Related Experiment Video
Updated: Sep 16, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
A Deep Learning Model for Comprehensive Automated Bone Lesion Detection and Classification on Staging Computed
Benjamin D Simon1, Stephanie A Harmon2, Dong Yang3
1Molecular Imaging Branch, NCI, NIH, Bethesda, Maryland (B.D.S., S.A.H., M.J.B., P.L.C., B.T.); Institute of Biomedical Engineering, Department Engineering Science, University of Oxford, England, UK (B.D.S.).
Academic Radiology
|July 9, 2025
Summary
This study developed an artificial intelligence (AI) model to detect and classify bone lesions on CT scans, showing potential to improve cancer staging accuracy and assist physicians.
Area of Science:
- Oncology
- Radiology
- Artificial Intelligence
Background:
- Bone metastases are common in various cancers, posing challenges for staging.
- Accurate detection and classification of bone lesions are crucial for cancer management.
Purpose of the Study:
- To develop a deep learning model for detecting and classifying bone lesions on staging CT scans.
- To evaluate the performance of the AI model in lesion detection and classification.
Main Methods:
- An nnUNet model was trained on CT scans from 402 patients, including those with prostate cancer and other primary cancers.
- The model was evaluated on lesion detection and classification accuracy, sensitivity, and specificity using an independent test set.
- Area Under the Curve (AUC) was calculated for patient-level disease burden prediction.
Main Results:
- The AI model detected 70% of all lesions, including 67% of malignant and 72% of benign lesions.
- Classification accuracy for malignant versus benign lesions was 85%, with 91% sensitivity and 81% specificity.
- Patient-level AUC for disease burden prediction was 0.82.
Conclusions:
- The developed AI model demonstrates accurate performance in detecting and classifying bone lesions.
- The AI model has the potential to aid physicians in cancer staging and reduce errors.
- Further research is needed to assess the model's impact on clinical workflow and physician review.
Related Concept Videos
01:18Classification of Bones
7.4K
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 and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
7.4K
01:10Computed Tomography
6.3K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
6.3K