Training robust T1-weighted magnetic resonance imaging liver segmentation models using ensembles of datasets with different contrast protocols and liver disease etiologies.

Image segmentation of the liver is an important step in treatment planning for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a generalizable deep learning model to segment the liver on T1-weighted MR images. In particular, three distinct deep learning architectures (nnUNet, PocketNet, Swin UNETR) were considered using data gathered from six geographically different institutions. A total of 819 T1-weighted MR images were gathered from both public and internal sources. Our experiments compared each architecture's testing performance when trained both intra-institutionally and inter-institutionally. Models trained using nnUNet and its PocketNet variant achieved mean Dice-Sorensen similarity coefficients>0.9 on both intra- and inter-institutional test set data. The performance of these models suggests that nnUNet and PocketNet liver segmentation models trained on a large and diverse collection of T1-weighted MR images would on average achieve good intra-institutional segmentation performance.

1D Thermoembolization Model Using CT Imaging Data for Porcine Liver.

Objective: Innovative therapies such as thermoembolization are expected to play an important role in improving care for patients with diseases such as hepatocellular carcinoma. Thermoembolization is a minimally invasive strategy that combines thermal ablation and embolization in a single procedure. This approach exploits an exothermic chemical reaction that occurs when an acid chloride is delivered via an endovascular route. However, comprehension of the complexities of the biophysics of thermoembolization is challenging. Mathematical models can aid in understanding such complex processes and assisting clinicians in making informed decisions. In this study, we used a Hagen-Poiseuille 1D blood flow model to predict the mass transport and possible embolization locations in a porcine hepatic artery. Method: The 1D flow model was used on imaging data of in-vivo embolization imaging data of three pigs. The hydrolysis time constant of acid chloride chemical reaction was optimized for each pig, and LOOCV method was used to test the model's predictive ability. Conclusion: This basic model provided a balanced accuracy rate of 66.8% for identifying the possible locations of damage in the hepatic artery. Use of the model provides an initial understanding of the vascular transport phenomena that are predicted to occur as a result of thermoembolization.

Artificial intelligence uncertainty quantification in radiotherapy applications - A scoping review.

BACKGROUND/PURPOSE: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. METHODS: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. RESULTS: We identified 56 articles published from 2015 to 2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50 %), followed by image-synthesis (13 %), and multiple applications simultaneously (11 %). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32 %). Imaging data was used in 91 % of studies, while only 13 % incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60 %), with Monte Carlo dropout being the most commonly implemented UQ method (32 %) followed by ensembling (16 %). 55 % of studies did not share code or datasets. CONCLUSION: Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, we identified a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

Computed tomography radiomics-based cross-sectional detection of mandibular osteoradionecrosis in head and neck cancer survivors.

Purpose: This study aims to identify radiomic features extracted from contrast-enhanced CT scans that differentiate osteoradionecrosis (ORN) from normal mandibular bone in patients with head and neck cancer (HNC) treated with radiotherapy (RT). Materials and Methods: Contrast-enhanced CT (CECT) images were collected for 150 patients (80% train, 20% test) with confirmed ORN diagnosis at The University of Texas MD Anderson Cancer Center between 2008 and 2018. Using PyRadiomics, radiomic features were extracted from manually segmented ORN regions and the corresponding automated control regions, the later defined as the contralateral healthy mandible region. A subset of pre-selected features was obtained based on correlation analysis (r > 0.95) and used to train a Random Forest (RF) classifier with Recursive Feature Elimination. Model explainability SHapley Additive exPlanations (SHAP) analysis was performed on the 20 most important features identified by the trained RF classifier. Results: From a total of 1316 radiomic features extracted, 810 features were excluded due to high collinearity. From a set of 506 pre-selected radiomic features, the optimal subset resulting on the best discriminative accuracy of the RF classifier consisted of 67 features. The RF classifier was well calibrated (Log Loss 0.296, ECE 0.125) and achieved an accuracy of 88% and a ROC AUC of 0.96. The SHAP analysis revealed that higher values of Wavelet-LLH First-order Mean and Median were associated with ORN of the jaw (ORNJ). Conversely, higher Exponential GLDM Dependence Entropy and lower Square First-order Kurtosis were more characteristic of normal mandibular tissue. Conclusion: This study successfully developed a CECT-based radiomics model for differentiating ORNJ from healthy mandibular tissue in HNC patients after RT. Future work will focus on the detection of subclinical ORNJ regions to guide earlier interventions.

