Neck Muscle Ultrasound Images and Annotations for Cervical Dystonia Analysis

2172 transverse ultrasound images of the neck from 61 participants support the publication 'Objective analysis of neck muscle boundaries for cervical dystonia using ultrasound imaging and deep learning'. The dataset includes manually annotated labels segmenting 13 muscle, ligament, and vertebra structures. It was contributed by Ian Loram and includes clinical labels, sex, and age for each participant.

Use Cases

• Train segmentation models for neck anatomy based on 13 manually annotated muscle/ligament/vertebra labels
• Compare muscle boundary characteristics between patient groups based on clinical labels for cervical dystonia and controls
• Validate automated analysis methods for ultrasound imaging using a dataset of 2172 annotated images

Strengths

• Includes 2172 annotated ultrasound images, providing substantial material for model training
• Covers 61 participants (35 patients, 26 controls) with associated clinical, sex, and age metadata
• Labels segment 13 distinct anatomical structures, enabling detailed analysis

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Data is stored in a MATLAB (.mat) format, requiring specific software for access

Provenance

Source

Ian Loram via figshare

Collection Method

Collected via ultrasound imaging of 61 participants; annotations created manually.

Freshness

Last updated 2026-05-28 16:58:36; freshness should be verified