ScolView

2024: Product Announcement

At the end of January 2024, the Perm Polytechnic announced the creation of a neural network for the diagnosis of scoliosis from photographs. According to the developers, the use of computer vision makes the definition of the disease more accurate and accessible to the patient.

The new technology has found application in the ScolView application, which was developed at Yord Tech. A neural network from a photograph of a person's back determines key points on its surface.

𝓲

RuStore

To teach and test the algorithms, the researchers used 3,000 photos of the backs of adults (18-40 years old) and elementary school students. Key points in all photographs were determined using optical technologies that analyze the image of a person's body surface. So you can remotely and contactlessly determine the shape of the body of a patient with disorders of the musculoskeletal system.

Express analysis will determine violations using artificial intelligence in just one photo, and an expanded version - by a video file of the back surface taken from different angles.

As noted by Vladislav Nikitin, Candidate of Physical and Mathematical Sciences, Associate Professor of the Department of Computational Mathematics, Mechanics and Biomechanics at PNIPU, the location of the points relative to each other allows us to conclude that there are various posture disorders.

We compared the neural network model with a previously created spatial three-dimensional model based on the photogrammetry method. With its help, by filming the back with a smartphone camera from different angles, you can restore the volumetric model, "Nikitin explained.

The accuracy of the PNIPU neural network was estimated by the developers at 85%. A trained neural network can be used in clinical medicine, whose specialists are interested in the emergence of new and valid tools for diagnosing spinal deformity.^[1]

Notes