Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer.

PURPOSE: The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer. METHODS: A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers. RESULTS: The PQM score was 40.7 ± 13.1 for manual plans and 40.8 ± 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 ± 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 ± 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 ± 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 ± 20.0 min and 97.4 ± 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200). CONCLUSIONS: The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.

Impact of 1.5†T Magnetic Field on Treatment Plan Quality in MR-Guided Radiotherapy: Typical Phantom Test Cases.

PURPOSE: This study aims to investigate the influence of the magnetic field on treatment plan quality using typical phantom test cases, which encompass a circle target test case, AAPM TG119 test cases (prostate, head-and-neck, C-shape, multi-target test cases), and a lung test case. MATERIALS AND METHODS: For the typical phantom test cases, two plans were formulated. The first plan underwent optimization in the presence of a 1.5 Tesla magnetic field (1.5 T plan). The second plan was re-optimized without a magnetic field (0 T plan), utilizing the same optimization conditions as the first plan. The two plans were compared based on various parameters, including con-formity index (CI), homogeneity index (HI), fit index (FI) and dose coverage of the planning target volume (PTV), dose delivered to organs at risk (OARs) and normal tissue (NT), monitor unit (MU). A plan-quality metric (PQM) scoring procedure was employed. For the 1.5 T plans, dose verifications were performed using an MR-compatible ArcCHECK phantom. RESULTS: A smaller dose influence of the magnetic field was found for the circle target, prostate, head-and-neck, and C-shape test cases, compared with the multi-target and lung test cases. In the multi-target test case, the significant dose influence was on the inferior PTV, followed by the superior PTV. There was a relatively large dose influence on the PTV and OARs for lung test case. No statistically significant differences in PQM and MUs were observed. For the 1.5 T plans, gamma passing rates were all higher than 95% with criteria of 2 mm/3% and 2 mm/2%. CONCLUSION: The presence of a 1.5 T magnetic field had a relatively large impact on dose parameters in the multi-target and lung test cases compared with other test cases. However, there were no significant influences on the plan-quality metric, MU and dose accuracy for all test cases.

Dose rate correction for the novel 2D diode array MapCHECK 3.

PURPOSE: To investigate the dose rate dependence of MapCHECK3 and its influence on measurement accuracy, as well as the effect of dose rate correction. MATERIALS AND METHODS: The average and instantaneous dose rate dependence of MapCHECK2 and MapCHECK3 were studied. The accuracy of measurements was investigated where the dose rate differed significantly between dose calibration of the MapCHECK and the measurement. Measurements investigated include: the central axis dose for different fields at different depths, off-axis doses outside the field, and off-axis doses along the wedge direction. Measurements using an ion chamber were taken as the reference. Exponential functions were fit to account for average and instantaneous dose rate dependence for MapCHECK3 and used for dose rate correction. The effect of the dose rate correction was studied by comparing the differences between the measurements for MapCHECK (with and without the correction) and the reference. RESULTS: The maximum dose rate dependence of MapCHECK3 is greater than 2.5%. If the dose calibration factor derived from a 10 × 10 cm2 open field at 10 cm depth was used for measurements, the average differences in central diode dose were 0.8% ± 1.0% and 1.0% ± 0.8% for the studied field sizes and measurement depths, respectively. The introduction of wedge would not only induce -1.8% ± 1.3% difference in central diode dose, but also overestimate the effective wedge angle. After the instantaneous dose rate correction, above differences can be changed to 1.9% ± 8.1%, 0.2% ± 0.1%, and 0.0% ± 0.9%. The pass rate can be improved from 98.4% to 98.8%, 98.3%-100.0%, and 96.3%-100.0%, respectively. CONCLUSION: Compared with MapCHECK2 (SunPoint1 diodes), the more pronounced dose rate dependence of MapCHECK3 (SunPoint2 diodes) should be carefully considered. To ensure highly accurate measurement, it is suggested to perform the dose calibration at the same condition where measurement will be performed. Otherwise, the dose rate correction should be applied.

Applying the six-sigma methodology to determine the limits of quality control (QC) tests for a specific linear accelerator.

