Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma


A pathological evaluation is one of the most important methods for the diagnosis of malignant lymphoma. A standardized diagnosis is occasionally difficult to achieve even by experienced hematopathologists. Therefore, established procedures including a computer-aided diagnosis are desired. This study aims to classify histopathological images of malignant lymphomas through deep learning, which is a computer algorithm and type of artificial intelligence (AI) technology. We prepared hematoxylin and eosin (H&E) slides of a lesion area from 388 sections, namely, 259 with diffuse large B-cell lymphoma, 89 with follicular lymphoma, and 40 with reactive lymphoid hyperplasia, and created whole slide images (WSIs) using a whole slide system. WSI was annotated in the lesion area by experienced hematopathologists. Image patches were cropped from the WSI to train and evaluate the classifiers. Image patches at magnifications of ×5, ×20, and ×40 were randomly divided into a test set and a training and evaluation set. The classifier was assessed using the test set through a cross-validation after training. The classifier achieved the highest levels of accuracy of 94.0%, 93.0%, and 92.0% for image patches with magnifications of ×5, ×20, and ×40, respectively, in comparison to diffuse large B-cell lymphoma, follicular lymphoma, and reactive lymphoid hyperplasia. Comparing the diagnostic accuracies between the proposed classifier and seven pathologists, including experienced hematopathologists, using the test set made up of image patches with magnifications of ×5, ×20, and ×40, the best accuracy demonstrated by the classifier was 97.0%, whereas the average accuracy achieved by the pathologists using WSIs was 76.0%, with the highest accuracy reaching 83.3%. In conclusion, the neural classifier can outperform pathologists in a morphological evaluation. These results suggest that the AI system can potentially support the diagnosis of malignant lymphoma.

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Procedure for creating image patches.
Fig. 2: Preprocess during the training and testing phase.
Fig. 3: Examples of image patches.
Fig. 4: Deep neural network classifier used in this study.
Fig. 5: Examples of predicted images.
Fig. 6: Receiver operating characteristic curves of cross-validation.
Fig. 7: Model ensemble.
Fig. 8: ROC curves of the ensembled classifier as compared with the diagnosis of the pathologists.
Fig. 9: Confusion matrices of classifiers and pathologists.


  1. 1.

    Swerdlow SH, Campo E, Harris NL, Jaffe ES, Pileri SA, Stein H, et al. World Health Organization classification of tumours of haematopoietic and lymphoid tissues. Revised 4th ed. Lyon, IARC Press; 2017.

  2. 2.

    Piccaluga PP, Fuligni F, De Leo A, Bertuzzi C, Rossi M, Bacci F, et al. Molecular profiling improves classification and prognostication of nodal peripheral T-cell lymphomas: Results of a phase III diagnostic accuracy study. J Clin Oncol. 2013;31:3019–25.

    Article  Google Scholar 

  3. 3.

    LeCun Y, Bengio Y, Hinton G. Deep learning. Nat Lett. 2015;512:436–44.

    Article  Google Scholar 

  4. 4.

    Krizhevsky A, Sutskever I.Hinton GE. ImageNet classification with deep convolutional neural networks. NIPS'12 Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012;1:1097–105.

  5. 5.

    Coudray N, Ocampo PS, Sakellaropoulos T, Narula N, Snuderl M, Fenyö D, et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018;24:1559–67.

    CAS  Article  Google Scholar 

  6. 6.

    Steiner DF, MacDonald R, Liu Y, Truszkowski P, Hipp JD, Gammage C, et al. Impact of deep learning assistance on the histopathologic review of lymph nodes for metastatic breast cancer. Am J Surg Pathol. 2018;42:1636–46.

    Article  Google Scholar 

  7. 7.

    Janowczyk A, Madabhushi A. Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases. J Pathol Inform. 2016;7:29.

    Article  Google Scholar 

  8. 8.

    Muto R, Miyoshi H, Sato K, Furuta T, Muta H, Kawamoto K, et al. Epidemiology and secular trends of malignant lymphoma in Japan: Analysis of 9426 cases according to the World Health Organization classification. Cancer Med. 2018;7:5843–58.

    Article  Google Scholar 

  9. 9.

    Gascoyne RD, Campo E, Jaffe ES, Chan WC, Chan JKC, Rosenwald A, et al. World Health Organization classification of tumours of haematopoietic and lymphoid tissues. Revised 4th ed. Lyon, IARC Press; 2017. p. 291–7.

  10. 10.

    Kawamoto K, Miyoshi H, Yoshida N, Nakamura N, Ohshima K, Sone H, et al. MYC translocation and/or BCL 2 protein expression are associated with poor prognosis in diffuse large B-cell lymphoma. Cancer Sci. 2016;107:853–61.

    CAS  Article  Google Scholar 

  11. 11.

    Jaffe ES, Harris NL, Swerdlow SH, Ott G, Nathwani BN, de Jong D, et al. World Health Organization classification of tumours of haematopoietic and lymphoid tissues. Revised 4th ed. Lyon, IARC Press; 2017. p. 267–73.

  12. 12.

    Shimono J, Miyoshi H, Yoshida N, Kato T, Sato K, Sugio T, et al. Analysis of GNA13 protein in follicular lymphoma and its association with poor prognosis. Am J Surg Pathol. 2018;42:1466–71.

    Article  Google Scholar 

  13. 13.

    Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine Learning for Medical Imaging. Radiographics. 2017;37:505–15.

    Article  Google Scholar 

  14. 14.

    Uthoff J, Sieren JC. Information theory optimization based feature selection in breast mammography lesion classification. International Symposium on Biomedical Imaging (ISBI). 2018. p. 817–21.

  15. 15.

    Oksuz I, Ruijsink B, Puyol-Anton E, Sinclair M, Rueckert D, Schnabel JA, et al. Automatic left ventricular outflow tract classification for accurate cardiac MR planning. International Symposium on Biomedical Imaging (ISBI). 2018. p. 462–5.

  16. 16.

    Zhang Z, Xiao J, Wu S, Lv F, Gong J, Jiang L, et al. Deep convolutional radiomic features on diffusion tensor images for classification of glioma grades. J Digital Imaging. 2020 (Epub ahead of print).

  17. 17.

    Sakamoto M, Nakano H, Zhao K, Sekiyama T. Multi-stage neural networks with single-sided classifiers for false positive reduction and its evaluation using lung X-ray CT images. ICIAP; 2017. p. 370–9.

  18. 18.

    Kabeya Y, Takeuchi Y, Nakano H, Nishino I, Okubo M, Inoue M, et al. Physician-level muscle disease classifier for computer-aided diagnostics with deep neural networks. International Symposium on Biomedical Imaging (ISBI). 2018.

  19. 19.

    Achi HE, Belousova T, Chen L, Wahed A, Wang I, Hu Z, et al. Automated diagnosis of lymphoma with digital pathology images using deep learning. Ann Clin Lab Sci. 2019;49:153–60.

    PubMed  Google Scholar 

  20. 20.

    Mohlman JS, Leventhal SD, Hansen T, Kohan J, Pascucci V, Salama ME. Improving augmented human intelligence to distinguish Burkitt lymphoma from diffuse large b-cell lymphoma cases. Am J Clin Pathol. 2020 (Epub ahead of print).

Download references


Chugai Pharmaceutical Co., Ltd provided funding for this study based on a joint research contract.

Author information



Corresponding author

Correspondence to Hiroaki Miyoshi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Miyoshi, H., Sato, K., Kabeya, Y. et al. Deep learning shows the capability of high-level computer-aided diagnosis in malignant lymphoma. Lab Invest 100, 1300–1310 (2020).

Download citation


Quick links