Automatic segmentation of brain metastases using T1 magnetic resonance and computed tomography images Journal Article
| Authors: | Hsu, D. G.; Ballangrud, Å.; Shamseddine, A.; Deasy, J. O.; Veeraraghavan, H.; Cervino, L.; Beal, K.; Aristophanous, M. |
| Article Title: | Automatic segmentation of brain metastases using T1 magnetic resonance and computed tomography images |
| Abstract: | An increasing number of patients with multiple brain metastases are being treated with stereotactic radiosurgery (SRS). Manually identifying and contouring all metastatic lesions is difficult and time-consuming, and a potential source of variability. Hence, we developed a 3D deep learning approach for segmenting brain metastases on MR and CT images. Five-hundred eleven patients treated with SRS were retrospectively identified for this study. Prior to radiotherapy, the patients were imaged with 3D T1 spoiled-gradient MR post-Gd (T1 + C) and contrast-enhanced CT (CECT), which were co-registered by a treatment planner. The gross tumor volume contours, authored by the attending radiation oncologist, were taken as the ground truth. There were 3 ± 4 metastases per patient, with volume up to 57 ml. We produced a multi-stage model that automatically performs brain extraction, followed by detection and segmentation of brain metastases using co-registered T1 + C and CECT. Augmented data from 80% of these patients were used to train modified 3D V-Net convolutional neural networks for this task. We combined a normalized boundary loss function with soft Dice loss to improve the model optimization, and employed gradient accumulation to stabilize the training. The average Dice similarity coefficient (DSC) for brain extraction was 0.975 ± 0.002 (95% CI). The detection sensitivity per metastasis was 90% (329/367), with moderate dependence on metastasis size. Averaged across 102 test patients, our approach had metastasis detection sensitivity 95 ± 3%, 2.4 ± 0.5 false positives, DSC of 0.76 ± 0.03, and 95th-percentile Hausdorff distance of 2.5 ± 0.3 mm (95% CIs). The volumes of automatic and manual segmentations were strongly correlated for metastases of volume up to 20 ml (r = 0.97, p < 0.001). This work expounds a fully 3D deep learning approach capable of automatically detecting and segmenting brain metastases using co-registered T1 + C and CECT. © 2021 Institute of Physics and Engineering in Medicine. |
| Keywords: | radiotherapy; patient monitoring; pathology; image enhancement; brain; computerized tomography; computed tomography images; magnetic resonance; stereotactic radiosurgery; mri; radiation oncologists; brain metastases; extraction; image segmentation; automatic segmentations; detection sensitivity; deep learning; convolutional neural network; multiple brain metastasis; convolutional neural networks; similarity coefficients; boundary loss; cect; skull stripping; multi stage modeling |
| Journal Title: | Physics in Medicine and Biology |
| Volume: | 66 |
| Issue: | 17 |
| ISSN: | 0031-9155 |
| Publisher: | IOP Publishing Ltd |
| Date Published: | 2021-09-07 |
| Start Page: | 175014 |
| Language: | English |
| DOI: | 10.1088/1361-6560/ac1835 |
| PROVIDER: | scopus |
| PUBMED: | 34315148 |
| PMCID: | PMC9345139 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 1 October 2021 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
-
221Beal -
523Deasy -
159Veeraraghavan -
135Cervino Arriba -
21Shamseddine -
8Hsu
Related MSK Work