) and squamous cell carcinoma (LSCC) from adjacent non-cancerous tissue (normal). First, using NLST data, we developed a contrastive learning framework to generate a feature extractor. This allowed us to compute feature vectors of individual WSI patches, which were used to represent the nodes of the graph followed by construction of the GTP framework. Our model trained on the CPTAC data achieved consistently high performance on three-label classification (normal versus LUAD versus LSCC: mean accuracy = 91.2 ± 2.5%) based on five-fold cross-validation, and mean accuracy = 82.3 ± 1.0% on external test data (TCGA). We also introduced a graph-based saliency mapping technique, called GraphCAM, that can identify regions that are highly associated with the class label. Our findings demonstrate GTP as an interpretable and effective deep learning framework for WSI-level classification.

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

Crossref · 10.1109/tmi.2022.3176598

Cites

47 of 47 references verified0 citation errors · 0 not checkable

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

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
Attention Is All You Need
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening
The National Lung Screening Trial Research Team (2011) · New England Journal of Medicine · doi:10.1056/nejmoa1102873 · Cited by 11,064
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027 · cited 1×
“row normalization function in transformers for computer vision tasks [36], [37].”
Background
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A. L., & Zhou, Y. (2021) · arXiv · doi:10.48550/arxiv.2102.04306 · Cited by 4,206

Flagged first, then by citations

Show all 47 references

Research works printed but not linked: 2

Dosovitskiy, An image is worth 16×16 words: Transformers for image recognition at scale
2021, The Cancer Genome Atlas Program

