Search

PURPOSE: Automation and computer assistance can support quality assurance tasks in radiotherapy. Retrospective image review requires significant human resources, and automation of image review remains a noteworthy missing element in previous work. Here, we present initial findings from a proof-of-concept clinical implementation of an AI-assisted review of CBCT registrations used for patient setup. METHODS: An automated pipeline was developed and executed nightly, utilizing python scripts to interact with the clinical database through DICOM networking protocol and automate data retrieval and analysis. A previously developed artificial intelligence (AI) algorithm scored CBCT setup registrations based on misalignment likelihood, using a scale from 0 (most unlikely) through 1 (most likely). Over a 45-day period, 1357 pre-treatment CBCT registrations from 197 patients were retrieved and analyzed by the pipeline. Daily summary reports of the previous days registrations were produced. Initial action levels targeted 10% of cases to highlight for in-depth physics review. A validation subset of 100 cases was scored by three independent observers to characterize AI-model performance. RESULTS: Following an ROC analysis, a global threshold for model predictions of 0.87 was determined, with a sensitivity of 100% and specificity of 82%. Inspecting the observer scores for the stratified validation dataset showed a statistically significant correlation between observer scores and model predictions. CONCLUSION: In this work, we describe the implementation of an automated AI-analysis pipeline for daily quantitative analysis of CBCT-guided patient setup registrations. The AI-model was validated against independent expert observers, and appropriate action levels were determined to minimize false positives without sacrificing sensitivity. Case studies demonstrate the potential benefits of such a pipeline to bolster quality and safety programs in radiotherapy. To the authors knowledge, there are no previous works performing AI-assisted assessment of pre-treatment CBCT-based patient alignment.

Nonsense-mediated RNA decay (NMD) degrades transcripts carrying premature termination codons. NMD is thought to prevent the synthesis of toxic truncated proteins. However, whether loss of NMD results in widespread production of truncated proteins is unclear. A human genetic disease, facioscapulohumeral muscular dystrophy (FSHD), features acute inhibition of NMD upon expression of the disease-causing transcription factor, DUX4. Using a cell-based model of FSHD, we show production of truncated proteins from physiological NMD targets and find that RNA-binding proteins are enriched for aberrant truncations. The NMD isoform of one RNA-binding protein, SRSF3, is translated to produce a stable truncated protein, which is detected in FSHD patient-derived myotubes. Ectopic expression of truncated SRSF3 confers toxicity, and its downregulation is cytoprotective. Our results delineate the genome-scale impact of NMD loss. This widespread production of potentially deleterious truncated proteins has implications for FSHD biology as well as other genetic diseases where NMD is therapeutically modulated.

The HIV epidemic is still one of the world's most serious public health challenges, affecting about 38 million people worldwide, especially in sub-Saharan African and Southeast Asian countries. In recent years, tests have been developed to discriminate recent from long-term infection in HIV-infected populations, and these tools can help identify new outbreaks and networks of transmission and target prevention and treatment plans. New rapid tests for recent infection are being deployed in point-of-care settings; however, quality assurance programs need to be implemented to ensure consistency and reliability of the results. We have developed a dried tube specimen (DTS) stabilized with disaccharide trehalose as a quality control reagent for rapid recency testing that can be stored unrefrigerated prior to reconstitution at temperatures up to 37°C for up to 12 weeks. Analysis of 10 trehalose-stabilized DTSs showed that they maintained the same recency classification in all of the samples stored at 4°C and 37°C up to 12 weeks and at 56°C for 2 weeks, while the DTSs prepared without trehalose changed their classification from long-term to recent or recent to negative after storage at 37°C for 12 weeks. Development of DTS quality control reagents will facilitate proficiency and training programs, particularly in settings without cold chain capability in field environments. IMPORTANCE Implementation of stabilized dried tube specimens (DTSs) for quality control and training would facilitate HIV recency programs, especially in point-of-care settings without cold chain availability. This study shows that addition of the disaccharide trehalose to DTSs prior to drying the samples increased stability of the samples across a range of temperatures. This finding provides an affordable way to increase the availability of these key reagents for quality control in resource-constrained settings.

