TransAnaNet: Transformer-based Anatomy Change Prediction Network for Head and Neck Cancer Patient Radiotherapy.

Background: Adaptive radiotherapy (ART) can compensate for the dosimetric impact of anatomic change during radiotherapy of head neck cancer (HNC) patients. However, implementing ART universally poses challenges in clinical workflow and resource allocation, given the variability in patient response and the constraints of available resources. Therefore, early identification of head and neck cancer (HNC) patients who would experience significant anatomical change during radiotherapy (RT) is of importance to optimize patient clinical benefit and treatment resources. Purpose: The purpose of this study is to assess the feasibility of using a vision-transformer (ViT) based neural network to predict radiotherapy induced anatomic change of HNC patients. Methods: We retrospectively included 121 HNC patients treated with definitive RT/CRT. We collected the planning CT (pCT), planned dose, CBCTs acquired at the initial treatment (CBCT01) and fraction 21 (CBCT21), and primary tumor volume (GTVp) and involved nodal volume (GTVn) delineated on both pCT and CBCTs for model construction and evaluation. A UNet-style ViT network was designed to learn the spatial correspondence and contextual information from embedded image patches of CT, dose, CBCT01, GTVp, and GTVn. The deformation vector field between CBCT01 and CBCT21 was estimated by the model as the prediction of anatomic change, and deformed CBCT01 was used as the prediction of CBCT21. We also generated binary masks of GTVp, GTVn and patient body for volumetric change evaluation. We used data from 100 patients for training and validation, and the remaining 21 patients for testing. Image and volumetric similarity metrics including mean square error (MSE), structural similarity index (SSIM), dice coefficient, and average surface distance were used to measure the similarity between the target image and predicted CBCT. Results: The predicted image from the proposed method yielded the best similarity to the real image (CBCT21) over pCT, CBCT01, and predicted CBCTs from other comparison models. The average MSE and SSIM between the normalized predicted CBCT to CBCT21 are 0.009 and 0.933, while the average dice coefficient between body mask, GTVp mask, and GTVn mask are 0.972, 0.792, and 0.821 respectively. Conclusions: The proposed method showed promising performance for predicting radiotherapy induced anatomic change, which has the potential to assist in the decision making of HNC Adaptive RT.

Deep learning based automatic segmentation of the Internal Pudendal Artery in definitive radiotherapy treatment planning of localized prostate cancer.

Background and purpose: Radiation-induced erectile dysfunction (RiED) commonly affects prostate cancer patients, prompting clinical trials across institutions to explore dose-sparing to internal-pudendal-arteries (IPA) for preserving sexual potency. IPA, challenging to segment, isn't conventionally considered an organ-at-risk (OAR). This study proposes a deep learning (DL) auto-segmentation model for IPA, using Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) or CT alone to accommodate varied clinical practices. Materials and methods: A total of 86 patients with CT and MRI images and noisy IPA labels were recruited in this study. We split the data into 42/14/30 for model training, testing, and a clinical observer study, respectively. There were three major innovations in this model: 1) we designed an architecture with squeeze-and-excite blocks and modality attention for effective feature extraction and production of accurate segmentation, 2) a novel loss function was used for training the model effectively with noisy labels, and 3) modality dropout strategy was used for making the model capable of segmentation in the absence of MRI. Results: Test dataset metrics were DSC 61.71 ± 7.7 %, ASD 2.5 ± .87 mm, and HD95 7.0 ± 2.3 mm. AI segmented contours showed dosimetric similarity to expert physician's contours. Observer study indicated higher scores for AI contours (mean = 3.7) compared to inexperienced physicians' contours (mean = 3.1). Inexperienced physicians improved scores to 3.7 when starting with AI contours. Conclusion: The proposed model achieved good quality IPA contours to improve uniformity of segmentation and to facilitate introduction of standardized IPA segmentation into clinical trials and practice.

Deep learning based direct segmentation assisted by deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy.

