Search

Additional file 1. Appendix.

PurposeThis study proposes a method to identify plans that failed patient-specific quality assurance (QA) and attempts to establish a criterion to prescreen treatment plans for patient-specific QA measurements with independent Monte Carlo dose calculations.Materials and methodsPatient-specific QA results measured with an ArcCHECK diode array of 207 patients (head and neck: 25; thorax: 61; abdomen: 121) were retrospectively analyzed. All patients were treated with the volumetric modulated arc therapy (VMAT) technique and plans were optimized with a Pinnacle v16.2 treatment planning system using an analytical algorithm-based dose engine. Afterwards, phantom verification plans were designed and recalculated by an independent GPU-accelerated Monte Carlo (MC) dose engine, ArcherQA. Moreover, sensitivity and specificity analyzes of gamma passing rates between measurements and MC calculations were carried out to show the ability of MC to monitor failing plans (ArcCHECK 3%/3 mm,ResultsThe thresholds for 100% sensitivity to detect plans that failed patient-specific QA by independent calculation were 97.0%, 95.4%, and 91.0% for criterion 3%/3 mm, 3%/2 mm, and 2%/2 mm, respectively, which corresponded to specificities of 0.720, 0.528, and 0.585, respectively. It was shown that the 3%/3 mm criterion with 97% threshold for ArcherQA demonstrated perfect sensitivity and the highest specificity compared with other criteria, which may be suitable for prescreening treatment plans treated with the investigated machine to implement measurement-based patient-specific QA of patient plans. In addition, the area under the curve (AUC) calculated from ROC analysis for criterion 3%/3 mm, 3%/2 mm, and 2%/2 mm used by ArcherQA were 0.948, 0.924, and 0.929, respectively.ConclusionsIndependent dose calculation with the MC-based program ArcherQA has potential as a prescreen treatment for measurement-based patient-specific QA. AUC values (>0.9) showed excellent classification accuracy for monitoring failing plans with independent MC calculations.

Additional file 1. The key codes of using pytorch for optimization.

PURPOSE Radiation pneumonitis (RP) is the main source of toxicity in thoracic radiotherapy. This study proposed a deep learning-based dual-omics model, which aims to improve the RP prediction performance by integrating more data points and exploring the data in greater depth. MATERIALS AND METHODS The bimodality data were the original dose (OD) distribution and the ventilation image (VI) derived from four-dimensional computed tomography (4DCT). The functional dose (FD) distribution was obtained by weighting OD with VI. A pre-trained three-dimensional convolution (C3D) network was used to extract the features from FD, VI, and OD. The extracted features were then filtered and selected using entropy-based methods. The prediction models were constructed with four most commonly used binary classifiers. Cross-validation, bootstrap, and nested sampling methods were adopted in the process of training and hyper-tuning. RESULTS Data from 217 thoracic cancer patients treated with radiotherapy were used to train and validate the prediction model. The 4DCT-based VI showed the inhomogeneous pulmonary function of the lungs. More than half of the extracted features were singular (of none-zero value for few patients), which were eliminated to improve the stability of the model. The area under curve (AUC) of the dual-omics model was 0.874 (95% confidence interval: 0.871-0.877), and the AUC of the single-omics model was 0.780 (0.775-0.785, VI) and 0.810 (0.804-0.811, OD), respectively. CONCLUSIONS The dual-omics outperformed single-omics for RP prediction, which can be contributed to: (1) using more data points; (2) exploring the data in greater depth; and (3) incorporating of the bimodality data.

Background: Metal artifacts introduce challenges in image-guided diagnosis or accurate dose calculations. This study aims to reduce metal artifacts from the spinal brace by using virtual generated artifacts through convolutional neural networks and to compare the performance of this approach with two other methods, namely, linear interpolation metal artifact reduction (LIMAR) and normalized metal artifact reduction (NMAR) .Method: A total of 3,600-slice CT images of 60 vertebral metastases patients were selected. The spinal cord center was marked in each image, metal masks were added to two sides of the marker to generate artifact-insert CT images, and the CT values of the metal parts were copied to original CT images to obtain reference CT images. These images were divided into training (3,000 slices) and test (600) sets. The modified U-Net and pix2pix architecture was applied to understand the relationship between the reference and artifact-insert images. The mean absolute error (MAE), mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were calculated between the reference CT images and the predicted CT through LIMAR, NMAR, U-Net, and pix2pix. The CT values of organs from different images were compared. Radiotherapy treatment plans for vertebral metastases were designed, and dose calculation was performed. The dose distribution in different types of images was also compared.Results: The MAE values between the reference images and those images generated by LIMAR, NMAR, U-Net, and pix2pix were 15.02, 16.16, 6.12, and 6.48 HU, respectively, and the corresponding PSNR values were 15.37, 152.70, 158.93, and 65.14 dB, respectively. Pix2pix restored more texture than U-Net according to the visual comparison. The average CT values in the artifact-insert images of the liver, spleen, and left and right kidneys were all significantly higher than those of the reference images (pConclusions: U-Net and pix2pix deep learning networks can remarkably reduce metal artifacts and improve critical structure visualization compared with LIMAR and NMAR according to the simulation data of artifact-insert images in the spinal brace. Pix2pix can restore more texture with the help of a discriminator. Metal artifacts increase the dose calculation uncertainty in radiotherapy. The dose calculated through images obtained by U-Net and pix2pix was identical with that calculated through reference images.

