Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Discrimination of dicentric chromosome from radiation exposure patient data using a pretrained deep learning model

  • Soon Woo Kwon (Lab of Biological Dosimetry, National Radiation Emergency Medical Center, Korea Institute of Radiological and Medical Sciences) ;
  • Won Il Jang (Radiation Oncology, Korea Cancer Center Hospital, Korea Institute of Radiological and Medical Sciences) ;
  • Mi-Sook Kim (Radiation Oncology, Korea Cancer Center Hospital, Korea Institute of Radiological and Medical Sciences) ;
  • Ki Moon Seong (Lab of Biological Dosimetry, National Radiation Emergency Medical Center, Korea Institute of Radiological and Medical Sciences) ;
  • Yang Hee Lee (Lab of Biological Dosimetry, National Radiation Emergency Medical Center, Korea Institute of Radiological and Medical Sciences) ;
  • Hyo Jin Yoon (Lab of Biological Dosimetry, National Radiation Emergency Medical Center, Korea Institute of Radiological and Medical Sciences) ;
  • Susan Yang (Lab of Biological Dosimetry, National Radiation Emergency Medical Center, Korea Institute of Radiological and Medical Sciences) ;
  • Younghyun Lee (Department of Biomedical Laboratory Science, College of Medical Sciences, Soonchunhyang University) ;
  • Hyung Jin Shim (Department of Nuclear Engineering, Seoul National University)
  • Received : 2023.07.27
  • Accepted : 2024.03.10
  • Published : 2024.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

The dicentric chromosome assay is a gold standard method to estimate radiation exposure by calculating the ratio of dicentric chromosomes existing in cells. The objective of this study was to propose an automatic dicentric chromosome discrimination method based on deep convolutional neural networks using radiation exposure patient data. From 45 patients with radiation exposure, conventional Giemsa-stained images of 116,258 normal and 2800 dicentric chromosomes were confirmed. ImageNet was used to pre-train VGG19, which was modified and fine-tuned. The proposed modified VGG19 demonstrated dicentric chromosome discrimination performance, with a true positive rate of 0.927, a true negative rate of 0.997, a positive predictive value of 0.882, a negative predictive value of 0.998, and an area under the receiver operating characteristic curve of 0.997.

Keywords

Acknowledgement

This research was supported by the grant of the Korea Institute of Radiological and Medical Sciences, funded by the Ministry of Science and ICT (No. 50445-2024)