Cone-beam CT (CBCT)-based online adaptive radiotherapy calls for accurate auto-segmentation to reduce the time cost for physicians. However, deep learning (DL)-based direct segmentation of CBCT images is a challenging task, mainly due to the poor image quality and lack of well-labelled large training datasets. Deformable image registration (DIR) is often used to propagate the manual contours on the planning CT (pCT) of the same patient to CBCT. In this work, we undertake solving the problems mentioned above with the assistance of DIR. Our method consists of three main components. First, we use deformed pCT contours derived from multiple DIR methods between pCT and CBCT as pseudo labels for initial training of the DL-based direct segmentation model. Second, we use deformed pCT contours from another DIR algorithm as influencer volumes to define the region of interest for DL-based direct segmentation. Third, the initially trained DL model is further fine-tuned using a smaller set of true labels. Nine patients are used for model evaluation. We found that DL-based direct segmentation on CBCT without influencer volumes has much poorer performance compared to DIR-based segmentation. However, adding deformed pCT contours as influencer volumes in the direct segmentation network dramatically improves segmentation performance, reaching the accuracy level of DIR-based segmentation. The DL model with influencer volumes can be further improved through fine-tuning using a smaller set of true labels, achieving mean Dice similarity coefficient of 0.86, Hausdorff distance at the 95th percentile of 2.34 mm, and average surface distance of 0.56 mm. A DL-based direct CBCT segmentation model can be improved to outperform DIR-based segmentation models by using deformed pCT contours as pseudo labels and influencer volumes for initial training, and by using a smaller set of true labels for model fine tuning.

Preliminary Evaluation of PTV Margins for Online Adaptive Radiation Therapy of the Prostatic Fossa.

PURPOSE: In modern trials, traditional planning target volume (PTV) margins for postoperative prostate radiation therapy have been large (7-10 mm) to account for both daily changes in patient positioning and target deformation. With daily adaptive radiation therapy, these interfractional changes could be minimized, potentially reducing the margins required for treatment and improving adjacent normal-tissue dosimetry. METHODS AND MATERIALS: A single-center retrospective study was conducted from March 2021 to November 2021. Patients receiving conventionally fractionated postoperative radiation therapy (PORT) for prostate cancer with pretreatment and posttreatment cone beam computed tomography (CBCT) imaging (pre-CBCT and post-CBCT, respectively) were included (248 paired images). Pretreatment and posttreatment clinical target volumes (pre-CTVs and post-CTVs) were contoured by a single observer on all CBCTs and verified by a second observer. Motion was calculated from pre-CTV to that of the post-CTV, and predicted margins were calculated with van Herk's formula. Adequate coverage of the proposed planning target volume (PTV) margin expansions (pre-PTV) were verified by determining overlap with post-CTV. In a smaller cohort (25 paired images), dosimetric changes with the proposed online adaptive margins were compared with conventional plans in the Ethos emulator environment. RESULTS: The estimated margins predicted to achieve ≥95% CTV coverage for 90% of the population were 1.6 mm, 2.0 mm, and 2.2 mm (x-, y-, and z -xes, respectively), with 95% of the absolute region of interest displacement being within 1.9 mm, 2.8 mm, and 2.1 mm. After symmetrically expanding all pre-CTVs by 3 mm, the percentage of paired images achieving ≥95% CTV coverage was 97.1%. When comparing adaptive plans (3-mm margins) with scheduled plans (7-mm margins), rectum dosimetry significantly improved, with an average relative reduction in V40Gy[cc] of 59.2% and V65Gy[cc] of 79.5% (where V40Gy and V65Gy are defined as the volumes receiving 40 Gy and 65 Gy or higher dose, respectively). CONCLUSIONS: Online daily adaptive radiation therapy could significantly decrease PTV margins for prostatic PORT and improve rectal dosimetry, with a symmetrical expansion of 3 mm achieving excellent coverage in this cohort. These results need to be validated in a larger prospective cohort.

Segmentation by test-time optimization for CBCT-based adaptive radiation therapy.