Sorted by citations

Items 101–200 of 255

A medical image segmentation method based on adaptive graph sparse algorithm under contrastive learning framework
Zhang, Y., Zhao, Y., Wang, M., Dong, Y., Yang, B., Gong, Y., & Feng, X. (2025) · Displays · doi:10.1016/j.displa.2025.102971 · Cited by 7
Spatially-Constrained and -Unconstrained Bi-Graph Interaction Network for Multi-Organ Pathology Image Classification
Bui, D. C., Song, B., Kim, K., & Kwak, J. T. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3436080 · Cited by 10
TAD-Graph: Enhancing Whole Slide Image Analysis via Task-Aware Subgraph Disentanglement
Wang, F., Xin, J., Zhao, W., Jiang, Y., Yeung, M. C. F., Wang, L., & Yu, L. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3545680 · Cited by 6
“GraphTransformer [29] innovatively combined GNNs with transformers for improved feature correlation and context capture.”
A Multitask Network for the Diagnosis of Autoimmune Gastritis
Cao, Y., Zhao, Y., Jin, X., Zhang, J., Zhang, G. Y., Huang, P., Zhang, G., & Han, Y.-H. (2025) · Journal of Imaging · doi:10.3390/jimaging11050154 · Cited by 6
“These efforts span various fields, including pathology images, X-ray images, CT images, ultrasound images, and endoscopic images [12–19].”
Slide-Based Graph Collaborative Training for Histopathology Whole Slide Image Analysis
Shi, J., Shu, T., Jiang, Z., Wang, W., Wu, H., & Zheng, Y. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3571152 · Cited by 5
“LAMIL [24] and GTP [25] follow the graph construction strategy of PatchGCN yet design different graph transformers to make efficient message passing.”
Self-citation
Dynamic hypergraph representation for bone metastasis analysis
Chen, Y., Li, J., Zhu, L., Yang, X., Guan, T., Shi, H., Yonghong, H., & Han, A. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108966 · Cited by 7
GraphMamba: Graph-driven spatial order-aware Mamba for medical image segmentation
Yu, C., Zhang, H., Pu, C., Lv, S., Yu, J., Wu, X., Ruan, D., Xuan, H., & Yan, Y. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112231 · Cited by 6
GCNet-Mamba: Leveraging state space models and CNN for medical image classification
Zhou, Y., Sun, L., Xiong, X., Ti, G., & Yang, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130733 · Cited by 7
Spatially aware transformer networks for contextual prediction of diabetic nephropathy progression from whole slide images
Shickel, B., Lucarelli, N., Rao, A. S., Yun, D., Moon, K. C., Seok, H. S., & Sarder, P. (2023) · SPIE Medical Imaging: Digital and Computational Pathology · doi:10.1117/12.2655266 · Cited by 7
“The past two years have seen a surge in popularity of transformer modeling for common computational pathology tasks such as WSI segmentation [40, 43, 44] and histology image classification [41, 45-47].”
Exploring the Utility of Self-Supervised Pretraining Strategies for the Detection of Absent Lung Sliding in M-Mode Lung Ultrasound
VanBerlo, B., Li, B., Wong, A. K. C., Hoey, J., & Arntfield, R. T. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00309 · Cited by 6
“This finding is consistent with the results of studies showing that SSL pretraining improves performance on external data in other medical imaging domains, such as chest X-ray classification [3, 24], dermatologic image classification [3], and pathology slide classification [28].”
Result
Neural Machine Translation Research on Syntactic Information Fusion Based on the Field of Electrical Engineering
Sang, Y., Chen, Y., & Zhang, J. (2023) · Applied Sciences · doi:10.3390/app132312905 · Cited by 7
DACTransNet: A Hybrid CNN-Transformer Network for Histopathological Image Classification of Pancreatic Cancer
Kou, Y., Xia, C., Jiao, Y., Zhang, D., & Ge, R. (2024) · Lecture notes in computer science · doi:10.1007/978-981-99-9119-8_38 · Cited by 6
NSB-H2GAN: “Negative Sample”-Boosted Hierarchical Heterogeneous Graph Attention Network for Interpretable Classification of Whole-Slide Images
Liang, M., Zhang, S., Wang, X., Li, B., Javed, M. H., Jia, X., & Wang, L. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3583127 · Cited by 6
“By constructing edges between instances (nodes), this method captures the context-aware information in slides [14], [21], [22], [23], [25], overcoming the i.i.d. limitations of CNN + MIL, and ensures that all instances within the slide contribute to the training process.”
Influential
Pulmonary diseases accurate recognition using adaptive multiscale feature fusion in chest radiography
Zhou, M., Gao, L., Bian, K., Wang, H., Wang, N., Chen, Y., & Liu, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-13479-1 · Cited by 5
“Zheng et al. 19 constructed a graph convolutional network by embedding image patches in feature vectors using contrast learning and then applied Vision Transformer to predict the whole-slice image analysis.”
CPGNet: Multimodal Graph Learning With Hierarchical Category Guidance for Multi-Label Whole Slide Image Classification
Zhao, H., Tao, D., Zhan, Y., Ni, J. F., & Chen, Y. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3620443 · Cited by 6
Learning with less: A survey of deep learning in medical imaging under varying supervision levels
