Fang-Fang Yin

Objective. Deep learning (DL) models for fluence map prediction (FMP) have great potential to reduce treatment planning time in intensity-modulated radiation therapy (IMRT) by avoiding the lengthy inverse optimization process. This study aims to improve the rigor of input feature design in a DL-FMP model by examining how different designs of input features influence model prediction performance.Approach. This study included 231 head-and-neck intensity-modulated radiation therapy patients. Three input feature designs were investigated. The first design (D1) assumed that information of all critical structures from all beam angles should be combined to predict fluence maps. The second design (D2) assumed that local anatomical information was sufficient for predicting radiation intensity of a beamlet at a respective beam angle. The third design (D3) assumed the need for both local anatomical information and inter-beam modulation to predict radiation intensity values of the beamlets that intersect at a voxel. For each input design, we tailored the DL model accordingly. All models were trained using the same set of ground truth plans (GT plans). The plans generated by DL models (DL plans) were analyzed using key dose-volume metrics. One-way ANOVA with multiple comparisons correction (Bonferroni method) was performed (significance level = 0.05).Main results. For PTV-related metrics, all DL plans had significantly higher maximum dose (p < 0.001), conformity index (p < 0.001), and heterogeneity index (p < 0.001) compared to GT plans, with D2 being the worst performer. Meanwhile, except for cord+5 mm (p < 0.001), DL plans of all designs resulted in OAR dose metrics that are comparable to those of GT plans.Significance. Local anatomical information contains most of the information that DL models need to predict fluence maps for clinically acceptable OAR sparing. Input features from beam angles are needed to achieve the best PTV coverage. These results provide valuable insights for further improvement of DL-FMP models and DL models in general.

To ensure measurement accuracy, it is necessary to generate a comprehensive quality assurance (QA) program. “The ‘quality’ of radiation oncology can be defined as the totality of features or characteristics of the radiation oncology service that bear on its ability to satisfy the stated or implied goal of effective patient care” (Kutcher et al. 1994, p. 585). The comprehensive QA program is used to maintain and monitor the performance characteristics of the treatment system, which includes, but is not limited to, the treatment machine, imaging technology, and the planning system. If necessary, action should be taken to correct any unacceptable deviations from the baseline values acquired during acceptance testing and commissioning. Deviation from the baseline values could compromise patient treatment, resulting in suboptimal treatment response and undesirable complication effects. The quality of radiation oncology is therefore directly affected by the acceptance testing and commissioning process. The signifi-cance of the acceptance testing and commissioning process is well-acknowledged, and the corresponding procedures have been published in the literature (Nath et al. 1994; Svensson et al. 1984; Das et al. 2008).

This chapter gives an overview of how to adapt diagnostic imaging technologies on to linear accelerators for image-guided frameless stereotactic radiation therapy (SRT) when the primary focus is on target localization and verification inside the treatment room. Basic applications of in-room imaging techniques are discussed along with a description of several commercially available image-guided radiation therapy (IGRT) solutions. The remainder of the chapter is devoted to current trends in frameless SRT treatment techniques with an emphasis on the role of image-guidance.

PURPOSE: Multiparametric MRI contains rich and complementary anatomical and functional information, which is often utilized separately. This study aims to propose an adaptive multiparametric MRI (mpMRI) fusion method and examine its capability in improving tumor contrast and synthesizing novel tissue contrasts among liver cancer patients. METHODS: An adaptive mpMRI fusion method was developed with five components: image pre-processing, fusion algorithm, database, adaptation rules, and fused MRI. Linear-weighted summation algorithm was used for fusion. Weight-driven and feature-driven adaptations were designed for different applications. A clinical-friendly graphic-user-interface (GUI) was developed in Matlab and used for mpMRI fusion. Twelve liver cancer patients and a digital human phantom were included in the study. Synthesis of novel image contrast and enhancement of image signal and contrast were examined in patient cases. Tumor contrast-to-noise ratio (CNR) and liver signal-to-noise ratio (SNR) were evaluated and compared before and after mpMRI fusion. RESULTS: The fusion platform was applicable in both XCAT phantom and patient cases. Novel image contrasts, including enhancement of soft-tissue boundary, vertebral body, tumor, and composition of multiple image features in a single image were achieved. Tumor CNR improved from -1.70 ± 2.57 to 4.88 ± 2.28 (p < 0.0001) for T1-w, from 3.39 ± 1.89 to 7.87 ± 3.47 (p < 0.01) for T2-w, and from 1.42 ± 1.66 to 7.69 ± 3.54 (p < 0.001) for T2/T1-w MRI. Liver SNR improved from 2.92 ± 2.39 to 9.96 ± 8.60 (p < 0.05) for DWI. The coefficient of variation (CV) of tumor CNR lowered from 1.57, 0.56, and 1.17 to 0.47, 0.44, and 0.46 for T1-w, T2-w and T2/T1-w MRI, respectively. CONCLUSION: A multiparametric MRI fusion method was proposed and a prototype was developed. The method showed potential in improving clinically relevant features such as tumor contrast and liver signal. Synthesis of novel image contrasts including the composition of multiple image features into single image set was achieved.

PURPOSE: An intensity-modulated X-ray brachytherapy system is being developed for various clinical applications. This new system makes it possible for clinical staff to control energy as well as dose rate for different tumor sites according to their sizes and radiobiological characteristics. MATERIALS AND METHODS: This system is mainly composed of an X-ray tube, guide tube collimation, and secondary (pseudo) target. Due to its configuration, convenient modulations of fluorescent X-ray energy and intensity are possible. To observe applicability of this novel system for various primary and secondary target combinations, Monte Carlo simulation using MCNP5 was performed, and air measurements were done. As a primary and pseudo-target combination, silver-molybdenum (Ag-Mo), tungsten-neodymium (W-Nd), and tungsten-erbium (W-Er) were used for the calculation for dose profile. Specifically, a dose distribution was calculated around each of these target combinations. Dose distributions as a function of target angles were also calculated. The Ag-Mo combination was analyzed for Cartesian coordinates of xy, xz, and yz planes of the pseudo-target to observe dose distribution as a function of the angle of secondary target. RESULTS: The results showed that radial dose fall-off of Ag-Mo was greater than commercially available brachytherapy sources (103 Pd and125 I) due to its low characteristic X-ray energy. CONCLUSIONS: Dose distribution variance should be considered in beam modulation for clinical application. Dynamic movement of the pseudo-target is feasible and remains as a subject for future research.