PURPOSE: Online adaptive radiotherapy (ART) requires accurate and efficient auto-segmentation of target volumes and organs-at-risk (OARs) in mostly cone-beam computed tomography (CBCT) images, which often have severe artifacts and lack soft-tissue contrast, making direct segmentation very challenging. Propagating expert-drawn contours from the pretreatment planning CT through traditional or deep learning (DL)-based deformable image registration (DIR) can achieve improved results in many situations. Typical DL-based DIR models are population based, that is, trained with a dataset for a population of patients, and so they may be affected by the generalizability problem. METHODS: In this paper, we propose a method called test-time optimization (TTO) to refine a pretrained DL-based DIR population model, first for each individual test patient, and then progressively for each fraction of online ART treatment. Our proposed method is less susceptible to the generalizability problem and thus can improve overall performance of different DL-based DIR models by improving model accuracy, especially for outliers. Our experiments used data from 239 patients with head-and-neck squamous cell carcinoma to test the proposed method. First, we trained a population model with 200 patients and then applied TTO to the remaining 39 test patients by refining the trained population model to obtain 39 individualized models. We compared each of the individualized models with the population model in terms of segmentation accuracy. RESULTS: The average improvement of the Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) of segmentation can be up to 0.04 (5%) and 0.98 mm (25%), respectively, with the individualized models compared to the population model over 17 selected OARs and a target of 39 patients. Although the average improvement may seem mild, we found that the improvement for outlier patients with structures of large anatomical changes is significant. The number of patients with at least 0.05 DSC improvement or 2 mm HD95 improvement by TTO averaged over the 17 selected structures for the state-of-the-art architecture VoxelMorph is 10 out of 39 test patients. By deriving the individualized model using TTO from the pretrained population model, TTO models can be ready in about 1 min. We also generated the adapted fractional models for each of the 39 test patients by progressively refining the individualized models using TTO to CBCT images acquired at later fractions of online ART treatment. When adapting the individualized model to a later fraction of the same patient, the model can be ready in less than a minute with slightly improved accuracy. CONCLUSIONS: The proposed TTO method is well suited for online ART and can boost segmentation accuracy for DL-based DIR models, especially for outlier patients where the pretrained models fail.

A Proof-of-Concept Study of Artificial Intelligence-assisted Contour Editing.

Purpose: To present a concept called artificial intelligence-assisted contour editing (AIACE) and demonstrate its feasibility. Materials and Methods: The conceptual workflow of AIACE is as follows: Given an initial contour that requires clinician editing, the clinician indicates where large editing is needed, and a trained deep learning model uses this input to update the contour. This process repeats until a clinically acceptable contour is achieved. In this retrospective, proof-of-concept study, the authors demonstrated the concept on two-dimensional (2D) axial CT images from three head-and-neck cancer datasets by simulating the interaction with the AIACE model to mimic the clinical environment. The input at each iteration was one mouse click on the desired location of the contour segment. Model performance is quantified with the Dice similarity coefficient (DSC) and 95th percentile of Hausdorff distance (HD95) based on three datasets with sample sizes of 10, 28, and 20 patients. Results: The average DSCs and HD95 values of the automatically generated initial contours were 0.82 and 4.3 mm, 0.73 and 5.6 mm, and 0.67 and 11.4 mm for the three datasets, which were improved to 0.91 and 2.1 mm, 0.86 and 2.5 mm, and 0.86 and 3.3 mm, respectively, with three mouse clicks. Each deep learning-based contour update required about 20 msec. Conclusion: The authors proposed the newly developed AIACE concept, which uses deep learning models to assist clinicians in editing contours efficiently and effectively, and demonstrated its feasibility by using 2D axial CT images from three head-and-neck cancer datasets.Keywords: Segmentation, Convolutional Neural Network (CNN), CT, Deep Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.

Use of deep learning to predict the need for aggressive nutritional supplementation during head and neck radiotherapy.

PURPOSE/OBJECTIVES: Radiation therapy (RT) for the treatment of patients with head and neck cancer (HNC) leads to side effects that can limit a person's oral intake. Early identification of patients who need aggressive nutrition supplementation via a feeding tube (FT) could improve outcomes. We hypothesize that traditional machine learning techniques used in combination with deep learning techniques could identify patients early during RT who will later need a FT. MATERIALS/METHODS: We evaluated 271 patients with HNC treated with RT. Sixteen clinical features, planning computed tomography (CT) scans, 3-dimensional dose, and treatment cone-beam CT scans were gathered for each patient. The outcome predicted was the need for a FT or ≥10% weight loss during RT. Three conventional classifiers, including logistic regression (LR), support vector machine, and multilayer perceptron, used the 16 clinical features for clinical modeling. A convolutional neural network (CNN) analyzed the imaging data. Five-fold cross validation was performed. The area under the curve (AUC) values were used to compare models' performances. ROC analyses were performed using a paired DeLong Test in R-4.1.2. The clinical and imaging model outcomes were combined to make a final prediction via evidential reasoning rule-based fusion. RESULTS: The LR model performed the best on the clinical dataset (AUC 0.69). The MedicalNet CNN trained via transfer learning performed the best on the imaging dataset (AUC 0.73). The combined clinical and image-based model obtained an AUC of 0.75. The combined model was statistically better than the clinical model alone (p = 0.001). CONCLUSIONS: An artificial intelligence model incorporating clinical parameters, dose distributions and on-treatment CBCT achieved the highest performance to identify the need to place a reactive feeding tube.