Analyzing the Relationship between Dose and Geometric Agreement Metrics for Auto-Contouring in Head and Neck Normal Tissues.

This study aimed to determine the relationship between geometric and dosimetric agreement metrics in head and neck (H&N) cancer radiotherapy plans. A total 287 plans were retrospectively analyzed, comparing auto-contoured and clinically used contours using a Dice similarity coefficient (DSC), surface DSC (sDSC), and Hausdorff distance (HD). Organs-at-risk (OARs) with ≥200 cGy dose differences from the clinical contour in terms of Dmax (D0.01cc) and Dmean were further examined against proximity to the planning target volume (PTV). A secondary set of 91 plans from multiple institutions validated these findings. For 4995 contour pairs across 19 OARs, 90% had a DSC, sDSC, and HD of at least 0.75, 0.86, and less than 7.65 mm, respectively. Dosimetrically, the absolute difference between the two contour sets was <200 cGy for 95% of OARs in terms of Dmax and 96% in terms of Dmean. In total, 97% of OARs exhibiting significant dose differences between the clinically edited contour and auto-contour were within 2.5 cm PTV regardless of geometric agreement. There was an approximately linear trend between geometric agreement and identifying at least 200 cGy dose differences, with higher geometric agreement corresponding to a lower fraction of cases being identified. Analysis of the secondary dataset validated these findings. Geometric indices are approximate indicators of contour quality and identify contours exhibiting significant dosimetric discordance. For a small subset of OARs within 2.5 cm of the PTV, geometric agreement metrics can be misleading in terms of contour quality.

Assessing the impact of storage conditions on RNA from human saliva and its application to the identification of mRNA biomarkers for asthma.

Introduction: Human saliva was used to develop non-invasive liquid biopsy biomarkers to establish saliva as an alternate to blood and plasma in translational research. The present study focused on understanding the impact of sample storage conditions on the extraction of RNA from saliva and the RNA yield, to be applied in clinical diagnosis. In this study, genes related to asthma were used to test the method developed. Methods: Salivary RNA was extracted from three subjects using the Qiazol® based method and quantified by both spectrophotometric (NanoDrop) and fluorometric (Qubit®) methods. RNA integrity was measured using a bioanalyzer. Quantitative PCR was used to monitor the impact of storage conditions on the expression of housekeeping genes: GAPDH and ß-actin, and the asthma related genes: POSTN and FBN2. In addition, an independent cohort of 38 asthmatics and 10 healthy controls were used to validate the expression of POSTN and FBN2 as mRNA salivary biomarkers. Results: Approximately 2 µg of total RNA was obtained from the saliva stored at 40°C without any preservative for 2 weeks showing consistent gene expression with RNA stored at room temperature (RT) for 48 h with RNAlater. Although saliva stored with RNAlater showed a substantial increase in the yield (110 to 234 ng/µL), a similar Cq (15.6 ± 1.4) for the 18s rRNA gene from saliva without preservative showed that the RNA was stable enough. Gene expression analysis from the degraded RNA can be performed by designing the assay using a smaller fragment size spanning a single exon as described below in the case of the POSTN and FBN2 genes in the asthma cohort. Conclusion: This study showed that samples stored at room temperature up to a temperature of 40°C without any preservative for 2 weeks yielded relatively stable RNA. The methodology developed can be employed to transport samples from the point of collection to the laboratory, under non-stringent storage conditions enabling the execution of gene expression studies in a cost effective and efficient manner.