BACKGROUND: Cardiopulmonary exercise testing is an increasingly common test and is considered the accepted standard for assessing exercise capacity. Quantifying variability is important to assess the instrument for quality control purposes. Though guidelines recommend biologic control testing, there are minimal data on how to do it. We sought to describe variability for oxygen consumption (V̇O2 ), carbon dioxide production (V̇CO2 ), and minute ventilation (V̇E) at various work rates under steady-state conditions in multiple subjects over a 1-y period to provide a practical approach to assess and perform biologic control testing. METHODS: We performed a single-center, prospective study with 4 healthy subjects, 2 men and 2 women. Subjects performed constant work rate exercise tests for 6 min each at 25-100 W intervals on a computer-controlled cycle ergometer. Data were averaged over the last 120 s at each work rate to reflect stepwise steady-state conditions. Descriptive statistics, including the mean, median, range, SD, and coefficient of variation (CoV) are reported for each individual across the 4 work rates and all repetitions. As these data were normative, z-scores were utilized, and a value greater than ± 1.96 z-scores was used to define significant test variability. RESULTS: Subjects performed 16-39 biocontrol studies over 1-y. The mean CoV for all subjects in V̇O2 was 6.59%, V̇CO2 was 6.41%, and V̇E was 6.32%. The ± 1.96 z-scores corresponded to a 9.4-18.1% change in V̇O2 , a 9.6-18.1% change in V̇CO2 , and a 9-21.5% change in V̇E across the 4 workloads. CONCLUSIONS: We report long-term variability for steady-state measurement of V̇O2 , V̇CO2 , and V̇E obtained during biocontrol testing. Utilizing ± 1.96 z-scores allows one to determine if a result exceeds expected variability, which may warrant investigation of the instrument.

As one of the two highly conserved cellular degradation systems, autophagy plays a critical role in regulation of protein, lipid, and organelle quality control and cellular homeostasis. This evolutionarily conserved pathway singles out intracellular substrates for elimination via encapsulation within a double-membrane vesicle and delivery to the lysosome for degradation. Multiple cancers disrupt normal regulation of autophagy and hijack its degradative ability to remodel their proteome, reprogram their metabolism, and adapt to environmental challenges, making the autophagy-lysosome system a prime target for anti-cancer interventions. Here, we discuss the roles of autophagy in tumor progression, including cancer-specific mechanisms of autophagy regulation and the contribution of tumor and host autophagy in metabolic regulation, immune evasion, and malignancy. We further discuss emerging proteomics-based approaches for systematic profiling of autophagosome-lysosome composition and contents. Together, these approaches are uncovering new features and functions of autophagy, leading to more effective strategies for targeting this pathway in cancer.

ObjectiveTo describe and quantify the effect of quality control (QC) metrics to increase testing efficiency in a high-complexity, Clinical Laboratory Improvement Amendments-certified laboratory that uses amplicon-based, next generation sequencing for the clinical detection of SARS-CoV-2. To enable rapid scalability to several thousands of specimens per day without fully automated platforms, we developed internal QC methods to ensure high-accuracy testing.MethodsWe implemented procedures to increase efficiency by applying the Lean Six Sigma model into our sequencing-based COVID-19 detection.ResultsThe application of the Lean Six Sigma model increased laboratory efficiency by reducing errors, allowing for a higher testing volume to be met with minimal staffing. Furthermore, these improvements resulted in an improved turnaround time.ConclusionLean Six Sigma model execution has increased laboratory efficiency by decreasing critical testing errors and has prepared the laboratory for future scaling up to 50,000 tests per day.

Structural hippocampal abnormalities are common in many neurological and psychiatric disorders, and variation in hippocampal measures is related to cognitive performance and other complex phenotypes such as stress sensitivity. Hippocampal subregions are increasingly studied, as automated algorithms have become available for mapping and volume quantification. In the context of the Enhancing Neuro Imaging Genetics through Meta Analysis Consortium, several Disease Working Groups are using the FreeSurfer software to analyze hippocampal subregion (subfield) volumes in patients with neurological and psychiatric conditions along with data from matched controls. In this overview, we explain the algorithm's principles, summarize measurement reliability studies, and demonstrate two additional aspects (subfield autocorrelation and volume/reliability correlation) with illustrative data. We then explain the rationale for a standardized hippocampal subfield segmentation quality control (QC) procedure for improved pipeline harmonization. To guide researchers to make optimal use of the algorithm, we discuss how global size and age effects can be modeled, how QC steps can be incorporated and how subfields may be aggregated into composite volumes. This discussion is based on a synopsis of 162 published neuroimaging studies (01/2013-12/2019) that applied the FreeSurfer hippocampal subfield segmentation in a broad range of domains including cognition and healthy aging, brain development and neurodegeneration, affective disorders, psychosis, stress regulation, neurotoxicity, epilepsy, inflammatory disease, childhood adversity and posttraumatic stress disorder, and candidate and whole genome (epi-)genetics. Finally, we highlight points where FreeSurfer-based hippocampal subfield studies may be optimized.

