Early Diagnosis of Scoliosis in Children from RGB-D Images Using Deep Learning

Final Year Project, Department of Computer Science

Project supervisor: Dr. Kenneth K.Y. Wong. (Department of Computer Science)

Project information

Project descriptions

Scoliosis is typically diagnosed from X-ray images, but diagnostic X-rays increase the risk of developmental problems and cancer in those exposed. This project aims to eliminate children’s X-ray exposure in the early diagnosis of scoliosis by generating X-ray images of children’s backs from the corresponding harmless RGB-D images. In this project, a deep learning model based on HRNet was built and trained to detect landmark locations of the backs on the RGB-D images first. With the detected landmarks, the X-ray images of the children’s backs were eventually synthesized from the corresponding RGB-D images by another deep learning model that was built and trained based on the pix2pix model.

Team information

Project leader: Li Gengyu, BEng(CompSc)

Team member(s): Huang Siyi, BEng(CompSc)

Project poster
Project video
Project images
Ground truth landmarks (left) and predicted landmarks (right) 1
Ground truth landmarks (left) and predicted landmarks (right) 2
Ground truth landmarks (left) and predicted landmarks (right) 3
Ground truth landmarks (left) and predicted landmarks (right) 4
Previous
Next
Landmarks on RGB image (left) and depth image (right)
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 1
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 2
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 3
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 4
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 5
RGB image (left), real X-ray image (middle), and synthetic X-ray image (right) 6
Previous
Next
Media links
Awards

Winner of the Dean’s Fund Award @ The 1st Engineering InnoShow

This project team was selected for the Dean’s fund award at the 1st Engineering InnoShow. 

This team has received HK$10,000 sponsorship to participate in external competitions or incubation/ entrepreneurship/ startup programmes.

 

The best project award - COMP3329 Computer Game Design and Programming @ The 1st Engineering InnoShow

This project team was selected for the best project award – COMP3329 Computer Game Design and Programming at the 1st Engineering InnoShow.

Members of the Club Grenade project team in HKUEAA Annual Dinner