Associations Between Radiation Oncologist Demographic Factors and Segmentation Similarity Benchmarks: Insights From a Crowd-Sourced Challenge Using Bayesian Estimation.

PURPOSE: The quality of radiotherapy auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of clinician-derived segmentations are poorly understood; our study aims to quantify these factors. METHODS: Organ at risk (OAR) and tumor-related segmentations provided by radiation oncologists from the Contouring Collaborative for Consensus in Radiation Oncology data set were used. Segmentations were derived from five disease sites: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and GI. Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus, which served as a reference standard benchmark. The Dice similarity coefficient (DSC) was primarily used as a metric for the comparisons. DSC was stratified into binary groups on the basis of structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Bayesian estimation were used to investigate the association between demographic variables and the binarized DSC for each disease site. Variables with a highest density interval excluding zero were considered to substantially affect the outcome measure. RESULTS: Five hundred seventy-four, 110, 452, 112, and 48 segmentations were used for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of segmentations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumors, respectively. Regression analysis revealed that the structure being tumor-related had a substantial negative impact on binarized DSC for the breast, sarcoma, H&N, and GI cases. There were no recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations. CONCLUSION: Our study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality relative to benchmarks.

Training Robust T1-Weighted Magnetic Resonance Imaging Liver Segmentation Models Using Ensembles of Datasets with Different Contrast Protocols and Liver Disease Etiologies.

Image segmentation of the liver is an important step in several treatments for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a deep learning model to segment the liver on T1w MR images. We sought to determine the best architecture by training, validating, and testing three different deep learning architectures using a total of 819 T1w MR images gathered from six different datasets, both publicly and internally available. Our experiments compared each architecture's testing performance when trained on data from the same dataset via 5-fold cross validation to its testing performance when trained on all other datasets. Models trained using nnUNet achieved mean Dice-Sorensen similarity coefficients > 90% when tested on each of the six datasets individually. The performance of these models suggests that an nnUNet liver segmentation model trained on a large and diverse collection of T1w MR images would be robust to potential changes in contrast protocol and disease etiology.

Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review.

Background/purpose: The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions. Methods: We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics. Results: We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets. Conclusion: Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

Evaluating the relationship between magnetic resonance image quality metrics and deep learning-based segmentation accuracy of brain tumors.

BACKGROUND: Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment-based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal-to-noise, contrast-to-noise) and segmentation accuracy. PURPOSE: Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL-based brain tumor segmentation accuracy toward developing more generalizable models for multi-institutional data. METHODS: We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non-ET on MRI; with performance quantified via a 5-fold cross-validated Dice coefficient. MRI scans were evaluated through the open-source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as "better" quality (BQ) or "worse" quality (WQ), via relative thresholding. Segmentation performance was re-evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts. RESULTS: For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal-to-noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models. CONCLUSIONS: Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet-based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.

Enhancement Pattern Mapping for Early Detection of Hepatocellular Carcinoma in Patients with Cirrhosis.

Background and Aims: Limited methods exist to accurately characterize the risk of malignant progression of liver lesions. Enhancement pattern mapping (EPM) measures voxel-based root mean square deviation (RMSD) of parenchyma and the contrast-to-noise (CNR) ratio enhances in malignant lesions. This study investigates the utilization of EPM to differentiate between HCC versus cirrhotic parenchyma with and without benign lesions. Methods: Patients with cirrhosis undergoing MRI surveillance were studied prospectively. Cases (n=48) were defined as patients with LI-RADS 3 and 4 lesions who developed HCC during surveillance. Controls (n=99) were patients with and without LI-RADS 3 and 4 lesions who did not develop HCC. Manual and automated EPM signals of liver parenchyma between cases and controls were quantitatively validated on an independent patient set using cross validation with manual methods avoiding parenchyma with artifacts or blood vessels. Results: With manual EPM, RMSD of 0.37 was identified as a cutoff for distinguishing lesions that progress to HCC from background parenchyma with and without lesions on pre-diagnostic scans (median time interval 6.8 months) with an area under the curve (AUC) of 0.83 (CI: 0.73-0.94) and a sensitivity, specificity, and accuracy of 0.65, 0.97, and 0.89, respectively. At the time of diagnostic scans, a sensitivity, specificity, and accuracy of 0.79, 0.93, and 0.88 were achieved with manual EPM with an AUC of 0.89 (CI: 0.82-0.96). EPM RMSD signals of background parenchyma that did not progress to HCC in cases and controls were similar (case EPM: 0.22 ± 0.08, control EPM: 0.22 ± 0.09, p=0.8). Automated EPM produced similar quantitative results and performance. Conclusion: With manual EPM, a cutoff of 0.37 identifies quantifiable differences between HCC cases and controls approximately six months prior to diagnosis of HCC with an accuracy of 89%.

