APPLICATION OF LINEAR REGRESSION METHOD FOR ANALYSIS OF CYTOLOGICAL IMAGES QUANTITATIVE CHARACTERISTICS

2021;
: 73-77
https://doi.org/10.23939/ujit2021.03.073
Received: April 26, 2021
Accepted: June 01, 2021

Ци­ту­ван­ня за ДСТУ: Бе­резь­кий О. М., Пі­цун О. Й., Мель­ник Г. М., Дац­ко Т. В. Зас­то­су­ван­ня ме­то­ду лі­нійної рег­ре­сії для ана­лі­зу кіль­кіс­них ха­рак­те­рис­ти­ки ци­то­ло­гіч­них зоб­ра­жень. Ук­ра­їнсь­кий жур­нал ін­форма­ційних тех­но­ло­гій. 2021, т. 3, № 1. С. 73–77.

Ci­ta­ti­on APA: Be­rezsky, O. M., Pit­sun, O. Yo., Melnyk, G. M., & Datsko, T. V. (2021). Appli­ca­ti­on of li­ne­ar reg­ressi­on met­hod for analysis of cyto­lo­gi­cal ima­ges qu­an­ti­ta­ti­ve cha­rac­te­ris­tics. Uk­ra­ini­an Jo­ur­nal of In­forma­ti­on Techno­logy, 3(1), 73–77. https://doi.org/10.23939/ujit2021.03.073

1
Ternopil National University, Ternopil, Ukraine; Lviv Polytechnic National University, Lviv, Ukraine
2
West Ukrainian National University, Ternopil, Ukraine
3
West Ukrainian National University, Ternopil, Ukraine
4
Ternopil National Medical University, Ternopil, Ukraine

This ar­ticle analyzes the pat­ho­lo­gi­cal con­di­ti­ons of the bre­ast ba­sed on the study of cyto­lo­gi­cal ima­ges. Cyto­lo­gi­cal ima­ges are a se­pa­ra­te class of bi­ome­di­cal ima­ges and are used in the di­ag­no­sis of can­cer. For di­ag­no­se pre­can­ce­ro­us and can­ce­ro­us con­di­ti­ons and tre­at­ment tac­tics, di­ag­nosti­ci­ans use cyto­lo­gi­cal, his­to­lo­gi­cal, and im­mu­no­his­toche­mi­cal ima­ges. For au­to­ma­ting the pro­cess of di­ag­no­sis in on­co­logy, au­to­ma­ted mic­roscopy systems are used. Au­to­ma­ted mic­roscopy systems use com­pu­ter vi­si­on al­go­rithms. Re­cently, mac­hi­ne le­ar­ning al­go­rithms ha­ve be­en used to clas­sify ima­ges. Mic­rosco­pic ima­ge pro­ces­sing is a complex and ti­me-con­su­ming pro­cess, as the ima­ges are cha­rac­te­ri­zed by high no­ise le­vels and the ab­sence of cle­ar con­to­urs of cell nuc­lei. To cal­cu­la­te the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of cell nuc­lei cyto­lo­gi­cal ima­ges, the met­hod for cal­cu­la­ting the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of cell nuc­lei ba­sed on ima­ge fil­te­ring al­go­rithms and the­ir au­to­ma­tic seg­menta­ti­on has be­en de­ve­lo­ped. An U-Net con­vo­lu­ti­onal neu­ral net­work archi­tec­tu­re has be­en de­ve­lo­ped for cell nuc­le­us seg­menta­ti­on. In this work, the met­hod of pro­ces­sing cyto­lo­gi­cal ima­ges is de­ve­lo­ped. The met­hod con­sists of six sta­ges. The first step is to lo­ad the ima­ge in­to the com­pu­ters me­mory. In the se­cond sta­ge, the ima­ges are prep­ro­ces­sed. The third sta­ge is the au­to­ma­tic seg­menta­ti­on of ima­ges ba­sed on the con­vo­lu­ti­onal neu­ral net­work of the U-Net type. In the fo­urth sta­ge, the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of cell nuc­lei are cal­cu­la­ted. In the fifth sta­ge, the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of the cell nuc­lei are sto­red in a da­ta­ba­se. In the sixth sta­ge, li­ne­ar reg­ressi­on al­go­rithms are used to ob­ta­in qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of cell nuc­lei. Cur­rently, li­ne­ar reg­ressi­on is one of the com­mon appro­ac­hes of mac­hi­ne le­ar­ning to da­ta analysis. In this work, the com­pa­ra­ti­ve analysis of the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics appli­ca­ti­on in cell nuc­lei is car­ri­ed out ba­sed on li­ne­ar reg­ressi­on. The sci­en­ti­fic no­velty of the work is de­ve­lop­ment the met­hod for cal­cu­la­ting the qu­an­ti­ta­ti­ve cha­rac­te­ris­tics of cell nuc­lei, which inclu­des sta­ges of ima­ge fil­te­ring and au­to­ma­tic seg­menta­ti­on ba­sed on the use of a neu­ral net­work such as U-Net. The prac­ti­cal sig­ni­fi­can­ce of the work is the softwa­re imple­men­ta­ti­on of the prep­ro­ces­sing mo­du­les and li­ne­ar reg­ressi­on. In par­ti­cu­lar, in­vesti­ga­ted that the set of pa­ra­me­ters "area, length of the ma­in axis" has 1.4 ti­mes less RMSE er­ror com­pa­red to the set "area, pe­ri­me­ter".

