Histographs: graphs in histopathology
Abstract
Spatial arrangement of cells of various types, such as tumor infiltrating lymphocytes and the advancing edge of a tumor, are important features for detecting and characterizing cancers. However, convolutional neural networks (CNNs) do not explicitly extract intricate features of the spatial arrangements of the cells from histopathology images. In this work, we propose to classify cancers using graph convolutional networks (GCNs) by modeling a tissue section as a multi-attributed multi-relational spatial graph of its constituent cells. Cells are detected using their nuclei in H and E stained tissue image, and each cell’s appearance is captured as a multi-attributed high-dimensional vertex feature. The spatial relations between neighboring cells are captured as edge features based on their distances in a multi-relational graph. We demonstrate the utility of this approach by obtaining classification accuracy that is competitive with CNNs, specifically, Inception-v3, on two tasks – cancerous versus non-cancerous and in situ versus invasive – on the BACH breast cancer dataset.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Protein structure representations generated by graph convolutions combined with protein sequence representations can predict the probability of compound-protein interactions.
“To be flexible with other graph- and non-graph-based methods, protein structure representations generated by graph convolutions has been combined with protein sequence representations (e.g., shallow network embedding methods or CNNs) to predict the probability of compound-protein interactions [174, 175, 176, 177].”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [177]
Fusing compound sequence, structure, and clinical implications has significantly improved drug-drug and drug-target interaction predictions.
“Fusing compound sequence, structure, and clinical implications has significantly improved drug-drug and drug-target interaction predictions.”
From Graph representation learning in biomedicine and healthcare (2022) · cites this paper as [177]
Cites
A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology
Kumar, N., Verma, R., Sharma, S., Bhargava, S., Vahadane, A., & Sethi, A. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2017.2677499 · Cited by 1,136 · cited 1× · see citing works
“To robustly detect all nuclei – including epithelial, stroma, inflammatory – we trained a fully convolutional neural network by augmenting a large annotated multi-organ dataset, 6 such that it was robust to change in organs, magnification, disease states, and stain appearance.”
MethodSelf-citationBACH: Grand challenge on breast cancer histology images
Aresta, G., Araújo, T., Kwok, S., Chennamsetty, S. S., Safwan, M., Alex, V., Marami, B., Prastawa, M. W., Chan, M. S. M., Donovan, M. J., et al. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.05.010 · Cited by 717 · cited 2× · see citing works
“Two pathologists annotated the images, and in the case of disagreement among them, the images were discarded 7.”
BackgroundMethodRobust Spatial Filtering With Graph Convolutional Neural Networks
Such, F. P., Sah, S., Domínguez, M., Pillai, S., Zhang, C., Michael, A., Cahill, N. D., & Ptucha, R. (2017) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2017.2726981 · Cited by 145 · see citing works
Basavanhally, A. N., Ganesan, S., Feldman, M. D., Shih, N. N. C., Mies, C., Tomaszewski, J., & Madabhushi, A. (2013) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2013.2245129 · Cited by 133 · cited 1× · see citing works
“Hand-crafted features of graphs have also been used for classifying ER+ breast cancer into high and low aggressiveness.(4) While hand-crafted features based on an expert’s intuition work well for a specific dataset, their utility for a general task is a matter of investigation.”
MethodDoyle, S. T., Feldman, M. D., Shih, N. N. C., Tomaszewski, J., & Madabhushi, A. (2012) · BMC Bioinformatics · doi:10.1186/1471-2105-13-282 · Cited by 104 · cited 1× · see citing works
“Until now, only hand-crafted graph features have been extracted from histopathology images, such as Voronoi diagram, Delaunay triangulation, minimum spanning tree, and nuclear density calculation for solving problems such as Gleason grading in prostate cancer 1.”
MethodLee, G., Sparks, R. E., Ali, S., Shih, N. N. C., Feldman, M. D., Spangler, E., Rebbeck, T. R., Tomaszewski, J. E., & Madabhushi, A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0097954 · Cited by 75 · cited 1× · see citing works
“Similarly, the local spatial architecture of cell clusters 2 and co-occurring gland angularity in localized sub-graphs 3 have been used to predict recurrence in prostate cancer.”
Ali, S., Veltri, R. W., Epstein, J. I., Christudass, C. S., & Madabhushi, A. (2013) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2008695 · Cited by 56 · cited 1× · see citing works
“Similarly, the local spatial architecture of cell clusters 2 and co-occurring gland angularity in localized sub-graphs 3 have been used to predict recurrence in prostate cancer.”