PURPOSE: We aimed to show the framework of the six-sigma methodology (SSM) that can be used to determine the limits of QC tests for the linear accelerator (Linac). Limits for QC tests are individually determined using the SSM. METHODS AND MATERIALS: The SSM is based on the define-measure-analyze-improve-control (DMAIC) stages to improve the process. In the "define" stage, the limits of QC tests were determined. In the "measure" stage, a retrospective collection of daily QC data using a Machine Performance Check platform was performed from January 2020 to December 2022. In the "analyze" stage, the process of determining the limits was proposed using statistical analyses and process capability indices. In the "improve" stage, the capability index was used to calculate the action limits. The tolerance limit was established using the larger one of the control limits in the individual control chart (I-chart). In the "control" stage, daily QC data were collected prospectively from January 2023 to May 2023 to monitor the effect of action limits and tolerance limits. RESULTS: A total of 798 sets of QC data including beam, isocenter, collimation, couch, and gantry tests were collected and analyzed. The Collimation Rotation offset test had the min-Cp, min-Cpk, min-Pp, and min-Ppk at 2.53, 1.99, 1.59, and 1.25, respectively. The Couch Rtn test had the max-Cp, max-Cpk, max-Pp, and max-Ppk at 31.5, 29.9, 23.4, and 22.2, respectively. There are three QC tests with higher action limits than the original tolerance. Some data on the I-chart of the beam output change, isocenter KV offset, and jaw X1 exceeded the lower tolerance and action limit, which indicated that a system deviation occurred and reminded the physicist to take action to improve the process. CONCLUSIONS: The SSM is an excellent framework to use in determining the limits of QC tests. The process capability index is an important parameter that provides quantitative information on determining the limits of QC tests.

The sparing effect of ultra-high dose rate irradiation on the esophagus.

Background and purpose: Current studies have substantiated the sparing effect of ultra-high dose rate irradiation (FLASH) in various organs including the brain, lungs, and intestines. Whether this sparing effect extends to esophageal tissue remains unexplored. This study aims to compare the different responses of esophageal tissue in histological and protein expression levels following conventional dose rate irradiation (CONV) and FLASH irradiation to ascertain the presence of a sparing effect. Methods and materials: C57 female mice were randomly divided into three groups: control, CONV, and FLASH groups. The chest region of the mice in the radiation groups was exposed to a prescribed dose of 20 Gy using a modified electron linear accelerator. The CONV group received an average dose rate of 0.1 Gy/s, while the FLASH group received an average dose rate of 125 Gy/s. On the 10th day after irradiation, the mice were euthanized and their esophagi were collected for histopathological analysis. Subsequently, label-free proteomic quantification analysis was performed on esophageal tissue. The validation process involved analyzing transmission electron microscopy images and utilizing the parallel reaction monitoring method. Results: Histopathology results indicated a significantly lower extent of esophageal tissue damage in the FLASH group compared to the CONV group (p < 0.05). Label-free quantitative proteomic analysis revealed that the sparing effect observed in the FLASH group may be attributed to a reduction in radiation-induced protein damage associated with mitochondrial functions, including proteins involved in the tricarboxylic acid cycle and oxidative phosphorylation, as well as a decrease in acute inflammatory responses. Conclusions: Compared with CONV irradiation, a sparing effect on esophageal tissue can be observed after FLASH irradiation. This sparing effect is associated with alleviated mitochondria damage and acute inflammation.

Improvement of accumulated dose distribution in combined cervical cancer radiotherapy with deep learning-based dose prediction.

Purpose: Difficulties remain in dose optimization and evaluation of cervical cancer radiotherapy that combines external beam radiotherapy (EBRT) and brachytherapy (BT). This study estimates and improves the accumulated dose distribution of EBRT and BT with deep learning-based dose prediction. Materials and methods: A total of 30 patients treated with combined cervical cancer radiotherapy were enrolled in this study. The dose distributions of EBRT and BT plans were accumulated using commercial deformable image registration. A ResNet-101-based deep learning model was trained to predict pixel-wise dose distributions. To test the role of the predicted accumulated dose in clinic, each EBRT plan was designed using conventional method and then redesigned referencing the predicted accumulated dose distribution. Bladder and rectum dosimetric parameters and normal tissue complication probability (NTCP) values were calculated and compared between the conventional and redesigned accumulated doses. Results: The redesigned accumulated doses showed a decrease in mean values of V50, V60, and D2cc for the bladder (-3.02%, -1.71%, and -1.19 Gy, respectively) and rectum (-4.82%, -1.97%, and -4.13 Gy, respectively). The mean NTCP values for the bladder and rectum were also decreased by 0.02‰ and 0.98%, respectively. All values had statistically significant differences (p < 0.01), except for the bladder D2cc (p = 0.112). Conclusion: This study realized accumulated dose prediction for combined cervical cancer radiotherapy without knowing the BT dose. The predicted dose served as a reference for EBRT treatment planning, leading to a superior accumulated dose distribution and lower NTCP values.

