Quantitative assessment of breast volume changes after whole-breast irradiation for breast cancer using breast auto-segmentation.

PURPOSE: This study aimed to quantitatively estimate the changes in breast volume associated with radiotherapy in patients undergoing breast-conserving surgery and whole-breast irradiation (WBI). METHODS: Pre-WBI simulation computed tomography (CT) scans and post-WBI follow-up chest CT scans from a total of 1,151 breast cancer patients were analyzed using a deep-learning-driven auto-segmentation approach. The CT-based asymmetry index (CTAI) was calculated by dividing the volume of the irradiated breast by the volume of the contralateral breast. Significant breast shrinkage was defined as a CTAI < 0.85. To quantify changes in CTAI over the follow-up period, the CTAI ratio was determined as the post-WBI CTAI divided by the pre-WBI CTAI. A multivariate logistic regression analysis was conducted to identify potential variables associated with post-WBI significant breast shrinkage. RESULTS: The median CTAI values for pre- and post-WBI CT scans were 0.973 (interquartile range: 0.887-1.069) and 0.866 (interquartile range: 0.773-0.967), respectively. The difference between them was statistically significant (p < 0.001). Following WBI, there was an increase in the rate of significant breast shrinkage from 16.3 to 44.8%. The CTAI ratio showed a negative association with the time interval (p < 0.001, Pearson r = - 0.310). In the multivariate logistic regression analysis, lower pre-WBI CTAI, younger age, and longer interval between CT scans were found to be significantly associated with a higher occurrence of post-WBI significant breast shrinkage. CONCLUSION: Breast volume decreases following WBI, and this decrease is correlated with an increased duration after WBI. These findings highlight the long-term consequences of WBI on breast asymmetry.

Evaluation of the dosimetric effect of scattered protons in clinical practice in passive scattering proton therapy.

The present study verified and evaluated the dosimetric effects of protons scattered from a snout and an aperture in clinical practice, when a range compensator was included. The dose distribution calculated by a treatment planning system (TPS) was compared with the measured dose distribution and the dose distribution calculated by Monte Carlo simulation at several depths. The difference between the measured and calculated results was analyzed using Monte Carlo simulation with filtration of scattering in the snout and aperture. The dependence of the effects of scattered protons on snout size, beam range, and minimum thickness of the range compensator was also investigated using the Monte Carlo simulation. The simulated and measured results showed that the additional dose compared with the results calculated by the TPS at shallow depths was mainly due to protons scattered by the snout and aperture. This additional dose was filtered by the structure of the range compensator so that it was observed under the thin region of the range compensator. The maximum difference was measured at a depth of 16 mm (8.25%), with the difference decreasing with depth. Analysis of protons contributing to the additional dose showed that the contribution of protons scattered from the snout was greater than that of protons scattered from the aperture when a narrow snout was used. In the Monte Carlo simulation, this effect of scattered protons was reduced when wider snouts and longer-range proton beams were used. This effect was also reduced when thicker range compensator bases were used, even with a narrow snout. This study verified the effect of scattered protons even when a range compensator was included and emphasized the importance of snout-scattered protons when a narrow snout is used for small fields. It indicated that this additional dose can be reduced by wider snouts, longer range proton beams, and thicker range compensator bases. These results provide a better understanding of the additional dose from scattered protons in clinical practice.

Facial expression monitoring system for predicting patient's sudden movement during radiotherapy using deep learning.

PURPOSE: Imaging, breath-holding/gating, and fixation devices have been developed to minimize setup errors so that the prescribed dose can be exactly delivered to the target volume in radiotherapy. Despite these efforts, additional patient monitoring devices have been installed in the treatment room to view patients' whole-body movement. We developed a facial expression recognition system using deep learning with a convolutional neural network (CNN) to predict patients' advanced movement, enhancing the stability of the radiation treatment by giving warning signs to radiation therapists. MATERIALS AND METHODS: Convolutional neural network model and extended Cohn-Kanade datasets with 447 facial expressions of source images for training were used. Additionally, a user interface that can be used in the treatment control room was developed to monitor real-time patient's facial expression in the treatment room, and the entire system was constructed by installing a camera in the treatment room. To predict the possibility of patients' sudden movement, we categorized facial expressions into two groups: (a) uncomfortable expressions and (b) comfortable expressions. We assumed that the warning sign about the sudden movement was given when the uncomfortable expression was recognized. RESULTS: We have constructed the facial expression monitoring system, and the training and test accuracy were 100% and 85.6%, respectively. In 10 patients, their emotions were recognized based on their comfortable and uncomfortable expressions with 100% detection rate. The detected various emotions were represented by a heatmap and motion prediction accuracy was analyzed for each patient. CONCLUSION: We developed a system that monitors the patient's facial expressions and predicts patient's advanced movement during the treatment. It was confirmed that our patient monitoring system can be complementarily used with the existing monitoring system. This system will help in maintaining the initial setup and improving the accuracy of radiotherapy for the patients using deep learning in radiotherapy.

