Convolutional neural network accurately identifies “mass effect” lesions in more than 50 disease entities.
An artificial intelligence model based on MRI images can accurately identify which brain lesions cause mass effect and which do not for a wide variety of brain diseases, according to findings presented at SIIM2020.
Brain lesions have a number of diagnostically and prognostically relevant features – a key one being whether it exerts a “mass effect” – a distortion or compression of ventricles and sulci. To make this determination, investigators from the University of Pennsylvania, University of California San Francisco, and University of Texas Austin developed a convolutional neural network (CNN) that can be used across many underlying pathologies.
To create the CNN and achieve a high level of accuracy, they extracted T1 and T2-FLAIR images from 384 MRI studies (298 negative, 88 positive) of patients who had 60 different disease entities. Of those images 189 were used for training, 54 for validation, and 142 for a held-out test, ensuring that two-to-three samples were in the test set. In addition, they extracted cerebral spinal fluid masks from the T1 images, and the brain was extracted from the FLAIR image.
Related Content: MRI Distinguishes Brain Lesions
Overall, researchers determined their mass effect detection model was 84.5 percent accurate. The network, they said, performed well across 53 disease entities.
As next steps, the team plans to: classify negative mass effect, use multiple channels to improve tissue segmentation, and produce saliency maps to determine why the classifier is making its decisions.
For more coverage of SIIM2020, click here.
Breast MRI and Background Parenchymal Enhancement: What a Meta-Analysis Reveals
May 29th 2025Moderate or marked background parenchymal enhancement (BPE) reduces the sensitivity and specificity of MRI for breast cancer detection by more than 10 percent in comparison to scans with minimal or mild BPE, according to a new meta-analysis.
New MRI Study Questions Use of Corticosteroid Injections for Knee OA
May 27th 2025Two years after intraarticular knee injections for knee osteoarthritis (OA), study participants who had corticosteroid knee injections had greater OA progression than control patients while the use of hyaluronic acid injections was associated with less OA progression.
Can a Six-Minute MRI Facilitate Detection of Multiple Sclerosis?
May 23rd 2025Recognition of the central vein sign with a six-minute MRI demonstrated comparable sensitivity for multiple sclerosis (MS) detection in comparison to oligoclonal band (OCB) assessment, which requires lumbar puncture, according to newly published research.