Registration-guided deep learning image segmentation for cone beam CT-based online adaptive radiotherapy.

PURPOSE: Adaptive radiotherapy (ART), especially online ART, effectively accounts for positioning errors and anatomical changes. One key component of online ART process is accurately and efficiently delineating organs at risk (OARs) and targets on online images, such as cone beam computed tomography (CBCT). Direct application of deep learning (DL)-based segmentation to CBCT images suffered from issues such as low image quality and limited available contour labels for training. To overcome these obstacles to online CBCT segmentation, we propose a registration-guided DL (RgDL) segmentation framework that integrates image registration algorithms and DL segmentation models. METHODS: The RgDL framework is composed of two components: image registration and RgDL segmentation. The image registration algorithm transforms/deforms planning contours that were subsequently used as guidance by the DL model to obtain accurate final segmentations. We had two implementations of the proposed framework-Rig-RgDL (Rig for rigid body) and Def-RgDL (Def for deformable)-with rigid body (RB) registration or deformable image registration (DIR) as the registration algorithm, respectively, and U-Net as the DL model architecture. The two implementations of RgDL framework were trained and evaluated on seven OARs in an institutional clinical head-and-neck dataset. RESULTS: Compared to the baseline approaches using the registration or the DL alone, RgDLs achieved more accurate segmentation, as measured by higher mean Dice similarity coefficients (DSCs) and other distance-based metrics. Rig-RgDL achieved a DSC of 84.5% on seven OARs on average, higher than RB or DL alone by 4.5% and 4.7%. The average DSC of Def-RgDL was 86.5%, higher than DIR or DL alone by 2.4% and 6.7%. The inference time required by the DL model component to generate final segmentations of seven OARs was less than 1 s in RgDL. By examining the contours from RgDLs and DL case by case, we found that RgDL was less susceptible to image artifacts. We also studied how the performances of RgDL and DL vary with the size of the training dataset. The DSC of DL dropped by 12.1% as the number of training data decreased from 22 to 5, whereas RgDL only dropped by 3.4%. CONCLUSION: By incorporating the patient-specific registration guidance to a population-based DL segmentation model, RgDL framework overcame the obstacles associated with online CBCT segmentation, including low image quality and insufficient training data, and achieved better segmentation accuracy than baseline methods. The resulting segmentation accuracy and efficiency show promise for applying this RgDL framework for online ART.

Preliminary Results of Multi-Institutional Phase 1 Dose Escalation Trial Using Single-Fraction Stereotactic Partial Breast Irradiation for Early Stage Breast Cancer.

PURPOSE: We report on our early experience of our prospective multicenter phase 1 dose- escalation study of single-fraction stereotactic partial breast irradiation (S-PBI) for early stage breast cancer after partial mastectomy using a robotic stereotactic radiation system. METHODS AND MATERIALS: Thirty women with in situ or invasive breast cancer stage 0, I, or II with tumor size <3 cm treated with lumpectomy were enrolled in this phase 1 single-fraction S-PBI dose-escalation trial. Women received either 22.5, 26.5, or 30 Gy in a single fraction using a robotic stereotactic radiation system. The primary outcome was to reach tumoricidal dose of 30 Gy in a single fraction to the lumpectomy cavity without exceeding the maximum tolerated dose. Secondary outcomes were to determine dose-limiting toxicity and cosmesis. Tertiary goals were ipsilateral breast recurrence rate, distant disease-free interval, recurrence-free survival, and overall survival. RESULTS: From June 2016 to January 2021, 11, 8, and 10 patients were treated to doses of 22.5, 26.5, or 30 Gy in a single fraction, respectively, with median follow-up being 47.9, 25.1, and 16.2 months. No patients experienced acute (<90 days) grade 3 or higher treatment-related toxicity, and maximum tolerated dose was not reached. There were 2 delayed grade 3 toxicities. Four patients (13.8%) developed fat necrosis across all 3 cohorts, which compares favorably with results from other PBI trials. No dose cohort had a statistically significant cosmetic detriment from baseline to 12 months or 24 months follow-up by patient- or physician-reported global cosmetic scores. There were no reports of disease recurrence. CONCLUSIONS: This phase 1 trial demonstrates that S-PBI can be used to safely escalate dose to 30 Gy in a single fraction with low toxicity and without detriment in cosmesis relative to baseline.

