Biomolecules & Therapeutics

The Korean Society of Applied Pharmacology (한국응용약물학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of Mouse Lung Metastatic Tumor with Deep Learning

  • Lee, Ha Neul (Department of Biomedical, Laboratory Science, Namseoul University) ;
  • Seo, Hong-Deok (Department of Industrial Promotion, Spatial Information Industry Promotion Agency) ;
  • Kim, Eui-Myoung (Department of Spatial Information Engineering, Namseoul University) ;
  • Han, Beom Seok (Department of Pharmaceutical Engineering, Hoseo University) ;
  • Kang, Jin Seok (Department of Biomedical, Laboratory Science, Namseoul University)
  • Received : 2021.08.02
  • Accepted : 2021.09.13
  • Published : 2022.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

Traditionally, pathologists microscopically examine tissue sections to detect pathological lesions; the many slides that must be evaluated impose severe work burdens. Also, diagnostic accuracy varies by pathologist training and experience; better diagnostic tools are required. Given the rapid development of computer vision, automated deep learning is now used to classify microscopic images, including medical images. Here, we used a Inception-v3 deep learning model to detect mouse lung metastatic tumors via whole slide imaging (WSI); we cropped the images to 151 by 151 pixels. The images were divided into training (53.8%) and test (46.2%) sets (21,017 and 18,016 images, respectively). When images from lung tissue containing tumor tissues were evaluated, the model accuracy was 98.76%. When images from normal lung tissue were evaluated, the model accuracy ("no tumor") was 99.87%. Thus, the deep learning model distinguished metastatic lesions from normal lung tissue. Our approach will allow the rapid and accurate analysis of various tissues.

Keywords

Acknowledgement

We would like to thank Ms. Nahyeon Gu and Kanghee Ryu for their technical assistance (Namseoul University). This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1F1A1058721).

