You are viewing the documentation for classic ASHS

For new projects we recommend HyperASHS, which produces isotropic-resolution segmentations of the same structures and is available in the cloud through ITK-SNAP as well as locally.

ASHS Classic¶

ASHS (Automatic Segmentation of Hippocampal Subfields) is software for automatic segmentation of the medial temporal lobe (MTL) substructures from brain MRI scans. These structures are involved in early Alzheimer's disease and in a number of other neurological conditions. They are also important in research on memory and cognition.

Automatically labels hippocampal subfields in T2-weighted MRI, or anterior/posterior hippocampus in T1-weighted MRI.
Automatically labels subregions of the MTL cortex, including entorhinal cortex, perirhinal cortex and parahippocampal cortex, in both T1-weighted and T2-weighted MRI scans.
Leverages advanced label fusion approaches for multi-atlas segmentation.
Can be easily retrained to use your own segmentation protocol.
Free, open-source software.
Runs on any computer through Cloud ASHS, or locally on Linux and MacOS.

3D rendering of ASHS segmentation from T2-weighted MRI — Segmentation of hippocampal subfields and MTL subregions by ASHS (3D rendering) from T2-weighted MRI.

ASHS segmentation from T1-weighted MRI — Segmentation of anterior/posterior hippocampus and MTL subregions by ASHS from T1-weighted MRI.

Getting started¶

Quick Start

Pick an atlas, check your MRI data and choose how to run ASHS.
Cloud ASHS

Send your scans to our server from ITK-SNAP. No installation needed.
Local ASHS

Install ASHS on a Linux or MacOS workstation or cluster.
Build your own atlas

Train ASHS on your own manual segmentation protocol.

About us¶

ASHS is developed by members of the Penn Image Computing and Science Laboratory (PICSL) in the Department of Radiology at the University of Pennsylvania. Please see Citations for authorship information.

See the equivalent page for HyperASHS.