Exploratory ensemble interpretable model for predicting local failure in head and neck cancer: the additive benefit of CT and intra-treatment cone-beam computed tomography features.

BACKGROUND: Local failure (LF) following chemoradiation (CRT) for head and neck cancer is associated with poor overall survival. If machine learning techniques could stratify patients at risk of treatment failure based on baseline and intra-treatment imaging, such a model could facilitate response-adapted approaches to escalate, de-escalate, or switch therapy. METHODS: A 1:2 retrospective case control cohort of patients treated at a single institution with definitive radiotherapy for head and neck cancer who failed locally, in-field at a primary or nodal structure were included. Radiomic features were extracted from baseline CT and CBCT scans at fractions 1 and 21 (delta) of radiotherapy with PyRadiomics and were selected for by: reproducibility (intra-class correlation coefficients ≥0.95), redundancy [maximum relevance and minimum redundancy (mRMR)], and informativeness [recursive feature elimination (RFE)]. Separate models predicting LF of primaries or nodes were created using the explainable boosting machine (EBM) classifier with 5-fold cross-validation for (I) clinical only, (II) radiomic only (CT1 and delta features), and (III) fused models (clinical + radiomic). Twenty-five iterations were performed, and predicted scores were averaged with a parallel ensemble design. Receiver operating characteristic curves were compared between models with paired-samples t-tests. RESULTS: The fused ensemble model for primaries (using clinical, CT1, and delta features) achieved an AUC of 0.871 with a sensitivity of 78.3% and specificity of 90.9% at the maximum Youden J statistic. The fused ensemble model trended towards improvement when compared to the clinical only ensemble model (AUC =0.788, P=0.134) but reached significance when compared to the radiomic ensemble model (AUC =0.770, P=0.017). The fused ensemble model for nodes achieved an AUC of 0.910 with a sensitivity of 100.0% and specificity of 68.0%, which also trended towards improvement when compared to the clinical model (AUC =0.865, P=0.080). CONCLUSIONS: The fused ensemble EBM model achieved high discriminatory ability at predicting LF for head and neck cancer in independent primary and nodal structures. Although an additive benefit of delta radiomics over clinical factors could not be proven, the results trended towards improvement with the fused ensemble model, which are promising and worthy of prospective investigation in a larger cohort.

PSA-Net: Deep learning-based physician style-aware segmentation network for postoperative prostate cancer clinical target volumes.

PURPOSE: Automatic segmentation of medical images with deep learning (DL) algorithms has proven highly successful in recent times. With most of these automation networks, inter-observer variation is an acknowledged problem that leads to suboptimal results. This problem is even more significant in segmenting postoperative clinical target volumes (CTV) because they lack a macroscopic visible tumor in the image. This study, using postoperative prostate CTV segmentation as the test case, tries to determine 1) whether physician styles are consistent and learnable, 2) whether physician style affects treatment outcome and toxicity, and 3) how to explicitly deal with different physician styles in DL-assisted CTV segmentation to facilitate its clinical acceptance. METHODS: A dataset of 373 postoperative prostate cancer patients from UT Southwestern Medical Center was used for this study. We used another 83 patients from Mayo Clinic to validate the developed model and its adaptability. To determine whether physician styles are consistent and learnable, we trained a 3D convolutional neural network classifier to identify which physician had contoured a CTV from just the contour and the corresponding CT scan. Next, we evaluated whether adapting automatic segmentation to specific physician styles would be clinically feasible based on a lack of difference between outcomes. Here, biochemical progression-free survival (BCFS) and grade 3+ genitourinary and gastrointestinal toxicity were estimated with the Kaplan-Meier method and compared between physician styles with the log rank test and subsequently with a multivariate Cox regression. When we found no statistically significant differences in outcome or toxicity between contouring styles, we proposed a concept called physician style-aware (PSA) segmentation by developing an encoder-multidecoder network with perceptual loss to model different physician styles of CTV segmentation. RESULTS: The classification network captured the different physician styles with 87% accuracy. Subsequent outcome analysis showed no differences in BCFS and grade 3+ toxicity among physicians. With the proposed physician style-aware network (PSA-Net), Dice similarity coefficient (DSC) accuracy for all physicians was 3.4% higher on average than with a general model that does not differentiate physician styles. We show that these stylistic contouring variations also exist between institutions that follow the same segmentation guidelines, and we show the proposed method's effectiveness in adapting to new institutional styles. We observed an accuracy improvement of 5% in terms of DSC when adapting to the style of a separate institution. CONCLUSION: The performance of the classification network established that physician styles are learnable, and the lack of difference between outcomes among physicians shows that the network can feasibly adapt to different styles in the clinic. Therefore, we developed a novel PSA-Net model that can produce contours specific to the treating physician, thus improving segmentation accuracy and avoiding the need to train multiple models to achieve different style segmentations. We successfully validated this model on data from a separate institution, thus supporting the model's generalizability to diverse datasets.