IntroductionAcademic trauma institutions rely on fracture databases as research and quality control tools. Frequently, these databases are populated by trainees, but the completeness and accuracy of such databases has not yet been evaluated. The purpose of this study is to determine the capture rate of a resident-populated database in collecting extremity fractures and to determine the accuracy of assigned Orthopaedic Trauma Association (OTA) classifications.Materials and methodsA retrospective study was performed at a level 1 trauma center of all adult patients who underwent treatment for extremity fractures after an emergency department or inpatient consultation. A 20% random sample was taken from these entries and compared to a resident-populated fracture database designed to capture the same patients. For all matching records containing a resident-assigned OTA classification, relevant imaging was blindly reviewed by a trauma fellowship-trained orthopedic attending surgeon for fracture pattern classification. Resident OTA classifications were compared to this gold standard to determine overall accuracy rate.ResultsThree hundred eighteen (80%) out of 400 entries were captured by the resident-populated database. Two hundred thirty-one of these 318 entries contained an OTA classification. One hundred fifty-three (66%) of these 231 entries demonstrated concordance between resident and attending assigned OTA classifications. On subgroup analysis, 133 (70%) of the 190 lower extremity classifications were accurately identified as compared to just 20 (49%) of the 41 upper extremity classifications (p = 0.009). Seventy-nine (65%) of the 121 end segment fractures showed agreement versus 42 (67%) of the 63 diaphyseal injury patterns (p = 0.85). Accuracy of classification did not significantly vary by resident year of training (p = 0.142).ConclusionTrainee generated databases at academic institutions may be subject to incomplete data entry and inaccurate fracture classifications. Quality control measures should be instituted to ensure accuracy in such databases if efforts are invested with the expectation of useful information.

The world's first total-body PET scanner with an axial field of view (AFOV) of 194 cm is now in clinical and research use at our institution. The uEXPLORER PET/CT system is the first commercially available total-body PET scanner. Here we present a detailed physical characterization of this scanner based on National Electrical Manufacturers Association (NEMA) NU 2-2018 along with a new set of measurements devised to appropriately characterize the total-body AFOV. Methods: Sensitivity, count-rate performance, time-of-flight resolution, spatial resolution, and image quality were evaluated following the NEMA NU 2-2018 protocol. Additional measurements of sensitivity and count-rate capabilities more representative of total-body imaging were performed using extended-geometry phantoms based on the world-average human height (∼165 cm). Lastly, image quality throughout the long AFOV was assessed with the NEMA image quality (IQ) phantom imaged at 5 axial positions and over a range of expected total-body PET imaging conditions (low dose, delayed imaging, short scan duration). Results: Our performance evaluation demonstrated that the scanner provides a very high sensitivity of 174 kcps/MBq, a count-rate performance with a peak noise-equivalent count rate of approximately 2 Mcps for total-body imaging, and good spatial resolution capabilities for human imaging (≤3.0 mm in full width at half maximum near the center of the AFOV). Excellent IQ, excellent contrast recovery, and low noise properties were illustrated across the AFOV in both NEMA IQ phantom evaluations and human imaging examples. Conclusion: In addition to standard NEMA NU 2-2018 characterization, a new set of measurements based on extending NEMA NU 2-2018 phantoms and experiments was devised to characterize the physical performance of the first total-body PET system. The rationale for these extended measurements was evident from differences in sensitivity, count-rate-activity relationships, and noise-equivalent count-rate limits imposed by differences in dead time and randoms fraction between the NEMA NU 2 70-cm phantoms and the more representative total-body imaging phantoms. Overall, the uEXPLORER PET system provides ultra-high sensitivity that supports excellent spatial resolution and IQ throughout the field of view in both phantom and human imaging.

