The treatment planning process for patients with head and neck (H&N) cancer is regarded as one of the most complicated due to large target volume, multiple prescription dose levels, and many radiation-sensitive critical structures near the target. Treatment planning for this site requires a high level of human expertise and a tremendous amount of effort to produce personalized high quality plans, taking as long as a week, which deteriorates the chances of tumor control and patient survival. To solve this problem, we propose to investigate a deep learning-based dose prediction model, Hierarchically Densely Connected U-net, based on two highly popular network architectures: U-net and DenseNet. We find that this new architecture is able to accurately and efficiently predict the dose distribution, outperforming the other two models, the Standard U-net and DenseNet, in homogeneity, dose conformity, and dose coverage on the test data. Averaging across all organs at risk, our proposed model is capable of predicting the organ-at-risk max dose within 6.3% and mean dose within 5.1% of the prescription dose on the test data. The other models, the Standard U-net and DenseNet, performed worse, having an averaged organ-at-risk max dose prediction error of 8.2% and 9.3%, respectively, and averaged mean dose prediction error of 6.4% and 6.8%, respectively. In addition, our proposed model used 12 times less trainable parameters than the Standard U-net, and predicted the patient dose 4 times faster than DenseNet.reduce the vanishing gradient issue, and decrease the number of trainable parameters needed. While the term "densely connected" was historically used to described fully connected neural network layers, this publication by Huang et al. had adopted this terminology to describe how his convolutional layers were connected. While requiring more memory to use, the authors showed that the DenseNet was capable of achieving a better performance while having far less parameters in the neural network. For example, they were able to have comparable accuracy with ResNet, which had 10 million parameters, using their DenseNet, which had 0.8M parameters. This indicates that DenseNet is far more efficient in feature calculation than existing network architectures. For its contribution to the AI community, the DenseNet publication was awarded for the CVPR 2017 best publication. However, it is recognized that DenseNet, while efficient in parameter usage, actually utilizes considerably more GPU RAM, rendering a 3D U-net with fully densely connected convolutional connections infeasible for today's current GPU technologies.Motivated by a 3D densely connected U-net, but requiring less memory usage, we developed a neural network architecture that combines the essence of these two influential neural network architectures into our proposed network while maintaining a respectable RAM usage, which we call Hierarchically Densely Connected U-net (HD U-net). The term "hierarchically" is used here to describe the different levels of resolution in the U-n...

Purpose The use of neural networks to directly predict three‐dimensional dose distributions for automatic planning is becoming popular. However, the existing methods use only patient anatomy as input and assume consistent beam configuration for all patients in the training database. The purpose of this work was to develop a more general model that considers variable beam configurations in addition to patient anatomy to achieve more comprehensive automatic planning with a potentially easier clinical implementation, without the need to train specific models for different beam settings. Methods The proposed anatomy and beam (AB) model is based on our newly developed deep learning architecture, and hierarchically densely connected U‐Net (HD U‐Net), which combines U‐Net and DenseNet. The AB model contains 10 input channels: one for beam setup and the other 9 for anatomical information (PTV and organs). The beam setup information is represented by a 3D matrix of the non‐modulated beam’s eye view ray‐tracing dose distribution. We used a set of images from 129 patients with lung cancer treated with IMRT with heterogeneous beam configurations (4–9 beams of various orientations) for training/validation (100 patients) and testing (29 patients). Mean squared error was used as the loss function. We evaluated the model’s accuracy by comparing the mean dose, maximum dose, and other relevant dose–volume metrics for the predicted dose distribution against those of the clinically delivered dose distribution. Dice similarity coefficients were computed to address the spatial correspondence of the isodose volumes between the predicted and clinically delivered doses. The model was also compared with our previous work, the anatomy only (AO) model, which does not consider beam setup information and uses only 9 channels for anatomical information. Results The AB model outperformed the AO model, especially in the low and medium dose regions. In terms of dose–volume metrics, AB outperformed AO by about 1–2%. The largest improvement was found to be about 5% in lung volume receiving a dose of 5Gy or more (V5). The improvement for spinal cord maximum dose was also important, that is, 3.6% for cross‐validation and 2.6% for testing. The AB model achieved Dice scores for isodose volumes as much as 10% higher than the AO model in low and medium dose regions and about 2–5% higher in high dose regions. Conclusions The AO model, which does not use beam configuration as input, can still predict dose distributions with reasonable accuracy in high dose regions but introduces large errors in low and medium dose regions for IMRT cases with variable beam numbers and orientations. The proposed AB model outperforms the AO model substantially in low and medium dose regions, and slightly in high dose regions, by considering beam setup information through a cumulative non‐modulated beam’s eye view ray‐tracing dose distribution. This new model represents a major step forward towards predicting 3D dose distributions in real clinical practices, where beam configu...