Kumari, S., & Singh, P. P. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103375 · Cited by 7
FlowerFormer: Empowering Neural Architecture Encoding Using a Flow-Aware Graph Transformer
Hwang, D., Kim, H., Kim, S., & Shin, K. (2024) · 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/cvpr52733.2024.00586 · Cited by 5
“Recently, GTs show remarkable performance in various graph-level tasks, including molecular property prediction [14, 33], image classification [25, 49], and human interaction recognition [30].”
Background
Ensemble of Prior-guided Expert Graph Models for Survival Prediction in Digital Pathology
Ramanathan, V., Pati, P., McNeil, M., & Martel, A. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72086-4_25 · Cited by 6
Efficient WSI classification with sequence reduction and transformers pretrained on text
Pisula, J. I., & Bożek, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-88139-5 · Cited by 10
Transformer-Based Multimodal Fusion for Survival Prediction by Integrating Whole Slide Images, Clinical, and Genomic Data
Chen, Y., Zhao, W., & Yu, L. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230804 · Cited by 5
“Recently, graph-based methods have emerged, by which people not only focus on feature extraction and aggregation of patches but also explore the topology structure of the WSI as a whole [5].”
BackgroundMethod
Semantic and Visual Attention-Driven Multi-LSTM Network for Automated Clinical Report Generation
Huang, C., Shen, J., Hu, B., Haqqani, M. A. A., Lee, T. J., Kooner, K., Zhang, N., & Zhang, J. (2024) · Studies in computational intelligence · doi:10.1007/978-3-031-63592-2_18 · Cited by 6
Multiplexed tumor profiling with generative AI accelerates histopathology workflows and improves clinical predictionsPreprint
Pati, P., Karkampouna, S., Bonollo, F., Compérat, É., Radić, M., Spahn, M., Martinelli, A. L., Wartenberg, M., Julio, M. K., & Rapsomaniki, M. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.29.568996 · Cited by 5
“Subsequently, Graph-Transformers [41] were trained under uni-modal and multi-modal settings using both real and virtually stained images, and evaluated on held-out independent test dataset.”
Method
Top-Down Attention-Based Multiple Instance Learning for Whole Slide Image Analysis
Reisenbüchler, D., Deng, R., Matek, C., Feuerhake, F., & Merhof, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04927-8_62 · Cited by 5
Diagnostic text-guided representation learning in hierarchical classification for pathological whole slide image
Li, J., Sun, Q., Yan, R., Wang, Y., Fu, Y., Wei, Y., Guan, T., Shi, H., He, Y., & Han, A. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103894 · Cited by 11
MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification
Xiang, T., Li, Y., Zhang, Q., & Li, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04971-1_40 · Cited by 4
FourierMIL: Fourier Filtering-based Multiple Instance Learning for Whole Slide Image Analysis
Zheng, Y., Sharma, H., Betke, M., Cherry, J. D., Mez, J., Beane, J., & Kolachalama, V. B. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02679-x · Cited by 4
“All models were evaluated using a consistent image resolution of 20X, in line with recommendations from the original publications.”
Self-citation
Object detection: A novel AI technology for the diagnosis of hepatocyte ballooning
Zheng, T., Sha, J., Deng, Q., Geng, S., Xiao, S., Yang, W., Byrne, C. D., Targher, G., Li, Y., Wang, X., et al. (2023) · Liver International · doi:10.1111/liv.15799 · Cited by 7
“Significant advances have been made in the diagnosis and treatment of primary brain tumours, 101 accurate prediction of lymph node metastasis, 102 precise classification of lung cancer, 103 and other related areas.”
Multi-Scale Heterogeneity-Aware Hypergraph Representation for Histopathology Whole Slide Images
Han, M., Zhang, X., Yang, D., Liu, T., Kuang, H., Feng, J., & Zhang, L. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10688366 · Cited by 5
“They include MIL-based methods: AttnMIL [28], DSMIL [11], CLAM-MB , and CLAM-SB [29]; homogeneous graph-based methods: PatchGCN [30], GTNMIL [31]; and heterogeneous graph-based method: HEAT [32].”
MethodInfluential
HCGN: Hierarchical Convolution and Graph Network for Predicting Knee Osteoarthritis
Yang, X., Tang, P., Zou, K., & Dai, D. (2024) · IEEE International Conference on Medical Artificial Intelligence (MedAI) · doi:10.1109/medai62885.2024.00018 · Cited by 4
“Yi et al. proposed the Graph-Transformer model [28] for the classification of WSIs, which is an interpretable and effective framework for WSI-level classification.”
Pseudo-label attention-based multiple instance learning for whole slide image classification
He, J., Ping, W., Cai, J., Tang, D., Yao, S., & Liu, R. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109908 · Cited by 3
SSR-Mam2MIL: Spatial sequence reordering Mamba2 based multiple instance learning for computational pathology
Zhang, H., Xu, H., & Lv, R. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109063 · Cited by 3
Evolving graph convolutional network with transformer for CT segmentation