References

  1. IAEA, Cytogenetic Dosimetry: Applications in Preparedness for and Response to Radiation Emergencies, International Atomic Energy Agency, 2011.
  2. C. Schunck, T. Johannes, D. Varga, T. Lorch, A. Plesch, New developments in automated cytogenetic imaging: unattended scoring of dicentric chromosomes, micronuclei, single cell gel electrophoresis, and fluorescence signals, Cytogenet. Genome Res. 104 (1-4) (2004) 383-389.
  3. P.K. Rogan, Y. Li, A. Wickramasinghe, A. Subasinghe, N. Caminsky, W. Khan, J. Samarabandu, R. Wilkins, F. Flegal, J.H. Knoll, Automating dicentric chromosome detection from cytogenetic biodosimetry data, Radiat Prot Dosimetry 159 (1-4) (2014) 95-104.
  4. B. Shirley, Y. Li, J.H.M. Knoll, P.K. Rogan, Expedited radiation biodosimetry by automated dicentric chromosome identification (ADCI) and dose estimation, J. Vis. Exp. 127 (2017).
  5. J. Liu, Y. Li, R. Wilkins, F. Flegal, J.H.M. Knoll, P.K. Rogan, Accurate cytogenetic biodosimetry through automated dicentric chromosome curation and metaphase cell selection, F1000Research 6 (2017) 1396.
  6. E. Royba, M. Repin, S. Pampou, C. Karan, D.J. Brenner, G. Garty, RABiT-II-DCA: a Fully-automated dicentric chromosome assay in Multiwell Plates, Radiat. Res. 192 (3) (2019) 311-323.
  7. X. Shen, Y. Qi, T. Ma, Z. Zhou, A dicentric chromosome identification method based on clustering and watershed algorithm, Sci. Rep. 9 (1) (2019) 2285.
  8. S. Jang, S.G. Shin, M.J. Lee, S. Han, C.H. Choi, S. Kim, W.S. Cho, S.H. Kim, Y. R. Kang, W. Jo, S. Jeong, S. Oh, Feasibility study on automatic Interpretation of radiation dose using deep learning technique for dicentric chromosome assay, Radiat. Res. 195 (2) (2021) 163-172.
  9. Y. Li, B.C. Shirley, R.C. Wilkins, F. Norton, J.H.M. Knoll, P.K. Rogan, Radiation dose estimation by completely automated Interpretation of the dicentric chromosome assay, Radiat Prot Dosimetry 186 (1) (2019) 42-47.
  10. X. Shen, T. Ma, C. Li, Z. Wen, J. Zheng, Z. Zhou, High-precision automatic identification method for dicentric chromosome images using two-stage convolutional neural network, Sci. Rep. 13 (1) (2023) 2124.
  11. G.M. Ludovici, M.G. Cascone, T. Huber, A. Chierici, P. Gaudio, S.O. de Souza, F. d'Errico, A. Malizia, Cytogenetic bio-dosimetry techniques in the detection of dicentric chromosomes induced by ionizing radiation: a review, The European Physical Journal Plus 136 (5) (2021) 482.
  12. T. Lorch, J. Bille, M. Frieben, G. Stephan, An Automated Biological Dosimetry System, Architectures and Algorithms for Digital Image Processing III, SPIE, 1986, pp. 199-206.
  13. J. Piper, J. Sprey, Adaptive classifiers for dicentric chromosomes, J. Radiat. Res. 33 (Suppl_1) (1992) 159-170.
  14. H. Romm, E. Ainsbury, S. Barnard, L. Barrios, J.F. Barquinero, C. Beinke, M. Deperas, E. Gregoire, A. Koivistoinen, C. Lindholm, J. Moquet, U. Oestreicher, R. Puig, K. Rothkamm, S. Sommer, H. Thierens, V. Vandersickel, A. Vral, A. Wojcik, Automatic scoring of dicentric chromosomes as a tool in large scale radiation accidents, Mutat. Res. 756 (1-2) (2013) 174-183.
  15. A.A. S, J. Samarabandu, J. Knoll, W. Khan, P. Rogan, An accurate image processing algorithm for detecting FISH Probe Locations relative to chromosome Landmarks on DAPI stained metaphase chromosome images, in: 2010 Canadian Conference on Computer and Robot Vision, 2010, pp. 223-230.
  16. A.S. Arachchige, J. Samarabandu, J.H. Knoll, P.K. Rogan, Intensity integrated Laplacian-based thickness measurement for detecting human metaphase chromosome centromere location, IEEE (Inst. Electr. Electron. Eng.) Trans. Biomed. Eng. 60 (7) (2013) 2005-2013.
  17. Y. Li, J.H. Knoll, R.C. Wilkins, F.N. Flegal, P.K. Rogan, Automated discrimination of dicentric and monocentric chromosomes by machine learning-based image processing, Microsc. Res. Tech. 79 (5) (2016) 393-402.
  18. A.S. Arachchige, J. Samarabandu, J. Knoll, W. Khan, P. Rogan, An image processing algorithm for accurate extraction of the centerline from human metaphase chromosomes, in: 2010 IEEE International Conference on Image Processing, IEEE, 2010, pp. 3613-3616.
  19. X. Bai, L.J. Latecki, W.-Y. Liu, Skeleton pruning by contour partitioning with discrete curve evolution, IEEE Trans. Pattern Anal. Mach. Intell. 29 (3) (2007) 449-462.
  20. A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep convolutional neural networks, in: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Curran Associates Inc., 2012, pp. 1097-1105.
  21. K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556 (2014).
  22. K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.
  23. G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700-4708.
  24. M. Tan, Q. Le, Efficientnet: Rethinking model scaling for convolutional neural networks, in: International Conference on Machine Learning, PMLR, 2019, pp. 6105-6114.
  25. M.S. Al-Kharraz, L.A. Elrefaei, M.A. Fadel, Automated system for chromosome karyotyping to Recognize the Most Common Numerical Abnormalities using deep learning, IEEE Access 8 (2020) 157727-157747.
  26. W. Zhang, S. Song, T. Bai, Y. Zhao, F. Ma, J. Su, L. Yu, Chromosome classification with convolutional neural network based deep learning, 2018 11th international congress on image and signal processing, in: Biomedical Engineering and Informatics (CISP-BMEI), IEEE, 2018, pp. 1-5.
  27. Y. Wu, Y. Yue, X. Tan, W. Wang, T. Lu, End-to-end chromosome Karyotyping with data augmentation using GAN, in: 2018 25th IEEE International Conference on Image Processing (ICIP), IEEE, 2018, pp. 2456-2460.
  28. N. Xie, X. Li, K. Li, Y. Yang, H.T. Shen, Statistical Karyotype Analysis using CNN and Geometric optimization, IEEE Access 7 (2019) 179445-179453.
  29. C. Lin, G. Zhao, Z. Yang, A. Yin, X. Wang, L. Guo, H. Chen, Z. Ma, L. Zhao, H. Luo, T. Wang, B. Ding, X. Pang, Q. Chen, CIR-net: automatic classification of human chromosome based on Inception-ResNet Architecture, IEEE ACM Trans. Comput. Biol. Bioinf 19 (3) (2022) 1285-1293.
  30. M. Sharma, L. Vig, Automatic chromosome classification using deep attention based sequence learning of chromosome bands, in: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, 2018, pp. 1-8.
  31. G. Swati, M. Yadav, M. Sharma, L. Vig, Siamese networks for chromosome classification, in: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2017, pp. 72-81.
  32. S. Ren, K. He, R. Girshick, J. Sun, Faster r-cnn: towards real-time object detection with region proposal networks, Adv. Neural Inf. Process. Syst. 28 (2015).
  33. T.-Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117-2125.
  34. F. Chollet, Others, Keras, 2015.
  35. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, Imagenet: a large-scale hierarchical image database, in: 2009 IEEE Conference on Computer Vision and Pattern Recognition, Ieee, 2009, pp. 248-255.
  36. A. Martin, A. Ashish, B. Paul, B. Eugene, C. Zhifeng, C. Craig, S.C. Greg, D. Andy, D. Jeffrey, D. Matthieu, G. Sanjay, G. Ian, H. Andrew, I. Geoffrey, I. Michael, Y. Jia, J. Rafal, K. Lukasz, K. Manjunath, L. Josh, M. Dandelion, M. Rajat, M. Sherry, M. Derek, O. Chris, S. Mike, S. Jonathon, S. Benoit, S. Ilya, T. Kunal, T. Paul, V. Vincent, V. Vijay, V. Fernanda, V. Oriol, W. Pete, W. Martin, W. Martin, Y. Yuan, Z. Xiaoqiang, TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, 2015.
  37. T. O'Malley, E. Bursztein, J. Long, F. Chollet, H. Jin, L. Invernizzi, Others, KerasTuner, 2019.
  38. G.E. Hinton, S. Roweis, Stochastic neighbor embedding, Adv. Neural Inf. Process. Syst. 15 (2002).