Whole-genome sequencing (WGS), a powerful tool for detecting novel coding and non-coding disease-causing variants, has largely been applied to clinical diagnosis of inherited disorders. Here we leveraged WGS data in up to 62,653 ethnically diverse participants from the NHLBI Trans-Omics for Precision Medicine (TOPMed) program and assessed statistical association of variants with seven red blood cell (RBC) quantitative traits. We discovered 14 single variant-RBC trait associations at 12 genomic loci, which have not been reported previously. Several of the RBC trait-variant associations (RPN1, ELL2, MIDN, HBB, HBA1, PIEZO1, and G6PD) were replicated in independent GWAS datasets imputed to the TOPMed reference panel. Most of these discovered variants are rare/low frequency, and several are observed disproportionately among non-European Ancestry (African, Hispanic/Latino, or East Asian) populations. We identified a 3 bp indel p.Lys2169del (g.88717175_88717177TCT[4]) (common only in the Ashkenazi Jewish population) of PIEZO1, a gene responsible for the Mendelian red cell disorder hereditary xerocytosis (MIM: 194380), associated with higher mean corpuscular hemoglobin concentration (MCHC). In stepwise conditional analysis and in gene-based rare variant aggregated association analysis, we identified several of the variants in HBB, HBA1, TMPRSS6, and G6PD that represent the carrier state for known coding, promoter, or splice site loss-of-function variants that cause inherited RBC disorders. Finally, we applied base and nuclease editing to demonstrate that the sentinel variant rs112097551 (nearest gene RPN1) acts through a cis-regulatory element that exerts long-range control of the gene RUVBL1 which is essential for hematopoiesis. Together, these results demonstrate the utility of WGS in ethnically diverse population-based samples and gene editing for expanding knowledge of the genetic architecture of quantitative hematologic traits and suggest a continuum between complex trait and Mendelian red cell disorders.

To our knowledge, no study has evaluated the quality of control groups in randomised controlled trials of multiple myeloma. We aimed to do a systematic review of randomised controlled trials of multiple myeloma to ascertain the quality of the control groups used. PubMed (MEDLINE), Embase, Cochrane Controlled Register of Trials, and CinicalTrials.gov were searched for articles of randomised controlled trials of multiple myeloma based in the USA that initiated participant enrolment between Jan 1, 2010, and June 30, 2020. A control group regimen was considered to be inferior if a previous randomised controlled trial had shown an improved progression-free survival versus the control group before enrolment. Of 49 identified randomised controlled trials, seven (14%) began enrolling patients into inferior control groups after an existing superior regimen to the control had already been published. Nine (18%) of the 49 trials continued enrolment on substandard control groups after data emerged during the study enrolment period. The median time that newer data emerged regarding inferiority of the control group from the time a trial first enrolled a patient was 13 months (IQR 8-29 months). 12 (75%) of these 16 randomised controlled trials are published, and nine (75%) of the 12 published trials had overlapping investigators with trials that had previously shown the inferiority of the control group being used. Greater scrutiny on the quality of control groups in randomised controlled trials of multiple myeloma is needed.

The Trans-Omics for Precision Medicine (TOPMed) programme seeks to elucidate the genetic architecture and biology of heart, lung, blood and sleep disorders, with the ultimate goal of improving diagnosis, treatment and prevention of these diseases. The initial phases of the programme focused on whole-genome sequencing of individuals with rich phenotypic data and diverse backgrounds. Here we describe the TOPMed goals and design as well as the available resources and early insights obtained from the sequence data. The resources include a variant browser, a genotype imputation server, and genomic and phenotypic data that are available through dbGaP (Database of Genotypes and Phenotypes)1. In the first 53,831 TOPMed samples, we detected more than 400 million single-nucleotide and insertion or deletion variants after alignment with the reference genome. Additional previously undescribed variants were detected through assembly of unmapped reads and customized analysis in highly variable loci. Among the more than 400 million detected variants, 97% have frequencies of less than 1% and 46% are singletons that are present in only one individual (53% among unrelated individuals). These rare variants provide insights into mutational processes and recent human evolutionary history. The extensive catalogue of genetic variation in TOPMed studies provides unique opportunities for exploring the contributions of rare and noncoding sequence variants to phenotypic variation. Furthermore, combining TOPMed haplotypes with modern imputation methods improves the power and reach of genome-wide association studies to include variants down to a frequency of approximately 0.01%.

Newly-translated glycoproteins in the endoplasmic reticulum (ER) often undergo cycles of chaperone binding and release in order to assist in folding. Quality control is required to distinguish between proteins that have completed native folding, those that have yet to fold, and those that have misfolded. Using quantitative modeling, we explore how the design of the quality-control pathway modulates its efficiency. Our results show that an energy-consuming cyclic quality-control process, similar to the observed physiological system, outperforms alternative designs. The kinetic parameters that optimize the performance of this system drastically change with protein production levels, while remaining relatively insensitive to the protein folding rate. Adjusting only the degradation rate, while fixing other parameters, allows the pathway to adapt across a range of protein production levels, aligning with in vivo measurements that implicate the release of degradation-associated enzymes as a rapid-response system for perturbations in protein homeostasis. The quantitative models developed here elucidate design principles for effective glycoprotein quality control in the ER, improving our mechanistic understanding of a system crucial to maintaining cellular health.