Cui, H., Jin, Q., Wu, X., Wang, L., Zhang, T., Nakaguchi, T., Xuan, P., & Feng, D. D. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112069 · Cited by 3
Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis
Gunes, I., Bernstein, E. J., Cowper, S. E., Panse, G., Pradhan, N., Camacho, L. D., Page, N., Bundschuh, E., Williams, A., Carns, M. A., et al. (2025) · Arthritis Research & Therapy · doi:10.1186/s13075-025-03508-9 · Cited by 3
“This may include developing more sophisticated frameworks such as graph neural networks [46–48] and improving averaging methods across selected patches to better represent the comprehensive details of the histological images.”
Self-citation
Histo-Miner: Deep learning based tissue features extraction pipeline from H&E whole slide images of cutaneous squamous cell carcinoma
Sancéré, L., Lorenz, C., Helbig, D., Persa, O., Dengler, S., Kreuter, A., Laimer, M., Lang, R., Fröhlich, A., Landsberg, J., et al. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013907 · Cited by 3
“A large panel of tasks can be performed by machine learning and deep learning models on this type of images: segmentation of nuclei and tumors in the WSIs [2,3], image classification [4], or discovery of new biomarkers [5].”
Transformer for medical image analysis
Shamshad, F., Khan, S. A., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2024) · Elsevier eBooks · doi:10.1016/b978-0-32-385124-4.00012-x · Cited by 3
Enhancing Whole Slide Image Classification with Discriminative and Contrastive Learning
Liang, P., Zheng, H., Li, H., Gong, Y., Bakas, S., & Yong Fan, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72083-3_10 · Cited by 3
Leveraging commonality across multiple tissue slices for enhanced whole slide image classification using graph convolutional networks
Noree, S., Robles, W. R. Q., Ko, Y. S., & Yi, M. Y. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01760-8 · Cited by 3
“Given their ability to model non-square grid convolutions and capture spatial relationships, graph-based representations have proven to be a powerful tool in WSI analysis and have been successfully applied in various clinical applications, including WSI classification [8–10].”
Probabilistic smooth attention for deep multiple instance learning in medical imaging
Castro-Macías, F. M., Morales-Álvarez, P., Wu, Y., Molina, R., & Katsaggelos, A. K. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112097 · Cited by 4
Multi-attribute embedding network for breast cancer subtyping prediction reveals intrinsic molecular properties hidden in H&E images
Liu, Q., Zhao, Z., Liang, S., Zhang, Y., Jin, D., Guo, L., Zheng, S., Ying, J., & Bai, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109189 · Cited by 2
Topology-aware cross-modal learning with dynamic gradient modulation for survival prediction
Yuan, Y., Li, G., Jiang, N., Lv, J., Ye, C., Ji, D., Ren, Y., Luo, G., & Zhang, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130492 · Cited by 2
Enhancing Lung Cancer Histopathological Subtyping via Fuzzy Patch Scoring Integrated into an Ensemble Deep Learning Framework
Hosseini, M. M., & Rodd, B. (2025) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi67747.2025.11269475 · Cited by 2
“Seven of these baselines are non-graph-based approaches, including the TCGA-LUAD baseline, ResNet-101, DeepSlid [14], an unsupervised model [19], a weakly supervised model [15], Graph ViT [21], and ABMIL-GTI [21] (Table IV).”
Prioritized scanning: Combining spatial information multiple instance learning for computational pathology
Zhang, Y., Wang, J., Liang, B., Yang, Y., Wu, S., & Tong, C. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113151 · Cited by 2
Torchmil: A PyTorch-based library for deep multiple instance learning
Castro-Macías, F. M., Sáez-Maldonado, F. J., Morales-Álvarez, P., & Molina, R. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133286 · Cited by 2
Multi-level Graph Representations of Melanoma Whole Slide Images for Identifying Immune Subgroups
Godson, L., Alemi, N., Nsengimana, J., Cook, G. P., Clarke, E. L., Treanor, D. E., Bishop, D. T., Newton‐Bishop, J., & Magee, D. R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-55088-1_8 · Cited by 2
Concrete Crack Detection Using Multi-Source Data Augmentation in Deep Learning Models
Einarson, D., & Mengistu, D. (2024) · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) · doi:10.1109/acdsa59508.2024.10467321 · Cited by 2
“New deep learning methods in the domain of generative AI ([12]) have significantly improved the performance of machine learning solutions in the areas of vision, image classification and natural language processing (NLP).”
Background
Harnessing artificial intelligence for transpathology advancements
Liu, Z., Dong, S., Zhang, L., & Shi, K. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95223-1.00022-9 · Cited by 2
Semantics-Aware Attention Guidance for Diagnosing Whole Slide Images
Liu, K., Wu, W., Elmore, J. G., & Shapiro, L. G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72086-4_56 · Cited by 3
A Hierarchical Geometry-Guided Transformer for Histological Subtyping of Primary Liver Cancer
