A team of scientists from Kemerovo State University (KemSU), in collaboration with the Research Institute for Complex Problems of Cardiovascular Diseases, has developed an intelligent system for diagnosing sarcopenia — the loss of skeletal muscle mass.
The scientists explained that doctors currently make diagnoses based on CT scans. The doctor manually measures the abdominal area in the region of the L3 vertebra. Then, using a special formula, calculates the muscle mass index. The whole process takes more than 15 minutes. The scientists' intelligent system will speed up this process.
Our system performs this task in one minute. We have developed two neural networks: one segments the image and identifies muscle mass, and the other solves classification problems.
The presence of sarcopenia increases the risk of complications during surgical interventions and in the rehabilitation process. Automating the diagnostic process will simplify the diagnosis for doctors.
The program of Kemerovo scientists is registered as a result of intellectual activity (RIA), and neural networks are registered as know-how. The product is being implemented within the framework of the national program "Digital Economy of the Russian Federation".
Read more on the topic:
The Russian market for AI solutions in medicine may reach a volume of 15-17 billion rubles
Breakthrough in diagnostics: Sber has created the GigaDoc medical AI assistant
Yandex has developed a neural network for the early detection of rare pathologies during pregnancy