Choose a series

Rate image

BrowserQC

Automated MRI quality control, entirely in your browser — no upload, no server. Drag in a NIfTI image (or DICOM files or folders; with several series you pick one) and it runs automatically.

• Segmentation — a brainchop deep-learning model parcellates the brain into 17 gray/white-matter and subcortical regions (103 Desikan-Killiany regions with mindsnap, or GM/WM/CSF partial-volume fractions with PVE), shown as a colour overlay on your scan (adjust with the Opacity slider)
• Quality metrics — niimath computes MRIQC-style image-quality metrics (CJV, CNR, SNR, WM2MAX, EFC, tissue composition) from the scan and its segmentation
• Rate — your own rating, as in MRIQC's reports: overall quality, specific artifacts, comments and confidence, saved as MRIQC's rating JSON

Rendering uses NiiVue; DICOM import uses dcm2niix.

Inspired by MRIQC, whose metric definitions and naming this tool follows: Esteban et al. (2017) MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites. PLoS One 12(9):e0184661. PMID: 28945803. CNR includes an air-noise term and intensities are N4-corrected as in MRIQC; deep-learning segmentation still makes values approximate rather than comparable to MRIQC normative data.

Licensed BSD-2-Clause. Runs on WebGPU where available, WebGL2 otherwise.