Flagged first, then by citations
Cited by
Sorted by citations
Graph representation learning in biomedicine and healthcare
Li, M. M., Huang, K., & Zitnik, M. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00942-x · Cited by 294 · see citing works
Federated learning for computational pathology on gigapixel whole slide images
Lu, M. Y., Chen, R. J., Kong, D., Lipkova, J., Singh, R., Williamson, D. F. K., Chen, T. Y., & Mahmood, F. (2022) · Medical Image Analysis · doi:10.1016/j.media.2021.102298 · Cited by 267 · see citing works
Chen, R. J., Lu, M. Y., Shaban, M., Chen, C., Chen, T. Y., Williamson, D. F. K., & Mahmood, F. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-87237-3_33 · Cited by 176 · see citing works
“In addition to CNNs and MIL-based approaches, GCNs and other graph-based methods have received attention in computational pathology, solving problems such as cancer classification [23,24,11,25,26,27,28], cancer grading [29,30,31], and survival analysis [32,33].”
MethodHierarchical graph representations in digital pathology
Pati, P., Jaume, G., Foncubierta–Rodríguez, A., Feroce, F., Anniciello, A. M., Scognamiglio, G., Brancati, N., Fiche, M., Dubruc, E., Riccio, D., et al. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102264 · Cited by 168 · see citing works
“Subse-quently, a CG is processed by classical machine learning techniques ( Sharma et al., 2016, 2017 ) or GNN s ( Zhou et al., 2019 ; Pati et al., 2020 ; Chen et al., 2020 ; Anand et al., 2020 ) for mapping to tissue function.”
MethodWu, Z., Trevino, A. E., Wu, E., Swanson, K., Kim, H. J., D’Angio, H. B., Preska, R., Charville, G. W., Dalerba, P. D., Egloff, A. M., et al. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00951-w · Cited by 154 · see citing works
“There has been increased interest in applying graph-based deep learning methods to spatial cellular structures in recent literature 14–16 .”
BackgroundA survey on graph-based deep learning for computational histopathology
Ahmedt‐Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2021) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2021.102027 · Cited by 153 · see citing works
“Recreated from [28]. mechanism that can be learned by gradient-based methods [82] can be formulated as, where h t is the output of a layer; and W , u w and b are trainable weights and bias.”
BackgroundMethodInfluentialTrustworthy Graph Neural Networks: Aspects, Methods, and Trends
Zhang, H., Wu, B. Y., Yuan, X., Pan, S., Tong, H., & Pei, J. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3369017 · Cited by 173 · see citing works
“When GNNs are deployed in medical systems (e.g., breast cancer subtype classification [192] or histopathology analysis [193], [194]), prediction trust-worthiness can be improved by involving GNN explanation methods.”
MethodWaqas, A., Bui, M. M., Glassy, E. F., Naqa, I. E., Borkowski, P., Borkowski, A., & Rasool, G. (2023) · Laboratory Investigation · doi:10.1016/j.labinv.2023.100255 · Cited by 149 · see citing works
Representation Learning of Histopathology Images using Graph Neural Networks
Adnan, M., Kalra, S., & Tizhoosh, H. R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00502 · Cited by 109 · see citing works
“l. showed that GNNs can be used for MIL, where each instance acts as a node in a graph [28]. Anand et al. proposes a GNN based approach to classify WSIs represented by graphs of its constituent cells [1]. 3. Background Graph Representation. A graph can be fully represented by its node list V and adjacency matrix A. Gr…”
Quantifying Explainers of Graph Neural Networks in Computational Pathology
Jaume, G., Pati, P., Bozorgtabar, B., Foncubierta–Rodríguez, A., Anniciello, A. M., Feroce, F., Rau, T. T., Thiran, J., Gabrani, M., & Göksel, O. (2021) · 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/cvpr46437.2021.00801 · Cited by 82 · see citing works
“[56] Subsequently, the CGs are processed by classical machine learning [56, 55, 54] or GNN [71, 12, 18, 44] to map the tissue structure to function relationship.”
MethodGao, Z., Lu, Z., Wang, J., Ying, S., & Shi, J. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3153671 · Cited by 72 · see citing works
“The cell-graph is fed to a GCN to perform graph-level classification [18], [19].”