BackgroundBoth RNA-Seq and sample freeze-thaw are ubiquitous. However, knowledge about the impact of freeze-thaw on downstream analyses is limited. The lack of common quality metrics that are sufficiently sensitive to freeze-thaw and RNA degradation, e.g. the RNA Integrity Score, makes such assessments challenging.ResultsHere we quantify the impact of repeated freeze-thaw cycles on the reliability of RNA-Seq by examining poly(A)-enriched and ribosomal RNA depleted RNA-seq from frozen leukocytes drawn from a toddler Autism cohort. To do so, we estimate the relative noise, or percentage of random counts, separating technical replicates. Using this approach we measured noise associated with RIN and freeze-thaw cycles. As expected, RIN does not fully capture sample degradation due to freeze-thaw. We further examined differential expression results and found that three freeze-thaws should extinguish the differential expression reproducibility of similar experiments. Freeze-thaw also resulted in a 3' shift in the read coverage distribution along the gene body of poly(A)-enriched samples compared to ribosomal RNA depleted samples, suggesting that library preparation may exacerbate freeze-thaw-induced sample degradation.ConclusionThe use of poly(A)-enrichment for RNA sequencing is pervasive in library preparation of frozen tissue, and thus, it is important during experimental design and data analysis to consider the impact of repeated freeze-thaw cycles on reproducibility.

The purpose of this study was to compare various multisource configurations applied to cone beam CT (CBCT) using phantom imaging and Monte Carlo simulations. Image quality, scatter, and dose were evaluated in both overlapping (large cone angle) and collimated (small cone angle) configurations for CBCT. Four x-ray tube configurations were considered: traditional one source, three source overlapping, six source overlapping, and six source collimated. Image quality was evaluated on a prototype breast CT system using the following five phantoms: a Defrise phantom, a previously reported CBCT QA phantom (Corgi), a polyethylene cylinder, and two anthropomorphic phantoms (hand and knee). Scatter contamination and radiation dose were evaluated using Monte Carlo simulations of a voxelized polyethylene cylinder. The modulation of the Defrise phantom disks on average was 2.7X greater for the six source collimated configuration than the six source overlapping configuration. The data lost from cone beam artifact (spatial domain) and the null cone (frequency domain) in the overlapping configuration were completely recovered using the collimated configuration. The maximum scatter-to-primary ratio (SPR) for the overlapping configuration was 0.81 and the maximum SPR for the collimated configuration was 0.26. The average dose and maximum dose was 4X less in the collimated six source configuration when compared with the overlapping configurations. The maximum dose for the overlapping configurations (one, three & six) remained constant, but the average dose for the multisource (three & six source) overlapping configurations increased 25% when compared to the one source configuration. Use of a collimated multisource x-ray tube configuration was shown to provide significant improvements in image quality throughout the cone-beam geometry field-of-view, reduction in scatter contamination, and more efficient use of dose in comparison to both the traditional CBCT geometry with a single source and the overlapping multisource configurations.

New genome assemblies have been arriving at a rapidly increasing pace, thanks to decreases in sequencing costs and improvements in third-generation sequencing technologies1-3. For example, the number of vertebrate genome assemblies currently in the NCBI (National Center for Biotechnology Information) database4 increased by more than 50% to 1,485 assemblies in the year from July 2018 to July 2019. In addition to this influx of assemblies from different species, new human de novo assemblies5 are being produced, which enable the analysis of not only small polymorphisms, but also complex, large-scale structural differences between human individuals and haplotypes. This coming era and its unprecedented amount of data offer the opportunity to uncover many insights into genome evolution but also present challenges in how to adapt current analysis methods to meet the increased scale. Cactus6, a reference-free multiple genome alignment program, has been shown to be highly accurate, but the existing implementation scales poorly with increasing numbers of genomes, and struggles in regions of highly duplicated sequences. Here we describe progressive extensions to Cactus to create Progressive Cactus, which enables the reference-free alignment of tens to thousands of large vertebrate genomes while maintaining high alignment quality. We describe results from an alignment of more than 600 amniote genomes, which is to our knowledge the largest multiple vertebrate genome alignment created so far.

