Decision support system for medical pathology recognition
DOI:
https://doi.org/10.18372/2310-5461.49.15287Keywords:
computer vision, image recognition, decision support systemAbstract
Given article considers the problem of automation of chromosome pathology recognition. Overview of existing publications in adjacent topics has shown the need for further research due to the scientific relevance and lack of groundwork.
The application domain has been considered - both theoretical aspects of pathology recognition automation and the chromosome pathology diagnostics process itself. Classification of main chromosome abnormalities has been performed.
A formal algorithm has been derived from the aforementioned application domain analysis. The algorithm version provided in given publication is a high-level draft and will be extended. Along with the algorithm, requirements to the prototype software and the prototype software itself have been designed. It should accept karyogram image as an input and return information about chromosome anomaly as an output. Software has been implemented on Python programing language using OpenCV image processing library. Prototype has been implemented as a program library, allowing to use it in different contexts. For example, it is possible to use it via terminal or design a Web API wrapper around it. Prototype of a decision support system for chromosome pathology recognition is currently capable of detecting quantity chromosome abnormalities.
Results obtained from given paper prove the possibility of designing full-powered decision support system for chromosome pathology recognition automation and allow to focus on extending and improving functionality of each distinct step of the basic algorithm, allowing to cover more chromosome abnormality typesReferences
Boyle B., Addor M., Arriola L., et al. (2018). Estimating Global Burden of Disease due to congenital anomaly: an analysis of European data. Archives of Disease in Childhood - Fetal and Neonatal Edition. 103:F22-F28. doi.org/10.1136/archdischild-2016-311845 (eng)
Pal, A. K., Ambulkar, P. S., Waghmare, J. E., Wankhede, V., Shende, M. R., & Tarnekar, A. M. (2018). Chromosomal Aberrations in Couples with Pregnancy Loss: A Retrospective Study. Journal of human reproductive sciences, 11(3), 247–253. doi.org/10.4103/jhrs.JHRS_124_17/ (eng)
Riegel M. (2014). Human molecular cytogenetics: From cells to nucleotides. Genetics and molecular biology, 37(1 Suppl), 194–209. doi.org/10.1590/s1415-47572014000200006 (eng)
Lundsteen, C., Lind, A. M., & Granum, E. (1976). Visual classification of banded human chromosomes. I. Karyotyping compared with classification of isolated chromosomes. Annals of human genetics, 40(1), 87–97. doi.org/10.1111/j.1469-1809.1976.tb00167.x (eng)
Wang, X., Zheng, B., Wood, M., Li, S., Chen, W., & Liu, H. (2005). Development and evaluation of automated systems for detection and classification of banded chromosomes: current status and future perspectives. Journal of Physics D, 38, 2536-2542. doi.org/10.1088/0022-3727/38/15/003
Razzak M.I., Naz S., Zaib A. (2018) Deep Learning for Medical Image Processing: Overview, Challenges and the Future. In: Dey N., Ashour A., Borra S. (eds) Classification in BioApps. Lecture Notes in Computational Vision and Biomechanics, vol 26. Springer, Cham. doi.org/10.1007/978-3-319-65981-7_12
Y. Wu, Y. Yue, X. Tan, W. Wang and T. Lu, (2018). "End-To-End Chromosome Karyotyping with Data Augmentation Using GAN," 25th IEEE International Conference on Image Processing (ICIP), Athens, 2018, pp. 2456-2460, doi.org/10.1109/ICIP.2018.8451041