MethodPati, P., Jaume, G., Fernandes, L. A., Foncubierta–Rodríguez, A., Feroce, F., Anniciello, A. M., Scognamiglio, G., Brancati, N., Riccio, D., Bonito, M. D., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60365-6_20 · Cited by 71 · see citing works
Weakly Supervised Prostate Tma Classification Via Graph Convolutional Networks
Wang, J., Chen, R. J., Lu, M. Y., Baras, A. S., & Mahmood, F. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098534 · Cited by 69 · see citing works
“For comparison, we trained GCNs with the features generated from GLCMs and VGG19 in contrast to the features generated from CPC. Results show GCNs with a combination of GLCM and CPC features achieve state-of-the-art results with an AUC of 0.9659.”
BackgroundInfluentialFatema, K., Montaha, S., Rony, M. A. H., Azam, S., Hasan, M. Z., & Jonkman, M. (2022) · Biomedicines · doi:10.3390/biomedicines10112835 · Cited by 60 · see citing works
“MobileNetV2 architecture consists of 53 layers with 3.5 million trainable parameters [39].”
InfluentialClinical applications of graph neural networks in computational histopathology: A review
Meng, X., & Zou, T. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107201 · Cited by 38 · see citing works
Vanea, C., Džigurski, J., Rukins, V., Dodi, O., Siigur, S., Salumäe, L., Meir, K. S., Parks, W. T., Hochner‐Celnikier, D., Fraser, A., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-46986-2 · Cited by 36 · see citing works
Towards Explainable Graph Representations in Digital PathologyPreprint
Jaume, G., Pati, P., Foncubierta–Rodríguez, A., Feroce, F., Scognamiglio, G., Anniciello, A. M., Thiran, J., Göksel, O., & Gabrani, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.00311 · Cited by 29 · see citing works
“Recently, graph techniques have been adopted to map DP patches to graph representations and process such graphs for pathology tasks (Gunduz et al., 2004; Zhou et al., 2019; Sharma et al., 2016; Gadiya et al., 2019; Wang et al., 2019; Pati et al., 2020).”
Wang, H., Huang, G., Zhao, Z., Liang Cheng, C., Juncker‐Jensen, A., Nagy, M. L., Lü, X., Zhang, X., & Chen, D. Z. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3249343 · Cited by 30 · see citing works
“Cell-graph methods [1], [13], [44], [45] often define graph topology with k -Nearest Neighbors.”
BackgroundMethodLiu, M., Liu, Y., Xu, P., Cui, H., Ke, J., & Ma, J. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3381994 · Cited by 27 · see citing works
“Many studies [20], [39], [40], [41], [42] focus on pathological image classification by introducing GCNs into their models.”
BackgroundLi, Y., Shen, Y., Zhang, J., Song, S., Li, Z., Ke, J., & Shen, D. G. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3317132 · Cited by 28 · see citing works
“Nevertheless, most previous studies [6], [7], [15], [16], [17], [18], [19] focus on predicting individual patches without incorporating rich contextual information.”
BackgroundMethodInfluentialBreast Cancer Classification From Digital Pathology Images via Connectivity-Aware Graph Transformer
Wang, K., Zheng, F., Cheng, L., Dai, H., Dou, Q., & Qin, J. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3381239 · Cited by 28 · see citing works
“Anand et al. [31] proposed to use graph convolutional networks (GCNs) for classifying patients into cancerous or non-cancerous groups on the Breast Cancer Histology Challenge (BACH) dataset [25].”
BackgroundGraph Neural Network for representation learning of lung cancer
Aftab, R., Qiang, Y., Zhao, J., Urrehman, Z., & Zhao, Z. (2023) · BMC Cancer · doi:10.1186/s12885-023-11516-8 · Cited by 22 · see citing works
“In order to categorize WSIs expressed in terms of their constituent pixels, the methods based on GNN have been devised [30, 31].”
MethodMulti stain graph fusion for multimodal integration in pathology
Dwivedi, C., Nofallah, S., Pouryahya, M., Iyer, J. S., Leidal, K., Chung, C., Watkins, T. R., Billin, A. N., Myers, R. P., Abel, J., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00200 · Cited by 24 · see citing works
Ding, S., Gao, Z., Wang, J., Lu, M., & Shi, J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118793 · Cited by 22 · see citing works
A graph neural network framework for mapping histological topology in oral mucosal tissue
Nair, A. A., Arvidsson, H., V., J. E. G., Tudzarovski, N., Meinke, K., & Sugars, R. V. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-05063-5 · Cited by 24 · see citing works
“Anand D, Gadiya S, Sethi A. Histographs: graphs in histopathology.”
