DIGITAL IMAGES CLASSIFICATION IN AUTOMATIC LAPAROSCOPIC DIAGNOSTICS

The aim: To evaluate the automatic computer diagnostic (ACD) systems, which were 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.

Materials and methods: The training of HAAR features cascade, and AdaBoost classifiers were performed with images/ frames of 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 features.

Results: 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 (P<0.05). 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 (P<0.05).

Conclusions: The HAAR feature-based cascade classifier turned out to be less e"ective when compared with the AdaBoost classifier trained with MCLBP descriptors. Ovarian cysts were better diagnosed when compared with appendicitis with the developed ACD.