A deep learning-based method for the prediction of temporal lobe injury in patients with nasopharyngeal carcinoma.

PURPOSE: To establish a deep learning-based model to predict radiotherapy-induced temporal lobe injury (TLI). MATERIALS AND METHODS: Spatial features of dose distribution within the temporal lobe were extracted using both the three-dimensional convolution (C3D) network and the dosiomics method. The Minimal Redundancy-Maximal-Relevance (mRMR) method was employed to rank the extracted features and select the most relevant ones. Four machine learning (ML) classifiers, including logistic regression (LR), k-nearest neighbors (kNN), support vector machines (SVM) and random forest (RF), were used to establish prediction models. Nested sampling and hyperparameter tuning methods were applied to train and validate the prediction models. For comparison, a prediction model base on the conventional D0.5cc of the temporal lobe obtained from dose volume (DV) histogram was established. The area under the receiver operating characteristic (ROC) curve (AUC) was utilized to compare the predictive performance of the different models. RESULTS: A total of 127 nasopharyngeal carcinoma (NPC) patients were included in the study. In the model based on C3D deep learning features, the highest AUC value of 0.843 was achieved with 5 features. For the dosiomics features model, the highest AUC value of 0.715 was attained with 1 feature. Both of these models demonstrated superior performance compared to the prediction model based on DV parameters, which yielded an AUC of 0.695. CONCLUSION: The prediction model utilizing C3D deep learning features outperformed models based on dosiomics features or traditional parameters in predicting the onset of TLI. This approach holds promise for predicting radiation-induced toxicities and guide individualized radiotherapy.

Molluscicide screening and identification of novel targets against Pomacea canaliculata.

BACKGROUND: Owing to the nonavailability of any clear targets for molluscicides against Pomacea canaliculata, target-based screening strategy cannot be employed. In this study, the molluscicidal effects of typical pesticides on P. canaliculata were evaluated to obtain the molluscicide target. A series of arylpyrrole compounds were synthesized based on the discovered target, and their structure-activity relationships explored. A preliminary strategy for screening molluscicides based on specific targets was also developed. RESULTS: A laboratory colony of P. canaliculata was developed, which showed no difference in sensitivity to niclosamide compared with the wild group, while exhibiting a higher stability against pesticide response. Mitochondrial adenosine triphosphate (ATP) synthase inhibitors and mitochondrial membrane potential uncouplers were identified and validated as potential targets for molluscicide screening against P. canaliculata. A series of arylpyrrole compounds were designed and synthesized. The median lethal concentration of 4-bromo-2-(4-chlorophenyl)-5-(trifluoromethyl)-1H-pyrrole-3-carbonitrile (Compound 102) was 10-fold lower than that of niclosamide. CONCLUSION: New molluscicide targets were discovered and validated, and preliminary strategies were explored for pesticide screening based on these targets. Compound 102 exhibited a high molluscicidal activity and had a great potential value for exploring a molluscicide to control P. canaliculata. © 2024 Society of Chemical Industry.

Synergizing the interaction of single nucleotide polymorphisms with dosiomics features to build a dual-omics model for the prediction of radiation pneumonitis.

