Imaging Protocol
This page describes the image capture methodology for psoriasis PASI assessment, including the 8-perspective full-body protocol, decentralised capture, and quality control.
Smartphone-based capture
Legit.Health uses standard smartphone cameras for image acquisition. No specialised photography equipment is required.
Traditional clinical photography often relies on systems like Canfield VISIA, 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.
For psoriasis, the full-body protocol captures all four PASI regions using a standard smartphone; no dermatoscope or specialised camera is needed.
Standard multi-body-site protocol
The default protocol captures 8 images: 4 full-body perspectives for BSA segmentation and 4 close-ups for intensity sign scoring. The app guides the investigator or patient through each perspective in order, with silhouette guidance and a real-time quality check before moving to the next.
8 images (4 perspectives + 4 close-ups)
Perspectives
✓
✓
✓
✓Close-ups
✓
✓
✓
✓| Body region | Weight | Erythema | Desquamation | Induration | Lichenification | BSA % | Area score | Region PASI |
|---|---|---|---|---|---|---|---|---|
| Head | 0.1 | 2 | 2 | 1 | 0 | 15% | 2 | 1.0 |
| Trunk | 0.3 | 2 | 2 | 2 | 0 | 20% | 2 | 3.6 |
| Upper extremities | 0.2 | 2 | 1 | 2 | 0 | 15% | 2 | 2.0 |
| Lower extremities | 0.4 | 3 | 2 | 2 | 0 | 20% | 2 | 5.6 |
Psoriasis Area and Severity Index
PASI Score: 12.2
Capture time
The full 8-perspective protocol takes approximately 3–5 minutes using the guided Legit.Health mobile application.
Decentralised (home-based) capture
The 8-perspective protocol is specifically designed for decentralised imaging, allowing patients to capture images at home without visiting the clinic. This has been validated in a Phase 3 clinical trial for JNJ-77242113.
The Legit.Health mobile application provides:
- Step-by-step perspective guidance: Visual silhouettes for each of the 8 perspectives
- Real-time DIQA quality check: Each image is validated before acceptance
- Sequential capture flow: The app guides through all 8 perspectives in order
- Immediate feedback: If an image fails quality standards, the patient recaptures immediately
Alternative perspective protocols
The 8-perspective protocol is the default, but the body area coverage can be adapted to match any study design:
| Protocol | Perspectives | Use case |
|---|---|---|
| Full body (8) | 4 body + 4 close-ups | Complete PASI with BSA |
| Scalp focus | 1–3 perspectives | Scalp psoriasis (PSSI) studies |
| Palmoplantar | 1–2 perspectives | Palmoplantar psoriasis studies |
| Target lesion | 1–2 close-ups | Intensity scoring only (no BSA) |
Local PASI from visual signs
A full PASI assessment requires a standardised set of images. When part of that set is missing, the platform degrades gracefully and falls back to a Local PASI: visual signs are scored from whichever close-ups are available, even when BSA-dependent inputs are absent.
Each row below pairs the required input for PASI (left) with a partial dataset (right) showing how visual signs are still computed when imagery is missing.
8 images (4 perspectives + 4 close-ups)
Perspectives
✓✓✓✓Close-ups
✓✓✓✓| Body region | Weight | Erythema | Desquamation | Induration | Lichenification | BSA % | Area score | Region PASI |
|---|---|---|---|---|---|---|---|---|
| Head | 0.1 | 2 | 2 | 1 | 0 | 15% | 2 | 1.0 |
| Trunk | 0.3 | 2 | 2 | 2 | 0 | 20% | 2 | 3.6 |
| Upper extremities | 0.2 | 2 | 1 | 2 | 0 | 15% | 2 | 2.0 |
| Lower extremities | 0.4 | 3 | 2 | 2 | 0 | 20% | 2 | 5.6 |
Psoriasis Area and Severity Index
PASI Score: 12.2
5 images (4 perspectives + 1 close-up)
Perspectives
✓✓✓✓Close-ups
✗✓✗✗| Body region | Weight | Erythema | Desquamation | Induration | Lichenification | BSA % | Area score | Region PASI |
|---|---|---|---|---|---|---|---|---|
| Head | 0.1 | - | - | - | - | 15% | 2 | - |
| Trunk | 0.3 | 2 | 2 | 2 | 0 | 20% | 2 | 3.6 |
| Upper extremities | 0.2 | - | - | - | - | 15% | 2 | - |
| Lower extremities | 0.4 | - | - | - | - | 20% | 2 | - |
Psoriasis Area and Severity Index
PASI Score: -
PASI score not available: incomplete dataset (missing regions).
Local PASI and visual signs available
8 images (4 perspectives + 4 close-ups)
Perspectives
✓✓✓✓Close-ups
✓✓✓✓| Body region | Weight | Erythema | Desquamation | Induration | Lichenification | BSA % | Area score | Region PASI |
|---|---|---|---|---|---|---|---|---|
| Head | 0.1 | 2 | 2 | 1 | 0 | 15% | 2 | 1.0 |
| Trunk | 0.3 | 2 | 2 | 2 | 0 | 20% | 2 | 3.6 |
| Upper extremities | 0.2 | 2 | 1 | 2 | 0 | 15% | 2 | 2.0 |
| Lower extremities | 0.4 | 3 | 2 | 2 | 0 | 20% | 2 | 5.6 |
Psoriasis Area and Severity Index
PASI Score: 12.2
4 images (0 perspectives + 4 close-ups)
Perspectives
✗✗✗✗Close-ups
✓✓✓✓| Body region | Weight | Erythema | Desquamation | Induration | Lichenification | BSA % | Area score | Region PASI |
|---|---|---|---|---|---|---|---|---|
| Head | 0.1 | 2 | 2 | 1 | 0 | - | - | - |
| Trunk | 0.3 | 2 | 2 | 2 | 0 | - | - | - |
| Upper extremities | 0.2 | 2 | 1 | 2 | 0 | - | - | - |
| Lower extremities | 0.4 | 3 | 2 | 2 | 0 | - | - | - |
Psoriasis Area and Severity Index
PASI Score: -
PASI score not available: incomplete dataset (missing regions).
Visual signs available
When BSA-required perspectives are missing but representative close-up lesion images are available, PASI visual signs are still scored. AI and clinician panel scores are then compared on the visual-signs dimension only.
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 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 investigator receives immediate feedback explaining the quality issue and must recapture
Configurable thresholds
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
- Wear minimal, loose-fitting clothing: Full-body images require exposure of all four PASI regions (head, trunk, arms, legs)
- Remove topical treatments: Emollients and topical steroids can alter the appearance of erythema and scaling
- Consistent lighting: Even illumination across the body is critical for accurate erythema assessment. Avoid harsh shadows.
- Neutral background: A plain, non-reflective background helps the body segmentation AI delineate body boundaries accurately
Environmental conditions
- Well-lit room with even illumination; avoid harsh shadows that distort erythema assessment
- Neutral, non-reflective background, essential for body segmentation
- Consistent distance from camera (~1.5–2 metres for full-body, ~30 cm for close-ups)
- Same conditions at every visit: lighting, background, and distance should be consistent for reliable longitudinal comparison