Analyzing image...

Running hip dysplasia analysis...

Zoom

Developmental Dysplasia of the Hip (DDH)

AI-powered screening from ultrasound (Graf) or X-ray. Modality is detected automatically — no manual selection. Best results for infants 0–6 months; applicable up to 12 months.

Research tool — not a regulated medical device. Their results are not a diagnosis and can be wrong. Every result must be reviewed by a qualified clinician, who remains responsible for the clinical decision.

The same tool runs both Graf ultrasound and pelvic X-ray pipelines. When you run it from the PACS worklist, we automatically choose the correct pipeline (DICOM Modality when available; otherwise image layout). The detected modality is shown next to the results.

What it does

Assesses developmental dysplasia of the hip — Graf alpha/beta angles on infant hip ultrasound, or the acetabular index on a pelvis X-ray — and flags dysplastic hips.

Live example Pelvis X-ray
Example pelvis X-ray
Example: paediatric pelvis X-ray
Live example Ultrasound (Graf)
Example infant hip ultrasound
Example: infant hip ultrasound (Graf)
Sign in — it’s free — to try it Open a infant hip ultrasound or pelvis X-ray in the PACS worklist and choose “Hip Dysplasia”.

What is DDH?

Developmental Dysplasia of the Hip (DDH) is a condition where the hip joint does not develop properly — the femoral head is partially or completely displaced from the acetabulum (hip socket). If untreated, DDH leads to abnormal gait, pain, and early-onset arthritis.

Early detection is critical. Universal ultrasound screening at 4–6 weeks of age is recommended in many countries. X-ray becomes informative after ossification centers appear (~4 months).

  • Ultrasound (Graf method) — gold standard for infants 0–6 months. Measures Alpha angle and femoral head coverage.
  • X-Ray — used after 4–12 months. Measures ACE angle, Wiberg index, Tonnis grade, IHDI.
AI Model: retuve by Adam McArthur (RadOSS) — Apache 2.0 — documentation; its model weights: retuve-yolo-plugin — CC BY-NC-SA 3.0 and AGPL-3.0 (research use). X-Ray dataset: Fraiwan et al., Mendeley Data (2022).

This project is free. If you would like to help with hosting and development, you can donate in stablecoins — open the Donate page.

How to donate