OBJECTIVE: Radiation pneumonitis (RP) is the major dose-limiting toxicity of thoracic radiotherapy. This study aimed to developed a dual-omics (single nucleotide polymorphisms, SNP and dosiomics) prediction model for symptomatic RP. MATERIALS AND METHODS: The potential SNPs, which are of significant difference between the RP grade ≥ 3 group and the RP grade ≤ 1 group, were selected from the whole exome sequencing SNPs using the Fisher's exact test. Patients with lung cancer who received thoracic radiotherapy at our institution from 2009 to 2016 were enrolled for SNP selection and model construction. The factorization machine (FM) method was used to model the SNP epistasis effect, and to construct the RP prediction model (SNP-FM). The dosiomics features were extracted, and further selected using the minimum redundancy maximum relevance (mRMR) method. The selected dosiomics features were added to the SNP-FM model to construct the dual-omics model. RESULTS: For SNP screening, peripheral blood samples of 28 patients with RP grade ≥ 3 and the matched 28 patients with RP grade ≤ 1 were sequenced. 81 SNPs were of significant difference (P < 0.015) and considered as potential SNPs. In addition, 21 radiation toxicity related SNPs were also included. For model construction, 400 eligible patients (including 108 RP grade ≥ 2) were enrolled. Single SNP showed no strong correlation with RP. On the other hand, the SNP-SNP interaction (epistasis effect) of 19 SNPs were modeled by the FM method, and achieved an area under the curve (AUC) of 0.76 in the testing group. In addition, 4 dosiomics features were selected and added to the model, and increased the AUC to 0.81. CONCLUSIONS: A novel dual-omics model by synergizing the SNP epistasis effect with dosiomics features was developed. The enhanced the RP prediction suggested its promising clinical utility in identifying the patients with severe RP during thoracic radiotherapy.

A grayscale compression method to segment bone structures for 2D-3D registration of setup images in non-coplanar radiotherapy.

Purpose. To evaluate the performance of an automated 2D-3D bone registration algorithm incorporating a grayscale compression method for quantifying patient position errors in non-coplanar radiotherapy.Methods. An automated 2D-3D registration incorporating a grayscale compression method to segment bone structures was proposed. Portal images containing only bone structures (Portalbone) and digitally reconstructed radiographs containing only bone structures (DRRbone) were used for registration. First, the portal image was filtered by a high-pass finite impulse response (FIR) filter. Then the grayscale range of the filtered portal image was compressed. Thresholds were determined based on the difference in gray values of bone structures in the filtered and compressed portal image to obtainPortalbone.Another threshold was applied to generateDRRbonewhen the CT image uses the ray-casting algorithm to generate DRR images. The compression performance was assessed by registering theDRRbonewith thePortalboneobtained by compressing the portal image into various grayscale ranges. The proposed registration method was quantitatively and visually validated using (1) a CT image of an anthropomorphic head phantom and its portal images obtained in different poses and (2) CT images and pre-treatment portal images of 20 patients treated with non-coplanar radiotherapy.Results. Mean absolute registration errors for the best compression grayscale range test were 0.642 mm, 0.574 mm, and 0.643 mm, with calculation times of 50.6 min, 42.2 min, and 49.6 min for grayscale ranges of 0-127, 0-63 and 0-31, respectively. For the accuracy validation (1), the mean absolute registration errors for couch angles 0°, 45°, 90°, 270°, and 315° were 0.694 mm, 0.839 mm, 0.726 mm, 0.833 mm, and 0.873 mm, respectively. Among the six transformation parameters, the translation error in the vertical direction contributed the most to the registration errors. Visual inspection of the patient registration results revealed success in every instance.Conclusions. The implemented grayscale compression method successfully enhances and segments bone structures in portal images, allowing for accurate determination of patient setup errors in non-coplanar radiotherapy.

Novel multileaf collimator designs with tongues and grooves in leaf end and Monte Carlo simulations.

In this study, we proposed 2 new multileaf collimator leaf designs to eliminate leaf gaps for closed leaf pairs so that radiation leakage can be avoided. In the new designs, multi tongues and grooves were added to the conventional multileaf collimators leaf ends. Thus, when a pair of leaves closed, tongues of a leaf can enter grooves of its opposing leaf. Consequently, there would be no radiation leakage through closed leaves. One design was named finger-shaped MLC, and another design with doubled leaf end thickness was named hand-shaped MLC. Monte Carlo simulations were performed to simulate dosimetric characteristics of the new MLC designs and comparison to conventional MLCs was performed. The simulations show that for the closed field, the new designs reduce leakage dramatically. And for the open field, the finger-shaped MLC has a larger penumbra width than conventional MLC, while the penumbra for the hand-shaped MLC is comparable to that of conventional MLC. With the application of new MLC designs, it is expected to eliminate leaf gaps for MLC usage and protect normal tissues better.