BackgroundMethodInfluentialA Scalable Graph-Based Framework for Multi-Organ Histology Image Classification
Bai, Y., Mi, Y., Su, Y., Zhang, B., Zhang, Z., Wu, J., Huang, H., Xiong, Y., Gong, X., & Wang, W. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3199110 · Cited by 20 · see citing works
“And many [9],[39],[41].”
BackgroundMethodInfluentialClassification of Intestinal Gland Cell-Graphs Using Graph Neural Networks
Studer, L., Wallau, J., Dawson, H., et al. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412535 · Cited by 16 · see citing works
“GNNs have also been applied to a number of tasks in digital pathology, such as region-of-interest classification [14], detection of malignancy and invasiveness [7], as well as survival-analysis [15].”
MethodMs-Gwnn: Multi-Scale Graph Wavelet Neural Network for Breast Cancer Diagnosis
Zhang, M., Dong, B., & Li, Q. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761464 · Cited by 13 · see citing works
“To overcome this limitation, some researchers have attempted to use graph convolutional networks (GCNs) for pathological image classification (Zhou et al. 2019; Anand, Gadiya, and Sethi 2020; Wang et al. 2020; Adnan, Kalra, and Tizhoosh 2020).”
BackgroundDeep Learning and Its Applications in Computational Pathology
Hong, R., & Fenyö, D. (2022) · BioMedInformatics · doi:10.3390/biomedinformatics2010010 · Cited by 14 · see citing works
Prognosis prediction based on liver histopathological image via graph deep learning and transformer
Zhang, J., Sun, Z., Wang, K., Wang, C., Cheng, S., Jiang, Y. Y., & Bai, Q. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111653 · Cited by 12 · see citing works
Artificial intelligence techniques for neuropathological diagnostics and research
Alzoubi, I., Bao, G., Zheng, Y., Wang, X., & Graeber, M. B. (2022) · Neuropathology · doi:10.1111/neup.12880 · Cited by 12 · see citing works
“GNNs have already been used for ROI classi fi cation, 145 detection of malignancy and invasiveness, 146 and survival analysis.”
Cell Graph Transformer for Nuclei Classification
Lou, W., Li, G., Wan, X., & Li, H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i4.28179 · Cited by 12 · see citing works
Alzoubi, I., Zhang, L., Zheng, Y., Loh, C., Wang, X., & Graeber, M. B. (2024) · Cancers · doi:10.3390/cancers16040750 · Cited by 11 · see citing works
“Anand et al. [43] developed a framework named Histograph for breast cancer WSI classification.”
MethodHistoCartography: A Toolkit for Graph Analytics in Digital PathologyPreprint
Jaume, G., Pati, P., Anklin, V., Foncubierta–Rodríguez, A., & Gabrani, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10073 · Cited by 34 · see citing works
“…(Demir et al., 2004; Zhou et al., 2019; Wang et al., 2020; Chen et al., 2020; Pati et al., 2021), tissue regions (Pati et al., 2021), patches (Anand et al., 2020; Adnan et al., 2020; Ay-gunes et al., 2020; Zhao et al., 2020; Li et al., 2018; Levy et al., 2021), etc. Typically nodes include…”
BackgroundShen, M., & Jiang, Z. (2024) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s485724 · Cited by 7 · see citing works
“110 To address the ethical and regulatory challenges associated with AI in lymphoma management, several key initiatives are needed.”
Invasive carcinoma segmentation in whole slide images using MS-ResMTUNet
Liu, Y., Shi, H., He, Q., Fu, Y., Wang, Y., He, Y., Han, A., & Guan, T. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26413 · Cited by 7 · see citing works
“In recent research, Anand et al. [32] have utilized graph convolutional networks (GCNs) to classify cancer by modeling images from tissue sections as multi-attribute graphs of their component cells.”
XFibrosis: Explicit Vessel-Fiber Modeling for Fibrosis Staging from Liver Pathology Images
Yin, C., Liu, S., Lyu, F., Lu, J., Darkner, S., Wong, V. W., & Yuen, P. C. (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/cvpr52733.2024.01072 · Cited by 6 · see citing works
“Following [4,19,28] which mainly focus on small-scale histopathology image datasets, the position embeddings { z Xijt , z Yijt } and morphological features z Mijt are stacked together to generate the node feature embedding f ijt : where ⊕ is the concatenation operator.”
