Related Experiment Video
Updated: May 11, 2026
07:25
Ovine Lumbar Intervertebral Disc Degeneration Model Utilizing a Lateral Retroperitoneal Drill Bit Injury
Published on: May 25, 2017
11.6K
Compare three deep learning-based artificial intelligence models for classification of calcified lumbar disc
Zhiming Liu1, Hao Zhang1, Min Zhang2
1Department of Spine Surgery, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Frontiers in Surgery
|November 21, 2024
Summary
An AI model accurately identifies calcified lumbar disc herniation using MRI scans. This deep learning tool, ResNet-34, offers a promising advancement for clinical diagnosis and surgical planning.
Area of Science:
- Radiology and Medical Imaging
- Artificial Intelligence in Medicine
- Spine Surgery
Background:
- Calcified lumbar disc herniation poses diagnostic challenges.
- Accurate identification is crucial for effective treatment planning.
- Current diagnostic methods may have limitations.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) diagnostic model.
- The model aims to identify calcified lumbar disc herniation.
- The identification is based on lateral lumbar magnetic resonance imaging (MRI).
Main Methods:
- A deep learning model, specifically ResNet-34, was developed.
- Data from 1,224 patients (Jan 2019 - Mar 2024) undergoing MRI and CT were used.
- The model was trained, tested, and externally validated.
Main Results:
- The ResNet-34 model achieved high accuracy in identifying calcified lumbar disc herniation.
- Test datasets showed 91.67% accuracy and an AUC of 0.96.
- External validation datasets demonstrated 88.76% accuracy and an AUC of 0.88.
Conclusions:
- A deep learning model was successfully established for identifying calcified intervertebral discs.
- The model demonstrates excellent diagnostic performance.
- This AI tool offers an efficient diagnostic solution for surgeons.