Objective Preterm birth (PTB) is a significant public health problem. We aimed to explore whether alpha fetal protein (AFP) or β-human gonadotropin (β-HCG) levels during pregnancy were associated with PTB in Chinese population. Study Design The clinical data collected Nanjing Medical University Affiliated Suzhou Hospital and Wuxi Maternity and Child Health Care Hospital between January 2006 and December 2011 were analyzed retrospectively. A total of 64,999 pregnant women were registered. In addition, 13,828 pregnant women were collected serum from the second trimester. The maternal serum AFP and β-HCG were measured by enzyme immunoassay. Results In our study, the rate of PTB is 6.23%. With each unit increase of maternal AFP concentration, the adjusted odds of PTB was increased by 69.3% (odds ratio = 1.693, 95% confidence interval: 1.434–1.999, p = 0.00). We set AFP concentrations as high, medium, and low levels. When comparing with low concentration of AFP, high concentration of AFP (≥1.179 M) was positively associated with PTB with adjustment for potential confounders (p Conclusion In this study, maternal AFP concentration was associated with increased risk of PTB.

We investigated the association between 12 single nucleotide polymorphisms (SNPs) in 11 genes involved in folate metabolic and preterm birth. A subset of SNPs selected from 11 genes/loci involved in the folic acid metabolism pathway were subjected to SNaPshot analysis in a case-control study. Twelve SNPs (CBS-C699T, DHFR-c594+59del19, GST01-C428T, MTHFD-G1958A, MTHFR-C677T, MTHFR-A1298C, MTR-A2756G, MTRR-A66G, NFE2L2-ins1+C11108T, RFC1-G80A, TCN2-C776G, and TYMS-1494del6) in 503 DNA samples were simultaneously tested, and included 315 preterm births and 188 controls. None of the 12 SNP genotype distributions related to the folic acid metabolism pathway showed a significant difference between preterm and term babies. The frequency of the compound mutation genotype of MTHFD-G1958A, MTR-A2756G and RFC1-G80A in preterm babies was 7.3%, which was significantly higher than the 2.7% in term babies. Seven babies carried the compound mutation genotype of MTHFD-G1958A, MTR-A2756G, and CBS-C699T, but this was not observed in term babies. The frequency of the combined wild-type genotype of MTHFD-G1958A, MTR-A2756G, MTRR-A66G, MTHFR-A1298C, NFE2L2-ins1+C11108T, and RFC1- G80A in preterm babies was 3.17%, which was significantly lower than the 7.4% in term babies. The 12 SNPs screened in this study were not independent risk factors of preterm birth. Compound mutation genotypes, including MTHFD-G1958A, MTR-A2756G, and RFC1- G80A and MTHFD-G1958A, MTR-A2756G, and CBS-C699T, may increase the risk of preterm birth. The combined wild-type genotype MTHFD-G1958A, MTR-A2756G, MTRR-A66G, MTHFR-A1298C, NFE2L2-ins1+C11108T, and RFC1-G80A may decrease the risk of preterm birth.

An algorithm for optimizing beam orientations and beam weights for conformal radiotherapy has been developed. The algorithm models the optimization of beam orientations and beam weights as a problem of mixed integer linear programming (MILP), and optimizes the beam orientations and beam weights simultaneously. The application process of the algorithm has four steps: (a) prepare a pool of beam orientation candidates with the consideration of avoiding any patient-gantry collision and avoiding direct irradiation of organs at risk with quite low tolerances (e.g., eyes). (b) Represent each beam orientation candidate with a binary variable, and each beam weight with a continuous variable. (c) Set up an optimization problem according to dose prescriptions and the maximum allowed number of beam orientations. (d) Solve the optimization problem with a ready-to-use MILP solver. After optimization, the candidates with unity binary variables remain in the final beam configuration. The performance of the algorithm was tested with clinical cases. Compared with standard treatment plans, the beam-orientation-optimized plans had better dose distributions in terms of target coverage and avoidance of critical structures. The optimization processes took less than 1 h on a PC with a Pentium IV 2.4 GHz processor.