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.

Automating the treatment planning process for 3D-conformal pediatric craniospinal irradiation therapy.

PURPOSE: Pediatric patients with medulloblastoma in low- and middle-income countries (LMICs) are most treated with 3D-conformal photon craniospinal irradiation (CSI), a time-consuming, complex treatment to plan, especially in resource-constrained settings. Therefore, we developed and tested a 3D-conformal CSI autoplanning tool for varying patient lengths. METHODS AND MATERIALS: Autocontours were generated with a deep learning model trained:tested (80:20 ratio) on 143 pediatric medulloblastoma CT scans (patient ages: 2-19 years, median = 7 years). Using the verified autocontours, the autoplanning tool generated two lateral brain fields matched to a single spine field, an extended single spine field, or two matched spine fields. Additional spine subfields were added to optimize the corresponding dose distribution. Feathering was implemented (yielding nine to 12 fields) to give a composite plan. Each planning approach was tested on six patients (ages 3-10 years). A pediatric radiation oncologist assessed clinical acceptability of each autoplan. RESULTS: The autocontoured structures' average Dice similarity coefficient ranged from .65 to .98. The average V95 for the brain/spinal canal for single, extended, and multi-field spine configurations was 99.9% ± 0.06%/99.9% ± 0.10%, 99.9% ± 0.07%/99.4% ± 0.30%, and 99.9% ± 0.06%/99.4% ± 0.40%, respectively. The average maximum dose across all field configurations to the brainstem, eyes (L/R), lenses (L/R), and spinal cord were 23.7 ± 0.08, 24.1 ± 0.28, 13.3 ± 5.27, and 25.5 ± 0.34 Gy, respectively (prescription = 23.4 Gy/13 fractions). Of the 18 plans tested, all were scored as clinically acceptable as-is or clinically acceptable with minor, time-efficient edits preferred or required. No plans were scored as clinically unacceptable. CONCLUSION: The autoplanning tool successfully generated pediatric CSI plans for varying patient lengths in 3.50 ± 0.4 minutes on average, indicating potential for an efficient planning aid in a resource-constrained settings.

Resection cavity auto-contouring for patients with pediatric medulloblastoma using only CT information.

PURPOSE: Target delineation for radiation therapy is a time-consuming and complex task. Autocontouring gross tumor volumes (GTVs) has been shown to increase efficiency. However, there is limited literature on post-operative target delineation, particularly for CT-based studies. To this end, we trained a CT-based autocontouring model to contour the post-operative GTV of pediatric patients with medulloblastoma. METHODS: One hundred four retrospective pediatric CT scans were used to train a GTV auto-contouring model. Eighty patients were then preselected for contour visibility, continuity, and location to train an additional model. Each GTV was manually annotated with a visibility score based on the number of slices with a visible GTV (1 = < 25%, 2 = 25-50%, 3 = > 50-75%, and 4 = > 75-100%). Contrast and the contrast-to-noise ratio (CNR) were calculated for the GTV contour with respect to a cropped background image. Both models were tested on the original and pre-selected testing sets. The resulting surface and overlap metrics were calculated comparing the clinical and autocontoured GTVs and the corresponding clinical target volumes (CTVs). RESULTS: Eighty patients were pre-selected to have a continuous GTV within the posterior fossa. Of these, 7, 41, 21, and 11 were visibly scored as 4, 3, 2, and 1, respectively. The contrast and CNR removed an additional 11 and 20 patients from the dataset, respectively. The Dice similarity coefficients (DSC) were 0.61 ± 0.29 and 0.67 ± 0.22 on the models without pre-selected training data and 0.55 ± 13.01 and 0.83 ± 0.17 on the models with pre-selected data, respectively. The DSC on the CTV expansions were 0.90 ± 0.13. CONCLUSION: We successfully automatically contoured continuous GTVs within the posterior fossa on scans that had contrast > ± 10 HU. CT-Based auto-contouring algorithms have potential to positively impact centers with limited MRI access.

Random Forest Modeling of Acute Toxicity in Anal Cancer: Effects of Peritoneal Cavity Contouring Approaches on Model Performance.

