Related Experiment Video
Updated: Dec 26, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Deep-Learning Detection of Cancer Metastases to the Brain on MRI
Min Zhang1, Geoffrey S Young1, Huai Chen1,2
1Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
Background:
Approximately one-fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Purpose:
To develop a deep-learning-based approach for finding brain metastasis on MRI.
Study Type:
Retrospective.
Sequence:
Axial postcontrast 3D T1 -weighted imaging.
Field Strength:
1.5T and 3T.
Population:
A total of 361 scans of 121 patients were used to train and test the Faster region-based convolutional neural network (Faster R-CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R-CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing.
Assessment:
Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2-step pipeline consisting of a Faster R-CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false-positive foci detected.
Statistical Tests:
The performance of the algorithm was evaluated by using sensitivity, false-positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per-metastases and per-slice.
Results:
Testing on held-out brain MRI data demonstrated 96% sensitivity and 20 false-positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false-positive metastases per slice. The area under the ROC curve was 0.79.
Conclusion:
Our results showed that deep-learning-based computer-aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity.
Level Of Evidence:
3 TECHNICAL EFFICACY STAGE: 2 J. Magn. Reson. Imaging 2020;52:1227-1236.
Insights
This study developed a deep learning approach to detect brain metastases on MRI scans. The computer-aided detection system achieved high sensitivity, aiding in early diagnosis of small, subcentimeter lesions.
Area of Science:
- Medical imaging and artificial intelligence.
- Radiology and oncology.
Background:
- Brain metastases are a common complication of cancer, affecting approximately one-fourth of all cancer patients.
- Magnetic Resonance Imaging (MRI) is crucial for detecting brain metastases, guiding radiotherapy, and monitoring treatment response.
- Early detection of small, subcentimeter metastases is essential for effective cancer therapy.
Purpose of the Study:
- To develop and evaluate a deep learning-based computer-aided detection (CAD) system for identifying brain metastases on MRI.
- To improve the accuracy and efficiency of brain metastasis detection in clinical practice.
Main Methods:
- A retrospective study utilizing 361 axial postcontrast 3D T1-weighted MRI scans from 121 patients.
- Implementation of a two-step deep learning pipeline: Faster region-based convolutional neural network (Faster R-CNN) for initial lesion detection and RUSBoost classifier for reducing false positives.
- Training and testing datasets comprised 1565 and 488 lesions, respectively, with ground truth established by two expert radiologists.
Main Results:
- The deep learning algorithm demonstrated high performance in detecting brain metastases on MRI.
- Testing yielded a sensitivity of 96% with 20 false-positive metastases per scan, and 87.1% sensitivity with 0.24 false-positive metastases per slice.
- The receiver operating characteristic (ROC) curve analysis showed an area under the curve of 0.79, indicating good diagnostic capability.
Conclusions:
- Deep learning-based computer-aided detection (CAD) shows significant potential for detecting brain metastases with high sensitivity and reasonable specificity.
- This AI approach can aid radiologists in the early and accurate identification of brain metastases, potentially improving patient outcomes.
