“
Vlad Cherevko I have been interested in all kinds of electronics and technologies since 2004. I like to play computer games, and I understand the work of different gadgets. I regularly monitor the news of the technology in the world and write materials about it.
Brain metastases are the most common type of central nervous system tumors that occur in approximately 17% of adult patients with cancer. The problem is that these tumors mostly have a diameter of less than 3 mm, which is why it is difficult to identify even with numerous MRI images.
Brainmets.ai reached a sensitivity of 97.4% when lesions are found in general. For tumors more than 12 mm, the accuracy was 100%, for the size of 6-12 mm – 98%, 3–6 mm – 97.9%, and for tumors less than 3 mm – 93%.
“This technology is an important step forward. It increases the confidence in identifying even the smallest lesions, helping doctors make more timely and accurate treatment decisions,” said Dr. Lorens Topff, a neuroradiologist at the Dutch Cancer Institute and a project leader.
It is noted that this technology is not intended to replace physicians, but aims to speed up the diagnostic process and reduce the risk of missing cases. According to the developers, an important factor in accuracy was the quality of the training data on which the AI is trained. Thanks to carefully selected data, accurate annotations and optimized architecture of the neural network, such highly effective results were obtained.
”, – WRITE: mezha.media
Vlad Cherevko I have been interested in all kinds of electronics and technologies since 2004. I like to play computer games, and I understand the work of different gadgets. I regularly monitor the news of the technology in the world and write materials about it.
Brain metastases are the most common type of central nervous system tumors that occur in approximately 17% of adult patients with cancer. The problem is that these tumors mostly have a diameter of less than 3 mm, which is why it is difficult to identify even with numerous MRI images.
Brainmets.ai reached a sensitivity of 97.4% when lesions are found in general. For tumors more than 12 mm, the accuracy was 100%, for the size of 6-12 mm – 98%, 3–6 mm – 97.9%, and for tumors less than 3 mm – 93%.
“This technology is an important step forward. It increases the confidence in identifying even the smallest lesions, helping doctors make more timely and accurate treatment decisions,” said Dr. Lorens Topff, a neuroradiologist at the Dutch Cancer Institute and a project leader.
It is noted that this technology is not intended to replace physicians, but aims to speed up the diagnostic process and reduce the risk of missing cases. According to the developers, an important factor in accuracy was the quality of the training data on which the AI is trained. Thanks to carefully selected data, accurate annotations and optimized architecture of the neural network, such highly effective results were obtained.