Is it necessary to perform measurement-based patient-specific quality assurance for online adaptive radiotherapy with Elekta Unity MR-Linac?

This study aimed to investigate the necessity of measurement-based patient-specific quality assurance (PSQA) for online adaptive radiotherapy by analyzing measurement-based PSQA results and calculation-based 3D independent dose verification results with Elekta Unity MR-Linac. There are two workflows for Elekta Unity enabled in the treatment planning system: adapt to position (ATP) and adapt to shape (ATS). ATP plans are those which have relatively slighter shifts from reference plans by adjusting beam shapes or weights, whereas ATS plans are the new plans optimized from the beginning with probable re-contouring targets and organs-at-risk. PSQA gamma passing rates were measured using an MR-compatible ArcCHECK diode array for 78 reference plans and corresponding 208 adaptive plans (129 ATP plans and 79 ATS plans) of Elekta Unity. Subsequently, the relationships between ATP, or ATS plans and reference plans were evaluated separately. The Pearson's r correlation coefficients between ATP or ATS adaptive plans and corresponding reference plans were also characterized using regression analysis. Moreover, the Bland-Altman plot method was used to describe the agreement of PSQA results between ATP or ATS adaptive plans and reference plans. Additionally, Monte Carlo-based independent dose verification software ArcherQA was used to perform secondary dose check for adaptive plans. For ArcCHECK measurements, the average gamma passing rates (ArcCHECK vs. TPS) of PSQA (3%/2 mm criterion) were 99.51% ± 0.88% and 99.43% ± 0.54% for ATP and ATS plans, respectively, which were higher than the corresponding reference plans 99.34% ± 1.04% (p < 0.05) and 99.20% ± 0.71% (p < 0.05), respectively. The Pearson's r correlation coefficients were 0.720 between ATP and reference plans and 0.300 between ATS and reference plans with ArcCHECK, respectively. Furthermore, >95% of data points of differences between both ATP and ATS plans and reference plans were within ±2σ (standard deviation) of the mean difference between adaptive and reference plans with ArcCHECK measurements. With ArcherQA calculation, the average gamma passing rates (ArcherQA vs. TPS) were 98.23% ± 1.64% and 98.15% ± 1.07% for ATP and ATS adaptive plans, separately. It might be unnecessary to perform measurement-based PSQA for both ATP and ATS adaptive plans for Unity if the gamma passing rates of both measurements of corresponding reference plans and independent dose verification of adaptive plans have high gamma passing rates. Periodic machine QA and verification of adaptive plans were recommended to ensure treatment safety.

A novel loss function to reproduce texture features for deep learning-based MRI-to-CT synthesis.

BACKGROUND: Studies on computed tomography (CT) synthesis based on magnetic resonance imaging (MRI) have mainly focused on pixel-wise consistency, but the texture features of regions of interest (ROIs) have not received appropriate attention. PURPOSE: This study aimed to propose a novel loss function to reproduce texture features of ROIs and pixel-wise consistency for deep learning-based MRI-to-CT synthesis. The method was expected to assist the multi-modality studies for radiomics. METHODS: The study retrospectively enrolled 127 patients with nasopharyngeal carcinoma. CT and MRI images were collected for each patient, and then rigidly registered as pre-procession. We proposed a gray-level co-occurrence matrix (GLCM)-based loss function to improve the reproducibility of texture features. This novel loss function could be embedded into the present deep learning-based framework for image synthesis. In this study, a typical image synthesis model was selected as the baseline, which contained a Unet trained mean square error (MSE) loss function. We embedded the proposed loss function and designed experiments to supervise different ROIs to prove its effectiveness. The concordance correlation coefficient (CCC) of the GLCM feature was employed to evaluate the reproducibility of GLCM features, which are typical texture features. Besides, we used a publicly available dataset of brain tumors to verify our loss function. RESULTS: Compared with the baseline, the proposed method improved the pixel-wise image quality metrics (MAE: 107.5 to 106.8 HU; SSIM: 0.9728 to 0.9730). CCC values of the GLCM features in GTVnx were significantly improved from 0.78 ± 0.12 to 0.82 ± 0.11 (p < 0.05 for paired t-test). Generally, > 90% (22/24) of the GLCM-based features were improved compared with the baseline, where the Informational Measure of Correlation feature was improved the most (CCC: 0.74 to 0.83). For the public dataset, the loss function also shows its effectiveness. With our proposed loss function added, the ability to reproduce texture features was improved in the ROIs. CONCLUSIONS: The proposed method reproduced texture features for MRI-to-CT synthesis, which would benefit radiomics studies based on image multi-modality synthesis.