Interleukin- (IL-) 23/IL-17 axis is a newly discovered proinflammatory signaling pathway and has been implicated in the pathogenesis of many chronic inflammatory and immune disorders. Here we investigated whether the IL-23/IL-17 axis was present and functional in the lesions of oral lichen planus (OLP), a chronic inflammatory disease affecting the oral mucosa. Using immunohistochemistry and quantitative PCR, we found that the subunits of IL-23 and IL-17 were overexpressed in OLP lesions than in normal oral mucosa tissues. In addition, the expressions of IL-23 and IL-17 are positively correlated in reticular OLP tissues. Results from in vitro studies revealed that exogenous IL-23 could increase the percentage of Th17 cells and IL-17 production in the CD4+T cells from reticular OLP patients. Furthermore, we also found that exogenous IL-17 could significantly enhance the mRNA expressions of β-defensin-2, -3, CCL-20, IL-8, and TNF-α, but not β-defensin-1, CXCL-9, -10, -11, CCL-5, and IL-6 in human oral keratinocytes. Taken together, our results revealed an overexpression pattern and selectively regulatory roles of IL-23/IL-17 axis in the OLP lesions, suggesting that it may be a pivotal regulatory pathway in the complex immune network of OLP lesions.

Treatment of (o-ethynyl)phenyl epoxides with TpRuPPh(3)(CH(3)CN)(2)PF(6) (10 mol %) in hot toluene (100 degrees C, 3-6 h) gave 2-naphthols or 1-alkylidene-2-indanones very selectively with isolated yields exceeding 72%, depending on the nature of the epoxide substituents. Surprisingly, the reaction intermediate proved to be a ruthenium-pi-ketene species that can be trapped efficiently by alcohol to give an ester compound. This phenomenon indicates a novel oxygen transfer from epoxide to its terminal alkyne catalyzed by a ruthenium complex. A plausible mechanism is proposed on the basis of reaction products and the deuterium-labeling experiment. The 2-naphthol products are thought to derive from 6-endo-dig cyclization of (o-alkenyl)phenyl ketene intermediates, whereas 1-alkylidene-2-indanones are given from the 5-endo-dig cyclization pathway.

This paper investigates the clinical significance of real‐time monitoring of intrafractional prostate motion during external beam radiotherapy using a commercial 4D localization system. Intrafractional prostate motion was tracked during 8,660 treatment fractions for 236 patients. The following statistics were analyzed: 1) the percentage of fractions in which the prostate shifted 2−7 mm for a certain duration; 2) the proportion of the entire tracking time during which the prostate shifted 2−7 mm; and 3) the proportion of each minute in which the shift exceeded 2−7 mm. The ten patients exhibiting maximum intrafractional‐motion patterns were analyzed separately. Our results showed that the percentage of fractions in which the prostate shifted by >2,3,5,and 7 mm off the baseline in any direction for >30 normals was 56.8%, 27.2%, 4.6%, and 0.7% for intact prostate and 68.7%, 35.6%, 10.1%, and 1.8% for postprostatectomy patients, respectively. For the ten patients, these percentages were 91.3%, 72.4%, 36.3%, and 6%, respectively. The percentage of tracking time during which the prostate shifted >2,3,5,and 7 mm was 27.8%, 10.7%, 1.6%, and 0.3%, respectively, and it was 56.2%, 33.7%, 11.2%, and 2.1%, respectively, for the ten patients. The percentage of tracking time for a >3 mm posterior motion was four to five times higher than that in other directions. For treatments completed in 5 min (VMAT) and 10 min (IMRT), the proportion for the prostate to shift by >3 mm was 4% and 12%, respectively. Although intrafractional prostate motion was generally small, caution should be taken for patients who exhibit frequent large intrafractional motion. For those patients, adjustment of patient positioning may be necessary or a larger treatment margin may be used. After the initial alignment, the likelihood of prostate motion increases with time. Therefore, it is favorable to use advanced techniques (e.g., VMAT) that require less delivery time in order to reduce the treatment uncertainty resulting from intrafractional prostate motion.PACS number: 87.50.S‐, 87.53.Kn, 87.55.N‐, 87.55.ne