YzzLiu/FracSegNet
A deep-learning method for segmenting fractures from 3D CT images.
Employs a two-stage cascaded architecture: anatomical segmentation first isolates individual pelvic bones (ilia and sacrum), then a specialized fracture network segments bone fragments within each masked region. Includes a curated dataset of 150 CT scans with manual fracture annotations and integrates distance-weighted loss functions to handle the complex morphology and high shape variability of pelvic fractures.
No commits in the last 6 months.
Stars
37
Forks
7
Language
Python
License
MIT
Category
Last pushed
May 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YzzLiu/FracSegNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Alkoby/Bone-Fracture-Detection
Bone Fracture Detection using deep learning (Resnet50) - Final project in the fourth year of the degree
ashita03/Bone-Fracture-Detection
Streamlit web-app based Bone Fracture detection using YoloV8, FasterRCNN with ResNet, and VGG16 with SSD
arianaira/Radiography-bone-fracture-segmentation
Detecting fracture in bone using SAM ViT-b
ammarlodhi255/pediatric_wrist_abnormality_detection-end-to-end-implementation
This repository contains the official code for the paper "Enhancing wrist abnormality detection...
ayzrixsiev/MedVision-XRay-Anomaly-Detection
A system to detect anomalies such as fractures in X-ray images using image processing and...