Gastric cancer possesses great histological and molecular diversity, which creates obstacles for rapid and efficient diagnoses. Classic diagnoses either depend on the pathologist’s judgment, which relies heavily on subjective experience, or time-consuming molecular assays for subtype diagnosis. Here, we present a deep learning (DL) system to achieve interpretable tumor differentiation grade and microsatellite instability (MSI) recognition in gastric cancer directly using hematoxylin-eosin (HE) staining whole-slide images (WSIs). WSIs from 467 patients were divided into three cohorts: the training cohort with 348 annotated WSIs, the testing cohort with 88 annotated WSIs, and the integration testing cohort with 31 original WSIs without tumor contour annotation. First, the DL models comprehensibly achieved tumor differentiation recognition with an F1 values of 0.8615 and 0.8977 for poorly differentiated adenocarcinoma (PDA) and well-differentiated adenocarcinoma (WDA) classes. Its ability to extract pathological features about the glandular structure formation, which is the key to distinguishing between PDA and WDA, increased the interpretability of the DL models. Second, the DL models achieved MSI status recognition with a patient-level accuracy of 86.36% directly from HE-stained WSIs in the testing cohort. Finally, the integrated end-to-end system achieved patient-level MSI recognition from original HE staining WSIs with an accuracy of 83.87% in the integration testing cohort with no tumor contour annotation. The proposed system, therefore, demonstrated high accuracy and interpretability, which can potentially promote the implementation of artificial intelligence healthcare.
This is a preview of subscription content, access via your institution
Subscribe to Journal
Get full journal access for 1 year
We are sorry, but there is no personal subscription option available for your country.
Get time limited or full article access on ReadCube.
All prices are NET prices.
The dataset was collected and held by the Beijing Cancer Hospital. Annotated image tile datasets are available for noncommercial use at https://zenodo.org/record/5155995#.YQoeccgl3RR. Other datasets analyzed during the current study are available from the corresponding author upon reasonable request.
Source codes are available at https://github.com/Benson0704/MSI_MSS_Prediction.
Esteva, A. et al. A guide to deep learning in healthcare. Nat. Med. 25, 24–29 (2019).
Norgeot, B., Glicksberg, B. S. & Butte, A. J. A call for deep-learning healthcare. Nat. Med. 25, 14–15 (2019).
Su, F. et al. Development and validation of a deep learning system for ascites cytopathology interpretation. Gastric Cancer 23, 1041–1050 (2020).
Kather, J. N. et al. Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Med. 16, e1002730 (2019).
Hu, Y. et al. Deep learning system for lymph nodes quantification and metastatic cancer identification from whole-slide pathology images. Gastric Cancer 24, 868–877 (2021).
Kather, J. N. & Calderaro, J. Development of AI-based pathology biomarkers in gastrointestinal and liver cancer. Nat. Rev. Gastroenterol. Hepatol. 17, 591–592 (2020).
Arai, T. et al. Frequent microsatellite instability in papillary and solid-type, poorly differentiated adenocarcinomas of the stomach. Gastric Cancer 16, 505–512 (2013).
Sugimura, H. Editorial: an obsession with subtyping gastric cancer. Gastric Cancer 16, 451–453 (2013). vol.
Cancer Genome Atlas Research Network. Comprehensive molecular characterization of gastric adenocarcinoma. Nature 513, 202–209 (2014).
Kanesaka, T. et al. Clinical predictors of histologic type of gastric cancer. Gastrointest. Endosc. 87, 1014–1022 (2017).
Kuwata, T. et al. Establishment of novel gastric cancer patient-derived xenografts and cell lines: pathological comparison between primary tumor, patient-derived, and cell-line derived xenografts. Cells 8, 585 (2019).
Feng, F. et al. Prognostic value of differentiation status in gastric cancer. BMC Cancer 18, 865 (2018).
Liu, S. et al. Apparent diffusion coefficient value of gastric cancer by diffusion-weighted imaging: Correlations with the histological differentiation and Lauren classification. Eur. J. Radiol. 83, 2122–2128 (2014).
Kather, J. N. et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nat. Med. 25, 1054–1056 (2019).
Cortes-Ciriano, I., Lee, S., Park, W.-Y., Kim, T.-M. & Park, P. J. A molecular portrait of microsatellite instability across multiple cancers. Nat. Commun. 8, 15180 (2017).
Hause, R. J., Pritchard, C. C., Shendure, J. & Salipante, S. J. Classification and characterization of microsatellite instability across 18 cancer types. Nat. Med. 22, 1342–1350 (2016).
