News | Artificial Intelligence | November 04, 2020

AI Helps Detect Brain Aneurysms on CT Angiography

Images show examples of false-positive aneurysms, including (a) bony structures and vessel bifurcation, (b) veins, (c) vessel curvatures, and (d) calcified plaques. Red box (d) indicates aneurysms annotated by radiologists, and the blue boxes indicate aneurysm candidates provided by the algorithm. Images courtesy of the Radiological Society of North America

Images show examples of false-positive aneurysms, including (a) bony structures and vessel bifurcation, (b) veins, (c) vessel curvatures, and (d) calcified plaques. Red box (d) indicates aneurysms annotated by radiologists, and the blue boxes indicate aneurysm candidates provided by the algorithm. Images courtesy of the Radiological Society of North America

November 4, 2020 — A powerful type of artificial intelligence known as deep learning can help physicians detect potentially life-threatening cerebral aneurysms on computed tomography CT angiography, according to a study published in the journal Radiology.

Cerebral aneurysms are weakened areas of blood vessels in the brain. Left untreated, they can leak or rupture, with sometimes fatal results. Detection and characterization of these aneurysms are critical, as the risk of rupture depends on the size, shape and location of the aneurysm.

CT angiography is usually the first choice for evaluating cerebral aneurysms. The exam is highly accurate, but cerebral aneurysms can be overlooked on the initial assessment due to their small size and the complexity of the blood vessels in the brain.

"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."

Deep learning offers tremendous potential as a supplementary tool for a more accurate interpretation of cerebral aneurysms. A deep learning system is trained on existing images and learns to recognize abnormalities that can be difficult for a human observer to see. In radiology, deep learning has been recently been used as in a variety of roles assisting radiologists, such as in the detection of tuberculosis on chest X-rays.

In the new study, Long and colleagues developed a fully automated, highly sensitive algorithm for the detection of cerebral aneurysms on CT angiography images. They 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.

The algorithm detected 633 of the 649 cerebral aneurysms for a sensitivity of 97.5%. It also found eight new aneurysms that were overlooked on the initial assessment.

Statistical analysis revealed that deep learning assistance enhanced radiologists' performance. The improvement was most pronounced in the less experienced radiologists.

"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."

The results suggest that the deep learning algorithm has promise as a supportive tool for detecting cerebral aneurysms with a potential to be used clinically for a second opinion during interpretation of head CT angiography images. It has a number of advantages in this setting,  Long said, primarily due to the fact that the computer is not influenced by factors like the level of experience, working time and mood that affect human performance.

The system has some limitations, Long noted. It can miss very small aneurysms or aneurysms located close to similar density structures like bones. It also suffers from false positive results, meaning that it mistakenly identifies structures similar to aneurysms as aneurysms, which necessitates careful revision of the system suggestions by human readers.

"Simply put, the deep-learning system is intended to assist human readers, not to replace them," Long said.

The system needs further validation on more heterogeneous data, such as images from people in different parts of the world, which is essential for assessing its generalizability and applicability to daily clinical 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," Long said. "The combined work of the human reader and computer system improves the diagnostic accuracy for the patient's sake."

For more information: www.rsna.org

Related Content

More complex, longer interventional procedures such as structural heart interventions or this revascularization of a coronary chronic total occlusion (CTO) at Henry Ford Hospital in Detroit, requires angiography imaging systems that have improved image detail and lower radiation dose. However, purchase of new systems was put on hold by many hospitals in 2020 due to the sudden drop in elective procedures and diversion of resources due to the COVID-19. Photo by Dave Fornell.

More complex, longer interventional procedures such as structural heart interventions or this revascularization of a coronary chronic total occlusion (CTO) at Henry Ford Hospital in Detroit, requires angiography imaging systems that have improved image detail and lower radiation dose. However, purchase of new systems was put on hold by many hospitals in 2020 due to the sudden drop in elective procedures and diversion of resources due to the COVID-19. Photo by Dave Fornell.

Feature | Angiography | January 19, 2021 | By Bhvita Jani
January 19, 2021 – With the postponement of non-essential elective surgeries and medical procedures in 2020 to conser
AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient care, announced today that the U.S. Food and Drug Administration (FDA) has granted 510(k) clearance for the company’s flagship image analysis platform.
News | Artificial Intelligence | January 18, 2021
January 18, 2021 — AI Metrics, LLC, a medical imaging startup focused on augmented intelligence to improve patient ca
Coronary CT angiography images courtesy of Canon Medical Systems.

Coronary CT angiography images courtesy of Canon Medical Systems.

News | Computed Tomography (CT) | January 18, 2021
MRI of Nonferromagnetic Ballistics Suspended in Gelatin. 

MRI of Nonferromagnetic Ballistics Suspended in Gelatin. Scout (A), T1-weighted spin-echo (SE) (B), T2-weighted SE (C), T2-weighted gradient-recalled echo (GRE) (TR/TE, 500/10; D), and T2-weighted GRE (TR/TE, 700/30; E) MR images show jacket hollow point .45 automatic Colt pistol bullet (Corbon) (1), solid lead .45 Long Colt bullet (Winchester) (2), full metal jacket (FMJ) automatic Colt pistol bullet (Winchester) (3), 5.56-mm FMJ bullet (Federal Ammunition) (4), #7 lead shotgun pellet (Winchester) (5), and 5-mm lead air gun pellet (Sheridan) (6). On all sequences, metallic artifact is minimal. Although metallic artifact increases or blooms with increased TR/TE in GRE images (D and E), amount of surrounding distortion is still minimal.

News | Magnetic Resonance Imaging (MRI) | January 15, 2021
January 15, 2021 — 
Novel Coronavirus SARS-CoV-2 Transmission electron micrograph of SARS-CoV-2 virus particles, isolated from a patient. Image captured and color-enhanced at the NIAID Integrated Research Facility (IRF) in Fort Detrick, Maryland. Credit: National Institute of Allergy and Infectious Diseases, NIH

Novel Coronavirus SARS-CoV-2 Transmission electron micrograph of SARS-CoV-2 virus particles, isolated from a patient. Image captured and color-enhanced at the NIAID Integrated Research Facility (IRF) in Fort Detrick, Maryland. Image courtesy of  National Institute of Allergy and Infectious Diseases (NIH)

News | Coronavirus (COVID-19) | January 15, 2021
January 15, 2021 — In one of the first studies to examine the impact of the...
Multidisciplinary functionality supports high-capacity utilization and economic efficiency
News | Mobile C-Arms | January 14, 2021
January 14, 2021 — Siemens Healthineers has announced the Food and Drug Administration (FDA) clearance of the...
Use of telehealth jumped sharply during the first months of the coronavirus pandemic shutdown, with the approach being used more often for behavioral health services than for medical care, according to a new RAND Corporation study.

Getty Images

News | Teleradiology | January 13, 2021
January 13, 2021 — Use of telehealth jumped sha
This cutting-edge technology assists radiologists in the interpretation of screening mammograms and allows them to diagnose breast cancer earlier and more accurately
News | Mammography | January 12, 2021
January 12, 2021 — Therapixel announced that...