Deep learning-based target decomposition for markerless lung tumor tracking in radiotherapy Journal Article
| Authors: | Fu, Y.; Zhang, P.; Fan, Q.; Cai, W.; Pham, H.; Rimner, A.; Cuaron, J.; Cervino, L.; Moran, J. M.; Li, T.; Li, X. |
| Article Title: | Deep learning-based target decomposition for markerless lung tumor tracking in radiotherapy |
| Abstract: | Background: In radiotherapy, real-time tumor tracking can verify tumor position during beam delivery, guide the radiation beam to target the tumor, and reduce the chance of a geometric miss. Markerless kV x-ray image-based tumor tracking is challenging due to the low tumor visibility caused by tumor-obscuring structures. Developing a new method to enhance tumor visibility for real-time tumor tracking is essential. Purpose: To introduce a novel method for markerless kV image-based tracking of lung tumors via deep learning-based target decomposition. Methods: We utilized a conditional Generative Adversarial Network (cGAN), known as Pix2Pix, to build a patient-specific model and generate the synthetic decomposed target image (sDTI) to enhance tumor visibility on the real-time kV projection images acquired by the onboard kV imager equipped on modern linear accelerators. We used 4DCT simulation images to generate the digitally reconstructed radiograph (DRR) and DTI image pairs for model training. We augmented the training dataset by randomly shifting the 4DCT in the superior-inferior, anterior-posterior, and left-right directions during the DRR and DTI generation process. We performed real-time 2D tumor tracking via template matching between the DTI generated from the CT simulation and the sDTI generated from the real-time kV projection images. We validated the proposed method using nine patients’ datasets with implanted beacons near the tumor. Results: The sDTI can effectively improve the image contrast around the lung tumors on the kV projection images for the nine patients. With the beacon motion as ground truth, the tracking errors were on average 0.8 ± 0.7 mm in the superior-inferior (SI) direction and 0.9 ± 0.8 mm in the in-plane left-right (IPLR) direction. The percentage of successful tracking, defined as a tracking error less than 2 mm in the SI direction, is 92.2% on the 4312 tested images. The patient-specific model took approximately 12 h to train. During testing, it took approximately 35 ms to generate one sDTI, and 13 ms to perform the tumor tracking using template matching. Conclusions: Our method offers the potential solution for nearly real-time markerless lung tumor tracking. It achieved a high level of accuracy and an impressive tracking rate. Further development of 3D lung tumor tracking is warranted. © 2024 American Association of Physicists in Medicine. |
| Keywords: | clinical article; controlled study; lung neoplasms; radiotherapy; diagnostic imaging; retrospective study; simulation; lung tumor; image enhancement; computerized tomography; tumors; image processing, computer-assisted; image processing; stereotactic body radiation therapy; biological organs; model; measurement error; cone beam computed tomography; tracking; digital imaging; x-ray; image guided radiotherapy; conventional radiotherapy; procedures; visibility; radiotherapy, image-guided; three-dimensional imaging; tensors; tumor tracking; four dimensional computed tomography; four-dimensional computed tomography; measurement accuracy; humans; human; article; deep learning; real-time tumor tracking; real- time; markerless; target tracking; projection image; template matching; target decomposition; target images; adversarial learning |
| Journal Title: | Medical Physics |
| Volume: | 51 |
| Issue: | 6 |
| ISSN: | 0094-2405 |
| Publisher: | American Association of Physicists in Medicine |
| Date Published: | 2024-06-01 |
| Start Page: | 4271 |
| End Page: | 4282 |
| Language: | English |
| DOI: | 10.1002/mp.17039 |
| PUBMED: | 38507259 |
| PROVIDER: | scopus |
| PMCID: | PMC12123686 |
| DOI/URL: | |
| Notes: | Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Yabo Fu -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
Related MSK Work