Current surveillance and diagnostic methods in hepatocellular carcinoma are suboptimal. Enhancement pattern mapping is an imaging technique that quantifies lesion signals and may be useful in diagnostic and surveillance methods. Enhancement pattern mapping describes quantifiable differences between malignant and benign liver tissue on contrast-enhanced MRI. It amplifies lesion signal and distinguishes malignancy in a surveillance population. The novel imaging technique was investigated at single institution and analyzed lesions compared to cirrhotic parenchyma. Future efforts will include further risk stratification across LI-RADS group categories. The results provide evidence that enhancement pattern mapping uses available imaging data to distinguish hepatocellular carcinoma from non-cancerous parenchyma with and without benign lesions on scans six months prior to diagnosis with standard MRI. The technique introduces a prospective modality to improve diagnostic accuracy and early detection with the goal of improving clinical outcomes.

Automatic end-to-end VMAT treatment planning for rectal cancers.

BACKGROUND: The treatment planning process from segmentation to producing a deliverable plan is time-consuming and labor-intensive. Existing solutions automate the segmentation and planning processes individually. The feasibility of combining auto-segmentation and auto-planning for volumetric modulated arc therapy (VMAT) for rectal cancers in an end-to-end process is not clear. PURPOSE: To create and clinically evaluate a complete end-to-end process for auto-segmentation and auto-planning of VMAT for rectal cancer requiring only the gross tumor volume contour and a CT scan as inputs. METHODS: Patient scans and data were retrospectively selected from our institutional records for patients treated for malignant neoplasm of the rectum. We trained, validated, and tested deep learning auto-segmentation models using nnU-Net architecture for clinical target volume (CTV), bowel bag, large bowel, small bowel, total bowel, femurs, bladder, bone marrow, and female and male genitalia. For the CTV, we identified 174 patients with clinically drawn CTVs. We used data for 18 patients for all structures other than the CTV. The structures were contoured under the guidance of and reviewed by a gastrointestinal (GI) radiation oncologist. The predicted results for CTV in 35 patients and organs at risk (OAR) in six patients were scored by the GI radiation oncologist using a five-point Likert scale. For auto-planning, a RapidPlan knowledge-based planning solution was modeled for VMAT delivery with a prescription of 25 Gy in five fractions. The model was trained and tested on 20 and 34 patients, respectively. The resulting plans were scored by two GI radiation oncologists using a five-point Likert scale. Finally, the end-to-end pipeline was evaluated on 16 patients, and the resulting plans were scored by two GI radiation oncologists. RESULTS: In 31 of 35 patients, CTV contours were clinically acceptable without necessary modifications. The CTV achieved a Dice similarity coefficient of 0.85 (±0.05) and 95% Hausdorff distance of 15.25 (±5.59) mm. All OAR contours were clinically acceptable without edits, except for large and small bowel which were challenging to differentiate. However, contours for total, large, and small bowel were clinically acceptable. The two physicians accepted 100% and 91% of the auto-plans. For the end-to-end pipeline, the two physicians accepted 88% and 62% of the auto-plans. CONCLUSIONS: This study demonstrated that the VMAT treatment planning technique for rectal cancer can be automated to generate clinically acceptable and safe plans with minimal human interventions.

