CBCT Verification of SRT for Patients With Brain Metastases

Improved automatic segmentation of brain metastasis gross tumor volume in computed tomography images for radiotherapy: a position attention module for U-Net architecture

Background

Brain metastases present significant challenges in radiotherapy due to the need for precise tumor delineation. Traditional methods often lack the efficiency and accuracy required for optimal treatment planning. This paper proposes an improved U-Net model that uses a position attention module (PAM) for automated segmentation of gross tumor volumes (GTVs) in computed tomography (CT) simulation images of patients with brain metastases to improve the efficiency and accuracy of radiotherapy planning and segmentation.

Methods

We retrospectively collected CT simulation imaging datasets of patients with brain metastases from two centers, which were designated as the training and external validation datasets. The U-Net architecture was enhanced by incorporating a PAM into the transition layer, which improved the automated segmentation capability of the U-Net model. With cross-entropy loss employed as the loss function, the samples from the training dataset underwent training. The model's segmentation performance on the external validation dataset was assessed using metrics including the Dice similarity coefficient (DSC), intersection over union (IoU), accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and Hausdorff distance (HD).

Results

The proposed automated segmentation model demonstrated promising performance on the external validation dataset, achieving a DSC of 0.753±0.172. In terms of evaluation metrics (including the DSC, IoU, accuracy, sensitivity, MCC, and HD), the model outperformed the standard U-Net, which had a DSC of 0.691±0.142. The proposed model produced segmentation results that were closer to the ground truth and could reveal more detailed features of brain metastases.

Conclusions

The PAM-improved U-Net model offers considerable advantages in the automated segmentation of the GTV in CT simulation images for patients with brain metastases. Its superior performance in comparison with the standard U-Net model supports its potential for streamlining and improving the accuracy of radiotherapy. With its ability to produce segmentation results consistent with the ground truth, the proposed model holds promise for clinical adoption and provides a reference for radiation oncologists to make more informed GTV segmentation decisions.

Evaluation of a head rest prototype for rotational corrections in three degrees of freedom

Cranial stereotactic irradiations require accurate reproduction of the planning CT patient position at the time of treatment, including removal of rotational offsets. A device prototype was evaluated for potential clinical use to correct rotational positional offsets in image-guided radiotherapy workflow. Analysis was carried out with a prototype device "RPS head" by gKteso GmbH, rotatable up to 4° in three dimensions by hand wheels. A software tool accounts for the nonrectangular rotation axes and also indicates translational motions to be performed with the standard couch to correct the initial offset and translational shifts introduced by the rotational motion. The accuracy of angular corrections and positioning of an Alderson RANDO head phantom using the prototype device was evaluated for nine treatment plans for cranial targets. Corrections were obtained from cone beam computed tomography (CBCT) imaging. The phantom position was adjusted and the final position was then verified by another CBCT. The long-term stability of the prototype device was evaluated. Attenuation by the device along its three main axes was assessed. A planning study was performed to evaluate if regions of high-density material can be avoided during plan generation. The device enabled the accurate correction of rotational offsets in a clinical setup with a mean residual angular difference of (0.0 ± 0.1)° and a maximum deviation of 0.2°. Translational offsets were less than 1 mm. The device was stable over a period of 20 min, not changing the head support plate position by more than (0.7 ± 0.6) mm. The device contains high-density material in the adjustment mechanism and slightly higher density in the support structures. These can be avoided during planning generation maintaining comparable plan quality. The head positioning device can be used to correct rotational offsets in a clinical setting.

Multi-Intensity Optimization-Based CT and Cone Beam CT Image Registration

Cancer is a highly lethal disease that is mainly treated by image-guided radiotherapy. Because the low dose of cone beam CT is less harmful to patients, cone beam CT images are often used for target delineation in image-guided radiotherapy of various cancers, especially in breast and lung cancer. However, breathing and heartbeat can cause position errors in images taken during different periods, and the low dose of cone beam CT also results in insufficient imaging clarity, rendering existing registration methods unable to meet the CT and cone beam CT registration tasks. In this paper, we propose a novel multi-intensity optimization-based CT and cone beam CT registration method. First, we use a multi-weighted mean curvature filtering algorithm to preserve the multi-intensity details of the input image pairs. Then, the strong edge retention results are registered using and intensity-based method to obtain the multi-intensity registration results. Next, a novel evaluation method called intersection mutual information is proposed to evaluate the registration accuracy of the different multi-intensity registration results. Finally, we determine the optimal registration transformation by intersection mutual information and apply it to the input image pairs to obtain the final registration results. The experimental results demonstrate the excellent performance of the proposed method, meeting the requirements of image-guided radiotherapy.