TY - JOUR
T1 - Development and clinical implementation of SeedNet
T2 - A sliding-window convolutional neural network for radioactive seed identification in MRI-assisted radiosurgery (MARS)
AU - Sanders, Jeremiah W.
AU - Frank, Steven J.
AU - Kudchadker, Rajat J.
AU - Bruno, Teresa L.
AU - Ma, Jingfei
N1 - Funding Information:
The authors would like to thank The University of Texas MD Anderson Cancer Center’s Department of Scientific Publications for their help editing this paper.
Publisher Copyright:
© 2019 International Society for Magnetic Resonance in Medicine
PY - 2019/6
Y1 - 2019/6
N2 - Purpose: To develop and evaluate a sliding-window convolutional neural network (CNN) for radioactive seed identification in MRI of the prostate after permanent implant brachytherapy. Methods: Sixty-eight patients underwent prostate cancer low-dose-rate (LDR) brachytherapy using radioactive seeds stranded with positive contrast MR-signal seed markers and were scanned using a balanced steady-state free precession pulse sequence with and without an endorectal coil (ERC). A sliding-window CNN algorithm (SeedNet) was developed to scan the prostate images using 3D sub-windows and to identify the implanted radioactive seeds. The algorithm was trained on sub-windows extracted from 18 patient images. Seed detection performance was evaluated by computing precision, recall, F1-score, false discovery rate, and false–negative rate. Seed localization performance was evaluated by computing the RMS error (RMSE) between the manually identified and algorithm-inferred seed locations. SeedNet was implemented into a clinical software package and evaluated on sub-windows extracted from 40 test patients. Results: SeedNet achieved 97.6 ± 2.2% recall and 97.2 ± 1.9% precision for radioactive seed detection and 0.19 ± 0.04 mm RMSE for seed localization in the images acquired with an ERC. Without the ERC, the recall remained high, but the false–positive rate increased; the RMSE of the seed locations increased marginally. The clinical integration of SeedNet slightly increased the run-time, but the overall run-time was still low. Conclusion: SeedNet can be used to perform automated radioactive seed identification in prostate MRI after LDR brachytherapy. Image quality improvement through pulse sequence optimization is expected to improve SeedNet’s performance when imaging without an ERC.
AB - Purpose: To develop and evaluate a sliding-window convolutional neural network (CNN) for radioactive seed identification in MRI of the prostate after permanent implant brachytherapy. Methods: Sixty-eight patients underwent prostate cancer low-dose-rate (LDR) brachytherapy using radioactive seeds stranded with positive contrast MR-signal seed markers and were scanned using a balanced steady-state free precession pulse sequence with and without an endorectal coil (ERC). A sliding-window CNN algorithm (SeedNet) was developed to scan the prostate images using 3D sub-windows and to identify the implanted radioactive seeds. The algorithm was trained on sub-windows extracted from 18 patient images. Seed detection performance was evaluated by computing precision, recall, F1-score, false discovery rate, and false–negative rate. Seed localization performance was evaluated by computing the RMS error (RMSE) between the manually identified and algorithm-inferred seed locations. SeedNet was implemented into a clinical software package and evaluated on sub-windows extracted from 40 test patients. Results: SeedNet achieved 97.6 ± 2.2% recall and 97.2 ± 1.9% precision for radioactive seed detection and 0.19 ± 0.04 mm RMSE for seed localization in the images acquired with an ERC. Without the ERC, the recall remained high, but the false–positive rate increased; the RMSE of the seed locations increased marginally. The clinical integration of SeedNet slightly increased the run-time, but the overall run-time was still low. Conclusion: SeedNet can be used to perform automated radioactive seed identification in prostate MRI after LDR brachytherapy. Image quality improvement through pulse sequence optimization is expected to improve SeedNet’s performance when imaging without an ERC.
KW - convolutional neural network (CNN)
KW - magnetic resonance imaging (MRI)
KW - prostate brachytherapy
KW - radioactive seed
UR - http://www.scopus.com/inward/record.url?scp=85061243498&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061243498&partnerID=8YFLogxK
U2 - 10.1002/mrm.27677
DO - 10.1002/mrm.27677
M3 - Article
C2 - 30737827
AN - SCOPUS:85061243498
SN - 0740-3194
VL - 81
SP - 3888
EP - 3900
JO - Magnetic resonance in medicine
JF - Magnetic resonance in medicine
IS - 6
ER -