Lu, A., Liu, M., Jiao, Y., Xu, G., Gong, H., Cai, C., Chen, J., & Xu, J. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11357200 · Cited by 2
“The methods for comparison include: ABMIL [15], DSMIL [17], CLAM-SB [23], CLAM-MB [23], TransMIL [25], ACMIL [33], IBMIL [18], MHIM-MIL [27], Patch-GCN [8], GTMIL [34], and NPKC-MIL [30].”
PathEX: Make good choice for whole slide image extraction
Yang, X., Zhang, R., Yang, Y., Zhang, Y., & Chen, K. (2024) · PLoS ONE · doi:10.1371/journal.pone.0304702 · Cited by 2
Enhancing Cross-Institute Generalisation of GNNs in Histopathology Through Multiple Embedding Graph Augmentation (MEGA)
Campbell, J., Vanea, C., Salumäe, L., Meir, K. S., Hochner‐Celnikier, D., Hochner, H., Laisk, T., Ernst, L. M., Lindgren, C. M., Xie, W., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-66958-3_20 · Cited by 1
Tissue type classification for whole slide histological images with graph convolutional neural network
Sun, Z., Khvostikov, A. V., & Krylov, A. S. (2024) · International Conference on Biomedical Imaging, Signal Processing (ICBSP) · doi:10.1145/3707172.3707175 · Cited by 1
A Hybrid Transformer-Graph Model for Multi-Class Lymph Node Segmentation in Histopathology
Budginaite, E., Magee, D. R., Kloft, M., Nankivell, M. G., Langley, R. E., Cunningham, D., Allum, W., Raghuram, G., Yoshikawa, T., Oshima, T., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-98694-9_7 · Cited by 1
An adaptive multi-graph fusion for tumor grading in pathology images
Alzoubi, I., Xin, B., Bjerkvig, R., Wang, J., & Wang, X. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112214 · Cited by 2
BPMambaMIL: A bio-inspired prototype-guided multiple instance learning for oncotype DX risk assessment in histopathology
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 4
KPVG: Knowledge-prompted vision-genomics model for cancer survival prediction in whole slide images
Shi, J., Li, C., Zheng, Y., & Fu, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103660 · Cited by 2
Self-citation
Integrating GANs, Contrastive Learning, and Transformers for Robust Medical Image Analysis
Heng, Y., Khan, F. G., Yinghua, M., Khan, A., Ali, F., Khan, N., & Kwak, D. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3604845 · Cited by 2
Interpretable Gastric Cancer Survival Prediction via Concept Bottleneck Model
Zhao, F., Li, A., Tian, X., & Wang, M. (2025) · International Conference on Artificial Intelligence Technologies and Applications (ICAITA) · doi:10.1109/icaita67588.2025.11137851 · Cited by 1
“By such procedures, such methods [4-6] have attained success in gastric cancer prognosis tasks.”
Machine Learning Models Using General and Tissue-Specific Feature Extractors for Accurate Subtyping of Biopsy Samples: Advancing Lung Cancer Diagnosis in Latin America
de Alencar, V. T. L., Alves, F. N. B., Velozo, G. D. S., Mizutani, L. E. L., Caminha, I., Silva, G. B., de Lima, V. C. C., & Tavora, F. R. F. (2025) · JTO Clinical and Research Reports · doi:10.1016/j.jtocrr.2025.100906 · Cited by 1
A cognitive dual-attention network with feature specificity for automated CRC polyp detection
Raseena, T. P., Balasundaram, S. R., & Kumar, J. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122727 · Cited by 1
Whole slide image redundancy reduction for efficient pathological diagnosis
Li, S., Chen, Z., Chen, F., & Gao, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.109289 · Cited by 1
HMHGT: Hierarchical Multi-Scale Hypergraph Representation for Histopathology Whole Slide Images
Wang, S., Jiang, L., & Qiu, C. (2026) · IEEE Access · doi:10.1109/access.2026.3655215 · Cited by 1
“Zheng et al. [18] further advanced this direction with GTMIL, a graph-transformer architecture that integrates the spatial modeling capabilities of GNNs with the global attention mechanisms of transformers.”
A hypergraph-based model for tumor prognosis using local and global information fusion on H&E-stained histology images
Tang, C., Liu, J., Cui, Y., Li, Z., Zhang, X., Yao, S., Lin, H., Yang, D., Liu, Z., Zhao, W., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.103991 · Cited by 1
GE-ViP: Graph-enhanced vision pipeline for weakly supervised histopathology slide analysis
Rahman, M., Ahad, J. I., Hassan, M. M., Moursalin, G., & Momen, S. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133230 · Cited by 1
Mani-NENet: Manifold Neuron Energy Network-Enhancing Dysplastic Cell Perception for Lung Adenocarcinoma Subtype Recognition
Mao, Y., Xu, X., Luo, J., Cui, H., Luo, F., Huang, P., & Feng, P. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3670553 · Cited by 1
“Furthermore, we also found that most existing studies [18], [19], [32], [33] focus primarily on the low-level subtype identiﬁcation of invasive lung adenocarcinoma.”
PTCMIL: multiple instance learning via prompt token clustering for whole slide image analysis
Zhao, B., Kim, S., Chen, H., Zhou, C., Gao, Z., Wang, G., & Li, X. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104013 · Cited by 4
Exploiting Label-Independent Regularization from Spatial Patterns for Whole Slide Image Analysis
