medigraphic.com
ISSN 1727-897X (Electronic)

2022, Number 2

<< Back Next >>

Medisur 2022; 20 (2)

HistoBCAD: Open-source tool for breast cancer detection in histopathological images

Pérez MCA, Vázquez RT, Mulet RA, Vázquez SCR, Perdigón RF

Language: Spanish
References: 18
Page: 210-221
PDF size: 628.49 Kb.


ABSTRACT

Background: the accurate detection and classification of breast cancer through histopathological diagnosis is of vital importance for the effective treatment of the disease. Among the types of breast cancer, invasive ductal carcinoma (IDC) is the most common. Visual analysis of tissue samples under the microscope is a manual, time-consuming and observer-dependent process. However, in many countries, including Cuba, the use of software tools to assist diagnosis is scarce.
Objective: to develop a software tool to detect IDC subtype breast cancer tissue in histopathological images.
Methods: the tool is implemented in Python and includes IDC detection methods in histopathological images, based on algorithms for extraction of color and texture features in combination with a random forest classifier.
Results: the open source tool provides a series of facilities for the reading, writing and visualization of histopathological images, automatic and manual delineation of cancer areas, management of patient diagnostic data and collaborative remote evaluation. It was evaluated in a database with 162 images of patients diagnosed with IDC, obtaining a balanced accuracy of 84 % and a F1 factor of 75 %.
Conclusions: the tool allowed an interactive, fast, reproducible, precise and collaborative analysis through a simple and intuitive graphical interface. Future versions are expected to include new incremental machine learning methods for the analysis of digital histopathology images.


REFERENCES

  1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021;71(3):209-49.

  2. Registro Nacional del Cáncer. Anuario de incidencia de cáncer en Cuba 2015[Internet]. La Habana: RNC; 2016[citado 06/09/2020]. Disponible en: Disponible en: http://www.rnc.sld.cu/wp-content/uploads/2016/07/Incidencia-de-Cáncer-2015_General-vers2.pdf 2.

  3. Registro Nacional de Cáncer de Cuba. Mortalidad de cáncer según sexo y localización. Número de casos, tasas crudas y ajustadas. Cuba. 2015[Internet]. La Habana: RNC; 2016[citado 06/09/2020]. Disponible en: Disponible en: http://www.rnc.sld.cu/wp-content/uploads/2013/07/Mortalidad-de-cáncer-según-sexo-y-localización.pdf 3.

  4. Malhotra GK, Zhao X, Band H, Band V. Histological, molecular and functional subtypes of breast cancers. Cancer Biol Ther. 2010;10(10):955-60.

  5. Robertson S, Azizpour H, Smith K, Hartman J. Digital image analysis in breast pathology-from image processing techniques to artificial intelligence. Transl Res J Lab Clin Med[Internet]. 2018[citado 28/02/2020];194:19-35.

  6. Elmore J, Longton G, Carney P, Geller B. Diagnostic Concordance Among Pathologists Interpreting Breast Biopsy Specimens. Am Med Assoc[Internet]. 2015 [citado 04/09/2021];313(11):1122-32.

  7. Sadoughi F, Kazemy Z, Hamedan F, Owji L, Rahmanikatigari M, Azadboni TT. Artificial intelligence methods for the diagnosis of breast cancer by image processing: A review. Breast Cancer (Dove Med Press). 2018;10:219-30l.

  8. Janowczyk A, Madabhushi A. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. J Pathol Inform. 2016;7(1):29.

  9. Cruz-Roa A, Basavanhally A, González F, Gilmore H, Feldman M, Ganesan S, et al. Automatic detection of invasive ductal carcinoma in whole slide images with convolutional neural networks. Med Imaging Digit Pathol. 2014;9041(216):904103.

  10. Coro RM, Borrajero I. DIGIPAT: Un sistema cubano para morfometría de imágenes. Rev Latinoam Patol. 1996;34:9-10.

  11. Antúnez Potashkina I, Coro Antich R, Rodriguez Ceballos S. Morfometría computerizada en aspirados celulares del carcinoma ductal infiltrante de la mama. Modelo de estadística multivariada. Rev Esp Patol. 1997;30(3):193-9.

  12. Morales RR, Martínez T, Cuello L. MADIP: Morphometrical analysis by digital image processing. In: Sánchez JS. Pattern Recognition and Image Analysis. Castellón de la Plana: Universitat Jaime I, 2001.p. 291-8.

  13. Sharma S, Mehra R. Conventional Machine Learning and Deep Learning Approach for Multi-Classification of Breast Cancer Histopathology Images - a Comparative Insight. J Digit Imaging. 2020;33(3):632-54.

  14. Masters BR, Gonzalez RC, Woods RE. Digital Image Processing. J Biomed Opt. 2009;14(2):029901.

  15. Zwanenburg A, Leger S, Vallières M, L ¨ock S. Image biomarker standardisation initiative.arXiv preprint arXiv:1612.07003[Internet]. Ithaca: Cornell University; 2019 [citado 14/05/2020]; Disponible en: Disponible en: https://arxiv.org/pdf/1612.07003.pdf 15.

  16. Haralick RM, Shanmugam K, Dinstein IH. Textural features for image classification. IEEE Trans Syst Man Cybern[Internet]. 1973[citado 08/09/2021];3(6):610-21. Disponible en: https://ieeexplore.ieee.org/abstract/document/4309314/16.

  17. Afshar P, Mohammadi A, Plataniotis KN, Oikonomou A, Benali H. From handcrafted to deep-learning-based cancer radiomics: Challenges and opportunities. IEEE Signal Process Mag. 2019;36(4):132-60.

  18. Brodersen KH, Ong CS, Stephan KE, Buhmann JM. The balanced accuracy and its posterior distribution. In: 20th International Conference on Pattern Recognition, 2010 [Internet]. Estambul: Interaction Design Foundation; 2010[citado 08/09/2021]. Disponible en: Disponible en: https://ieeexplore.ieee.org/document/5597285 18.




2020     |     www.medigraphic.com