Messersmith, W. A. NCCN guidelines updates: management of metastatic colorectal cancer. J. Natl. Compr. Cancer Netw. 17, 599–601 (2019). vol.
Li, K., Luo, H., Huang, L., Luo, H. & Zhu, X. Microsatellite instability: a review of what the oncologist should know. Cancer Cell Int. 20, 16 (2020).
Hildebrand, L. A., Pierce, C. J., Dennis, M., Paracha, M. & Maoz, A. Artificial intelligence for histology-based detection of microsatellite instability and prediction of response to immunotherapy in colorectal cancer. Cancers. 13, 391 (2021).
Yamashita, R. et al. Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study. Lancet. Oncol. 22, 132–141 (2021).
Echle, A. et al. Clinical-grade detection of microsatellite instability in colorectal tumors by deep learning. Gastroenterology 159, 1406–1416 (2020). e11.
Pantanowitz, L. et al. Twenty years of digital pathology: an overview of the road travelled, what is on the horizon, and the emergence of vendor-neutral archives. J. Pathol. Inform. 9, 40 (2018).
Herrmann, M. D. et al. Implementing the DICOM standard for digital pathology. J. Pathol. Inform. 9, 37 (2018).
Goode, A., Gilbert, B., Harkes, J., Jukic, D. & Satyanarayanan, M. OpenSlide: a vendor-neutral software foundation for digital pathology. J. Pathol. Inform. 4, 27 (2013).
Bankhead, P. et al. QuPath: open source software for digital pathology image analysis. Sci. Rep. 7, 16878 (2017).
Macenko, M., et al. A method for normalizing histology slides for quantitative analysis. in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro 1107–1110 (2009).
He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition 770–778 (2016).
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proceedings of the IEEE conference on computer vision and pattern recognition 2921–2929 (2016).
Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128, 336–359 (2020).
Chen, Y.-C. et al. Clinicopathological variation of lauren classification in gastric cancer. Pathol. Oncol. Res. 22, 197–202 (2016).
Baretti, M. & Le, D. T. DNA mismatch repair in cancer. Pharmacol. Ther. 189, 45–62 (2018).
Fan, J. P., Qian, J. & Zhao, Y. J. The loss of PTEN expression and microsatellite stability (MSS) were predictors of unfavorable prognosis in gastric cancer (GC). Neoplasma 67, 1359–1366 (2020).
Suraweera, N. et al. Evaluation of tumor microsatellite instability using five quasimonomorphic mononucleotide repeats and pentaplex PCR. Gastroenterology 123, 1804–1811 (2002).
Hempelmann, J. A. et al. Microsatellite instability in prostate cancer by PCR or next-generation sequencing. J. Immunother. cancer 6, 29 (2018).
Bilal, M., et al. Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. Lancet. Digit. Heal. (2021) https://doi.org/10.1016/S2589-7500(21)00180-1.
Muti, H. S. et al. Development and validation of deep learning classifiers to detect Epstein-Barr virus and microsatellite instability status in gastric cancer: a retrospective multicentre cohort study. Lancet. Digit. Heal 3, e654–e664 (2021).
Chen, Y. et al. The immune subtypes and landscape of gastric cancer and to predict based on the whole-slide images using deep learning. Front. Immunol. 12, 685992 (2021).
Hinata, M. & Ushiku, T. Detecting immunotherapy-sensitive subtype in gastric cancer using histologic image-based deep learning. Sci. Rep. 11, 22636 (2021).
Ratti, M., Lampis, A., Hahne, J. C., Passalacqua, R. & Valeri, N. Microsatellite instability in gastric cancer: molecular bases, clinical perspectives, and new treatment approaches. Cell. Mol. Life Sci. 75, 4151–4162 (2018).
Zhang, S. et al. REUR: a unified deep framework for signet ring cell detection in low-resolution pathological images. Comput. Biol. Med. 136, 104711 (2021).
This work was supported by the National Key Research and Development Program of China (2018YFC0910700), the Major Program of National Natural Science Foundation of China (91959205).
The authors declare no competing interests.
Ethics Approval/Consent to Participate
The study was performed in accordance with relevant guidelines and regulations and approved by the institutional review board at Beijing Cancer Hospital. All patients provided written informed consent to participate in the institutional review board-approved protocol.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Su, F., Li, J., Zhao, X. et al. Interpretable tumor differentiation grade and microsatellite instability recognition in gastric cancer using deep learning. Lab Invest 102, 641–649 (2022). https://doi.org/10.1038/s41374-022-00742-6