Wu, W., Xu, X., Gao, C., Diao, X., Li, S. X., & Gui, J. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00833 · Cited by 1
“This observation leads us to hypothesize that clean, label-independent regularization should lead to more robust representations without the risk of introducing noise.”
Deep learning-powered quantification of endocrine cells and CD3+ T cells in the natural history of type 1 diabetes
Kang, S., Maya, N., MORILLO, M., OUTAR, M., Posgai, A. L., Lamb, D. G., Campbell‐Thompson, M., & Kim, S. (2026) · Diabetologia · doi:10.1007/s00125-026-06742-1 · Cited by 1
Lymph node metastases detection in Whole Slide Images using prototypical patterns and transformer-guided multiple instance learning
Heinlein, L., Benz, M., Kuritcyn, P., Bruns, V., Hartmann, A., Keil, F., Geppert, C. I., Evert, K., & Wittenberg, T. C. (2023) · Current Directions in Biomedical Engineering · doi:10.1515/cdbme-2023-1042 · Cited by 2
Norma: A Noise Robust Memory-Augmented Framework for Whole Slide Image Classification
Bai, Y., Zhang, B., Zhang, Z., Yan, S., Ma, Z., Liu, W., Zhou, X., Gong, X., & Wang, W. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72983-6_24 · Cited by 1
Intervention-Based Mixup Augmentation for Multiple Instance Learning in Whole-Slide Image Survival Analysis
Tang, L.-Z., Zhang, Z., Yang, J., Feng, Y., Wang, Q., Sun, S., & Shao, H. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3592359 · Cited by 2
“Most research focuses on diagnosis and grading (MIL Classification) [4], [5], [6], [7], [8], [9], while studies on time-to-event analysis (MIL Regression) [10], [11] remain relatively scarce.”
Prompt-guided foundation model tuning for pathology image classification
Lin, Y., Zhu, Z., Cheng, K.-T. T., & Chen, H. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104214 · Cited by 4
RACR-MIL: Rank-aware contextual reasoning for weakly supervised grading of squamous cell carcinoma using whole slide images
Choudhary, A., Aouad, M., Saboo, K., Hwang, A., Kechter, J. A., Bordeaux, B., Bhullar, P. K., DiCaudo, D. J., Nelson, S., Comfere, N. I., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104262 · Cited by 1
When Multiple Instance Learning Meets Foundation Models: Advancing Histological Whole Slide Image AnalysisPreprint
Lu, C. Y., Xu, H., Wang, M., Shi, D., Qin, H., Madabhushi, A., Gao, P., & Cong, F. (2024) · Research Square · doi:10.21203/rs.3.rs-4704418/v1 · Cited by 1
Hypergraph-based Multi-instance Contrastive Reinforcement Learning for Annotation-free Pan-cancer Survival Prediction on Whole Slide Histology ImagesPreprint
Lu, C. Y., Tang, C., Cui, Y., Liu, J., Li, Z., Zhang, X., Suo, Y., Lin, H., Yang, D., Liu, Z., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4918308/v1 · Cited by 1
CLWD: a Chinese histopathology dataset for lung adenocarcinoma subtype classification
Chen, Y., Zhao, H., Wang, L., Li, L., Liu, R., Jiang, Y., Tang, P., Li, Y., Ni, J. F., Tao, D., et al. (2026) · Scientific Data · doi:10.1038/s41597-026-06906-z · Cited by 1
Artificial intelligence in pathology and application to liver disease
Caldéraro, J., & Vij, M. (2023) · Elsevier eBooks · doi:10.1016/b978-0-323-99136-0.00014-3 · Cited by 1
Cross-Channel and Regional Node Relation Enhanced Hybrid Graph Convolution Transformer for Ct SegmentationPreprint
Cui, H., Jin, Q., Wu, X., Wang, L., Zhang, T., Nakaguchi, T., Xuan, P., & Feng, D. D. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4558735
Annotation-efficient deep learning for breast cancer whole-slide image classification using Tumor Infiltrating Lymphocytes and slide-level labelsPreprint
Perera, R. D., Savas, P. S., Senanayake, D., Salgado, R., Joensuu, H., O’Toole, S. A., Li, J., Loi, S., & Halgamuge, S. K. (2023) · Research Square · doi:10.21203/rs.3.rs-3158169/v1
Digital Pathology, Deep Learning, and Cancer: A Narrative ReviewPreprint
Williams, D. K. A., Graifman, G., Hussain, N., Amiel, M., Priscilla, T., Reddy, A., Haider, A., Kavitesh, B. K., Li, A., Alishahian, L., et al. (2024) · medRxiv · doi:10.1101/2024.03.14.24304308
Digital pathology and artificial intelligence in cancer research
Han, C., Lu, C. Y., & Liu, Z. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95223-1.00016-3
Interpretable Phenotypic Profiling of 3D Cellular Morphodynamics
Vries, M. D., Naidoo, R., Fourkioti, O., Dent, L., Curry, N., Dunsby, C. W., & Bakal, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72117-5_45
Using segmentation methods based on artificial intelligence technologies to build 3D models
Иванов, В. М., Knyazev, A., Strelkov, S., Sinegub, A. V., & Smirnov, A. Y. (2024) · Vestnik nevrologii psihiatrii i nejrohirurgii (Bulletin of Neurology Psychiatry and Neurosurgery) · doi:10.33920/med-01-2412-15
Leveraging Graph Theory for Advanced Embryo Stage Identification in Assisted Reproductive Technologies
Muñoz-Herrera, S., & Paredes, O. (2025) · World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany · doi:10.1007/978-3-031-82123-3_14
Not seeing the trees for the forest. The impact of neighbours on graph-based configurations in histopathology
Fourkioti, O., Vries, M. D., Naidoo, R., & Bakal, C. (2025) · BMC Bioinformatics · doi:10.1186/s12859-024-06007-x · Cited by 2
