Osteoporosis diagnosis system and interpretation method using x-ray images
The osteoporosis diagnosis system addresses image artifacts and data scarcity by employing an ensemble algorithm and transfer learning, ensuring accurate osteoporosis diagnosis and efficient model training.
WO2025220843A1 Publication Date: 2025-10-23PROMEDIUS INC
6 Cites 0 Cited by
Patent Information
- Application Number
- PCT/KR2025/000389
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-09-26
- Filing Date
- 2025-01-08
- Publication Date
- 2025-10-23
AI Technical Summary
Technical Problem
Existing osteoporosis diagnosis systems using X-ray images face challenges in accurately processing images due to artifacts and require large amounts of standardized medical data for training, leading to high costs and inefficiencies in model accuracy.
Method used
An osteoporosis diagnosis system utilizing an ensemble algorithm to synthesize output results from multiple models and apply transfer learning to enhance learning efficiency and accuracy, incorporating image segmentation and classification models for chest X-ray images.
Benefits of technology
The system provides accurate osteoporosis diagnosis by inferring bone-related information despite image incompleteness and quickly secures learning efficiency and accuracy through transfer learning.
✦ Generated by Eureka AI based on patent content.
Abstract
An osteoporosis diagnosis system according to one embodiment comprises: a classification model training device which includes a plurality of classification models, at least one of the plurality of classification models being an artificial intelligence model corresponding to each of a plurality of divided images obtained by dividing an entire image in correspondence to each anatomical part, and which trains a corresponding classification model on the basis of the plurality of divided images and a training label corresponding to each divided image, the training label being labeled as normal or osteoporosis; and a bone disease classification device for diagnosing the presence or absence of osteoporosis by inputting, into the corresponding classification model of the classification model training device, a plurality of divided images divided from an image to be interpreted.
Need to check novelty before this filing date? Find Prior Art