Recently, several efforts have been made to develop the deep learning (DL) algorithms for automatic detection and segmentation of brain metastases (BM). In this study, we developed an advanced DL model to BM detection and segmentation, especially for small-volume BM. From the institutional cancer registry, contrast-enhanced magnetic resonance images of 65 patients and 603 BM were collected to train and evaluate our DL model. Of the 65 patients, 12 patients with 58 BM were assigned to test-set for performance evaluation. Ground-truth for BM was assigned to one radiation oncologist to manually delineate BM and another one to cross-check. Unlike other previous studies, our study dealt with relatively small BM, so the area occupied by the BM in the high-resolution images were small. Our study applied training techniques such as the overlapping patch technique and 2.5-dimensional (2.5D) training to the well-known U-Net architecture to learn better in smaller BM. As a DL architecture, 2D U-Net was utilized by 2.5D training. For better efficacy and accuracy of a two-dimensional U-Net, we applied effective preprocessing include 2.5D overlapping patch technique. The sensitivity and average false positive rate were measured as detection performance, and their values were 97% and 1.25 per patient, respectively. The dice coefficient with dilation and 95% Hausdorff distance were measured as segmentation performance, and their values were 75% and 2.057 mm, respectively. Our DL model can detect and segment BM with small volume with good performance. Our model provides considerable benefit for clinicians with automatic detection and segmentation of BM for stereotactic ablative radiotherapy.

Purpose: To develop an one-click option on treatment planning system that enables for the automated breast FIF planning by combining the Eclipse Scripting application programming interfaces and user-executed programming in Windows. Methods: Scripting application programming interfaces were designed to promote automation in clinical workflow associated with radiation oncology. However, scripting cannot provide all functions that users want to perform. Thus, a new framework proposes to integrate the benefits of the scripting application and user-executed programming for the automated field-in-field technique. We adopted the Eclipse Scripting applications, which provide an interface between treatment planning system server and client and enable for running the executed program to create dose clouds and adjust the planning parameters such as multi-leaf collimator placements and monitor unit values. Importantly, all tasks are designed to perform with one-click option on treatment planning system, including the automated pushback of the proposed plan to the treatment planning system. Results: The plans produced from the proposed framework were validated against the manual field-in-field plans with 40 retrospective breast patient cases in planning efficiency and plan quality. The elapsed time for running the framework was less than 1 minute, which significantly reduced the manual multi-leaf collimator/monitor unit adjustment time. It decreased the total planning time by more than 50%, relative to the manual field-in-field planning. In dosimetric aspects, the mean and maximum dose of the heart, lung, and whole breast did not exceed 1% deviation from the manual plans in most patient cases, while maintaining the target dose coverage and homogeneity index inside the target volume. From numerical analysis, the automated plans were demonstrated to be sufficiently close to the manual plans. Conclusion: The combination of scripting applications and user-executed programming for automated breast field-in-field planning accomplished a significant enhancement in planning efficiency without degrading the plan quality, relative to the manual field-in-field procedure.

Dong Wook Kim, Kwangwoo Park, Hojin Kim, Jinsung Kim. Progress in Medical Physics 2020;31:54-62. https://doi.org/10.14316/pmp.2020.31.3.54

The feasibility of proton minibeam radiation therapy (pMBRT) using a multislit collimator (MSC) and a scattering device was evaluated for clinical use at a clinical proton therapy facility. We fabricated, through Monte Carlo (MC) simulations, not only an MSC with a high peak-to-valley dose ratio (PVDR) at the entrance of the proton beam, to prevent radiation toxicity, but also a scattering device to modulate the PVDR in depth. The slit width and center-to-center distance of the diverging MSC were 2.5 mm and 5.0 mm at the large end, respectively, and its thickness and available field size were 100 mm and 76 × 77.5 mm², respectively. Spatially fractionated dose distributions were measured at various depths using radiochromic EBT3 films and also tested on bacterial cells. MC simulation showed that the thicker the MSC, the higher the PVDR at the phantom surface. Dosimetric evaluations showed that lateral dose profiles varied according to the scatterer’s thickness, and the depths satisfying PVDR = 1.1 moved toward the surface as their thickness increased. The response of the bacterial cells to the proton minibeams’ depth was also established, in a manner similar to the dosimetric pattern. Conclusively, these results strongly suggest that pMBRT can be implemented in clinical centers by using MSC and scatterers.

Deep convolutional neural network (CNN) helped enhance image quality of cone-beam computed tomography (CBCT) by generating synthetic CT. Most of the previous works, however, trained network by intensity-based loss functions, possibly undermining to promote image feature similarity. The verifications were not sufficient to demonstrate clinical applicability, either. This work investigated the effect of variable loss functions combining feature- and intensity-driven losses in synthetic CT generation, followed by strengthening the verification of generated images in both image similarity and dosimetry accuracy. The proposed strategy highlighted the feature-driven quantification in (1) training the network by perceptual loss, besides L1 and structural similarity (SSIM) losses regarding anatomical similarity, and (2) evaluating image similarity by feature mapping ratio (FMR), besides conventional metrics. In addition, the synthetic CT images were assessed in terms of dose calculating accuracy by a commercial Monte-Carlo algorithm. The network was trained with 50 paired CBCT-CT scans acquired at the same CT simulator and treatment unit to constrain environmental factors any other than loss functions. For 10 independent cases, incorporating perceptual loss into L1 and SSIM losses outperformed the other combinations, which enhanced FMR of image similarity by 10%, and the dose calculating accuracy by 1–2% of gamma passing rate in 1%/1mm criterion.