Simpseudo: Enhancing Whole Slide Imaging Classification with Similarity and Prototype-Based Example-Level Pseudo-SupervisionPreprint
Yu, H., Diao, Y., Liu, X., Wang, H., Zhu, J., & Gao, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5142683
Multi-Scale Graph-Based Cross-Attention Transformer for Whole Slide Image Classification
Wan, J., Hao, Y., Ma, X., & Wang, H. (2024) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv63323.2024.10918883
“To validate the effectiveness of the proposed method in this paper, we compare its classification performance with existing MIL algorithms, including the classical attention-based pooling method ABMIL[12] and its variants CLAM[6] and DSMIL[14], the Transformer-based method TransMIL, and the Graph-Transformer-based met…”
MFANEDH: Multimodal Fusion of MRI, PET, CT, and Ultrasound Using Advanced Neural Architectures for Enhanced Early Detection of Heart Cancer
Khandare, K. S., Divtelwar, G., Suri, C., & Bondade, A. (2024) · International Conference on Emerging Trends in Engineering and Medical Sciences (ICETEMS) · doi:10.1109/icetems64039.2024.10965068
Effective latent hierarchical feature fusion in multiple instance learning for Whole Slide Image classification
Lan, Q., Wu, Y., Ding, W., & Yuan, J. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113191
Predicting Ulcer in H&E Images of Inflammatory Bowel Disease Using Domain-Knowledge-Driven Graph Neural Network
Ding, R., Li, L., Soans, R. E., Shah, T., Krishnan, R., Sze, M. A., Lukyanov, S., Deshpande, Y., & Chen, A. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980783
“[16] 5) GPT: A graph transformer model [17] that first passes the WSI-built graph into a GNN followed by a vision transformer to classify WSIs.”
Influential
LungNeXt: An Attention-Based Classification Network for Non-standard Medical Images of Lung Tumors
Wang, Y., Zhang, P., Lin, C., Zheng, Z., Lin, Z., Zhou, H., Lin, H., Zhao, G., & Yang, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6960-8_15
Comparative Validation of Graph Neural Networks for Glioma Grading in Whole Slide Images
Chen, Q., Xu, H., Qin, H., Hao, X., Jin, S., Hämäläinen, T., & Cong, F. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2432-4_4
SjöGNet: A Multimodal Graph Transformer for Integrated Analysis of Salivary Gland Biopsies and Clinical Data in Sjögren's DiseasePreprint
Brahim, I., Zeghlache, R., Frutoso, M., Rochais, M. L., Bandeira, M., Romão, V. C., Asselineau, J., Jaloustre, H., Hillion, S., Saraux, A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5333602
Dual-track collaboration: Joint processing of heterogeneous positive and negative graph convolutional network for whole-slide image analysis
Liang, M., Wang, X., Li, B., Zhang, S., Javed, M. H., Wang, Y., Jia, X., & Wang, L. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108970
Multi-headed Graph-Based Attention Aided U-Net Model for Nuclei Segmentation
Dutta, S., Bose, S., Roy, D., Kaplun, D., Sinitca, A., & Sarkar, R. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6688-1_16
BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology
Gallagher-Syed, A., Senior, H., Alwazzan, O., Pontarini, E., Bombardieri, M., Pitzalis, C., Lewis, M., Barnes, M. R., Rossi, L., & Slabaugh, G. (2025) · 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/cvpr52734.2025.00970
“DeepGraph-Conv [37], PatchGCN [9], GTP [63], CAMIL [16] and HEAT [8] adopt this approach by constructing a graph connecting either the k -nearest neighbors in feature space or region adjacent patches.”
LUF-Net:A U-Net Based Medical Classification Model
Wang, Y., Wang, H., & Liu, Z. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04601-x
Reducing Variability of Multiple Instance Learning Methods for Digital Pathology
Mammadov, A., Folgoc, L. L., Hocquet, G., & Gori, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04981-0_48
Helicobacter Pylori Infection Diagnosis from Endoscopic Images via Multi-Class Token based Multiple Instance Learning
Ting, W.-T., Tsai, Y.-C., Huang, C.-R., Cheng, H., & Sheu, B. (2025) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb66090.2025.11177067
“To further formulate the correlations of instances in the WSI, graph-based multiple instance learning methods [30]– [32] are proposed.”
Image super-resolution reconstruction algorithm based on multi-scale recursive attention and feature fusion
Liu, H., & Wang, M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0333398
“However, traditional image reconstruction algorithms are often affected by multiple factors, resulting in low efficiency in extracting and utilizing feature information from the original image, leading to severe distortion of the output image [31].”
Graph neural networks in the nephropathological diagnosis of antibody-mediated rejection
Mateos-Aparicio-Ruiz, I., Pedraza, A., Altini, N., González, L., & Bueno, G. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.10.005
“In contrast to previous work that relies on dense tiling of the entire WSI [29,30], we construct graphs using only regions of interest (glomeruli, arteries, and cortical TI tiles).”

