Abstract
Computer tomography is most commonly used for diagnosing lung cancer, which is one of the deadliest cancers in the world. Online services that allow users to share their single-channel monochrome images, in particular computer tomography scans, in order to receive independent medical advice are becoming wide-spread these days. In this paper, we propose an optimization for the previously known two-staged architecture for detecting cancerous tumors in computer tomography scans that demonstrates the state-of-the-art results on Open Joint Monochrome Lungs Computer Tomography dataset. Modernized architecture allows to reduce the number of weights of the neural network based model (4 920 073 parameters vs. 26 468 315 in the original model) and its inference time (0.38 vs. 2.15 s in the original model) without loss of neoplasms recognition quality (0.996 F1 score). The proposed results were obtained using heavyweight encoder elimination, special combined loss function and watershed based method for the automated dataset markup and a consistency regularization approach adaptation that are described in the current paper.
Similar content being viewed by others
REFERENCES
P. Bachman, O. Alsharif, and D. Precup, “Learning with pseudo-ensembles,” in Advances in Neural Information Processing Systems, Ed. by Z. Gharamani, M. Welling, C. Cortes, N. Lawrence, and K. Q. Weinberger (2014), Vol. 27, pp. 3365–3373.
K. Clark, B. Vendt, K. Smith, J. Freymann, J. Kirby, P. Koppel, S. Moore, S. Phillips, D. Maffitt, M. Pringle, L.Tarbox, and F. Prior, “The cancer imaging archive (TCIA): Maintaining and operating a public information repository,” J. Digital Imaging 26, 1045–1057 (2013). https://doi.org/10.1007/s10278-013-9622-7
C. Goutte and E. Gaussier, “A probabilistic interpretation of precision, recall and F-score, with implication for evaluation,” in Advances in Information Retrieval, Ed. by D. E. Losada and J. M. Fernández-Luna, Lecture Notes in Computer Science, Vol. 3408 (Springer, 2005), pp. 345–359. https://doi.org/10.1007/978-3-540-31865-1-25
M. A. Heuvelmans, P. M. van Ooijen, S. Ather, C. F. Silva, D. Han, C. P. Heussel, W. Hickes, H. U. Kauczor, P. Novotny, H. Peschl, M. Rook, R. Rubtsov, O. von Stackelberg, M. T. Tsakok, C. Arteta, J. Declerck, T. Kadir, L. Pickup, F. Gleeson, and M. Oudkerk, “Lung cancer prediction by deep learning to identify benign lung nodules,” Lung Cancer 154, 1–4 (2021). https://doi.org/10.1016/j.lungcan.2021.01.027
S. Jadon, “A survey of loss functions for semantic segmentation,” in IEEE Conf. on Computational Intelligence in Bioinformatics and Computational Biology, Via del Mar, Chile, 2020 (IEEE, 2020). https://doi.org/10.1109/CIBCB48159.2020.9277638
K. V. Lalitha, R. Amrutha, S. Michahial, and M. Shivakumar, “Implementation of watershed segmentation,” Int. J. Adv. Res. Comput. Commun. Eng. 5, 196–199 (2016). https://doi.org/10.17148/IJARCCE.2016.51243
G. Kasinathan and S. Jayakumar, “Cloud-based lung tumor detection and stage classification using deep learning techniques,” BioMed Res. Int. 2022, 4185835 (2022). https://doi.org/10.1155/2022/4185835
A. Kaur, “Image segmentation using watershed transform,” Int. J. Soft Comput. Eng. 4, 5–8 (2014).
K. Kobylińska, T. Orlowski, M. Adamek, and P. Biecek, “Explainable machine learning for lung cancer screening models,” Appl. Sci. 12, 1926 (2022). https://doi.org/10.3390/app12041926
C.-W. Kuo, C.-Y. Ma, J.-B. Huang, and Z. Kira, “Featmatch: Feature-based augmentation for semi-supervised learning,” in Computer Vision–ECCV 2020, Lecture Notes in Computer Science, Vol. 12363 (Springer, Cham, 2020), pp. 479–495. https://doi.org/10.1007/978-3-030-58523-5_28
S. P. Morozov, N. S. Kul’berg, and V. A. Gombolevskij, “Tagged lung computer tomography results,” Certificate of Registration of Database RF 2018620500 (2018).
