Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Deep convolutional neural network-based algorithm for muscle biopsy diagnosis


Histopathologic evaluation of muscle biopsy samples is essential for classifying and diagnosing muscle diseases. However, the numbers of experienced specialists and pathologists are limited. Although new technologies such as artificial intelligence are expected to improve medical reach, their use with rare diseases, such as muscle diseases, is challenging because of the limited availability of training datasets. To address this gap, we developed an algorithm based on deep convolutional neural networks (CNNs) and collected 4041 microscopic images of 1400 hematoxylin-and-eosin-stained pathology slides stored in the National Center of Neurology and Psychiatry for training CNNs. Our trained algorithm differentiated idiopathic inflammatory myopathies (mostly treatable) from hereditary muscle diseases (mostly non-treatable) with an area under the curve (AUC) of 0.996 and achieved better sensitivity and specificity than the diagnoses done by nine physicians under limited diseases and conditions. Furthermore, it successfully and accurately classified four subtypes of the idiopathic inflammatory myopathies with an average AUC of 0.958 and classified seven subtypes of hereditary muscle disease with an average AUC of 0.936. We also established a method to validate the similarity between the predictions made by the algorithm and the seven physicians using visualization technology and clarified the validity of the predictions. These results support the reliability of the algorithm and suggest that our algorithm has the potential to be used straightforwardly in a clinical setting.

This is a preview of subscription content

Access options

Rent or Buy article

Get time limited or full article access on ReadCube.


All prices are NET prices.

Fig. 1: Strategy, masked sample images, and deep convolutional neural network architecture.
Fig. 2: Differentiation of IIM and classification of IIM and non-myositis muscle disease.
Fig. 3: Visualization of CNNs predictions.

Data availability

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.


  1. 1.

    Ghebreyesus, T. A. Statement for Rare Disease Day. World Health Organization. (2018).

  2. 2.

    Rare Diseases International. Rare diseases feature for first time at World Health Assembly. Available from (2019).

  3. 3.

    LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

    Article  CAS  Google Scholar 

  4. 4.

    Bejnordi, B. E. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 2199–2210 (2017).

    Article  Google Scholar 

  5. 5.

    Coudray, N. et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559–1567 (2018).

    Article  CAS  Google Scholar 

  6. 6.

    McKinney, S. M. et al. International evaluation of an AI system for breast cancer screening. Nature 577, 89–94 (2020).

    Article  CAS  Google Scholar 

  7. 7.

    Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402–2410 (2016).

    Article  Google Scholar 

  8. 8.

    Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).

    Article  CAS  Google Scholar 

  9. 9.

    Iizuka, O. et al. Deep learning models for histopathological classification of gastric and colonic epithelial tumours. Sci. Rep. 10, 1504 (2020).

    Article  CAS  Google Scholar 

  10. 10.

    Morrow, J. M. & Sormani, M. P. Machine learning outperforms human experts in MRI pattern analysis of muscular dystrophies. Neurology 94, 421–422 (2020).

    Article  Google Scholar 

  11. 11.

    Verdu-Dıaz, J. et al. Accuracy of a machine learning muscle MRI-based tool for the diagnosis of muscular dystrophies. Neurology 94, e1094–e1102 (2020).

    Article  Google Scholar 

  12. 12.

    Nishino, I. ABC in muscle pathology. Rinsho Shinkeigaku 51, 669–676 (2011).

    Article  Google Scholar 

  13. 13.

    Xie, Y., Liu, F., Xing, F. & Yang, L. Deep learning for muscle pathology image analysis. In: Deep learning and convolutional neural networks for medical imaging and clinical informatics (eds Le, L., Wang, X., Carneiro, G. & Yang, L.) Ch. 2. 23–41 (Springer, Cham, 2019)

  14. 14.

    Tizhoosh, H. R. & Pantanowitz, L. Artificial intelligence and digital pathology: challenges and opportunities. J. Pathol. Inform. 9, 38 (2018).

    Article  Google Scholar 

  15. 15.

    Kabeya, Y. et al. Physician-level aggregated classifier for genetic muscle disorders. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) 1850–1854. (IEEE, 2019).

  16. 16.

    Kohavi, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on Artificial Intelligence (IJCAI) 1137–1143 (1995).

  17. 17.

    Selvaraju, R. R. et al. Grad-cam: visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer Vision 618–626. (IEEE, 2017).

  18. 18.

    Huang, G., Liu, Z., Maaten, L. V. D. & Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2261–2269. (IEEE, 2017).

  19. 19.

    Deng, J. et al. ImageNet: a large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 248–255. (IEEE, 2009).

  20. 20.

    Dietterich, T. G. Ensemble methods in machine learning. In Proceedings of the First International Workshop on Multiple Classifier Systems, 1–15. (2000).

  21. 21.

    Liu, L. et al. On the variance of the adaptive learning rate and beyond. Conference paper at ICLR 2020. Available from (2020).

  22. 22.

    Kingma, D. & Ba, J. Adam: a method for stochastic optimization. Published as conference paper at the 3rd International Conference for Learning Representations, San Diego, 2015. (2015).

  23. 23.

    Oquab, M., Bottou, L., Laptev, I. & Sivic, J. Learning and transferring mid-level image representations using convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1717–1724. (IEEE, 2014).

  24. 24.

    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 (CVPR) 2921–2929. (2016).

  25. 25.

    Mori, K. et al. Visual explanation by attention branch network for end-to-end learning-based self-driving. In 2019 IEEE Intelligent Vehicles Symposium, 1577–1582. (IEEE, 2019).

  26. 26.

    Liang, W. C. et al. Pediatric necrotizing myopathy associated with anti-3-hydroxy-3-methylglutaryl-coenzyme A reductase antibodies. Rheumatology 56, 287–293 (2017).

    Article  Google Scholar 

  27. 27.

    Tanboon, J. & Nishino, I. Classification of idiopathic inflammatory myopathies: pathology perspectives. Curr. Opin. Neurol. 32, 704–714 (2019).

    Article  CAS  Google Scholar 

  28. 28.

    Mariampillai, K. et al. Development of a new classification system for idiopathic inflammatory myopathies based on clinical manifestations and myositis-specific autoantibodies. JAMA Neurol. 75, 1528–1537 (2018).

    Article  Google Scholar 

  29. 29.

    Chen, P. H. C. et al. An augmented reality microscope with real-time artificial intelligence integration for cancer diagnosis. Nat. Med. 25, 1453–1457 (2019).

    Article  CAS  Google Scholar 

Download references


This study was supported by AMED under Grant Number 20ek0109348s0503 and Intramural Research Grant (2-5) for Neurological and Psychiatric Disorders of NCNP.

Author information




Y.K. designed and conducted the experiments and wrote the manuscript; M.O. reviewed the pathological and genetic data and performed the physicians’ test; H.N. and S.Y. analyzed the data and contributed to writing the manuscript; M.I., M.O., Y.S., J.T., A.I., T.K., YL.C., W.Y., and S.H. performed the physicians’ test; T.I. designed the deep learning algorithm; Y.T. prepared the experimental environment; R.T. and A.T. directed the project; F.M. contributed to obtaining grants and designing the framework of the study; I.N. made the pathological diagnoses for all cases and supervised the study. All authors read and approved the final paper.

Corresponding author

Correspondence to Ichizo Nishino.

Ethics declarations

Competing interests

The authors declare no competing interests.

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

Kabeya, Y., Okubo, M., Yonezawa, S. et al. Deep convolutional neural network-based algorithm for muscle biopsy diagnosis. Lab Invest (2021).

Download citation


Quick links