AI to Assist Physicians in Detecting Brain Aneurysms

Deep learning, which is a powerful type of artificial intelligence, can help physicians detect potentially life-threatening cerebral aneurysms on CT angiography, according to a study published in the journal Radiology.

Cerebral aneurysms are weakened areas of blood vessels in the brain. If left untreated, they can leak or rupture, depending on their size, shape, or location. This can result in a fatal prognosis for the patient if left undetected.

Brain Aneurysms can Now be Successfully Treated Using a Robot
Using a robot to treat brain aneurysms is feasible now and could allow improved precision when placing stents, coils, and other devices, according to a new study.

‘Deep learning using artificial intelligence has tremendous potential in detecting cerebral aneurysms that can be overlooked during a routine assessment due to their small size or complexity of blood vessels.’
Read More..

Tweet it Now

CT angiography is usually used to detect aneurysms. Aneurysms which are smaller in size can be overlooked during initial assessment using CT angiography.

"In our daily work we are always faced with cases in which some important lesions have been missed by the human eye," said study senior author Xi Long, Ph.D., from the Department of Radiology at Tongji Medical College's Union Hospital in Wuhan, China. "Cerebral aneurysms are among those small lesions that may be overlooked on the routine assessment of radiological images."

The deep learning system is trained on existing images of cerebral aneurysms. It learns to recognize the abnormalities that is not easily visible to a human observer. Deep learning has been used in the detection of tuberculosis on chest x-rays.

New Stretchable Wireless Sensor Could Track Healing of Cerebral Aneurysms
Newly developed wireless sensor small enough to be implanted in the blood vessels of the human brain could help clinicians to evaluate the healing of aneurysms (bulges that can cause death or serious injury if they burst).

For the recent study, a fully automated and highly sensitive algorithm was used for the detection of cerebral aneurysms on CT angiography images.

Researchers used CT angiograms from more than 500 patients to train the deep learning system, and then they tested it on another 534 CT angiograms that included 649 aneurysms.

Screening for Brain Aneurysms in Polycystic Kidney Disease Patients
Among polycystic kidney disease patients who had evidence of aneurysms at the initial screening, new brain aneurysms were detected in 5 patients during an average follow-up of 8 years, and none of the aneurysms ruptured.

The algorithm detected 633 of the 649 cerebral aneurysms for a sensitivity of 97.5%. the algorithm was also able to detect a few new aneurysms that were missed during the initial assessment.

Deep learning assistance helped to enhance radiologists' performance.

Artificial Intelligence Tool Helps Detect Brain Aneurysms
New AI tool, which is built around an algorithm called HeadXNet, improved clinicians' ability to correctly identify brain aneurysms.

"The developed deep-learning system has shown excellent performance in detecting aneurysms," Dr. Long said. "We found some aneurysms that were overlooked by the human readers on the initial reports, but they were successfully depicted by the deep-learning system."

Deep-learning algorithm can be used as a supportive tool for the second opinion while detecting aneurysms .

Some disadvantages of the deep learning system can be that it may miss very small aneurysms or those aneurysms located close to similar density structures like bones. It also delivers from false-positive results, where it wrongly identifies structures that are similar to aneurysms as aneurysms.

The deep-learning system is intended to assist physicians and not as a replacement to their work.

"At this time, the role of this deep-learning system, which has been trained to recognize aneurysms, is to give suggestions to the human reader to improve their performance and reduce mistakes," Dr. Long said."The combined work of the human reader and computer system improves the diagnostic accuracy for the patient's sake."

Source-Medindia