Saltar al contenido principal

Imaging Protocol

This page describes the image capture methodology, quality control system, and protocol flexibility available for atopic dermatitis clinical trials using Legit.Health.

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.

Standard multi-body-site protocol

The default protocol captures 11 images: 7 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.

Full-body perspectives (7 images)

Head front perspective silhouette

Head front:face and anterior scalp

Head back perspective silhouette

Head back:posterior scalp and neck

Arms and hands front perspective silhouette

Arms front:anterior surface including antecubital fossae

Arms and hands back perspective silhouette

Arms back:posterior surface including hands

Legs and foot front perspective silhouette

Legs front:anterior thighs, knees, shins

Legs and foot back perspective silhouette

Legs back:posterior thighs and calves including popliteal fossae

Foot back perspective silhouette

Foot back:soles and ankles

Close-up perspectives (4 images)

One close-up per body region for detailed intensity sign scoring. Close-ups should capture the most representative eczematous area in each region. The AI uses these for fine-grained scoring of the six SCORAD intensity signs.

Close-up head perspective silhouette

Close-up: head:representative eczematous area on face or scalp

Close-up trunk perspective silhouette

Close-up: trunk:representative lesion on chest or back

Close-up arms perspective silhouette

Close-up: arms:representative lesion at antecubital fossa or forearm

Close-up legs perspective silhouette

Close-up: legs:representative lesion at popliteal fossa or shin

Capture time

The full 11-perspective protocol takes approximately 3–5 minutes using the guided Legit.Health mobile application.

Alternative perspective protocols

The 11-perspective protocol is the default, but the body area coverage can be adapted to match any study design:

ProtocolPerspectivesUse case
Full body (11)7 body + 4 close-upsComplete SCORAD/EASI with BSA
Flexural focus4 perspectives (antecubital + popliteal)Flexural-dominant AD protocols
Face only1–3 perspectivesFacial AD studies
Target lesion1–2 close-upsIntensity scoring only (no BSA)

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 dimensionWhat it checksWhy it matters
FocusSharpness of the image; absence of motion blurOut-of-focus images can obscure small lesions, leading to undercounting
LightingAdequate, even illumination; absence of harsh shadows or glarePoor lighting creates shadows that mimic or hide lesions
FramingCorrect anatomical region captured at the required angleIncorrect framing means the AI analyses the wrong area
ResolutionSufficient pixel density for lesion detectionLow resolution makes small features undetectable

How it works in the workflow

  1. The investigator captures an image through the mobile application
  2. DIQA evaluates the image immediately (sub-second processing)
  3. If the image passes: it is accepted and queued for AI scoring
  4. 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

  • Remove clothing from the area being photographed
  • No moisturiser or topical treatments applied within 2 hours of the visit (unless protocol specifies otherwise)
  • Hair pinned back for face and neck assessments
  • Remove jewellery from the area being photographed
  • Neutral, well-lit background; standard smartphone flash or even natural light

Environmental conditions

  • Patient positioning: Seated or standing comfortably, remaining still during capture
  • Background: Neutral, non-reflective background to reduce artefacts
  • Lighting: Well-lit environment with even illumination. Natural light or smartphone flash can be used. Avoid harsh directional lighting that creates deep shadows.
  • Distance: Approximately 30–50 cm from camera to skin surface, adjusted per body area

Consistency across visits

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, not variations in image acquisition.

Anonymization

All photographs are processed with automatic face anonymization. The system applies irreversible blurring to facial features, ensuring patient privacy for stored and exported images.

Before anonymization
Original capture
After anonymization

Irreversible face blurring applied