Multitask 3D CBCT-to-CT translation and organs-at-risk segmentation using physics-based data augmentation Journal Article
| Authors: | Dahiya, N.; Alam, S. R.; Zhang, P.; Zhang, S. Y.; Li, T.; Yezzi, A.; Nadeem, S. |
| Article Title: | Multitask 3D CBCT-to-CT translation and organs-at-risk segmentation using physics-based data augmentation |
| Abstract: | Purpose: In current clinical practice, noisy and artifact-ridden weekly cone beam computed tomography (CBCT) images are only used for patient setup during radiotherapy. Treatment planning is performed once at the beginning of the treatment using high-quality planning CT (pCT) images and manual contours for organs-at-risk (OARs) structures. If the quality of the weekly CBCT images can be improved while simultaneously segmenting OAR structures, this can provide critical information for adapting radiotherapy mid-treatment as well as for deriving biomarkers for treatment response. Methods: Using a novel physics-based data augmentation strategy, we synthesize a large dataset of perfectly/inherently registered pCT and synthetic-CBCT pairs for locally advanced lung cancer patient cohort, which are then used in a multitask three-dimensional (3D) deep learning framework to simultaneously segment and translate real weekly CBCT images to high-quality pCT-like images. Results: We compared the synthetic CT and OAR segmentations generated by the model to real pCT and manual OAR segmentations and showed promising results. The real week 1 (baseline) CBCT images which had an average mean absolute error (MAE) of 162.77 HU compared to pCT images are translated to synthetic CT images that exhibit a drastically improved average MAE of 29.31 HU and average structural similarity of 92% with the pCT images. The average DICE scores of the 3D OARs segmentations are: lungs 0.96, heart 0.88, spinal cord 0.83, and esophagus 0.66. Conclusions: We demonstrate an approach to translate artifact-ridden CBCT images to high-quality synthetic CT images, while simultaneously generating good quality segmentation masks for different OARs. This approach could allow clinicians to adjust treatment plans using only the routine low-quality CBCT images, potentially improving patient outcomes. Our code, data, and pre-trained models will be made available via our physics-based data augmentation library, Physics-ArX, at https://github.com/nadeemlab/Physics-ArX. © 2021 American Association of Physicists in Medicine. |
| Keywords: | treatment response; treatment planning; radiotherapy; image enhancement; computerized tomography; image segmentation; clinical practices; learning frameworks; structural similarity; deep learning; threedimensional (3-d); mean absolute error; large dataset; 3d cbct-to-ct translation; oars segmentation; cone beam computed tomography image (cbct) |
| Journal Title: | Medical Physics |
| Volume: | 48 |
| Issue: | 9 |
| ISSN: | 0094-2405 |
| Publisher: | American Association of Physicists in Medicine |
| Date Published: | 2021-09-01 |
| Start Page: | 5130 |
| End Page: | 5141 |
| Language: | English |
| DOI: | 10.1002/mp.15083 |
| PUBMED: | 34245012 |
| PROVIDER: | scopus |
| PMCID: | PMC8455439 |
| DOI/URL: | |
| Notes: | Article -- Export Date: 1 October 2021 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
-
175Zhang -
48Li -
49
Riyahi Alam -
50Nadeem
Related MSK Work