Özet:

Abstract The problem of automatic recognition – diagnostics of cirrhotic and metastatic liver damage has been solved on the basis of laparoscopic images analysis. The object of the investigation was confined to the process of diagnostic automatic system of laparoscopic images recognition building up. The subject of investigation was confined to composing of training images for the learning of cascade Haar’s classificatory. The establishing of the system of decision support for laparoscopic surgeons was the aim of the investigation. The automatic diagnostic technology was developed on the basis of Haar’s features usage. The classification of images was performed using cascade classificator exploration, and 1000 positive images along with 500 negative ones have been used for the learning . It was established that the sensitivity of cirrhosis of the liver diagnostics was 68,8% and exceeded that one which was determined after expert analysis (31,0%) (P<0,01). The sensitivity of metastatic damage was 80,0% and 46,7% after developed and expert diagnostics were performed correspondently (P<0,02).Besides, the specificity was also elevated – from 52,5% after expert diagnostics up to 85,0% (P<0,01) after developed method. The net increasing of both positive prognostic index (from 42,4% up to 80,0%, P<0,01), as well as negative one (from 56,8% up to 87,2%, P<0,01) was also observed. In accordance to results of tests, the AUC ROC for cascade classificator was 0,891, while such one for expert analysis was 0,723. That is in favor for higher effectiveness of cascade classificator. The worked out technology is recommended for laparoscopic surgery clinical exploration. References Albisser Z. Computer-aided screening of capsule endoscopy videos / Z. Albisser // Master’s Thesis, University of Oslo. – 2015. – № 1. – P. 74–245. 2. Segmentation of uterus using laparoscopic ultrasound by an imagebased active contour approach for guiding gynecological diagnosis and surgery / X-H. Gong, J. Lu, J. Liu et al. // PLoS ONE. – 2015. – Vol. 10(10): e0141046. DOI:10.1371/journal.pone.0141046 3. Shu Y. Segmentation of laparoscopic images: Integrating graphbased segmentation and multistage region merging/ Y. Shu, G. A. Bilodeau, F. Cheriet // The 2nd Canadian Conference on Computer and Robot Vision (CRV’05), May 09 – 11, 2005 : Proceeding. IEEE Computer Society Washington, 2005. – P. 429–436. DOI: 10.1109/CRV.2005.74 4. Computer-aided diagnosis in hysteroscopic imaging / [M. S. Neofytou, V. Tanos, I. Constantinou et al.] // IEEE Journal of Biomed. Health Inform. – 2015. – Vol. 19(3). – P. 1129–1136. DOI: 10.1109/JBHI.2014.2332760. 5. Marcinczak J. M. Closed contour specular reflection segmentation in laparoscopic images / J. M. Marcinczak, R. R. Grigat // J. of Biomed. Umaging. – 2013. – Vol. 2013, Jan. 2013, Article No 18; DOI: 1155/2013/593183 6. Boisvert J. Segmentation of laparoscopic images for computer assisted surgery / J. Boisvert, F. Cheriet, G. Grimard // 13th Scandinavian Conference Image Analysis, June 29 – July 2, 2003, Halmstad, Sweden : Proceedings. Lecture Notes in Computer Sciences, 2003. – Vol. 2749. – P. 587–594. 7. Application of mobile photography with smartphone cameras for monitoring of orthodontic correction with dental brackets/ [L. S. Godlevsky, E. A. Bidnyuk, N. R. Bayazitov et al.] // Chinese Journal of Modern Medicine. – 2014. – No. 15. – P. 10–14. 8. Application of mobile photography with smartphone cameras for monitoring of early caries appearance in the course of orthodontic correction with dental brackets/ [L. S. Godlevsky, E. A. Bidnyuk, N. R. Bayazitov et al.] // Applied Med. Informatics. – 2013. – Vol. 33, No. 4. – P. 21–26. 9. Diagnostic laparoscopy in the era of modern imaging – retrospective analysis from a single center / D. Amarapurkar, N. Bhatt, N. Patel et al. // Indian Journal of Gastroenterology. – 2013. – Vol. 32, No. 5. – P. 302–306. 10. Polyp detection and radius measurement in small intestine using video capsule endoscopy/ [M. Zhou, G. Bao, Y. Geng et al.] // 7th International Conference on Biomedical Engineering and Informatics (BMEI) IEEE, 7th Oct. 2014. – P. 237–241. 11. Tissue classification for laparoscopic image understanding based on multispectral texture analysis / [Y. Zhang, S. J. Wirkett, J. Iszatt et al.] // Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling. – March 18, 2016 : SPIE Proceedings. – 2016. – Vol. 9786; DOI:10.1117/12.2216090 12. Lux M. Annotation of endoscopic videos on mobile devices: A bottom-up approach / M. Lux, M. Riegler // In: Proceedings of the 4th ACM Multimedia Systems Conference, MMSys ’13, New York, USA. – 2013. – P. 141–145.

Anahtar Kelimeler: