Machine learning with different digital images classification in laparoscopic surgery
The evaluation of the effectiveness of the automatic computer diagnostic (ACD) systems developed based on two classifiers – HAAR features cascade and AdaBoost for the laparoscopic diagnostics of appendicitis and ovarian cysts in women with chronic pelvic pain is presented. The training of HAAR feat...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Kazimierz Wielki University
2022-03-01
|
Series: | Journal of Education, Health and Sport |
Subjects: | |
Online Access: | https://apcz.umk.pl/JEHS/article/view/39863 |
_version_ | 1798001774002438144 |
---|---|
author | M. Bayazitov A. Liashenko D. Bayazitov T. Stoeva T. Godlevska |
author_facet | M. Bayazitov A. Liashenko D. Bayazitov T. Stoeva T. Godlevska |
author_sort | M. Bayazitov |
collection | DOAJ |
description |
The evaluation of the effectiveness of the automatic computer diagnostic (ACD) systems developed based on two classifiers – HAAR features cascade and AdaBoost for the laparoscopic diagnostics of appendicitis and ovarian cysts in women with chronic pelvic pain is presented. The training of HAAR features cascade, and AdaBoost classifiers were performed with images/ frames, which have been extracted from video gained in laparoscopic diagnostics. Both gamma-corrected RGB and RGB converted into HSV frames were used for training. Descriptors were extracted from images with the method of Local Binary Pattern (LBP), which includes both data on color characteristics («modified color LBP» - MCLBP) and textural characteristics, which have been used later on for AdaBoost classifier training. Classification of test video images revealed that the highest recall for appendicitis diagnostics was achieved after training of AdaBoost with MCLBP descriptors extracted from RGB images – 0.708, and in the case of ovarian cysts diagnostics – for MCLBP gained from RGB images – 0.886.
Developed AdaBoost-based ACD system achieved a 73.6% correct classification rate (accuracy) for appendicitis and 85.4% for ovarian cysts. The accuracy of the HAAR features classifier was highest in the case of ovarian cysts identification and achieved 0.653 (RGB) – 0.708 (HSV) values. It was concluded that the HAAR feature-based cascade classifier turned to be less effective when compared with the AdaBoost classifier trained with MCLBP descriptors. Ovarian cysts were better diagnosed when compared with appendicitis with the developed ACD.
|
first_indexed | 2024-04-11T11:41:40Z |
format | Article |
id | doaj.art-ca7bb4a7bd6e448782effedbe217a3bf |
institution | Directory Open Access Journal |
issn | 2391-8306 |
language | English |
last_indexed | 2024-04-11T11:41:40Z |
publishDate | 2022-03-01 |
publisher | Kazimierz Wielki University |
record_format | Article |
series | Journal of Education, Health and Sport |
spelling | doaj.art-ca7bb4a7bd6e448782effedbe217a3bf2022-12-22T04:25:48ZengKazimierz Wielki UniversityJournal of Education, Health and Sport2391-83062022-03-0112310.12775/JEHS.2022.12.03.025Machine learning with different digital images classification in laparoscopic surgeryM. Bayazitov0A. Liashenko1D. Bayazitov2T. Stoeva3T. Godlevska4Odessa National Medical UniversityOdessa National Medical UniversityOdessa National Medical UniversityOdessa National Medical UniversityOdessa National Medical University The evaluation of the effectiveness of the automatic computer diagnostic (ACD) systems developed based on two classifiers – HAAR features cascade and AdaBoost for the laparoscopic diagnostics of appendicitis and ovarian cysts in women with chronic pelvic pain is presented. The training of HAAR features cascade, and AdaBoost classifiers were performed with images/ frames, which have been extracted from video gained in laparoscopic diagnostics. Both gamma-corrected RGB and RGB converted into HSV frames were used for training. Descriptors were extracted from images with the method of Local Binary Pattern (LBP), which includes both data on color characteristics («modified color LBP» - MCLBP) and textural characteristics, which have been used later on for AdaBoost classifier training. Classification of test video images revealed that the highest recall for appendicitis diagnostics was achieved after training of AdaBoost with MCLBP descriptors extracted from RGB images – 0.708, and in the case of ovarian cysts diagnostics – for MCLBP gained from RGB images – 0.886. Developed AdaBoost-based ACD system achieved a 73.6% correct classification rate (accuracy) for appendicitis and 85.4% for ovarian cysts. The accuracy of the HAAR features classifier was highest in the case of ovarian cysts identification and achieved 0.653 (RGB) – 0.708 (HSV) values. It was concluded that the HAAR feature-based cascade classifier turned to be less effective when compared with the AdaBoost classifier trained with MCLBP descriptors. Ovarian cysts were better diagnosed when compared with appendicitis with the developed ACD. https://apcz.umk.pl/JEHS/article/view/39863machine learningimages analysisHAAR features cascadeAdaBoost classifierlaparoscopic surgery |
spellingShingle | M. Bayazitov A. Liashenko D. Bayazitov T. Stoeva T. Godlevska Machine learning with different digital images classification in laparoscopic surgery Journal of Education, Health and Sport machine learning images analysis HAAR features cascade AdaBoost classifier laparoscopic surgery |
title | Machine learning with different digital images classification in laparoscopic surgery |
title_full | Machine learning with different digital images classification in laparoscopic surgery |
title_fullStr | Machine learning with different digital images classification in laparoscopic surgery |
title_full_unstemmed | Machine learning with different digital images classification in laparoscopic surgery |
title_short | Machine learning with different digital images classification in laparoscopic surgery |
title_sort | machine learning with different digital images classification in laparoscopic surgery |
topic | machine learning images analysis HAAR features cascade AdaBoost classifier laparoscopic surgery |
url | https://apcz.umk.pl/JEHS/article/view/39863 |
work_keys_str_mv | AT mbayazitov machinelearningwithdifferentdigitalimagesclassificationinlaparoscopicsurgery AT aliashenko machinelearningwithdifferentdigitalimagesclassificationinlaparoscopicsurgery AT dbayazitov machinelearningwithdifferentdigitalimagesclassificationinlaparoscopicsurgery AT tstoeva machinelearningwithdifferentdigitalimagesclassificationinlaparoscopicsurgery AT tgodlevska machinelearningwithdifferentdigitalimagesclassificationinlaparoscopicsurgery |