  1. Ab­dulqa­der, Q. (2017). Applying the Bi­nary Lo­gis­tic Reg­ressi­on Analysis on The Me­di­cal Da­ta. Sci­en­ce Jo­ur­nal of Uni­ver­sity of Zak­ho, 5(4), 330–334. https://doi.org/10.25271/2017.5.4.388
  2. Altman, N. & Krzywinski, M. (2015). Simple li­ne­ar reg­ressi­on. Nat Met­hods, 12, 999–1000. https://doi.org/10.1038/nmeth.3627
  3. Be­rezsky, O. M. (Ed.) (2017). Met­hods, al­go­rithms and softwa­re for pro­ces­sing bi­ome­di­cal ima­ges. Ter­no­pil: Eko­no­michna dum­ka, TNEU, 330. [In Uk­ra­ini­an].
  4. Be­rezsky, O. M., Melnyk, G. M. & Be­rez­ka, K. M. (2013). Fuzzy know­ledge ba­se of the in­telli­gent system for di­ag­no­sing bre­ast can­cer. Visnyk Khmelnytsko­ho nat­si­onal­no­ho uni­versyte­tu. Tekhnichni na­uky, 6, 284–291. [In Uk­ra­ini­an].
  5. Be­rezsky, O. M., Melnyk, G. M., Bat­ko, Y. M., & Datsko, T. V. (2013). In­telli­gent system for di­ag­no­sing va­ri­ous forms of bre­ast can­cer ba­sed on the analysis of his­to­lo­gi­cal and cyto­lo­gi­cal ima­ges. Sci­en­ti­fic Bul­le­tin of UN­FU, 23(13), 357–367. [In Uk­ra­ini­an].
  6. Be­rezsky, O., Pit­sun, O., Dubchak, L., Be­rez­ka, K., Dolynyuk, T., & De­rish, B. (2020). Cyto­lo­gi­cal Ima­ges Clus­te­ring of Bre­ast Pat­ho­lo­gi­es. 2020 IEEE 15th In­terna­ti­onal Con­fe­ren­ce on Com­pu­ter Sci­en­ces and In­forma­ti­on Techno­lo­gi­es (CSIT), Zba­razh, Uk­ra­ine, 62–65. https://doi.org/10.1109/CSIT49958.2020.9321867
  7. De­epa, S. N. & Aru­na De­vi, B. (2011). A sur­vey on ar­ti­fi­ci­al in­telli­gen­ce appro­ac­hes for me­di­cal ima­ge clas­si­fi­ca­ti­on. In­di­an Jo­ur­nal of Sci­en­ce and Techno­logy, 4(11), 1583–1595. https://doi.org/10.17485/ijst/2011/v4i11.35
  8. Dre­ise­itl, S. & Oh­no-Mac­ha­do, L. (2002). Lo­gis­tic reg­ressi­on and ar­ti­fi­ci­al neu­ral net­work clas­si­fi­ca­ti­on mo­dels: a met­ho­do­logy re­vi­ew. Jo­ur­nal of Bi­ome­di­cal In­forma­tics, 35(5–6), 352–359. https://doi.org/10.1016/s1532-0464(03)00034-0
  9. Fa­bi­jańska, A. & San­kowski, D. (2011). No­ise adap­ti­ve switching me­di­an-ba­sed fil­ter for im­pulse no­ise re­mo­val from extre­mely cor­rupted ima­ges. IET Ima­ge Pro­ces­sing, 5(5), 472–480. https://doi.org/10.1049/iet-ipr.2009.0178
  10. Omer, A. A., Has­san, O. I., Ah­med, A. I. & Ab­delrah­man, A. (2018). De­no­ising CT Ima­ges using Me­di­an ba­sed Fil­ters: a Re­vi­ew. In­terna­ti­onal Con­fe­ren­ce on Com­pu­ter, Control, Electri­cal and Electro­nics En­gi­ne­ering (ICCCEEE). Khar­to­um, Su­dan, 1–6. https:// doi.org/10.1109/ICCCEEE.2018.8515829
  11. Ti­an, C., Fei, L., Zheng, W., Xu, Y., Zuo, W., & Lin, C.-W. (2020). De­ep le­ar­ning on ima­ge de­no­ising: An over­vi­ew. Neu­ral Net­works, 131, 251–275. https:// doi.org/10.1016/j.neu­net.2020.07.025
  12. Zhang, J., Xiea, Y., Wu, Q. & Xia Y. (2019). Me­di­cal ima­ge clas­si­fi­ca­ti­on using syner­gic de­ep le­ar­ning. Me­di­cal Ima­ge Analysis, 54, 10–19. https://doi.org/10.1016/j.me­dia.2019.02.010
  13. Zhu, Y., & Hu­ang, C. (2012). An Impro­ved Me­di­an Fil­te­ring Al­go­rithm for Ima­ge No­ise Re­duc­ti­on. Physics Pro­ce­dia, 25, 609–616. https://doi.org/10.1016/j.phpro.2012.03.133