CoChat
Sign Up
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 accountOpen 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.

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tmi.2022.3176598

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1. The GTP framework. (a) Each whole slide image (WSI) was divided into patches. Patches that predominantly contained the background were removed, and the remaining patches were embedded in feature vectors by a contrastive learning-based patch embedding module. The feature vectors were then used to build the graph followed by a transformer that takes the graph as the input and predicts WSI-level class label. (b) Each selected patch was represented as a node and a graph was constructed on the entire WSI using the nodes with an 8-node adjacency matrix. Here, two sets of patches of an WSI and their corresponding subgraphs are shown. The subgraphs are connected within the graph representing the entire WSI. (c) We applied three distinct augmentation functions, including random color distortions, random Gaussian blur, and random cropping followed by resizing back to the original size, on the same sample in a mini-batch. If the mini-batch size is K, then we ended up with 2 × K augmented observations in the mini-batch. The ResNet received an augmented image leading to an embedding vector as the output. Subsequently, a projection head was applied to the embedding vector which produced the inputs to contrastive learning. The projection head is a multilayer perceptron (MLP) with 2 dense layers. In this example, we considered K = 3 samples in a minibatch (A, B & C). For sample A, the positive pairs are (A1, A2) and (A2, A1), and the negative pairs are (A1, B1), (A1, B2), (A1, C1), (A1, C2). All pairs were used for computing contrastive learning loss to train the Resnet. After training, we used the embedding vectors (straight from the ResNet) for constructing the graph.
Fig. 1. The GTP framework. (a) Each whole slide image (WSI) was divided into patches. Patches that predominantly contained the background were removed, and the remaining patches were embedded in feature vectors by a contrastive learning-based patch embedding module. The feature vectors were then used to build the graph followed by a transformer that takes the graph as the input and predicts WSI-level class label. (b) Each selected patch was represented as a node and a graph was constructed on the entire WSI using the nodes with an 8-node adjacency matrix. Here, two sets of patches of an WSI and their corresponding subgraphs are shown. The subgraphs are connected within the graph representing the entire WSI. (c) We applied three distinct augmentation functions, including random color distortions, random Gaussian blur, and random cropping followed by resizing back to the original size, on the same sample in a mini-batch. If the mini-batch size is K, then we ended up with 2 × K augmented observations in the mini-batch. The ResNet received an augmented image leading to an embedding vector as the output. Subsequently, a projection head was applied to the embedding vector which produced the inputs to contrastive learning. The projection head is a multilayer perceptron (MLP) with 2 dense layers. In this example, we considered K = 3 samples in a minibatch (A, B & C). For sample A, the positive pairs are (A1, A2) and (A2, A1), and the negative pairs are (A1, B1), (A1, B2), (A1, C1), (A1, C2). All pairs were used for computing contrastive learning loss to train the Resnet. After training, we used the embedding vectors (straight from the ResNet) for constructing the graph.CC BY · PubMed Central
Fig. 2. Schematic of the GraphCAM. Gradients and relevance are propagated through the network and integrated with an attention map to produce the transformer relevancy maps. Transformer relevancy maps are then mapped to graph class activation maps via reverse pooling.
Fig. 2. Schematic of the GraphCAM. Gradients and relevance are propagated through the network and integrated with an attention map to produce the transformer relevancy maps. Transformer relevancy maps are then mapped to graph class activation maps via reverse pooling.CC BY · PubMed Central
Fig. 3. Model performance on the CPTAC and TCGA datasets. Mean ROC and PR curves along with standard deviations for the classification tasks (normal vs. tumor; LUAD vs. others; LSCC vs. others) are shown.
Fig. 3. Model performance on the CPTAC and TCGA datasets. Mean ROC and PR curves along with standard deviations for the classification tasks (normal vs. tumor; LUAD vs. others; LSCC vs. others) are shown.CC BY · PubMed Central
Fig. 4. GraphCAMs and their comparison with the expert annotations. For each WSI, we generated GraphCAMs and compared them with annotations from the pathologist. The first column contains the original WSIs, the second and third columns contain GraphCAMs and pathologist’s annotations, respectively and the fourth column contains the binarized GraphCAMs based on the threshold from the Intersection of Union (IoU) plot in the last column. The first row shows an LUAD case and the second row denotes an LSCC case.
Fig. 4. GraphCAMs and their comparison with the expert annotations. For each WSI, we generated GraphCAMs and compared them with annotations from the pathologist. The first column contains the original WSIs, the second and third columns contain GraphCAMs and pathologist’s annotations, respectively and the fourth column contains the binarized GraphCAMs based on the threshold from the Intersection of Union (IoU) plot in the last column. The first row shows an LUAD case and the second row denotes an LSCC case.CC BY · PubMed Central
Fig. 5. Graph class activation map performance. GraphCAMs generated on WSIs across the runs performed via 5-fold cross validation are shown. The first column shows the original WSIs and the other columns show the GraphCAMs with prediction probabilities on the cross-validated model runs. The first row shows a sample WSI from the LUAD class and the second row shows an WSI from the LSCC class. The colormap represents the probability by which an WSI region is associated with the output label of interest.
Fig. 5. Graph class activation map performance. GraphCAMs generated on WSIs across the runs performed via 5-fold cross validation are shown. The first column shows the original WSIs and the other columns show the GraphCAMs with prediction probabilities on the cross-validated model runs. The first row shows a sample WSI from the LUAD class and the second row shows an WSI from the LSCC class. The colormap represents the probability by which an WSI region is associated with the output label of interest.CC BY · PubMed Central
Fig. 6. GraphCAMs for failure cases. The first row shows a sample WSI from the LUAD class where the model prediction was LSCC, and the second row shows an WSI from the LSCC class where the model prediction was LUAD. The first column shows the original WSI, and the second and third columns show the generated GraphCAMs along with prediction probabilities. The bold font underneath certain GraphCAMs was used to indicate the model predicted class label for the respective cases. Since this is a 3-label classification task (normal vs. LUAD vs. LSCC), the LUAD and LSCC probability values do not add up to 1.
Fig. 6. GraphCAMs for failure cases. The first row shows a sample WSI from the LUAD class where the model prediction was LSCC, and the second row shows an WSI from the LSCC class where the model prediction was LUAD. The first column shows the original WSI, and the second and third columns show the generated GraphCAMs along with prediction probabilities. The bold font underneath certain GraphCAMs was used to indicate the model predicted class label for the respective cases. Since this is a 3-label classification task (normal vs. LUAD vs. LSCC), the LUAD and LSCC probability values do not add up to 1.CC BY · PubMed Central

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

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.

Citations

Cites

Show all 47 references

Research works printed but not linked: 2

  1. Dosovitskiy, An image is worth 16×16 words: Transformers for image recognition at scale
  2. 2021, The Cancer Genome Atlas Program

Cited by

Sorted by citations

Items 201–255 of 255

Related

See all

Metadata

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
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
Licence
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