A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy.

In post-operative radiotherapy for prostate cancer, precisely contouring the clinical target volume (CTV) to be irradiated is challenging, because the cancerous prostate gland has been surgically removed, so the CTV encompasses the microscopic spread of tumor cells, which cannot be visualized in clinical images like computed tomography or magnetic resonance imaging. In current clinical practice, physicians' segment CTVs manually based on their relationship with nearby organs and other clinical information, but this allows large inter-physician variability. Automating post-operative prostate CTV segmentation with traditional image segmentation methods has yielded suboptimal results. We propose using deep learning to accurately segment post-operative prostate CTVs. The model proposed is trained using labels that were clinically approved and used for patient treatment. To segment the CTV, we segment nearby organs first, then use their relationship with the CTV to assist CTV segmentation. To ease the encoding of distance-based features, which are important for learning both the CTV contours' overlap with the surrounding OARs and the distance from their borders, we add distance prediction as an auxiliary task to the CTV network. To make the DL model practical for clinical use, we use Monte Carlo dropout (MCDO) to estimate model uncertainty. Using MCDO, we estimate and visualize the 95% upper and lower confidence bounds for each prediction which informs the physicians of areas that might require correction. The model proposed achieves an average Dice similarity coefficient (DSC) of 0.87 on a holdout test dataset, much better than established methods, such as atlas-based methods (DSC<0.7). The predicted contours agree with physician contours better than medical resident contours do. A reader study showed that the clinical acceptability of the automatically segmented CTV contours is equal to that of approved clinical contours manually drawn by physicians. Our deep learning model can accurately segment CTVs with the help of surrounding organ masks. Because the DL framework can outperform residents, it can be implemented practically in a clinical workflow to generate initial CTV contours or to guide residents in generating these contours for physicians to review and revise. Providing physicians with the 95% confidence bounds could streamline the review process for an efficient clinical workflow as this would enable physicians to concentrate their inspecting and editing efforts on the large uncertain areas.

Cosmetic Outcomes of a Phase 1 Dose Escalation Study of 5-Fraction Stereotactic Partial Breast Irradiation for Early Stage Breast Cancer.