Pretreatment information-aided automatic segmentation for online magnetic resonance imaging-guided prostate radiotherapy.

BACKGROUND: It is necessary to contour regions of interest (ROIs) for online magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART). These updated contours are used for online replanning to obtain maximum dosimetric benefits. Contouring can be accomplished using deformable image registration (DIR) and deep learning (DL)-based autosegmentation methods. However, these methods may require considerable manual editing and thus prolong treatment time. PURPOSE: The present study aimed to improve autosegmentation performance by integrating patients' pretreatment information in a DL-based segmentation algorithm. It is expected to improve the efficiency of current MRIgART process. METHODS: Forty patients with prostate cancer were enrolled retrospectively. The online adaptive MR images, patient-specific planning computed tomography (CT), and contours in CT were used for segmentation. The deformable registration of planning CT and MR images was performed first to obtain a deformable CT and corresponding contours. A novel DL network, which can integrate such patient-specific information (deformable CT and corresponding contours) into the segmentation task of MR images was designed. We performed a four-fold cross-validation for the DL models. The proposed method was compared with DIR and DL methods on segmentation of prostate cancer. The ROIs included the clinical target volume (CTV), bladder, rectum, left femur head, and right femur head. Dosimetric parameters of automatically generated ROIs were evaluated using a clinical treatment planning system. RESULTS: The proposed method enhanced the segmentation accuracy of conventional procedures. Its mean value of the dice similarity coefficient (93.5%) over the five ROIs was higher than both DIR (87.5%) and DL (87.2%). The number of patients (n = 40) that required major editing using DIR, DL, and our method were 12, 18, and 7 (CTV); 17, 4, and 1 (bladder); 8, 11, and 5 (rectum); 2, 4, and 1 (left femur head); and 3, 7, and 1 (right femur head), respectively. The Spearman rank correlation coefficient of dosimetry parameters between the proposed method and ground truth was 0.972 ± 0.040, higher than that of DIR (0.897 ± 0.098) and DL (0.871 ± 0.134). CONCLUSION: This study proposed a novel method that integrates patient-specific pretreatment information into DL-based segmentation algorithm. It outperformed baseline methods, thereby improving the efficiency and segmentation accuracy in adaptive radiotherapy.

Determination of internal target volume with Cine-MRI sequence for prostate MRI-Guided radiotherapy.

BACKGROUND: In prostate radiotherapy, the intrafractional target motion negatively affects treatment accuracy. Generating internal target volume (ITV) using four-dimensional (4D) images may resolve the issue of intrafractional target motion induced by bladder filling and bowel movement. However, no 4D imaging techniques suitable for the prostate are currently available in clinical practice. PURPOSE: This study aimed to determine the ITV based on cine magnetic resonance imaging (MRI) sequence for intrafractional target motion management in prostate MRI-guided radiotherapy. MATERIALS AND METHODS: A reference ITV was generated in simulation process. Then, the reference ITV was adapted with cine MRI sequence before online planning in each fraction. Finally, the reference ITV was updated with the cine MRI sequence acquired during beam delivery after each fraction. Cine MRI sequences and positioning three-dimensional (3D) MRI from 35 patients were retrospectively collected. Clinical target volume (CTV) coverage was computed according to the two-dimensional contour of CTV and ITV on cine MRI images. Relative target size was calculated as the ratio of the volume of ITV and CTV. Isotropic planning target volume (PTV; 5 mm margin) and anisotropic PTV (3 mm margin in the posterior direction and 5 mm margin in other directions) were generated for comparison. RESULTS: The CTV coverage rate of the proposed ITV had a mean value of 98.61% ± 0.51%, whereas the CTV coverage rates of the isotropic and anisotropic PTVs were 97.43% ± 0.41% and 96.58% ± 0.73%, respectively. The proposed ITV had a relative target size of 1.79 ± 0.17, whereas the anisotropic and isotropic PTVs had relative target sizes of 1.92 ± 0.12 and 2.21 ± 0.19, respectively. For both the CTV coverage rate and target relative size, significant differences were observed between the proposed ITV and the other two PTVs (p < 0.05). CONCLUSION: The ITV achieved higher CTV coverage with smaller size than conventional isotropic and anisotropic PTVs, indicating that it can effectively deal with the intrafractional movement of the prostate.