References

  1. Aeffner, F., Zarella, M. D., Buchbinder, N., Bui, M. M., Goodman, M. R., Hartman, D. J., Lujan, G. M., Molani, M. A., Parwani, A. V., Lillard, K., Turner, O. C., Vemuri, V. N. P., Yuil-Valdes, A. G. and Bowman, D. (2019) Introduction to digital image analysis in whole-slide imaging: a white paper from the Digital Pathology Association. J. Pathol. Inform. 10, 9. https://doi.org/10.4103/jpi.jpi_82_18
  2. Boorman, G. A., Maronpot, R. R. and Eustis, S. L. (1994) Rodent carcinogenicity bioassay: past, present, and future. Toxicol. Pathol. 22, 105-111. https://doi.org/10.1177/019262339402200204
  3. Bos, P. D., Nguyen, D. X. and Massague, J. (2010) Modeling metastasis in the mouse. Curr. Opin. Pharmacol. 10, 571-577. https://doi.org/10.1016/j.coph.2010.06.003
  4. Bradley, A. and Jacobsen, M. (2019) Toxicologic Pathology Forum*: opinion on considerations for the use of whole slide images in GLP pathology peer review. Toxicol. Pathol. 47, 100-107. https://doi.org/10.1177/0192623318818790
  5. Brent, R. and Boucheron, L. (2018) Deep learning to predict microscope images. Nat. Methods 15, 868-870. https://doi.org/10.1038/s41592-018-0194-9
  6. Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyo, D., Moreira, A. L., Razavian, N. and Tsirigos, A. (2018) Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559-1567. https://doi.org/10.1038/s41591-018-0177-5
  7. Farahani, N., Parwani, A. V. and Pantanowitz, L. (2015) Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathol. Lab. Med. Int. 7, 23-33.
  8. Gilhodes, J. C., Jule, Y., Kreuz, S., Stierstorfer, B., Stiller, D. and Wollin, L. (2017) Quantification of pulmonary fibrosis in a bleomycin mouse model using automated histological image analysis. PLoS ONE 12, e0170561. https://doi.org/10.1371/journal.pone.0170561
  9. Hart, I. R. and Fidler, I. J. (1980) Role of organ selectivity in the determination of metastatic patterns of B16 melanoma. Cancer Res. 40, 2281-2287.
  10. Hoefling, H., Sing, T., Hossain, I., Boisclair, J., Doelemeyer, A., Flandre, T., Piaia, A., Romanet, V., Santarossa, G., Saravanan, C., Sutter, E., Turner, O., Wuersch, K. and Moulin, P. (2021) HistoNet: a deep learning-based model of normal histology. Toxicol. Pathol. 49, 784-797. https://doi.org/10.1177/0192623321993425
  11. Kannan, S., Morgan, L. A., Liang, B., Cheung, M. G., Lin, C. Q., Mun, D., Nader, R. G., Belghasem, M. E., Henderson, J. M., Francis, J. M., Chitalia, V. C. and Kolachalama, V. B. (2019) Segmentation of glomeruli within trichrome images using deep learning. Kidney Int. Rep. 4, 955-962. https://doi.org/10.1016/j.ekir.2019.04.008
  12. Komura, D. and Ishikawa, S. (2019) Machine learning approaches for pathologic diagnosis. Virchows Arch. 475, 131-138. https://doi.org/10.1007/s00428-019-02594-w
  13. Kuo, K. H. and Leo, J. M. (2019) Optical versus virtual microscope for medical education: a systematic review. Anat. Sci. Educ. 12, 678-685. https://doi.org/10.1002/ase.1844
  14. Mazer, B. L., Homer, R. J. and Rimm, D. L. (2019) False-positive pathology: improving reproducibility with the next generation of pathologists. Lab. Invest. 99, 1260-1265. https://doi.org/10.1038/s41374-019-0257-2
  15. Nam, S., Chong, Y., Jung, C. K., Kwak, T. Y., Lee, J. Y., Park, J., Rho, M. J. and Go, H. (2020) Introduction to digital pathology and computer-aided pathology. J. Pathol. Transl. Med. 54, 125-134. https://doi.org/10.4132/jptm.2019.12.31
  16. Pell, R., Oien, K., Robinson, M., Pitman, H., Rajpoot, N., Rittscher, J., Snead, D. and Verrill, C. (2019) The use of digital pathology and image analysis in clinical trials. J. Pathol. Clin. Res. 5, 81-90. https://doi.org/10.1002/cjp2.127
  17. Schaer, R., Otalora, S., Jimenez-Del-Toro, O., Atzori, M. and Muller, H. (2019) Deep learning-based retrieval system for gigapixel histopathology cases and the open access literature. J. Pathol. Inform. 10, 19. https://doi.org/10.4103/jpi.jpi_88_18
  18. Seger, S., Stritt, M., Vezzali, E., Nayler, O., Hess, P., Groenen, P. M. A. and Stalder, A. K. (2018) A fully automated image analysis method to quantify lung fibrosis in the bleomycin-induced rat model. PLoS ONE 13, e0193057. https://doi.org/10.1371/journal.pone.0193057
  19. Smith, M. A., Westerling-Bui, T., Wilcox, A. and Schwartz, J. (2021) Screening for bone marrow cellularity changes in cynomolgus macaques in toxicology safety studies using artificial intelligence models. Toxicol. Pathol. 49, 905-911. https://doi.org/10.1177/0192623320981560
  20. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z. (2016) Rethinking the inception architecture for computer vision. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826.
  21. Veta, M., van Diest, P. J., Kornegoor, R., Huisman, A., Viergever, M. A. and Pluim, J. P. (2013) Automatic nuclei segmentation in H&E stained breast cancer histopathology images. PLoS ONE 8, e70221. https://doi.org/10.1371/journal.pone.0070221
  22. Zarella, M. D., Bowman, D., Aeffner, F., Farahani, N., Xthona, A., Absar, S. F., Parwani, A., Bui, M. and Hartman, D. J. (2019) A practical guide to whole slide imaging: a white paper from the Digital Pathology Association. Arch. Pathol. Lab. Med. 143, 222-234. https://doi.org/10.5858/arpa.2018-0343-RA
  23. Zarella, M. D., Yeoh, C., Breen, D. E. and Garcia, F. U. (2017) An alternative reference space for H&E color normalization. PLoS ONE 12, e0174489. https://doi.org/10.1371/journal.pone.0174489