Impact of COVID-19 on Pharmacy Education and Practice: Strategies to Boost Advocacy and Unity among Health Care Organizations.

The global COVID-19 pandemic impacted pharmacy education and changed the pharmacists' scope of practice at the federal and state levels. Based on the Amended Public Readiness and Emergency Preparedness Act, pharmacists were authorized to provide essential services, including testing, treatments, and immunizations at various practice settings. Specifically, the United States Food and Drug Administration issued emergency use authorization for several medications, vaccines, and medical devices. The pandemic also affected the regulatory landscape for pharmacists, pharmacy education, access to care, and delivery of pharmacy services in-person and through telehealth. The pandemic's specific impact on pharmacy education heightened awareness of the well-being of the Academy. This commentary will highlight the impact of COVID-19 on both pharmacy education and practice. It will also provide strategies that educators, researchers, and practitioners can take into future research and action to help promote advocacy and unity among pharmacy organizations.

Mutual-information based optimal experimental design for hyperpolarized [Formula: see text]C-pyruvate MRI.

A key parameter of interest recovered from hyperpolarized (HP) MRI measurements is the apparent pyruvate-to-lactate exchange rate, [Formula: see text], for measuring tumor metabolism. This manuscript presents an information-theory-based optimal experimental design approach that minimizes the uncertainty in the rate parameter, [Formula: see text], recovered from HP-MRI measurements. Mutual information is employed to measure the information content of the HP measurements with respect to the first-order exchange kinetics of the pyruvate conversion to lactate. Flip angles of the pulse sequence acquisition are optimized with respect to the mutual information. A time-varying flip angle scheme leads to a higher parameter optimization that can further improve the quantitative value of mutual information over a constant flip angle scheme. However, the constant flip angle scheme, 35 and 28 degrees for pyruvate and lactate measurements, leads to an accuracy and precision comparable to the variable flip angle schemes obtained from our method. Combining the comparable performance and practical implementation, optimized pyruvate and lactate flip angles of 35 and 28 degrees, respectively, are recommended.

Validation of an automated contouring and treatment planning tool for pediatric craniospinal radiation therapy.

Purpose: Treatment planning for craniospinal irradiation (CSI) is complex and time-consuming, especially for resource-constrained centers. To alleviate demanding workflows, we successfully automated the pediatric CSI planning pipeline in previous work. In this work, we validated our CSI autosegmentation and autoplanning tool on a large dataset from St. Jude Children's Research Hospital. Methods: Sixty-three CSI patient CT scans were involved in the study. Pre-planning scripts were used to automatically verify anatomical compatibility with the autoplanning tool. The autoplanning pipeline generated 15 contours and a composite CSI treatment plan for each of the compatible test patients (n=51). Plan quality was evaluated quantitatively with target coverage and dose to normal tissue metrics and qualitatively with physician review, using a 5-point Likert scale. Three pediatric radiation oncologists from 3 institutions reviewed and scored 15 contours and a corresponding composite CSI plan for the final 51 test patients. One patient was scored by 3 physicians, resulting in 53 plans scored total. Results: The algorithm automatically detected 12 incompatible patients due to insufficient junction spacing or head tilt and removed them from the study. Of the 795 autosegmented contours reviewed, 97% were scored as clinically acceptable, with 92% requiring no edits. Of the 53 plans scored, all 51 brain dose distributions were scored as clinically acceptable. For the spine dose distributions, 92%, 100%, and 68% of single, extended, and multiple-field cases, respectively, were scored as clinically acceptable. In all cases (major or minor edits), the physicians noted that they would rather edit the autoplan than create a new plan. Conclusions: We successfully validated an autoplanning pipeline on 51 patients from another institution, indicating that our algorithm is robust in its adjustment to differing patient populations. We automatically generated 15 contours and a comprehensive CSI treatment plan for each patient without physician intervention, indicating the potential for increased treatment planning efficiency and global access to high-quality radiation therapy.

