rphammonds/scalesurfer-stats-v6

ScaleSurfer FreeSurfer v6 Stats Prediction Model

This repository contains a ScaleSurfer multi-head model for predicting FreeSurfer-style .stats targets from a T1w image and an aparc+aseg segmentation.

Files

• stats_model.pt: full PyTorch stats checkpoint, including frozen encoder weights, prediction heads, target normalization, and target columns.
• config.json: architecture and feature-schema metadata needed by ScaleSurferStatsPredictor.
• metadata.json: checksums and training/evaluation metadata.
• summary.csv, history.csv, target_metrics.csv: copied training diagnostics.

Test Summary

Group	Targets	Values	Normalized MAE	Median absolute percent error
aseg	113	22311	0.3919653041731878	6.885092735290527
global	62	9232	0.18882636669453873	2.3171700835227966
lh_aparc	306	61506	0.385072138514816	6.9706995487213135
rh_aparc	306	61504	0.38465992092747486	7.11681056022644

Loading

from scalesurfer.stats import ScaleSurferStatsPredictor

predictor = ScaleSurferStatsPredictor.from_pretrained(6)
features = predictor.predict_subjects(subjects_dir, subjects, return_format="wide")

This model is intended for research workflows and is not a clinical diagnostic device.