Evaluating brain MRI scans with the help of artificial intelligence
Greece is one example of a population in which the share of older people and the incidences of neurodegenerative disease are increasing. Among these, Alzheimer’s disease is the most prevalent, accounting for 70% of neurodegenerative disease cases in Greece. According to estimates published by the Alzheimer Society of Greece, 197,000 people are suffering from the disease at present. This number is expected to rise to 354,000 by 2050.
Dr. Andreas Papadopoulos1, a physician and scientific coordinator at Iatropolis Medical Group, a leading diagnostic provider near Athens, Greece, explains the key role of early diagnosis: “The likelihood of developing Alzheimer’s may be only 1% to 2% at age 65. It doubles every five year. The degeneration cannot be reversed by existing drugs; they can only slow it. This is why it’s crucial to make the right diagnosis in the preliminary stages–when the first mild cognitive disorder appears–and to filter out Alzheimer’s patients2.”
Deadly diseases like Alzheimer’s and other neurodegenerative pathologies have a slow progression. This makes it difficult to identify and quantify pathological changes in brain MRI images early on. Radiologists refer to the evaluation of scans as “guesstimation,” because it is difficult to see the complex anatomy of the brain with the human eye. Artificial intelligence and other technical innovations can help interpret clinical images.
One such tool is the AI-Rad Companion Brain MR3. AI-Rad Companion Brain MR, a brain volumetry program that automatically quantifies different brain segments, is part of a family AI-based decision-support solutions. Dr. Papadopoulos says, “It can segment them from one another: it isolates hippocampi as well as the lobes and quantifies white matter volume and gray matter volumes for each segment separately.” In total, it has the capacity to segment, measure volumes, and highlight more than 40 regions of the brain.
Calculating volumetric properties manually can be an extremely laborious and time-consuming task. Dr. Papadopoulos says that it requires precise observation that humans simply are not capable of. Papadopoulos was a pioneer in the field of imaging and has welcomed new technologies throughout his career. The AI-powered tool allows Papadopoulos to compare quantifications with normative data taken from a healthy population. The software can display the data in a structured report, and generate a highlighted deviation map according to user settings. This software allows users to monitor volumetric changes manually, with all the key data already prepared in advance.
Positive opportunities to observe and evaluate volumetric changes in the brain more accurately encourage Papadopoulos, who considers how important early detection of neurodegenerative disease is. He explained that volumetric changes in the early stages are very small. In the hippocampus, for example, there is a volume reduction of 10% to 15%, which is very difficult for the eye to detect. The system’s objective calculations could be a huge help
. AI’s goal is to alleviate physicians of a significant burden and to save time when integrated into the workflow. This particular AI-powered postprocessing tool plays an important role. It can identify deviations of structures that are difficult to see with the naked eye. Papadopoulos already recognizes that the greatest advantage in his work is “the objective framework that AI-Rad Companion Brain MR provides on which he can base his subjective assessment during an examination.”
AI-Rad Companion4 from Siemens Healthineers supports clinicians in their daily routine of diagnostic decision-making. Our AI-powered tools offer regular software updates and upgrades, which are delivered to customers via the cloud. This ensures that there is a continuous stream of value. Customers have the option of integrating a cloud-based approach to their work environment, leveraging all the benefits offered by the cloud or a hybrid approach that allows for them to process their imaging data within their hospital IT infrastructure.
The new software version of AI–Rad Companion Brain MR includes new algorithms that can segment, quantify, and visualize white matter hyperintensities. Reporting WHM is an aid in multiple sclerosis (MS), evaluation.
One functionality, also of other AI-Rad Companion product family members, is quantification. Access to numbers allows you to compare the progression of a disease through the patient pathway. Quantification can, furthermore, positively impact objectivity in reporting in cases where different radiologists are involved.
Given the range of AI-based decision support solutions for imaging in clinical work routines, the AI-Rad Companion application family will continue to expand. It will cover more modalities and other body regions. Siemens Healthineers is committed in delivering innovative health care.
Learn more about AI in diagnostic imaging here.
This content was produced by Siemens Healthineers. It was not written by the editorial staff of MIT Technology Review.
I’m a journalist who specializes in investigative reporting and writing. I have written for the New York Times and other publications.