Segmentation AI

Spine segmentation powered by AI.

This module identifies and segments the spine from frontal X-ray images, helping visualize the vertebral column and individual vertebrae in a clearer, structured way.

Try the Prediction Tool

This tool is for research and educational purposes only. It is not a medical diagnosis tool.

Project overview

Current focus: thoracic and lumbar spine.

The Segmentation AI module analyzes spine X-ray images and produces visual predictions of the vertebral region, currently focused on T1 through L5.

Model outputs

Different segmentation views for visual inspection.

Raw pixel-based predictions

Binary spine masks

Multiclass vertebrae masks

Polygon-based vertebrae approximations

Main purpose

Clearer vertebrae localization.

The module supports spine analysis by making vertebrae localization clearer. This can be useful for future workflows related to spinal alignment, scoliosis review, and Cobb-angle support.

Public scope

No confidential datasets or private annotations.

Public examples should be synthetic, self-created, open-source, or otherwise approved for public use.

Prototype status

MVP first, review tools next.

Editing tools

Measurement support

Improved review controls

Guided analysis steps