Oxylipins are potent lipid mediators involved in a variety of physiological processes. Their profiling has the potential to provide a wealth of information regarding human health and disease and is a promising technology for translation into clinical applications. However, results generated by independent groups are rarely comparable, which increases the need for the implementation of internationally agreed upon protocols. We performed an interlaboratory comparison for the MS-based quantitative analysis of total oxylipins. Five independent laboratories assessed the technical variability and comparability of 133 oxylipins using a harmonized and standardized protocol, common biological materials (i.e., seven quality control plasmas), standard calibration series, and analytical methods. The quantitative analysis was based on a standard calibration series with isotopically labeled internal standards. Using the standardized protocol, the technical variance was within ±15% for 73% of oxylipins; however, most epoxy fatty acids were identified as critical analytes due to high variabilities in concentrations. The comparability of concentrations determined by the laboratories was examined using consensus value estimates and unsupervised/supervised multivariate analysis (i.e., principal component analysis and partial least squares discriminant analysis). Interlaboratory variability was limited and did not interfere with our ability to distinguish the different plasmas. Moreover, all laboratories were able to identify similar differences between plasmas. In summary, we show that by using a standardized protocol for sample preparation, low technical variability can be achieved. Harmonization of all oxylipin extraction and analysis steps led to reliable, reproducible, and comparable oxylipin concentrations in independent laboratories, allowing the generation of biologically meaningful oxylipin patterns.

Ribosome-associated quality control (RQC) pathways protect cells from toxicity caused by incomplete protein products resulting from translation of damaged or problematic mRNAs. Extensive work in yeast has identified highly conserved mechanisms that lead to degradation of faulty mRNA and partially synthesized polypeptides. Here we used CRISPR-Cas9-based screening to search for additional RQC strategies in mammals. We found that failed translation leads to specific inhibition of translation initiation on that message. This negative feedback loop is mediated by two translation inhibitors, GIGYF2 and 4EHP. Model substrates and growth-based assays established that inhibition of additional rounds of translation acts in concert with known RQC pathways to prevent buildup of toxic proteins. Inability to block translation of faulty mRNAs and subsequent accumulation of partially synthesized polypeptides could explain the neurodevelopmental and neuropsychiatric disorders observed in mice and humans with compromised GIGYF2 function.

PurposeThe purpose of this study is to explore knowledge-based organ-at-risk dose estimation for intracavitary brachytherapy planning for cervical cancer. Using established external-beam knowledge-based dose-volume histogram (DVH) estimation methods, we sought to predict bladder, rectum, and sigmoid D2cc for tandem and ovoid treatments.Methods and materialsA total of 136 patients with loco-regionally advanced cervical cancer treated with 456 (356:100 training:validation ratio) CT-based tandem and ovoid brachytherapy fractions were analyzed. Single fraction prescription doses were 5.5-8 Gy with dose criteria for the high-risk clinical target volume, bladder, rectum, and sigmoid. DVH estimations were obtained by subdividing training set organs-at-risk into high-risk clinical target volume boundary distance subvolumes and computing cohort-averaged differential DVHs. Full DVH estimation was then performed on the training and validation sets. Model performance was quantified by ΔD2cc = D2cc(actual)-D2cc(predicted) (mean and standard deviation). ΔD2cc between training and validation sets were compared with a Student's t test (p < 0.01 significant). Categorical variables (physician, fraction-number, total fractions, and case complexity) that might explain model variance were examined using an analysis of variance test (Bonferroni-corrected p < 0.01 threshold).ResultsTraining set deviations were bladder ΔD2cc = -0.04 ± 0.61 Gy, rectum ΔD2cc = 0.02 ± 0.57 Gy, and sigmoid ΔD2cc = -0.05 ± 0.52 Gy. Model predictions on validation set did not statistically differ: bladder ΔD2cc = -0.02 ± 0.46 Gy (p = 0.80), rectum ΔD2cc = -0.007 ± 0.47 Gy (p = 0.53), and sigmoid ΔD2cc = -0.07 ± 0.47 Gy (p = 0.70). The only significant categorical variable was the attending physician for bladder and rectum ΔD2cc. CONCLUSION: A simple boundary distance-driven knowledge-based DVH estimation exhibited promising results in predicting critical brachytherapy dose metrics. Future work will examine the utility of these predictions for quality control and automated brachytherapy planning.