Does enhanced environmental cleaning reduce carbapenem-resistant Acinetobacter baumannii colonization in the intensive care unit?

OBJECTIVE: To evaluate the impact of enhanced environmental cleaning (two times per day) compared with conventional cleaning on the acquisition of carbapenem-resistant Acinetobacter baumannii (CRAB) in a highly endemic intensive care unit (ICU). METHODS: The intervention consisted of alternating environmental cleaning and conventional cleaning every 3 months during the study period from July 2018 to June 2019. CRAB acquisition was assessed using incidence and prevalence rates, and colonization pressure. RESULTS: The incidence rates of CRAB with and without enhanced cleaning were 16.3 and 13.9 cases per 1000 population, respectively; and the prevalence rates were 66.9 and 61.7 cases per 1000 population, respectively. Colonization pressure was 53.3% with enhanced cleaning and 51.3% without enhanced cleaning. No association was found between enhanced environmental cleaning and the incidence (P=0.156), prevalence (P=0.888) and colonization pressure (P=0.825) of CRAB acquisition. The ventilator utilization ratio increased the colonization pressure of CRAB acquisition (P=0.010, ß coefficient=0.37). The proportion of new nurses with <3 years of clinical practice experience was positively correlated with the incidence and prevalence of CRAB acquisition. CONCLUSION: Enhanced environmental cleaning alone failed to reduce CRAB acquisition in a highly endemic ICU. The ventilator utilization ratio may be of more importance than environmental cleaning. Inexperienced nurses may need to be monitored regarding infection control activities in addition to hand hygiene adherence.

Deep learning method for prediction of patient-specific dose distribution in breast cancer.

BACKGROUND: Patient-specific dose prediction improves the efficiency and quality of radiation treatment planning and reduces the time required to find the optimal plan. In this study, a patient-specific dose prediction model was developed for a left-sided breast clinical case using deep learning, and its performance was compared with that of conventional knowledge-based planning using RapidPlan™. METHODS: Patient-specific dose prediction was performed using a contour image of the planning target volume (PTV) and organs at risk (OARs) with a U-net-based modified dose prediction neural network. A database of 50 volumetric modulated arc therapy (VMAT) plans for left-sided breast cancer patients was utilized to produce training and validation datasets. The dose prediction deep neural network (DpNet) feature weights of the previously learned convolution layers were applied to the test on a cohort of 10 test sets. With the same patient data set, dose prediction was performed for the 10 test sets after training in RapidPlan. The 3D dose distribution, absolute dose difference error, dose-volume histogram, 2D gamma index, and iso-dose dice similarity coefficient were used for quantitative evaluation of the dose prediction. RESULTS: The mean absolute error (MAE) and one standard deviation (SD) between the clinical and deep learning dose prediction models were 0.02 ± 0.04%, 0.01 ± 0.83%, 0.16 ± 0.82%, 0.52 ± 0.97, - 0.88 ± 1.83%, - 1.16 ± 2.58%, and - 0.97 ± 1.73% for D95%, Dmean in the PTV, and the OARs of the body, left breast, heart, left lung, and right lung, respectively, and those measured between the clinical and RapidPlan dose prediction models were 0.02 ± 0.14%, 0.87 ± 0.63%, - 0.29 ± 0.98%, 1.30 ± 0.86%, - 0.32 ± 1.10%, 0.12 ± 2.13%, and - 1.74 ± 1.79, respectively. CONCLUSIONS: In this study, a deep learning method for dose prediction was developed and was demonstrated to accurately predict patient-specific doses for left-sided breast cancer. Using the deep learning framework, the efficiency and accuracy of the dose prediction were compared to those of RapidPlan. The doses predicted by deep learning were superior to the results of the RapidPlan-generated VMAT plan.

Beam Angle Optimization for Double-Scattering Proton Delivery Technique Using an Eclipse Application Programming Interface and Convolutional Neural Network.

