Deep Learning–Based CT-to-CBCT Deformable Image Registration for Autosegmentation in Head and Neck Adaptive Radiation Therapy

Liang, Xiao; Morgan, Howard E.; Nguyen, Dan; Jiang, Steve B

doi:10.2991/jaims.d.210527.001

Cited by 7 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 8 provides a summary of studies reporting parotid gland segmentation. When the literature is examined, 8–30 it is seen that the parotid glands are generally segmented separately as left and right. At this point, the proposed system can segment both the left and right parotid glands.…”

Section: Resultsmentioning

confidence: 99%

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Sünnetci

Kaba

Çeliker

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Nowadays, artificial intelligence‐based medicine plays an important role in determining correlations not comprehensible to humans. In addition, the segmentation of organs at risk is a tedious and time‐consuming procedure. Segmentation of these organs or tissues is widely used in early diagnosis, treatment planning, and diagnosis. In this study, we trained semantic segmentation networks to segment healthy parotid glands using deep learning. The dataset we used in the study was obtained from Recep Tayyip Erdogan University Training and Research Hospital, and there were 72 T2‐weighted magnetic resonance (MR) images in this dataset. After these images were manually segmented by experts, masks of these images were obtained according to them and all images were cropped. Afterward, these cropped images and masks were rotated 45°, 120°, and 210°, quadrupling the number of images. We trained ResNet‐18/MobileNetV2‐based DeepLab v3+ without augmentation and ResNet‐18/MobileNetV2‐based DeepLab v3+ with augmentation using these datasets. Here, we set the training set and testing set sizes for all architectures to be 80% and 20%, respectively. We designed two different graphical user interface (GUI) applications so that users can easily segment their parotid glands by utilizing all of these deep learning‐based semantic segmentation networks. From the results, mean‐weighted dice values of MobileNetV2‐based DeepLab v3+ without augmentation and ResNet‐18‐based DeepLab v3+ with augmentation were equal to 0.90845–0.93931 and 0.93237–0.96960, respectively. We also noted that the sensitivity (%), specificity (%), F1 score (%) values of these models were equal to 83.21, 96.65, 85.04 and 89.81, 97.84, 87.80, respectively. As a result, these designed models were found to be clinically successful, and the user‐friendly GUI applications of these proposed systems can be used by clinicians. This study is competitive as it uses MR images, can automatically segment both parotid glands, the results are meaningful according to the literature and have software application.

show abstract

Section: Resultsmentioning

confidence: 99%

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Sünnetci

Kaba

Çeliker

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…A potential extension of this method would be to use deep learning to deform pCT as well (Dalca et al 2019), which might significantly reduce the computation time for DIR. The deep learning-based DIR could be further improved by deforming the pCT to CycleGAN sCT instead of CBCT, thereby reducing the misregistration induced by CBCT artifacts (Liang et al 2021). Another approach of using deep learning for pCT is to develop a new deep network, wherein the network learns the relation from the dual input of pCT and CBCT to the single output of sCT via a supervised (Chen et al 2020) or unsupervised (Chen et al 2021a) training.…”

Section: Discussionmentioning

confidence: 99%

A hybrid method of correcting CBCT for proton range estimation with deep learning and deformable image registration

Wang

Jordan

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: This study aimed to develop a novel method for generating synthetic CT (sCT) from cone-beam CT (CBCT) of the abdomen/pelvis with bowel gas pockets to facilitate estimation of proton ranges. Approach: CBCT, the same-day repeat CT, and the planning CT (pCT) of 81 pediatric patients were used for training (n=60), validation (n=6), and testing (n=15) of the method. The proposed method hybridizes unsupervised deep learning (CycleGAN) and deformable image registration (DIR) of the pCT to CBCT. The CycleGAN and DIR are respectively applied to generate the geometry-weighted (high spatial-frequency) and intensity-weighted (low spatial-frequency) components of the sCT, thereby each process deals with only the component weighted toward its strength. The resultant sCT is further improved in bowel gas regions and other tissues by iteratively feeding back the sCT to adjust incorrect DIR and by increasing the contribution of the deformed pCT in regions of accurate DIR. Main results: The hybrid sCT was more accurate than deformed pCT and CycleGAN-only sCT as indicated by the smaller mean absolute error in CT numbers (28.7±7.1 HU vs 38.8±19.9 HU/53.2±5.5 HU; P ≤ 0.012) and higher Dice similarity of the internal gas regions (0.722±0.088 vs 0.180±0.098/0.659±0.129; P ≤ 0.002). Accordingly, the hybrid method resulted in more accurate proton range for the beams intersecting gas pockets (11 fields in 6 patients) than the individual methods (the 90th percentile error in 80% distal fall-off, 1.8±0.6 mm vs 6.5±7.8 mm/3.7±1.5 mm; P ≤ 0.013). The gamma passing rates also showed a significant dosimetric advantage by the hybrid method (99.7±0.8% vs 98.4±3.1%/98.3±1.8%; P ≤ 0.007). Significance: The hybrid method significantly improved the accuracy of sCT and showed promises in CBCT-based proton range verification and adaptive replanning of abdominal/pelvic proton therapy even when gas pockets are present in the beam path.

show abstract

“…However, such methods may be harder to apply to CBCT images due to the lower quality of these images compared to CT, with poor soft tissue contrast and high noise levels. Moreover, those supervised methods require the training of a convolutional neural network (CNN) from a database of segmented CBCT images, which can be difficult to obtain and may contain relatively large contours uncertainties 9 compared to contours made on CT 2 …”

Section: Introductionmentioning

confidence: 99%

Deep learning‐based segmentation in prostate radiation therapy using Monte Carlo simulated cone‐beam computed tomography

et al. 2022

View full text Add to dashboard Cite

show abstract

Deep Learning–Based CT-to-CBCT Deformable Image Registration for Autosegmentation in Head and Neck Adaptive Radiation Therapy

Cited by 7 publications

References 23 publications

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

Comparative parotid gland segmentation by using ResNet‐18 and MobileNetV2 based DeepLab v3+ architectures from magnetic resonance images

A hybrid method of correcting CBCT for proton range estimation with deep learning and deformable image registration

Deep learning‐based segmentation in prostate radiation therapy using Monte Carlo simulated cone‐beam computed tomography

Contact Info

Product

Resources

About