Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec;56(6):1885-1898.
doi: 10.1002/jmri.28274. Epub 2022 May 27.

Automated Detection of Brain Metastases on T1-Weighted MRI Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

Gabriel Chartrand  1 , Ramón D Emiliani  1 , Sophie A Pawlowski  1 , Daniel A Markel  2 , Houda Bahig  2 , Alexandre Cengarle-Samak  3 , Selvan Rajakesari  4 , Jeremi Lavoie  1 , Simon Ducharme  1   5   6 , David Roberge  2
Affiliations

Automated Detection of Brain Metastases on T1-Weighted MRI Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

Gabriel Chartrand et al. J Magn Reson Imaging. 2022 Dec.

Abstract

Background: Detection of brain metastases (BM) and segmentation for treatment planning could be optimized with machine learning methods. Convolutional neural networks (CNNs) are promising, but their trade-offs between sensitivity and precision frequently lead to missing small lesions.

Hypothesis: Combining volume aware (VA) loss function and sampling strategy could improve BM detection sensitivity.

Study type: Retrospective.

Population: A total of 530 radiation oncology patients (55% women) were split into a training/validation set (433 patients/1460 BM) and an independent test set (97 patients/296 BM).

Field strength/sequence: 1.5 T and 3 T, contrast-enhanced three-dimensional (3D) T1-weighted fast gradient echo sequences.

Assessment: Ground truth masks were based on radiotherapy treatment planning contours reviewed by experts. A U-Net inspired model was trained. Three loss functions (Dice, Dice + boundary, and VA) and two sampling methods (label and VA) were compared. Results were reported with Dice scores, volumetric error, lesion detection sensitivity, and precision. A detected voxel within the ground truth constituted a true positive.

Statistical tests: McNemar's exact test to compare detected lesions between models. Pearson's correlation coefficient and Bland-Altman analysis to compare volume agreement between predicted and ground truth volumes. Statistical significance was set at P ≤ 0.05.

Results: Combining VA loss and VA sampling performed best with an overall sensitivity of 91% and precision of 81%. For BM in the 2.5-6 mm estimated sphere diameter range, VA loss reduced false negatives by 58% and VA sampling reduced it further by 30%. In the same range, the boundary loss achieved the highest precision at 81%, but a low sensitivity (24%) and a 31% Dice loss.

Data conclusion: Considering BM size in the loss and sampling function of CNN may increase the detection sensitivity regarding small BM. Our pipeline relying on a single contrast-enhanced T1-weighted MRI sequence could reach a detection sensitivity of 91%, with an average of only 0.66 false positives per scan.

Evidence level: 3 TECHNICAL EFFICACY: Stage 2.

Keywords: brain metastases; deep learning; detection; loss function; radiotherapy; segmentation.

PubMed Disclaimer

Comment in

References

    1. Gállego Pérez-Larraya J, Hildebrand J. Brain metastases. Handb Clin Neurol. 2014;121:1143-1157.
    1. Lamba N, Wen PY, Aizer AA. Epidemiology of brain metastases and leptomeningeal disease. Neuro-Oncol. 2021;23(9):1447-1456.
    1. O'Halloran PJ, Gutierrez E, Kalyvas A, et al. Brain metastases: A modern multidisciplinary approach. Can J Neurol Sci J Can Sci Neurol. 2021;48(2):189-197.
    1. Palmer JD, Trifiletti DM, Gondi V, et al. Multidisciplinary patient-centered management of brain metastases and future directions. Neuro-Oncol Adv 2020;2(1):vdaa034.
    1. Redmond KJ, Salles AAFD, Fariselli L, et al. Stereotactic radiosurgery for postoperative metastatic surgical cavities: A critical review and International Stereotactic Radiosurgery Society (ISRS) practice guidelines. Int J Radiat Oncol Biol Phys. 2021;111:68-80.

Publication types

LinkOut - more resources