PURPOSE: Our purpose was to evaluate cosmetic changes after 5-fraction adjuvant stereotactic partial breast irradiation (S-PBI). METHODS AND MATERIALS: Seventy-five women with in situ or invasive breast cancer stage 0, I, or II, with tumor size ≤3 cm, were enrolled after lumpectomy in a phase 1 dose escalation trial of S-PBI into cohorts receiving 30, 32.5, 35, 37.5, or 40 Gy in 5 fractions. Before S-PBI, 3 to 4 gold fiducial markers were placed in the lumpectomy cavity for tracking with the Synchrony respiratory tracking system. S-PBI was delivered with a CyberKnife robotic radiosurgery system. Patients and physicians evaluated global cosmesis using the Harvard Breast Cosmesis Scale. Eight independent panelists evaluated digital photography for global cosmesis and 10 subdomains at baseline and follow-up. McNemar tests were used to evaluate change in cosmesis, graded as excellent/good or fair/poor, from baseline to year 3. Wilcoxon signed rank tests were used to evaluate change in subdomains. Cohen's kappa (κ) statistic was used to estimate interobserver agreement (IOA) between raters, and Fleiss' κ was used to estimate IOA between panelists. RESULTS: Median cosmetic follow-up was 5, 5, 5, 4, and 3 years for the 30, 32.5, 35, 37.5, and 40 Gy cohorts. Most patients reported excellent/good cosmesis at both baseline (86.3%) and year 3 (89.8%). No dose cohort had significantly worsened cosmesis by year 3 on McNemar analysis. No cosmetic subdomain had significant worsening by year 3. IOA was fair for patient-physician (κ = 0.300, P < .001), patient-panel (κ = 0.295, P < .001), physician-panel (κ = 0.256, P < .001), and individual panelists (Fleiss κ = 0.327, P < .001). CONCLUSIONS: Dose escalation of S-PBI from 30 to 40 Gy in 5 fractions for early stage breast cancer was not associated with a detectable change in cosmesis by year 3. S-PBI is a promising modality for treatment of early stage breast cancer.

Risk Factors for Fat Necrosis After Stereotactic Partial Breast Irradiation for Early-Stage Breast Cancer in a Phase 1 Clinical Trial.

PURPOSE: This study reports predictive dosimetric and physiologic factors for fat necrosis after stereotactic-partial breast irradiation (S-PBI). METHODS AND MATERIALS: Seventy-five patients with ductal carcinoma-in situ or invasive nonlobular epithelial histologies stage 0, I, or II, with tumor size <3 cm were enrolled in a dose-escalation, phase I S-PBI trial between January 2011 and July 2015. Fat necrosis was evaluated clinically at each follow-up. Treatment data were extracted from the Multiplan Treatment Planning System (Cyberknife, Accuray). Univariate and stepwise logistic regression analyses were conducted to identify factors associated with palpable fat necrosis. RESULTS: With a median follow-up of 61 months (range: 4.3-99.5 months), 11 patients experienced palpable fat necrosis, 5 cases of which were painful. The median time to development of fat necrosis was 12.7 months (range, 3-42 months). On univariate analyses, higher V32.5-47.5 Gy (P < .05) and larger breast volume (P < .01) were predictive of any fat necrosis; higher V35-50 Gy (P < .05), receiving 2 treatments on consecutive days (P = .02), and higher Dmax (P = .01) were predictive of painful fat necrosis. On multivariate analyses, breast volume larger than 1063 cm3 remained a predictive factor for any fat necrosis; receiving 2 treatments on consecutive days and higher V45 Gy were predictive of painful fat necrosis. Breast laterality, planning target volume (PTV), race, body mass index, diabetic status, and tobacco or drug use were not significantly associated with fat necrosis on univariate analysis. CONCLUSIONS: Early-stage breast cancer patients treated with breast conserving surgery and S-PBI in our study had a fat necrosis rate comparable to other accelerated partial breast irradiation modalities, but S-PBI is less invasive. To reduce risk of painful fat necrosis, we recommend not delivering fractions on consecutive days; limiting V42.5 < 50 cm3, V45 < 20 cm3, V47.5 < 1 cm3, Dmax ≤ 48 Gy and PTV < 100 cm3 when feasible; and counseling patients about the increased risk for fat necrosis when constraints are not met and for those with breast volume >1000 cm3.

Adaptive radiotherapy for head and neck cancer.

BACKGROUND: Although there have been dramatic improvements in radiotherapy for head and neck squamous cell carcinoma (HNSCC), including robust intensity modulation and daily image guidance, these advances are not able to account for inherent structural and spatial changes that may occur during treatment. Many sources have reported volume reductions in the primary target, nodal volumes, and parotid glands over treatment, which may result in unintended dosimetric changes affecting the side effect profile and even efficacy of the treatment. Adaptive radiotherapy (ART) is an exciting treatment paradigm that has been developed to directly adjust for these changes. MAIN BODY: Adaptive radiotherapy may be divided into two categories: anatomy-adapted (A-ART) and response-adapted ART (R-ART). Anatomy-adapted ART is the process of re-planning patients based on structural and spatial changes occurring over treatment, with the intent of reducing overdosage of sensitive structures such as the parotids, improving dose homogeneity, and preserving coverage of the target. In contrast, response-adapted ART is the process of re-planning patients based on response to treatment, such that the target and/or dose changes as a function of interim imaging during treatment, with the intent of dose escalating persistent disease and/or de-escalating surrounding normal tissue. The impact of R-ART on local control and toxicity outcomes is actively being investigated in several currently accruing trials. CONCLUSIONS: Anatomy-adapted ART is a promising modality to improve rates of xerostomia and coverage in individuals who experience significant volumetric changes during radiation, while R-ART is currently being studied to assess its utility in either dose escalation of radioresistant disease, or de-intensification of surrounding normal tissue following treatment response. In this paper, we will review the existing literature and recent advances regarding A-ART and R-ART.

