Medical images of a brain, acquired with computer tomography (CT) and magnetic resonance (MR) are widely used in medicine for patient diagnosis. The analysis of medical images of a brain, acquired by CT or MRI is very actual in both clinical and research fields. To diagnose the patient it is relevant to analyze the pathology zones of the medical image and estimate their volume. The standard software for processing MR and CT images in many cases does not meet the requirements of physicians (problems with pathology zone extraction and volume estimation). Therefore, a task of medical image pathology zone volume estimation develops in medical image analysis. To solve this task, several medical image analysis tasks have to be considered: pathology zone extraction, volume estimation, and 3D visualization. The goal of this work is development of efficient volume estimation methods for evaluating volume of the pathology zones. Existing methods of volume estimation use the 2D data obtained from segmenting medical images. Unfortunately, this could lead to errors in volume calculation, because such methods cannot estimate the form of the pathological region. This means there is no information whatsoever about the pathology between the medical slices. Therefore, in this work it is proposed to use the visualized 3D model of the pathology zone to estimate its volume. The proposed approach uses the data of 3D brain model, which is rebuilt from 2D medical images. Since the proposed method has information about the form of the medical object, it can correctly estimate the volume even between slices, where there is no information about the object. The developed method can be used to obtain volume of the pathology zone with high precision and provide practical improvements to the reliability of medical diagnostics.