Comprehensive evaluation of similarity between synthetic and real CT images for nasopharyngeal carcinoma.

BACKGROUND: Although magnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis studies based on deep learning have significantly progressed, the similarity between synthetic CT (sCT) and real CT (rCT) has only been evaluated in image quality metrics (IQMs). To evaluate the similarity between synthetic CT (sCT) and real CT (rCT) comprehensively, we comprehensively evaluated IQMs and radiomic features for the first time. METHODS: This study enrolled 127 patients with nasopharyngeal carcinoma who underwent CT and MRI scans. Supervised-learning (Unet) and unsupervised-learning (CycleGAN) methods were applied to build MRI-to-CT synthesis models. The regions of interest (ROIs) included nasopharynx gross tumor volume (GTVnx), brainstem, parotid glands, and temporal lobes. The peak signal-to-noise ratio (PSNR), mean absolute error (MAE), root mean square error (RMSE), and structural similarity (SSIM) were used to evaluate image quality. Additionally, 837 radiomic features were extracted for each ROI, and the correlation was evaluated using the concordance correlation coefficient (CCC). RESULTS: The MAE, RMSE, SSIM, and PSNR of the body were 91.99, 187.12, 0.97, and 51.15 for Unet and 108.30, 211.63, 0.96, and 49.84 for CycleGAN. For the metrics, Unet was superior to CycleGAN (P < 0.05). For the radiomic features, the percentage of four levels (i.e., excellent, good, moderate, and poor, respectively) were as follows: GTVnx, 8.5%, 14.6%, 26.5%, and 50.4% for Unet and 12.3%, 25%, 38.4%, and 24.4% for CycleGAN; other ROIs, 5.44% ± 3.27%, 5.56% ± 2.92%, 21.38% ± 6.91%, and 67.58% ± 8.96% for Unet and 5.16% ± 1.69%, 3.5% ± 1.52%, 12.68% ± 7.51%, and 78.62% ± 8.57% for CycleGAN. CONCLUSIONS: Unet-sCT was superior to CycleGAN-sCT for the IQMs. However, neither exhibited absolute superiority in radiomic features, and both were far less similar to rCT. Therefore, further work is required to improve the radiomic similarity for MRI-to-CT synthesis. TRIAL REGISTRATION: This study was a retrospective study, so it was free from registration.

A generalized fit index for evaluating treatment plans of multiple target volumes with different prescribed dose: Generalized dose distribution fit index.

BACKGROUND AND PURPOSE: The differential fit index (dFI) and cumulative fit index (cFI) were defined in our previous study to evaluate the fit of isodose surfaces to the target volume. They were only applicable to plans for a single target volume. Therefore, this study aimed to generalize these indices for evaluating plans for multiple target volumes and different prescribed doses. MATERIALS AND METHODS: dFI was redefined as the ratio of the integral dose of the volume occupied by an isodose surface to that of the union of all target volumes. cFI was defined as the integral of dFI from a certain dose level of interest to the prescribed dose to be evaluated. To evaluate the performance of the generalized fit index, brain metastasis, head and neck, lung cancer, liver cancer, and cervical cancer cases were selected. For each case, a pair of plans was designed, with one plan having a better fitting dose distribution. The dose fit of these plans was investigated using cFI, the dose gradient index (GI), and the conformity index (CI). RESULTS: In total, 26 pairs of evaluations were performed. The correct evaluation rates for cFI, GI, and CI were 96%, 26.92%, and 92.31%, respectively, illustrating that GI was not valid for evaluating complex plans. CONCLUSIONS: The generalized fit index proved effective for evaluating the dose fit of plans for multiple target volumes with different prescribed doses.