Authors: Zheng, Y., Gindra, R. H., Green, E. J., Burks, E. J., Betke, M., Beane, J. E., & Kolachalama, V. B.
Affiliations: Boston University (US)
ORCID: Zheng, Yi
Gindra, Rushin H.
Green, Emily J.
Burks, Eric J.
Betke, Margrit
Beane, Jennifer E.
Kolachalama, Vijaya B.
Venue: IEEE Transactions on Medical Imaging
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Published: 2022-11
Volume: 41
Issue: 11
Pages: 3003-3015
ISSN: 0278-0062 (ISSN-L)
1558-254X
DOI: 10.1109/tmi.2022.3176598
PMC: PMC9670036
OpenAlex: W4281257868
Cited by: 255
References: 47
Citations by year: 2026: 54 · 2025: 81 · 2024: 73 · 2023: 42 · 2022: 5
FWCI: 16.55
Type: journal article
Language: en
Open access: hybrid
doi.org
Licence: cc-by
creativecommons.org/licenses/by/4.0/legalcode (vor)
creativecommons.org/licenses/by/4.0/legalcode (am)
Locations: IEEE Transactions on Medical Imaging (publishedVersion, cc-by)
medRxiv (acceptedVersion, cc-by)
PubMed (publishedVersion)
PubMed Central (acceptedVersion, cc-by)
arXiv (Cornell University) (submittedVersion)
arXiv (Cornell University) (cc-by)
Funders: Grants from the National Institutes of Heath (R21-CA253498, R01-HL159620)
Johnson & Johnson Enterprise Innovation, Inc.
American Heart Association (20SFRN35460031)
Karen Toffler Charitable Trust
National Science Foundation (1551572, 1838193)
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 › Advanced Neural Network Applications
Keywords: whole slide image classification, graph transformer, vision transformer, lung adenocarcinoma, squamous cell carcinoma, lung cancer histopathology, contrastive learning, interpretability
MeSH terms: Guanosine Triphosphate, Image Processing, Computer-Assisted, Proteomics

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

A Graph-Transformer for Whole Slide Image Classification

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks