Publications by authors named "Semen Kiselev"
In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams.
View Article and Find Full Text PDFArticle Synopsis
- A new fully automated deep learning framework has been developed to measure vertebral morphometry and Cobb angles from 3D CT scans of the spine and validated on an external dataset.
- The framework uses an ensemble of U-Nets for localizing and segmenting vertebrae, achieving accurate measurements of vertebral body heights, intervertebral disk heights, and spinal curvature with minimal errors compared to manual measurements.
- Results show a strong correlation between the automated and manual measurements, indicating that this framework can effectively handle external data and is efficient in terms of time and computational resources.
Morphological abnormalities of the femoroacetabular (hip) joint are among the most common human musculoskeletal disorders and often develop asymptomatically at early easily treatable stages. In this paper, we propose an automated framework for landmark-based detection and quantification of hip abnormalities from magnetic resonance (MR) images. The framework relies on a novel idea of multi-landmark environment analysis with reinforcement learning.
View Article and Find Full Text PDF