Altered Cortico-Limbic Network Connectivity in Parkinsonian Depression: The Effect of Antidepressants.

BACKGROUND: Depression is a common comorbidity of Parkinson's disease (PD); however, the impact of antidepressant status on cortical function in parkinsonian depression is not fully understood. While studies of resting state functional MRI in major depression have shown that antidepressant treatment affects cortical connectivity, data on connectivity and antidepressant status in PD is sparse. OBJECTIVE: We tested the hypothesis that cortico-limbic network (CLN) resting state connectivity is abnormal in antidepressant-treated parkinsonian depression. METHODS: Thirteen antidepressant-treated depressed PD and 47 non-depressed PD participants from the Parkinson's Progression Markers Initiative (PPMI) database were included. Data was collected using 3T Siemens TIM Trio MR scanners and analyzed using SPM and CONN functional connectivity toolbox. Volumetric analysis was also performed using BrainSuite. RESULTS: We found decreased connectivity in the antidepressant-treated depressed PD group when compared to non-depressed PD between the left frontal operculum and bilateral insula, and also reduced connectivity between right orbitofrontal cortex and left temporal fusiform structures. Increased depression scores were associated with decreased insular-frontal opercular connectivity. No ROI volumetric differences were found between groups. CONCLUSION: Given the relationship between depression scores and cortico-limbic connectivity in PD, the abnormal insular-frontal opercular hypoconnectivity in this cohort may be associated with persistent depressive symptoms or antidepressant effects.

Detecting Estrogenic Ligands in Personal Care Products using a Yeast Estrogen Screen Optimized for the Undergraduate Teaching Laboratory.

The Yeast Estrogen Screen (YES) is used to detect estrogenic ligands in environmental samples and has been broadly applied in studies of endocrine disruption. Estrogenic ligands include both natural and manmade "Environmental Estrogens" (EEs) found in many consumer goods including Personal Care Products (PCPs), plastics, pesticides, and foods. EEs disrupt hormone signaling in humans and other animals, potentially reducing fertility and increasing disease risk. Despite the importance of EEs and other Endocrine Disrupting Chemicals (EDCs) to public health, endocrine disruption is not typically included in undergraduate curricula. This shortcoming is partly due to a lack of relevant laboratory activities that illustrate the principles involved while also being accessible to undergraduate students. This article presents an optimized YES for quantifying ligands in personal care products that bind estrogen receptors alpha (ERα) and/or beta (ERß). The method incorporates one of the two colorimetric substrates (ortho-nitrophenyl-ß-D-galactopyranoside (ONPG) or chlorophenol red-ß-D-galactopyranoside (CPRG)) that are cleaved by ß-galactosidase, a 6-day refrigerated incubation step to facilitate use in undergraduate laboratory courses, an automated application for LacZ calculations, and R code for the associated 4-parameter logistic regression analysis. The protocol has been designed to allow undergraduate students to develop and conduct experiments in which they screen products of their choosing for estrogen mimics. In the process, they learn about endocrine disruption, cell culture, receptor binding, enzyme activity, genetic engineering, statistics, and experimental design. Simultaneously, they also practice fundamental and broadly applicable laboratory skills, such as: calculating concentrations; making solutions; demonstrating sterile technique; serially diluting standards; constructing and interpolating standard curves; identifying variables and controls; collecting, organizing, and analyzing data; constructing and interpreting graphs; and using common laboratory equipment such as micropipettors and spectrophotometers. Thus, implementing this assay encourages students to engage in inquiry-based learning while exploring emerging issues in environmental science and health.