BackgroundGraph Neural Networks for Colorectal Histopathological Image Classification
Tepe, E., & Bilgin, G. (2022) · Medical Technologies Congress (TIPTEKNO) · doi:10.1109/tiptekno56568.2022.9960184 · Cited by 6 · see citing works
“Graph Convolutional Networks (GCNs) were proposed for classifying WSIs represented by graphs of their component cells [21].”
BackgroundLee, W., Song, J., Lee, C. C., et al. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-03665-z · Cited by 5 · see citing works
Deep Learning for Ventricular Arrhythmia Prediction Using Fibrosis Segmentations on Cardiac MRI Data
van Lieshout, F. E., Klein, R., Kolk, M. Z. H., van Geijtenbeek, K., Vos, R., Ruipérez-Campillo, S., Feng, R., Deb, B., Ganesan, P., Knops, R. E., et al. (2022) · Computing in cardiology · doi:10.22489/cinc.2022.191 · Cited by 3 · see citing works
“medical domain, where the data can be naturally presented in the form of graphs, such as 3D mesh classification [6].”
BackgroundKapse, S., Torre-Healy, L. A., Moffitt, R. A., et al. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761461 · Cited by 4 · see citing works
“We will explore this in future via graph neural networks [25], [26].”
MethodMulti-Scale Graphical Representation of Cell Environment
Theissen, H., Chakraborty, T., Malacrino, S., Royston, D. J., & Rittscher, J. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc48229.2022.9871710 · Cited by 4 · see citing works
“Instead of using nuclei features as most other works [7] [2] we detect and segment complete cells for feature extraction.”
MethodGraham, S., Minhas, F., Bilal, M., Ali, M., Tsang, Y. W., Eastwood, M., Wahab, N., Jahanifar, M., Hero, E., Dodd, K., et al. (2022) · medRxiv · doi:10.1101/2022.10.17.22279804 · Cited by 2 · see citing works
Artificial Intelligence, Bioinformatics, and Pathology
Levy, J., Lu, Y., Montivero, M. K. S., Ramwala, O. A., McFadden, J. R., Miles, C., Diamond, A. G., Reddy, R., Reddy, R., Hudson, T. R., et al. (2022) · Advances in Molecular Pathology · doi:10.1016/j.yamp.2023.01.002 · Cited by 1 · see citing works
Li, P., Zhang, Y., Yang, Q., Li, T., Xing, X., Yeung, M. C. F., & Chen, Z. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822452 · Cited by 2 · see citing works
“Existing methods [4] attempt to correlate the complex images with diagnostic grades by uniformly processing the whole histopathology slides.”
BackgroundMethodKousha, A. A., & Zhang, J. (2024) · doi:10.36227/techrxiv.171625742.27255985/v1 · Cited by 2 · see citing works
Position-Aware Graph-Based Learning of Whole Slide Images
Aryal, M., & Soltani, N. Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096190
“Despite all the recent advances in adoption of GNN in WSI classification they fall short in distinguishing nodes with similar local neighborhoods [7], [8], [9], [10], [14], [15].”
BackgroundEdge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction
Hasegawa, T., Arvidsson, H., Tudzarovski, N., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-34048-2_21
A Two-stage Weakly Supervised Semantic Segmentation Model Based on Pathological Tissue RelationshipsPreprint
Huang, C., Liao, S., & Peng, Y. (2023) · doi:10.22541/au.168737060.07518207/v1 · Cited by 1 · see citing works
Kousha, A. A. (2025) · Journal of Biomedical Engineering and Biosciences · doi:10.11159/jbeb.2025.015
- Authors
- Anand, D., Gadiya, S., & Sethi, A.
- Affiliations
- Indian Institute of Technology Bombay (IN)
- Venue
- Medical Imaging 2020: Digital Pathology
- Publisher
- SPIE
- Published
- 2020-03-16
- Pages
- 23
- OpenAlex
- W3010855850
- Cited by
- 53
- References
- 7
- Citations by year
- 2025: 2 · 2024: 13 · 2023: 8 · 2022: 18 · 2021: 8 · 2020: 4
- FWCI
- 3.63
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- SPIE Medical Imaging: Digital and Computational Pathology (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Biophysics › Cell Image Analysis Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Imaging for Blood Diseases
- Keywords
- histopathological images, graph convolutional networks, cancer classification, breast cancer, tumor-infiltrating lymphocytes, tumor edge, nuclei detection, H&E staining, BACH dataset
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