O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Ed. by N. Navab, J. Hornegger, W. Wells, and A. Frangi, Lecture Notes in Computer Science, Vol. 9351 (Springer, 2015), pp. 234–241. https://doi.org/10.1007/978-3-319-24574-428
A. Samarin, A. Savelev, and V. Malykh, “Two-staged self-attention based neural model for lung cancer recognition,” in Science and Artificial Intelligence Conf. (S.A.I.ence), Novosibirsk, Russia, 2020 (IEEE, 2020), pp. 50–53. https://doi.org/10.1109/S.A.I.ence50533.2020.9303206
A. Shimazaki, D. Ueda, A. Choppin, A. Yamamoto, T. Honjo, Yu. Shimahara, and Yu. Miki, “Deep learning-based algorithm for lung cancer detection on chest radiographs using the segmentation method,” Sci. Rep. 12, 727 (2022). https://doi.org/10.1038/s41598-021-04667-w
K. Sohn, D. Berthelot, C. L. Li, Z. Zhang, N. Carlini, E. D. Cubuk, A. Kurakin, H. Zhang, and C. Raffel, “FixMatch: Simplifying semi-supervised learning with consistency and confidence,” in Advances in Neural Information Processing Systems, Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Curran Associates, 2020), pp. 596–608.
C. Sudre, T. Vercauteren, S. Ourselin, and M. J. Cardoso, “Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Lecture Notes in Computer Science, Vol. 10553 (Springer, Cham, 2017), pp. 240–248 (2017). https://doi.org/10.1007/978-3-319-67558-928
O. Tatanov and A. Samarin, “LFIEM: Lightweight filter-based image enhancement model,” in 25th Int. Conf. on Pattern Recognition (ICPR), Milan, 2021 (IEEE, 2021), pp. 873–878. https://doi.org/10.1109/ICPR48806.2021.9413138
A. Thai, B. Solomon, L. Sequist, J. Gainor, and R. Heist, “Lung cancer,” Lancet 398, 535–554 (2021). https://doi.org/10.1016/S0140-6736(21)00312-3
Q. Xie, Z. Dai, E. Hovy, M. T. Luong, and Q. V. Le, “Unsupervised data augmentation for consistency training,” in Advances in Neural Information Processing Systems, Ed. by H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Curran Associates, 2019), Vol. 33.
Y. Huan, L. Chen, Zh. Cheng, M. Yang, J. Wang, Ch. Lin, Yu. Wang, L. Huang, Ya. Chen, S. Peng, Z. Ke, and W. Li, “Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study,” BMC Med. 19, 80 (2021). https://doi.org/10.1186/s12916-021-01953-2
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
COMPLIANCE WITH ETHICAL STANDARDS
This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.
Conflict of Interest
The authors declare that they have no conflicts of interest.
Additional information
Aleksei Samarin. AI Researcher with more than 10 years scientific and industrial experience. Main areas of interest are related to computer vision, pattern recognition, and image processing and analysis. Author of more than 10 scientific publications.
Aleksandr Savelev. Master student at ITMO University with industrial experience in deep learning, computer vision, data analysis, and natural language processing. Author of 4 scientific publications.
Aleksei Toropov. Data scientist at computer vision laboratory with scientific and industrial experience in computer vision, image processing, and deep learning. Author of 2 scientific publications.
Alina Dzestelova. Master student at ITMO University. Author of 3 scientific publications.
Valentin Malykh. AI Researcher with more than 30 scientific publications, Doctor of Engineering. The main areas of research are related to natural language understanding and deep learning.
Elena Mikhailova. Director of the Higher School of Digital Culture at ITMO University. Docent, Candidate of Physical and Mathematical Sciences with more than 30 scientific publications.
Alexandr Motyko. Associate Professor at SPb ETU. Doctor of Engineering with more than 20 scientific publications. Main areas of research are related to image and video processing.
Rights and permissions
About this article
Cite this article
Samarin, A., Savelev, A., Toropov, A. et al. One-Staged Attention-Based Neoplasms Recognition Method for Single-Channel Monochrome Computer Tomography Snapshots. Pattern Recognit. Image Anal. 32, 645–650 (2022). https://doi.org/10.1134/S1054661822030361
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661822030361