The effectiveness of automatic laparoscopic diagnostics of liver pathology using different methods of digital images classification

Authors

  • D. N. Bayazitov Odesa National Medical University, Ukraine,
  • N. V. Kresyun Odesa National Medical University, Ukraine,
  • А. B. Buzinovsky International center on researches and education in the field of informational technologies and systems at National Academy of Sciences and Ministry of Education of Ukraine, Kyiv, Odesa Regional Clinic Hospital, Ukraine,
  • N. R. Bayazitov Odesa National Medical University, Ukraine,
  • A. V. Lyashenko Odesa National Medical University, Ukraine,
  • L. S. Godlevsky Odesa National Medical University, Ukraine,
  • T. V. Prybolovets Odesa National Medical University, Ukraine,
  • K. A. Bidnyuk Odesa National Medical University, Ukraine,

DOI:

https://doi.org/10.14739/2310-1237.2017.2.109219

Keywords:

liver diseases, laparoscopy, diagnostic imaging, image processing, computer-assisted

Abstract

 

Сomputer automatic diagnostic (CAD)/classification of video – images is actual for laparoscopic surgery. Such CAD is supposed to explore intraoperatively for support surgeon decisions.

Aim: to evaluate the effectiveness of the CAD systems developed on the basis of two classifiers – HAAR features cascade and AdaBoost for the detection of cirrhotic and metastatic damages of the liver.

Materials and methods. The development of CAD was based on training of HAAR features cascade and AdaBoost classifiers with images/frames, which have been cropped out from video gained in the course of laparoscopic diagnostics. RGB frames which were gamma-corrected and converted into HSV have been used for training. Also descriptors were extracted from images with the modified method of Local Binary Pattern (LBT), which includes data on color characteristics («modified color LBT» – MCLBT) and textural ones for AdaBoost classifier training. 1000 positive images along with 500 negative ones of both types of pathology were used for training. After cessation of training the tests were performed with the aim of the estimation of effectiveness of recognition. Test session images were different from those ones which have been used for training of the classifier. Test control sessions were performed with trained classifiers with 319 frames containing cirrhotic and 253 frames with metastatic deteriorations in liver tissue. 365 frames with the absence of mentioned pathology were used as a control group – practically healthy liver state.

Results. Classification of test video-images revealed that the highest recall for cirrhosis diagnostics was achieved after training of AdaBoost with MCLBT descriptors extracted from HSV images – 0.655, and in case for metastatic damages diagnostics – for MCLBT gained from RGB images – 0.925. Hence developed AdaBoost based CAD system achieved 69.0 % correct classification rate (accuracy) for cirrhotic and 92.7 % for metastatic images. The accuracy of Haar features classifier was highest in case of metastatic foci identification and achieved 0.701 (RGB) – 0.717 (HSV) values.

Conclusions. Haar features based cascade classifier turned to be less effective when compared with AdaBoost classifier trained with MCLBT descriptors. Metastatic foci are better diagnosed when compared with cirrhotic liver deterioration with the explored approaches to digital images classification.


 

References

Boisvert, J., Cheriet, F., & Grimard, G. (2003). Segmentation of laparoscopic images for computer assisted surgery. Lecture Notes in Computer Sciences, 2749, 587–594.

Lahane, A., Yesha, Y., Grasso, M., Joshi, A., Park, A., & Lo, J. (2012). Detection of unsafe action from laparoscopic cholecystectomy video. Proc. 2nd ACM SIGHIT International Health Informatics Symposium. (P. 315–322).

Lyashenko, A. V., Bayazitov, N. R., Godlevsky, L. S., Bayazitov, D. N., & Buzynovskiy, A. V. (2016). Informatsiino-tekhnichna systema avtomatyzovanoi laparoskopichnoi diahnostyky [Informational-technical system for the automatized laparoscopic diagnostics]. Radioelektronika, informatyka, upravlinnia, 4, 90–96. [in Ukrainian].

Neofytou, M. S., Tanos, V., Constantinou, I., Kyriacou, E. C., Pattichis M. S., & Pattichis, C. S. (2015). Computer-aided diagnosis in hysteroscopic imaging. IEEE J Biomed Health Inform, 19(3), 1129–1136. doi: 10.1109/JBHI.2014.2332760.

Shu, Y., Bilodeau, G. A., & Cheriet F. (2005). Segmentation of laparoscopic images: Integrating graph-based segmentation and multistage region merging. Proc 2nd Canadian Conference on Computer and Robot Vision (CRV’05). doi: 10.1109/ CRV. 2005.74.

Fatiev, D. (2015). Faculty of Science and Technology Department of Computer Science Object tracking for improved telementoring and telestration. INF-3997 Master's Thesis in Telemedicine and E-health, The Arctic University of Norway.

Albisser, Z. (2015). Computer-aided screening of capsule endoscopy videos. Master’s Thesis, University of Oslo.

Zhou, M., Bao, G., Geng, Y., Alkandari, B., & Li, X. (2014). Polyp detection and radius measurement in small intestine using video capsule endoscopy. Proc 7th International Conference on Biomedical Engineering and Informatics (BMEI), 237–241. doi: 10.1109/BMEI.2014.7002777.

Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. Proc IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1, 511–518. doi: 10.1109/CVPR.2001.990517.

Bouguet, J. (2000). Pyramidal implementation of the Lucas-Kanade feature tracker: description of the algorithm, openCV documentation. Retrieved from http://www.intel.com/research/mrl/research/opencv.

Zhu, C., Bichot, C. E., & Chen, L. (2010). Multi-scale color local binary patterns for visual object classes recognition. Proc ICPR, 3065–3068. doi: 10.1109/ICPR.2010.751.

Ledoux, A., Losson, O., & Macaire, L. (2016). Color local binary patterns: compact descriptors for texture classification. Journal of Electronic Imaging, Society of Photo-optical Instrumentation Engineers, 25(6), 061404.

Ojala, T., Pietikainen, M., & Maenpaa, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987. doi: 10.1109/TPAMI.2002.1017623.

Bay, H., Tuytelaars, T., & Van Gool, L. (2006). Surf: Speeded up robust features. ECCV 2006: Computer Vision – ECCV 2006, 3951, 404–417.

Parent, F., Mandal, K. K., Loranger, S., Hideki, E., Fernandes, W., Kashyap, R., & Kadoury, S. (2016). 3D shape tracking of minimally invasive instruments using optical frequency domain reflectometry. Proc of SPIE, 9786, doi: 10.1117/12.2214998.

Downloads

How to Cite

1.
Bayazitov DN, Kresyun NV, Buzinovsky АB, Bayazitov NR, Lyashenko AV, Godlevsky LS, Prybolovets TV, Bidnyuk KA. The effectiveness of automatic laparoscopic diagnostics of liver pathology using different methods of digital images classification. Pathologia [Internet]. 2017Sep.27 [cited 2024Apr.26];(2). Available from: http://pat.zsmu.edu.ua/article/view/109219

Issue

No. 2 (2017)

Section

Original research

License

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Лицензия Creative Commons
    1. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  1. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (SeeThe Effect of Open Access).