To automatically identify optimal beam angles for proton therapy configured with the double-scattering delivery technique, a beam angle optimization method based on a convolutional neural network (BAODS-Net) is proposed. Fifty liver plans were used for training in BAODS-Net. To generate a sequence of input data, 25 rays on the eye view of the beam were determined per angle. Each ray collects nine features, including the normalized Hounsfield unit and the position information of eight structures per 2° of gantry angle. The outputs are a set of beam angle ranking scores (S beam) ranging from 0° to 359°, with a step size of 1°. Based on these input and output designs, BAODS-Net consists of eight convolution layers and four fully connected layers. To evaluate the plan qualities of deep-learning, equi-spaced, and clinical plans, we compared the performances of three types of loss functions and performed K-fold cross-validation (K = 5). For statistical analysis, the volumes V27Gy and V30Gy as well as the mean, minimum, and maximum doses were calculated for organs-at-risk by using a paired-samples t-test. As a result, smooth-L1 loss showed the best optimization performance. At the end of the training procedure, the mean squared errors between the reference and predicted S beam were 0.031, 0.011, and 0.004 for L1, L2, and smooth-L1 loss, respectively. In terms of the plan quality, statistically, PlanBAO has no significant difference from PlanClinic (P >.05). In our test, a deep-learning based beam angle optimization method for proton double-scattering treatments was developed and verified. Using Eclipse API and BAODS-Net, a plan with clinically acceptable quality was created within 5 min.

Targeting DNA-dependent protein kinase sensitizes hepatocellular carcinoma cells to proton beam irradiation through apoptosis induction.

Recent studies have highlighted the implications of genetic variations in the relative biological effectiveness (RBE) of proton beam irradiation over conventional X-ray irradiation. Proton beam radiotherapy is a reasonable radiotherapy option for hepatocellular carcinoma (HCC), but the impact of genetic difference on the HCC RBE remains unknown. Here, we determined proton RBE in human HCC cells by exposing them to various doses of either 6-MV X-rays or 230-MeV proton beams. Clonogenic survival assay revealed variable radiosensitivity of human HCC cell lines with survival fraction at 2 Gy ranging from 0.38 to 0.83 and variable proton RBEs with 37% survival fraction ranging from 1.00 to 1.48. HCC cells appeared more sensitive to proton irradiation than X-rays, with more persistent activation of DNA damage repair proteins over time. Depletion of a DNA damage repair gene, DNA-PKcs, by siRNA dramatically increased the sensitivity of HCC cells to proton beams with a decrease in colony survival and an increase in apoptosis. Our findings suggest that there are large variations in proton RBE in HCC cells despite the use of a constant RBE of 1.1 in the clinic and targeting DNA-PKcs in combination with proton beam therapy may be a promising regimen for treating HCC.

Radiation hardness of cadmium telluride solar cells in proton therapy beam mode.

We evaluated the durability of cadmium telluride (CdTe) solar cells upon proton beam irradiation as well as the possibility of achieving a dosimeter usable in proton beam therapy by applying 100 MeV of pencil beam scanning (PBS) irradiation. Specifically, a 100 MeV proton PBS beam was applied at irradiation doses of 0, 1012, 1013, 1014, and 1015 cm-2. According to the results, the remaining factors (defined as the ratio of the degraded value to the initial value) of open-circuit voltage (Voc), short-circuit current (Jsc), fill-factor (FF), and efficiency (ƞ) which are solar cell performance parameters, were approximately 89%, 44%, 69%, and 30%, respectively, compared to those of the reference cell (without irradiation) at the highest dose of 1×1015 cm-2. In particular, the conversion efficiency, which is the main factor, was approximately 70% of that of the reference cell even at a high fluence of 1×1014 cm-2. In addition, we observed the projected range of the hydrogen atoms based on the PBS beam energy using the Tool for Particle Simulation software and assessed the amount of fluence accumulated in a CdTe cell. As the energy increased, the fluence accumulated inside the cell tended to decrease owing to the characteristics of the Bragg peak of the proton. Thus, the radiation damage to the cell induced by the proton beam was reduced. The results of this study are expected to provide valuable reference information for research on dosimetry sensors composed of thin-film solar cells, serving as the basis for future application in proton beam therapy with CdTe solar cells.

Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer.

