Automatically tracking brain metastases after stereotactic radiosurgery
Background and purpose: Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2–3 months. This study investigated whether it is possible to auto...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Physics and Imaging in Radiation Oncology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S240563162300043X |
| _version_ | 1827824111220424704 |
|---|---|
| author | Dylan G. Hsu Åse Ballangrud Kayla Prezelski Nathaniel C. Swinburne Robert Young Kathryn Beal Joseph O. Deasy Laura Cerviño Michalis Aristophanous |
| author_facet | Dylan G. Hsu Åse Ballangrud Kayla Prezelski Nathaniel C. Swinburne Robert Young Kathryn Beal Joseph O. Deasy Laura Cerviño Michalis Aristophanous |
| author_sort | Dylan G. Hsu |
| collection | DOAJ |
| description | Background and purpose: Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2–3 months. This study investigated whether it is possible to automatically track BMs on longitudinal imaging and quantify the tumor response after radiotherapy. Methods: The METRO process (MEtastasis Tracking with Repeated Observations was developed to automatically process patient data and track BMs. A longitudinal intrapatient registration method for T1 MR post-Gd was conceived and validated on 20 patients. Detections and volumetric measurements of BMs were obtained from a deep learning model. BM tracking was validated on 32 separate patients by comparing results with manual measurements of BM response and radiologists’ assessments of new BMs. Linear regression and residual analysis were used to assess accuracy in determining tumor response and size change. Results: A total of 123 irradiated BMs and 38 new BMs were successfully tracked. 66 irradiated BMs were visible on follow-up imaging 3–9 months after radiotherapy. Comparing their longest diameter changes measured manually vs. METRO, the Pearson correlation coefficient was 0.88 (p < 0.001); the mean residual error was −8 ± 17%. The mean registration error was 1.5 ± 0.2 mm. Conclusions: Automatic, longitudinal tracking of BMs using deep learning methods is feasible. In particular, the software system METRO fulfills a need to automatically track and quantify volumetric changes of BMs prior to, and in response to, radiation therapy. |
| first_indexed | 2024-03-12T02:21:20Z |
| format | Article |
| id | doaj.art-9330cb72f636477a88b2733b3aa9bf9d |
| institution | Directory Open Access Journal |
| issn | 2405-6316 |
| language | English |
| last_indexed | 2024-03-12T02:21:20Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Physics and Imaging in Radiation Oncology |
| spelling | doaj.art-9330cb72f636477a88b2733b3aa9bf9d2023-09-06T04:52:24ZengElsevierPhysics and Imaging in Radiation Oncology2405-63162023-07-0127100452Automatically tracking brain metastases after stereotactic radiosurgeryDylan G. Hsu0Åse Ballangrud1Kayla Prezelski2Nathaniel C. Swinburne3Robert Young4Kathryn Beal5Joseph O. Deasy6Laura Cerviño7Michalis Aristophanous8Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United States; Corresponding author at: Department of Medical Physics, 1275 York Ave, New York, NY 10065, United States.Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Radiation Oncology, Weill Cornell Medicine, New York, NY 10065, United StatesDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United StatesBackground and purpose: Patients with brain metastases (BMs) are surviving longer and returning for multiple courses of stereotactic radiosurgery. BMs are monitored after radiation with follow-up magnetic resonance (MR) imaging every 2–3 months. This study investigated whether it is possible to automatically track BMs on longitudinal imaging and quantify the tumor response after radiotherapy. Methods: The METRO process (MEtastasis Tracking with Repeated Observations was developed to automatically process patient data and track BMs. A longitudinal intrapatient registration method for T1 MR post-Gd was conceived and validated on 20 patients. Detections and volumetric measurements of BMs were obtained from a deep learning model. BM tracking was validated on 32 separate patients by comparing results with manual measurements of BM response and radiologists’ assessments of new BMs. Linear regression and residual analysis were used to assess accuracy in determining tumor response and size change. Results: A total of 123 irradiated BMs and 38 new BMs were successfully tracked. 66 irradiated BMs were visible on follow-up imaging 3–9 months after radiotherapy. Comparing their longest diameter changes measured manually vs. METRO, the Pearson correlation coefficient was 0.88 (p < 0.001); the mean residual error was −8 ± 17%. The mean registration error was 1.5 ± 0.2 mm. Conclusions: Automatic, longitudinal tracking of BMs using deep learning methods is feasible. In particular, the software system METRO fulfills a need to automatically track and quantify volumetric changes of BMs prior to, and in response to, radiation therapy.http://www.sciencedirect.com/science/article/pii/S240563162300043XLongitudinal tumor trackingBrain metastasesImage registrationT1 MR post-GdDeep learningStereotactic radiosurgery |
| spellingShingle | Dylan G. Hsu Åse Ballangrud Kayla Prezelski Nathaniel C. Swinburne Robert Young Kathryn Beal Joseph O. Deasy Laura Cerviño Michalis Aristophanous Automatically tracking brain metastases after stereotactic radiosurgery Physics and Imaging in Radiation Oncology Longitudinal tumor tracking Brain metastases Image registration T1 MR post-Gd Deep learning Stereotactic radiosurgery |
| title | Automatically tracking brain metastases after stereotactic radiosurgery |
| title_full | Automatically tracking brain metastases after stereotactic radiosurgery |
| title_fullStr | Automatically tracking brain metastases after stereotactic radiosurgery |
| title_full_unstemmed | Automatically tracking brain metastases after stereotactic radiosurgery |
| title_short | Automatically tracking brain metastases after stereotactic radiosurgery |
| title_sort | automatically tracking brain metastases after stereotactic radiosurgery |
| topic | Longitudinal tumor tracking Brain metastases Image registration T1 MR post-Gd Deep learning Stereotactic radiosurgery |
| url | http://www.sciencedirect.com/science/article/pii/S240563162300043X |
| work_keys_str_mv | AT dylanghsu automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT aseballangrud automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT kaylaprezelski automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT nathanielcswinburne automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT robertyoung automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT kathrynbeal automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT josephodeasy automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT lauracervino automaticallytrackingbrainmetastasesafterstereotacticradiosurgery AT michalisaristophanous automaticallytrackingbrainmetastasesafterstereotacticradiosurgery |