RSNA News: Siemens Introduces AI-Based MRI Assistants

At the 105th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA) in Chicago, Siemens Healthineers recently introduced two artificial intelligence-based software assistants in the established AI-Rad Companion family that are designed to free radiologists from routine activities during magnetic resonance imaging (MRI) examinations. The AI-Rad Companion Brain MR for Morphometry Analysis¹ automatically segments the brain in MRI images, measures brain volume, and marks volume deviations in result tables used by neurologists for diagnosis and treatment. The AI-Rad Companion Prostate MR for Biopsy Support¹ automatically segments the prostate on MRI images and enables radiologists to mark lesions, facilitating targeted prostate biopsies.
 
“With the new AI-based assistants, we are expanding our diagnostic offering to help our customers increase efficiency and improve the quality of care,” said Peter Koerte, head of Digital Health at Siemens Healthineers. “We firmly believe that AI will help physicians deal with their workload and benefit patients by helping physicians achieve an improved, patient-focused decision-making process. We demonstrated this at last year’s RSNA when we introduced the first application of the AI-Rad Companion focusing on CT for the chest region. At RSNA 2019, we present additional AI-Rad Companion applications for MRI examinations in the brain and prostate regions. Further applications for radiography and radio oncology will follow.”
 
AI-Rad Companion Brain MR for Morphometry Analysis
The AI-Rad Companion Brain MR for Morphometry Analysis supports brain volumetry, which is performed in clinical practice in cases of suspected dementia, for example. Brain volumetry involves measuring the volume of gray matter (nerve cells), white matter (nerve cell connections), and cerebrospinal fluid in various segments of the brain and comparing the results to normal volumes. A tendency for the brain volume to shrink may point to diseases like Parkinson’s disease, Alzheimer’s disease, or other dementia diseases. Previously, segmentation and comparison to the norm were performed manually or semi-automatically.
 
Based on AI algorithms, the AI-Rad Companion Brain MR for Morphometry Analysis can automatically identify about 30 brain segments on MRI images, measure their volumes, and compare the results to data in a normative reference database for brain morphometry from the Alzheimer’s Disease Neuroimaging Initiative (ADNI).² The AI-Rad Companion Brain MR for Morphometry Analysis feeds the results into a report where deviations from the norm are marked automatically, enabling the radiologist to provide the neurology department with objective, quantitative data relevant to differential diagnosis and therapy management. Additionally, patient care can improve by generating reports faster and in a more standardized, evidence-based form.
 
AI-Rad Companion Prostate MR for Biopsy Support
Traditionally, urologists have identified suspected areas of prostate cancer using written reports and pictograms of the prostate provided by the radiologist and based on MRI examinations, as well as acquired tissue samples from the areas in question using ultrasound-guided biopsy. The fusion procedure required manual segmentation of the prostate in the MRI images, which can take up to five minutes per patient.
 
The AI-Rad Companion Prostate MR for Biopsy Support automatically segments the prostate and marks the organ’s outer contour in seconds. The radiologist then marks the suspect areas and sends the annotated MRI images to the urologist for fusion with the ultrasound images during the biopsy. These targeted, MRI-supported biopsies can help the urologist detect significant prostate carcinomas and improve the quality of patient care.
 
Both new AI-Rad Companion software assistants can be used on MRI scanners from outside manufacturers and are available on teamplay,³ the Siemens Healthineers cloud-based platform that helps support compliance with the Health Information Portability and Accountability Act (HIPAA) and the EU GDPR (General Data Protection Regulation). The software is seamlessly integrated into the existing clinical workflow and is DICOM (Digital Imaging and Communications in Medicine) compliant. The clinical images and all supporting information can be made available automatically in the picture archiving and communication system (PACS).
 
References:
¹ AI-Rad Companion Brain MR for Morphometry Analysis and Al-Rad Companion Prostate MR for Biopsy Support are 510(k) pending with the FDA and not yet commercially available in all countries.
² http://adni.loni.usc.edu/
³ teamplay is not yet commercially available in all countries. For regulatory reasons, its future availability cannot be guaranteed. Please contact your local Siemens Healthineers organization for more details.