FDA Clears New Version of AI Segmentation Software for Brain MRI
Offering rapid automated segmentation of brain structures, the ClearPoint 2.2 software reportedly enhances visualization for a variety of targeted, MRI-guided procedures.
The Food and Drug Administration (FDA) has granted 510(k) clearance for the artificial intelligence (AI)-enabled ClearPoint 2.2 software, which provides automated segmentation of brain structures from magnetic resonance imaging (MRI) scans.
ClearPoint Neuro, the manufacturer of the software, said it provides rapid segmentation that facilitates a variety of targeted, MRI-guided procedures ranging from deep brain stimulation to laser ablation.
Here one can see a comparison of the ClearPoint Maestro Brain Model (a) and the ClearPoint 2.2 software (b), which includes segmentation of subnuclei. (Images courtesy of NeuroImage.)
The ClearPoint 2.2 software also includes the Maestro Brain Model, which was recently validated in a study published in NeuroImage. In a quantitative reproducibility analysis, researchers found the combination of the shape-constrained deformable brain model and voxel-wise tissue segmentation was superior to manual expert segmentation.
“The ClearPoint system can now offer fast, peri-procedural segmentation of the cortical structures of the brain to identify both targets and safety zones for cell and gene therapy delivery, laser ablation, biopsy and deep brain stimulation,” noted Joe Burnett, the president and CEO of ClearPoint Neuro.
Meta-Analysis Shows Merits of AI with CTA Detection of Coronary Artery Stenosis and Calcified Plaque
April 16th 2025Artificial intelligence demonstrated higher AUC, sensitivity, and specificity than radiologists for detecting coronary artery stenosis > 50 percent on computed tomography angiography (CTA), according to a new 17-study meta-analysis.
Can CT-Based AI Radiomics Enhance Prediction of Recurrence-Free Survival for Non-Metastatic ccRCC?
April 14th 2025In comparison to a model based on clinicopathological risk factors, a CT radiomics-based machine learning model offered greater than a 10 percent higher AUC for predicting five-year recurrence-free survival in patients with non-metastatic clear cell renal cell carcinoma (ccRCC).
