@article{Bayazitov_Bayazitov_Buzynovsky_Lyashenko_Novikov_Godlevsky_2020, title={THE COMPARATIVE EFFECTIVENESS OF IMAGES CLASSIFIERS IN THE COURSE OF RECOGNITION OF ZONES OF INTEREST DURING LAPAROSCOPIC INTERVENTION}, url={https://ojs.tdmu.edu.ua/index.php/here/article/view/11175}, DOI={10.11603/mie.1996-1960.2020.2.11175}, abstractNote={<p>Background. The purpose of the study is to evaluate the effectiveness of the automatic computer diagnostic (ACD) systems developed on the basis of two classifiers — HAAR features cascade and AdaBoost for the detection of appendicitis and metastatic damages of the liver.</p> <p>Materials and methods. For the classifiers training the images/frames, which have been cropped out from video gained in the course of laparoscopic diagnostics were used. Namely, RGB frames, and gamma-corrected RGB frames and converted into HSV have been explored. 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 were used later on for AdaBoost classifier 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.</p> <p>Results. The highest recall for appendicitis diagnostics was achieved after training of AdaBoost with MCLBT descriptors extracted from RGB images—0,745, and in case for metastatic damages diagnostics — 0,902. Hence developed AdaBoost based CAD system achieved 74,4 % correct classification rate (accuracy) for appendicitisc and 89,3 % for metastatic images. The accuracy of HAAR features classifier was highest in case of metastatic foci identification and achieved 0,672 (RGB) — 0,723 (HSV) values.</p> <p>Conclusions. Haar features based cascade classifier turned to be less effective when compared with AdaBoost classifier trained with MCLBT descriptors.</p>}, number={2}, journal={Medical Informatics and Engineering}, author={Bayazitov, N. R. and Bayazitov, D. N. and Buzynovsky, A. B. and Lyashenko, A. V. and Novikov, D. V. and Godlevsky, L. S.}, year={2020}, month={Jul.}, pages={62–69} }