PURPOSE: Our purpose was to analyze the effect on gastrointestinal (GI) toxicity models when their dose-volume metrics predictors are derived from segmentations of the peritoneal cavity after different contouring approaches. METHODS AND MATERIALS: A random forest machine learning approach was used to predict acute grade ≥3 GI toxicity from dose-volume metrics and clinicopathologic factors for 246 patients (toxicity incidence = 9.5%) treated with definitive chemoradiation for squamous cell carcinoma of the anus. Three types of random forest models were constructed based on different bowel bag segmentation approaches: (1) physician-delineated after Radiation Therapy Oncology Group (RTOG) guidelines, (2) autosegmented by a deep learning model (nnU-Net) following RTOG guidelines, and (3) autosegmented but spanning the entire bowel space. Each model type was evaluated using repeated cross-validation (100 iterations; 50%/50% training/test split). The performance of the models was assessed using area under the precision-recall curve (AUPRC) and the receiver operating characteristic curve (AUROCC), as well as optimal F1 score. RESULTS: When following RTOG guidelines, the models based on the nnU-Net auto segmentations (mean values: AUROCC, 0.71 ± 0.07; AUPRC, 0.42 ± 0.09; F1 score, 0.46 ± 0.08) significantly outperformed (P < .001) those based on the physician-delineated contours (mean values: AUROCC, 0.67 ± 0.07; AUPRC, 0.34 ± 0.08; F1 score, 0.36 ± 0.07). When spanning the entire bowel space, the performance of the autosegmentation models improved considerably (mean values: AUROCC, 0.87 ± 0.05; AUPRC, 0.70 ± 0.09; F1 score, 0.68 ± 0.09). CONCLUSIONS: Random forest models were superior at predicting acute grade ≥3 GI toxicity when based on RTOG-defined bowel bag autosegmentations rather than physician-delineated contours. Models based on autosegmentations spanning the entire bowel space show further considerable improvement in model performance. The results of this study should be further validated using an external data set.

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.

Automated contouring and statistical process control for plan quality in a breast clinical trial.

Background and purpose: Automatic review of breast plan quality for clinical trials is time-consuming and has some unique challenges due to the lack of target contours for some planning techniques. We propose using an auto-contouring model and statistical process control to independently assess planning consistency in retrospective data from a breast radiotherapy clinical trial. Materials and methods: A deep learning auto-contouring model was created and tested quantitatively and qualitatively on 104 post-lumpectomy patients' computed tomography images (nnUNet; train/test: 80/20). The auto-contouring model was then applied to 127 patients enrolled in a clinical trial. Statistical process control was used to assess the consistency of the mean dose to auto-contours between plans and treatment modalities by setting control limits within three standard deviations of the data's mean. Two physicians reviewed plans outside the limits for possible planning inconsistencies. Results: Mean Dice similarity coefficients comparing manual and auto-contours was above 0.7 for breast clinical target volume, supraclavicular and internal mammary nodes. Two radiation oncologists scored 95% of contours as clinically acceptable. The mean dose in the clinical trial plans was more variable for lymph node auto-contours than for breast, with a narrower distribution for volumetric modulated arc therapy than for 3D conformal treatment, requiring distinct control limits. Five plans (5%) were flagged and reviewed by physicians: one required editing, two had clinically acceptable variations in planning, and two had poor auto-contouring. Conclusions: An automated contouring model in a statistical process control framework was appropriate for assessing planning consistency in a breast radiotherapy clinical trial.

Identification of cell type-specific methylation signals in bulk whole genome bisulfite sequencing data.

BACKGROUND: The traditional approach to studying the epigenetic mechanism CpG methylation in tissue samples is to identify regions of concordant differential methylation spanning multiple CpG sites (differentially methylated regions). Variation limited to single or small numbers of CpGs has been assumed to reflect stochastic processes. To test this, we developed software, Cluster-Based analysis of CpG methylation (CluBCpG), and explored variation in read-level CpG methylation patterns in whole genome bisulfite sequencing data. RESULTS: Analysis of both human and mouse whole genome bisulfite sequencing datasets reveals read-level signatures associated with cell type and cell type-specific biological processes. These signatures, which are mostly orthogonal to classical differentially methylated regions, are enriched at cell type-specific enhancers and allow estimation of proportional cell composition in synthetic mixtures and improved prediction of gene expression. In tandem, we developed a machine learning algorithm, Precise Read-Level Imputation of Methylation (PReLIM), to increase coverage of existing whole genome bisulfite sequencing datasets by imputing CpG methylation states on individual sequencing reads. PReLIM both improves CluBCpG coverage and performance and enables identification of novel differentially methylated regions, which we independently validate. CONCLUSIONS: Our data indicate that, rather than stochastic variation, read-level CpG methylation patterns in tissue whole genome bisulfite sequencing libraries reflect cell type. Accordingly, these new computational tools should lead to an improved understanding of epigenetic regulation by DNA methylation.

