Estimation of MR brain scans using artificial intelligence

Estimation of MR brain scans using artificial intelligence

Greece is just one example of a growing population of older people, and with it the incidence of neurodegenerative diseases. Among them is Alzheimer’s disease most represented, which accounts for 70% of neurodegenerative disease cases in Greece. According to estimates published by the Alzheimer’s Society of Greece, 197,000 people currently suffer from this disease. This number is it is expected to rise to 354,000 until 2050.

Dr. Andreas Papadopoulos1, a physician and scientific coordinator at Iatropolis Medical Group, a leading diagnostician near Athens, Greece, explains the key role of early diagnosis: “The probability of developing Alzheimer’s disease can only be 1% to 2% at age 65. But then it doubles every five years. Existing drugs cannot reverse the course of degeneration; they can only slow it down. Therefore, it is crucial to make a correct diagnosis in the preliminary stages – when the first mild cognitive impairment appears – and to filter patients with Alzheimer’s.2. ”

Diseases such as Alzheimer’s disease or other neurodegenerative pathologies are typically very slow to progress, making it difficult to recognize and quantify pathological changes on early-stage brain MRI scans. In the assessment of the scan, some radiologists describe the process as a process of “guessing,” because visual changes in a very complex brain anatomy cannot always be well perceived by the human eye. Here, technical innovations such as artificial intelligence can offer support in interpreting clinical images.

One such tool is AI-Rad Companion Brain MR3. Part of a family of AI-based recording decision support solutions, AI-Rad Companion Brain MR is brain volumetric software that provides automatic volumetric quantification of different brain segments. “It can separate them from each other: it isolates the hippocampus and brain lobes and quantifies the volume of white and gray matter for each segment individually.” says Dr. Papadopoulos. In total, it has the capacity to segment, measure, and highlight more than 40 brain regions.

Manually calculating volumetric properties can be an extremely arduous and time-consuming task. “More importantly, it involves a certain degree of precise observation that people are simply unable to achieve.” says Dr. Papadopoulos. Papadopoulos has always been an early adopter and has welcomed technological innovations in pictorial painting throughout his career. This tool with AI means that it can now compare quantification with normative data from a healthy population. And it’s not all about automation: the software displays the data in a structured report and generates a prominent deviation map based on user preferences. This allows the user to manually monitor volumetric changes with all key data prepared automatically in advance.

Possibilities for more accurate observation and evaluation of volumetric changes in the brain encourage Papadopoulos when he considers the importance of early detection of neurodegenerative diseases. He explains: “In the early stages, the volumetric changes are small. In the hippocampus, for example, there is a reduction in volume from 10% to 15%, which is very difficult for the eye to notice. But the objective calculations provided by the system can be very helpful. ”

The goal of AI is to relieve physicians of a significant burden and, ultimately, save time when it is optimally embedded in the workflow. The extremely valuable role of this special post-processing tool that drives AI is that it can visualize the deviation of different structures that could be difficult to identify 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 to base its subjective assessment during the review.”

AI-Rad Companion4 Siemens Healthineers supports clinicians in their daily routine of making diagnostic decisions. To maintain a continuous flow of values, our artificial intelligence-based tools include regular software updates and updates that are delivered to users via the cloud. Users can decide whether they want to integrate a fully cloud-based approach into their work environment using all the benefits of the cloud or a hybrid approach that allows them to process image data within their own hospital IT settings.

The upcoming version of the AI-Rad Companion Brain MR software will feature new algorithms capable of segmenting, quantifying, and visualizing white matter hyperintensity (WMH). Together with McDonald’s criteria, WHM reporting helps evaluate multiple sclerosis (MS).



Source link

Leave a Reply