They design an algorithm that helps find aneurysms in the brain



[ad_1]

US scientists have developed an algorithm that may indicate aneurysms in the brain. The model is called HeadX and marks the possible place of the aneurysm in the brain image.

The algorithm is called HeadXStanford University

US scientists have developed an algorithm that may indicate aneurysms in the brain. The model based on the work of the convolutional neural network marks the possible place of the aneurysm in the cerebral image obtained by angiotomography, which greatly simplifies the diagnosis to radiologists. The study was published in JAMA Network Open.

The presence of an aneurysm (dilatation of the blood vessel) in the brain is a very dangerous condition: its rupture can cause a hemorrhage, being able to occur several neurological disorders or even death. The most effective way to avoid such consequences is early diagnosis and subsequent treatment to avoid rupture.

Computerized angiotomography is now used as one of the main methods of diagnosis because it allows accurate visualization of blood vessels and evaluation of the nature of blood flow from a three-dimensional image. However, aneurysms may be very small and difficult to examine.

The new algorithm

Now a team of researchers led by Allison Park of Stanford University has decided to improve the diagnosis of aneurysm in computed tomography angiography with automatic methods. They developed an algorithm called HeadXNet that is based on the analysis of three-dimensional images using convolutional neural networks. To train him, the researchers took pictures and results of 611 diagnoses: in the farms used, aneurysms and their absence were diagnosed. The resulting model highlighted the likely location of the aneurysm in one of the sections of the red image.

Thereafter, the resulting model was tested on 115 unpartitioned images and shown to 8 qualified radiologists along with the unidentified standard findings of CT angiography. Diagnostic accuracy with HeadXNet increased significantly (p = 0.01) compared to usual diagnoses. At the same time, however, there were no significant changes in the time the experts devoted to image analysis. (They design a system that converts thoughts into speech)

Despite the promising results and the high precision, the authors of the article clarify that it is not yet possible to use the new algorithm as the only diagnostic method. Any such automatic method should be accompanied by further evaluation by an experienced radiologist.

Most automatic methods for diagnosing illnesses are being developed precisely to simplify the work of medical personnel rather than to snatch away work as it was feared at some point.

[ad_2]

Source link