BACKGROUND: Accurate and standardized descriptions of organs at risk (OARs) are essential in radiation therapy for treatment planning and evaluation. Traditionally, physicians have contoured patient images manually, which, is time-consuming and subject to inter-observer variability. This study aims to a) investigate whether customized, deep-learning-based auto-segmentation could overcome the limitations of manual contouring and b) compare its performance against a typical, atlas-based auto-segmentation method organ structures in liver cancer. METHODS: On-contrast computer tomography image sets of 70 liver cancer patients were used, and four OARs (heart, liver, kidney, and stomach) were manually delineated by three experienced physicians as reference structures. Atlas and deep learning auto-segmentations were respectively performed with MIM Maestro 6.5 (MIM Software Inc., Cleveland, OH) and, with a deep convolution neural network (DCNN). The Hausdorff distance (HD) and, dice similarity coefficient (DSC), volume overlap error (VOE), and relative volume difference (RVD) were used to quantitatively evaluate the four different methods in the case of the reference set of the four OAR structures. RESULTS: The atlas-based method yielded the following average DSC and standard deviation values (SD) for the heart, liver, right kidney, left kidney, and stomach: 0.92 ± 0.04 (DSC ± SD), 0.93 ± 0.02, 0.86 ± 0.07, 0.85 ± 0.11, and 0.60 ± 0.13 respectively. The deep-learning-based method yielded corresponding values for the OARs of 0.94 ± 0.01, 0.93 ± 0.01, 0.88 ± 0.03, 0.86 ± 0.03, and 0.73 ± 0.09. The segmentation results show that the deep learning framework is superior to the atlas-based framwork except in the case of the liver. Specifically, in the case of the stomach, the DSC, VOE, and RVD showed a maximum difference of 21.67, 25.11, 28.80% respectively. CONCLUSIONS: In this study, we demonstrated that a deep learning framework could be used more effectively and efficiently compared to atlas-based auto-segmentation for most OARs in human liver cancer. Extended use of the deep-learning-based framework is anticipated for auto-segmentations of other body sites.

Feasibility study of Fe3O4/TaO x nanoparticles as a radiosensitizer for proton therapy.

We investigated the feasibility of using multifunctional Fe3O4/TaO x (core/shell) nanoparticles, developed for use in contrast agents for computed tomography (CT) and magnetic resonance imaging (MRI), as dose-enhancing radiosensitizers. First, to verify the detectability of Fe3O4/TaO x nanoparticles in imaging, in vivo tests were conducted. Approximately 600 mg kg-1 of 19 nm-diameter Fe3O4/TaO x nanoparticles dispersed in phosphate-buffered saline was injected into the tail vein of six Balb/c mice used as tumour (4T1 mammary carcinoma cell) models. Three mice underwent MRI (BioSpec 70/20 USR, Bruker, Billerica, MA, USA) and micro-CT (Inveon, Siemens Preclinical, Knoxville, TN, USA) before and after the injection. The difference between the pre- and post-injection images was quantified by finding the correlation coefficient. The aorta, blood vessel, and liver were clearly seen in the MRI and micro-CT images 60 min after intravenous injection of Fe3O4/TaO x nanoparticles, but the tumour region was not visible in the CT images until after 24 h. There were large differences between the pre- and post-injection images. Second, the therapeutic enhancement dose of nanomaterials was computed via Monte Carlo simulation. Monoenergetic 70- and 150 MeV proton beams irradiated x-ray contrast agent (iodine, BaSO4), MRI contrast agent (gadolinium, Fe3O4), Au, Fe3O4/TaO x (core/shell) nanoparticles and water located at the centre of a 4 × 4 × 4 µm3 water phantom, upon which the dose enhancement ratio (DER) (dose with/without nanoparticles) was computed. When 70 MeV protons irradiated the Au, gadolinium, Fe3O4/TaO x , Fe3O4, iodine, and BaSO4 nanoparticles, the DERs at 1 nm were 15.76, 7.68, 7.82, 6.17, 4.85, and 5.51, respectively. Fe3O4/TaO x nanoparticles have the potential to be used as a multifunctional agent that enhances tumour detection and increases the dose. Dose enhancement with Fe3O4/TaO x was half that with Au. However, Fe3O4/TaO x is much cheaper than Au, and it is expected that tumour targeting combined with magnetic field could overcome the low DER.

Study on dependence of dose enhancement on cluster morphology of gold nanoparticles in radiation therapy using a body-centred cubic model.