DNA methylation in AgRP neurons regulates voluntary exercise behavior in mice.

DNA methylation regulates cell type-specific gene expression. Here, in a transgenic mouse model, we show that deletion of the gene encoding DNA methyltransferase Dnmt3a in hypothalamic AgRP neurons causes a sedentary phenotype characterized by reduced voluntary exercise and increased adiposity. Whole-genome bisulfite sequencing (WGBS) and transcriptional profiling in neuronal nuclei from the arcuate nucleus of the hypothalamus (ARH) reveal differentially methylated genomic regions and reduced expression of AgRP neuron-associated genes in knockout mice. We use read-level analysis of WGBS data to infer putative ARH neural cell types affected by the knockout, and to localize promoter hypomethylation and increased expression of the growth factor Bmp7 to AgRP neurons, suggesting a role for aberrant TGF-ß signaling in the development of this phenotype. Together, these data demonstrate that DNA methylation in AgRP neurons is required for their normal epigenetic development and neuron-specific gene expression profiles, and regulates voluntary exercise behavior.

A genomic atlas of systemic interindividual epigenetic variation in humans.

BACKGROUND: DNA methylation is thought to be an important determinant of human phenotypic variation, but its inherent cell type specificity has impeded progress on this question. At exceptional genomic regions, interindividual variation in DNA methylation occurs systemically. Like genetic variants, systemic interindividual epigenetic variants are stable, can influence phenotype, and can be assessed in any easily biopsiable DNA sample. We describe an unbiased screen for human genomic regions at which interindividual variation in DNA methylation is not tissue-specific. RESULTS: For each of 10 donors from the NIH Genotype-Tissue Expression (GTEx) program, CpG methylation is measured by deep whole-genome bisulfite sequencing of genomic DNA from tissues representing the three germ layer lineages: thyroid (endoderm), heart (mesoderm), and brain (ectoderm). We develop a computational algorithm to identify genomic regions at which interindividual variation in DNA methylation is consistent across all three lineages. This approach identifies 9926 correlated regions of systemic interindividual variation (CoRSIVs). These regions, comprising just 0.1% of the human genome, are inter-correlated over long genomic distances, associated with transposable elements and subtelomeric regions, conserved across diverse human ethnic groups, sensitive to periconceptional environment, and associated with genes implicated in a broad range of human disorders and phenotypes. CoRSIV methylation in one tissue can predict expression of associated genes in other tissues. CONCLUSIONS: In addition to charting a previously unexplored molecular level of human individuality, this atlas of human CoRSIVs provides a resource for future population-based investigations into how interindividual epigenetic variation modulates risk of disease.

Epigenetic supersimilarity of monozygotic twin pairs.

BACKGROUND: Monozygotic twins have long been studied to estimate heritability and explore epigenetic influences on phenotypic variation. The phenotypic and epigenetic similarities of monozygotic twins have been assumed to be largely due to their genetic identity. RESULTS: Here, by analyzing data from a genome-scale study of DNA methylation in monozygotic and dizygotic twins, we identified genomic regions at which the epigenetic similarity of monozygotic twins is substantially greater than can be explained by their genetic identity. This "epigenetic supersimilarity" apparently results from locus-specific establishment of epigenotype prior to embryo cleavage during twinning. Epigenetically supersimilar loci exhibit systemic interindividual epigenetic variation and plasticity to periconceptional environment and are enriched in sub-telomeric regions. In case-control studies nested in a prospective cohort, blood DNA methylation at these loci years before diagnosis is associated with risk of developing several types of cancer. CONCLUSIONS: These results establish a link between early embryonic epigenetic development and adult disease. More broadly, epigenetic supersimilarity is a previously unrecognized phenomenon that may contribute to the phenotypic similarity of monozygotic twins.