Imaging Protocol
This page describes how images are captured for alopecia clinical trials using Legit.Health, and how a single standardised set of four scalp photographs produces the SALT score. It also covers image quality control, patient preparation, and site standardisation.
The example images on this page are synthetic dermatology imagery used for illustration; they are not patient records.
Image capture hardware compatibility
Smartphone-based capture
Legit.Health uses standard smartphone cameras for image acquisition. No specialised photography equipment is required.
Traditional clinical photography often relies on dedicated imaging systems, which require per-site hardware, per-site calibration, and significant rental or purchase costs. Smartphone-based capture eliminates these costs while maintaining the image quality needed for AI scoring.
The Legit.Health mobile application guides investigators through the capture process with visual perspective silhouettes, real-time DIQA quality checks, and immediate feedback on image adequacy.
Camera-based capture
Smartphones are the default input, but they are not the only one. The same AI also scores images from professional, camera-based photography systems, which capture higher-resolution, more consistent images than a smartphone. Sponsors that already run standardised imaging at their sites can keep that setup and still obtain automated Legit.Health endpoints.
For studies that require standardised photography hardware, Legit.Health partners with QuantifiCare, a specialist in standardised 2D and 3D clinical imaging for dermatology trials.
Standard capture protocol
The default protocol captures 4 images, one for each SALT quadrant: top, back, left side and right side. It follows the SALT methodology (Olsen et al., 2004), so each photograph maps to one weighted quadrant of the score. The app guides the person taking the photographs through each view in order, with silhouette guidance and a real-time DIQA quality check before moving to the next.
4 images (top, back, left side and right side)
Perspectives
✓
✓
✓
✓
Unlike indications scored from close-ups of selected lesions, the SALT capture set is fixed: every visit needs all four quadrants, whatever the pattern of hair loss, because the total score is the weighted sum of the four. A quadrant with no hair loss is still photographed, and it contributes zero to the score.
Capture technique
- Distance: Approximately 20 to 30 cm (7 to 12 inches) from the camera to the scalp, keeping the whole quadrant in frame
- Patient position: Seated, which is required for the top-of-scalp view and keeps the patient still during capture
- Angle: Camera held directly above or beside the relevant quadrant, perpendicular to the scalp surface
| Quadrant | Camera position |
|---|---|
| Top | Directly above the patient's head |
| Back | Behind the patient, level with the occiput |
| Left side | To the patient's left, level with the ear |
| Right side | To the patient's right, level with the ear |
DIQA: Dermatology Image Quality Assessment
What is DIQA?
DIQA (Dermatology Image Quality Assessment) is an AI-powered image quality assessment algorithm that evaluates every captured image in real time before it is accepted for analysis. It was developed by Legit.Health and published in the Journal of the American Academy of Dermatology (Hernández Montilla et al., 2023).
What DIQA evaluates
| Quality dimension | What it checks | Why it matters |
|---|---|---|
| Focus | Sharpness of the image; absence of motion blur | Out-of-focus images can obscure small lesions, leading to undercounting |
| Lighting | Adequate, even illumination; absence of harsh shadows or glare | Poor lighting creates shadows that mimic or hide lesions |
| Framing | Correct anatomical region captured at the required angle | Incorrect framing means the AI analyses the wrong area |
| Resolution | Sufficient pixel density for lesion detection | Low resolution makes small features undetectable |
How it works in the workflow
- The investigator or patient captures an image through the mobile application
- DIQA evaluates the image immediately (sub-second processing)
- If the image passes: it is accepted and queued for AI scoring
- If the image fails: the person capturing the image receives immediate feedback explaining the quality issue and must recapture
The DIQA pass/fail threshold is configurable per study protocol. Sponsors can choose stricter thresholds for pivotal studies (rejecting more images to ensure the highest quality) or more lenient thresholds for real-world evidence studies.
Patient preparation
- Remove all headwear: hats, caps, turbans, scarves and headbands
- Remove hair accessories such as pins, clips and beads, which can cover areas of hair loss or cast shadows
- Remove glasses and earrings for the side views, as they cover the scalp around the ears
- Remove wigs, extensions and hairpieces, which completely mask the underlying hair loss
- Leave the hair in its natural position; it must not be combed or styled to cover areas of loss
- Keep facial hair the same throughout the study, to minimise variability between visits
- Avoid high collars that hide the nape and the lower back of the scalp
Environmental conditions
- Background: Neutral, non-reflective background, which reduces artefacts and helps separate the head from its surroundings
- Lighting: Well-lit environment with even illumination. Natural light or the smartphone flash can be used. Avoid harsh directional lighting, which washes out the scalp or creates deep shadows where a shadow or a parting can look like hair loss.
The most important principle is consistency: the same lighting conditions, the same distance, the same angles, and the same patient preparation at every visit. Consistent capture conditions ensure that score changes between visits reflect actual clinical changes, hair regrowth or further loss, not variations in image acquisition.
Anonymisation
All photographs are anonymised automatically before they are stored or exported. The side views of the scalp include part of the face, so facial features are masked and cannot be used to re-identify the patient. Two masking styles are available, and the style is chosen for each study: pixelation of the facial features, or black bands over the eyes and mouth.
Facial features pixelated.
Alternative: black bands over the eyes and mouth.