Machine Log File and Calibration Errors-based Patient-specific Quality Assurance (QA) for Volumetric Modulated Arc Therapy (VMAT).

INTRODUCTION: Dose reconstructed based on linear accelerator (linac) log-files is one of the widely used solutions to perform patient-specific quality assurance (QA). However, it has a drawback that the accuracy of log-file is highly dependent on the linac calibration. The objective of the current study is to represent a new practical approach for a patient-specific QA during Volumetric modulated arc therapy (VMAT) using both log-file and calibration errors of linac. METHODS: A total of six cases, including two head and neck neoplasms, two lung cancers, and two rectal carcinomas, were selected. The VMAT-based delivery was optimized by the TPS of Pinnacle^3 subsequently, using Elekta Synergy VMAT linac (Elekta Oncology Systems, Crawley, UK), which was equipped with 80 Multi-leaf collimators (MLCs) and the energy of the ray selected at 6 MV. Clinical mode log-file of this linac was used in this study. A series of test fields validate the accuracy of log-file. Then, six plans of test cases were delivered and log-file of each was obtained. The log-file errors were added to the corresponding plans through the house script and the first reconstructed plan was obtained. Later, a series of tests were performed to evaluate the major calibration errors of the linac (dose-rate, gantry angle, MLC leaf position) and the errors were added to the first reconstruction plan to generate the second reconstruction plan. At last, all plans were imported to Pinnacle and recalculated dose distribution on patient CT and ArcCheck phantom (SUN Nuclear). For the former, both target and OAR dose differences between them were compared. For the latter, γ was evaluated by ArcCheck, and subsequently, the surface dose differences between them were performed. RESULTS: Accuracy of log-file was validated. If error recordings in the log file were only considered, there were four arcs whose proportion of control points with gantry angle errors more than ± 1°larger than 35%. Errors of leaves within ± 0.5 mm were 95% for all arcs. The distinctness of a single control point MU was bigger, but the distinctness of cumulative MU was smaller. The maximum, minimum, and mean doses for all targets were distributed between -6.79E-02-0.42%, -0.38-0.4%, 2.69E-02-8.54E-02% respectively, whereas for all OAR, the maximum and mean dose were distributed between -1.16-2.51%, -1.21-3.12% respectively. For the second reconstructed dose: the maximum, minimum, and mean dose for all targets was distributed between 0.0995~5.7145%, 0.6892~4.4727%, 0.5829~1.8931% separately. Due to OAR, maximum and mean dose distribution was observed between -3.1462~6.8920%, -6.9899~1.9316%, respectively. CONCLUSION: Patient-specific QA based on the log-file could reflect the accuracy of the linac execution plan, which usually has a small influence on dose delivery. When the linac calibration errors were considered, the reconstructed dose was closer to the actual delivery and the developed method was accurate and practical.

Prior information guided auto-segmentation of clinical target volume of tumor bed in postoperative breast cancer radiotherapy.

BACKGROUND: Accurate delineation of clinical target volume of tumor bed (CTV-TB) is important but it is also challenging due to surgical effects and soft tissue contrast. Recently a few auto-segmentation methods were developed to improve the process. However, those methods had comparatively low segmentation accuracy. In this study the prior information was introduced to aid auto-segmentation of CTV-TB based on a deep-learning model. METHODS: To aid the delineation of CTV-TB, the tumor contour on preoperative CT was transformed onto postoperative CT via deformable image registration. Both original and transformed tumor contours were used for prior information in training an auto-segmentation model. Then, the CTV-TB contour on postoperative CT was predicted by the model. 110 pairs of preoperative and postoperative CT images were used with a 5-fold cross-validation strategy. The predicted contour was compared with the clinically approved contour for accuracy evaluation using dice similarity coefficient (DSC) and Hausdorff distance. RESULTS: The average DSC of the deep-learning model with prior information was improved than the one without prior information (0.808 vs. 0.734, P < 0.05). The average DSC of the deep-learning model with prior information was higher than that of the traditional method (0.808 vs. 0.622, P < 0.05). CONCLUSIONS: The introduction of prior information in deep-learning model can improve segmentation accuracy of CTV-TB. The proposed method provided an effective way to automatically delineate CTV-TB in postoperative breast cancer radiotherapy.