Related Experiment Video
Updated: Jun 18, 2026
13:45
Hybrid µCT-FMT imaging and image analysis
Published on: June 4, 2015
13.1K
Enhanced CT and MRI Focal Bone Tumor Classification with Machine Learning-based Stratification: A Multicenter
Astrée Lemore1, Nora Vogt2, Julien Oster3
1CHRU de Nancy Pôle Imagerie, Service d'imagerie Guilloz, Nancy, Lorraine, France.
Radiology
|April 22, 2025
Summary
A machine learning model accurately grades bone tumor malignancy, creating a standardized Bone Tumor Imaging Reporting and Data System (BTI-RADS) 2.0 for improved patient management. This AI approach aids in differentiating benign from malignant lesions.
Area of Science:
- Medical Imaging
- Machine Learning in Oncology
- Skeletal Radiology
Background:
- Standardized bone tumor reporting is essential for consistent patient management.
- Existing systems lack multicenter validation and rely on expert consensus.
- Accurate differentiation between benign and malignant bone lesions is clinically critical.
Purpose of the Study:
- To evaluate a machine learning (ML) approach for bone tumor malignancy classification.
- To develop and propose a Bone Tumor Imaging Reporting and Data System (BTI-RADS) 2.0 for risk stratification.
- To compare ML performance against experienced radiologists.
Main Methods:
- Retrospective multicenter trial including 1113 patients with solitary bone tumors.
- Radiographic, CT, and MRI data analyzed using extreme gradient boosting (XGBoost) classifiers.
- Radioclinical features extracted and optimized using bootstrapped chi-squared analysis and cross-validation.
Main Results:
- An XGBoost model achieved an F1 score of 0.81, comparable to experienced radiologists (F1 score 0.83).
- The proposed BTI-RADS 2.0 system stratified patients into seven malignancy risk classes.
- The system demonstrated high sensitivity (96%) for identifying malignant lesions.
Conclusions:
- A machine learning algorithm effectively achieves standardized bone tumor malignancy grading.
- The BTI-RADS 2.0 system provides a validated tool for risk stratification.
- This approach enhances diagnostic accuracy and consistency in bone tumor management.
Related Concept Videos
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
01:14Imaging Studies I: CT and MRI
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...