Gold nanoparticles (GNPs) injected in a body for dose enhancement in radiation therapy are known to form clusters. We investigated the dependence of dose enhancement on the GNP morphology using Monte-Carlo simulations and compared the model predictions with experimental data. The cluster morphology was approximated as a body-centred cubic (BCC) structure by placing GNPs at the 8 corners and the centre of a cube with an edge length of 0.22-1.03 µm in a 4 × 4 × 4 µm3 water-filled phantom. We computed the dose enhancement ratio (DER) for 50 and 260 kVp photons as a function of the distance from the cube centre for 12 different cube sizes. A 10 nm-wide concentric shell shaped detector was placed up to 100 nm away from a GNP at the cube centre. For model validation, simulations based on BCC and nanoparticle random distribution (NRD) models were performed using parameters that corresponded to the experimental conditions, which measured increases in the relative biological effect due to GNPs. We employed the linear quadratic model to compute cell surviving fraction (SF) and sensitizer enhancement ratio (SER). The DER is inversely proportional to the distance to the GNPs. The largest DERs were 1.97 and 1.80 for 50 kVp and 260 kVp photons, respectively. The SF predicted by the BCC model agreed with the experimental value within 10%, up to a 5 Gy dose, while the NRD model showed a deviation larger than 10%. The SERs were 1.21 ± 0.13, 1.16 ± 0.11, and 1.08 ± 0.11 according to the experiment, BCC, and NRD models, respectively. We most accurately predicted the GNP radiosensitization effect using the BCC approximation and suggest that the BCC model is effective for use in nanoparticle dosimetry.

Preclinical investigation for developing injectable fiducial markers using a mixture of BaSO4 and biodegradable polymer for proton therapy.

PURPOSE: The aim of this study is to investigate the use of mixture of BaSO4 and biodegradable polymer as an injectable nonmetallic fiducial marker to reduce artifacts in x-ray images, decrease the absorbed dose distortion in proton therapy, and replace permanent metal markers. METHODS: Two samples were made with 90 wt. % polymer phosphate buffer saline (PBS) and 10 wt. % BaSO4 (B1) or 20 wt. % BaSO4 (B2). Two animal models (mice and rats) were used. To test the injectability and in vivo gelation, a volume of 200 µl at a pH 5.8 were injected into the Sprague-Dawley rats. After sacrificing the rats over time, the authors checked the gel morphology. Detectability of the markers in the x-ray images was tested for two sizes (diameters of 1 and 2 mm) for B1 and B2. Four samples were injected into BALB/C mice. The polymer mixed with BaSO4 transform from SOL at 20 °C with a pH of 6.0 to GEL in the living body at 37 °C with a pH of 7.4, so the size of the fiducial marker could be controlled by adjusting the injected volume. The detectability of the BaSO4 marker was measured in x-ray images of cone beam CT (CBCT), on-board imager [anterior-posterior (AP), lateral], and fluoroscopy (AP, lateral) using a Novalis-TX (Varian Medical Systems, Palo Alto, CA) repeatedly over 4 months. The volume, HU, and artifacts for the markers were measured in the CBCT images. Artifacts were compared to those of gold marker by analyzing the HU distribution. The dose distortion in proton therapy was computed by using a Monte Carlo (MC) code. A cylindrical shaped marker (diameter: 1 or 2 mm, length: 3 mm) made of gold, stainless-steel [304], titanium, and 20 wt. % BaSO4 was positioned at the center of the spread-out Bragg peak (SOBP) in parallel or perpendicular to the beam entrance. The dose distortion was measured on the depth dose profile across the markers. RESULTS: Transformation to GEL and the biodegradation were verified. All BaSO4 markers could be detected in the CBCT. In the OBI and fluoroscopy images, all markers visible in the AP, but only B2(2 mm) could be identified in the lateral images. Changes of BaSO4 position were not detected in vivo (mice). The volume of the markers decreased by up to 65% and the HU increased by 22%, on average. The mean HU values around the B1, B2, and gold markers were 121.30 [standard deviation (SD): 54.86], 126.31 (SD: 62.13), and 1070.7 (SD: 235.16), respectively. The MC-simulated dose distortion for the BaSO4 markers was less than that of the commercially used markers. The dose reduction due to the gold marker was largest (15.05%) followed by stainless steel (7.92%) and titanium (6.92%). Dose reduction by B2 (2 mm) was 4.75% and 0.53% in parallel and perpendicular orientations, respectively. CONCLUSIONS: BaSO4 mixed with PBS is a good contrast agent in biodegradable polymer marker because of minimal artifacts in x-ray images and minimal dose reduction in proton therapy. The flexibility of the size is considered to be an advantage of this material over solid type fiducials.