Determining The Role Of Radiation Oncologist Demographic Factors On Segmentation Quality: Insights From A Crowd-Sourced Challenge Using Bayesian Estimation.

BACKGROUND: Medical image auto-segmentation is poised to revolutionize radiotherapy workflows. The quality of auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of these clinician-derived segmentations have yet to be fully understood or quantified. Therefore, the purpose of this study was to determine the role of common observer demographic variables on quantitative segmentation performance. METHODS: Organ at risk (OAR) and tumor volume segmentations provided by radiation oncologist observers from the Contouring Collaborative for Consensus in Radiation Oncology public dataset were utilized for this study. Segmentations were derived from five separate disease sites comprised of one patient case each: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and gastrointestinal (GI). Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus gold standard primarily using the Dice Similarity Coefficient (DSC); surface DSC was investigated as a secondary metric. Metrics were stratified into binary groups based on previously established structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Markov chain Monte Carlo Bayesian estimation were used to investigate the association between demographic variables and the binarized segmentation quality for each disease site separately. Variables with a highest density interval excluding zero - loosely analogous to frequentist significance - were considered to substantially impact the outcome measure. RESULTS: After filtering by practicing radiation oncologists, 574, 110, 452, 112, and 48 structure observations remained for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of observations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumor volumes, respectively. Bayesian regression analysis revealed tumor category had a substantial negative impact on binarized DSC for the breast (coefficient mean ± standard deviation: -0.97 ± 0.20), sarcoma (-1.04 ± 0.54), H&N (-1.00 ± 0.24), and GI (-2.95 ± 0.98) cases. There were no clear recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations and wide highest density intervals. CONCLUSION: Our study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality. Future studies should investigate additional demographic variables, more patients and imaging modalities, and alternative metrics of segmentation acceptability.

Deep learning-based dose prediction to improve the plan quality of volumetric modulated arc therapy for gynecologic cancers.

BACKGROUND: In recent years, deep-learning models have been used to predict entire three-dimensional dose distributions. However, the usability of dose predictions to improve plan quality should be further investigated. PURPOSE: To develop a deep-learning model to predict high-quality dose distributions for volumetric modulated arc therapy (VMAT) plans for patients with gynecologic cancer and to evaluate their usability in driving plan quality improvements. METHODS: A total of 79 VMAT plans for the female pelvis were used to train (47 plans), validate (16 plans), and test (16 plans) 3D dense dilated U-Net models to predict 3D dose distributions. The models received the normalized CT scan, dose prescription, and target and normal tissue contours as inputs. Three models were used to predict the dose distributions for plans in the test set. A radiation oncologist specializing in the treatment of gynecologic cancers scored the test set predictions using a 5-point scale (5, acceptable as-is; 4, prefer minor edits; 3, minor edits needed; 2, major edits needed; and 1, unacceptable). The clinical plans for which the dose predictions indicated that improvements could be made were reoptimized with constraints extracted from the predictions. RESULTS: The predicted dose distributions in the test set were of comparable quality to the clinical plans. The mean voxel-wise dose difference was -0.14 ± 0.46 Gy. The percentage dose differences in the predicted target metrics of D 1 % ${D}_{1{\mathrm{\% }}}$ and D 98 % ${D}_{98{\mathrm{\% }}}$ were -1.05% ± 0.59% and 0.21% ± 0.28%, respectively. The dose differences in the predicted organ at risk mean and maximum doses were -0.30 ± 1.66 Gy and -0.42 ± 2.07 Gy, respectively. A radiation oncologist deemed all of the predicted dose distributions clinically acceptable; 12 received a score of 5, and four received a score of 4. Replanning of flagged plans (five plans) showed that the original plans could be further optimized to give dose distributions close to the predicted dose distributions. CONCLUSIONS: Deep-learning dose prediction can be used to predict high-quality and clinically acceptable dose distributions for VMAT female pelvis plans, which can then be used to identify plans that can be improved with additional optimization.