Markov models for clinical decision-making in radiation oncology: A systematic review

The intrinsic stochasticity of patients' response to treatment is a major consideration for clinical decision-making in radiation therapy. Markov models are powerful tools to capture this stochasticity and render effective treatment decisions. This paper provides an overview of the Markov models for clinical decision analysis in radiation oncology. A comprehensive literature search was conducted within MEDLINE using PubMed, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Only studies published from 2000 to 2023 were considered. Selected publications were summarized in two categories: (i) studies that compare two (or more) fixed treatment policies using Monte Carlo simulation and (ii) studies that seek an optimal treatment policy through Markov Decision Processes (MDPs). Relevant to the scope of this study, 61 publications were selected for detailed review. The majority of these publications (n = 56) focused on comparative analysis of two or more fixed treatment policies using Monte Carlo simulation. Classifications based on cancer site, utility measures and the type of sensitivity analysis are presented. Five publications considered MDPs with the aim of computing an optimal treatment policy; a detailed statement of the analysis and results is provided for each work. As an extension of Markov model-based simulation analysis, MDP offers a flexible framework to identify an optimal treatment policy among a possibly large set of treatment policies. However, the applications of MDPs to oncological decision-making have been understudied, and the full capacity of this framework to render complex optimal treatment decisions warrants further consideration.

Cluster-Based Toxicity Estimation of Osteoradionecrosis Via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification

PURPOSE

Given the limitations of extant models for normal tissue complication probability estimation for osteoradionecrosis (ORN) of the mandible, the purpose of this study was to enrich statistical inference by exploiting structural properties of data and provide a clinically reliable model for ORN risk evaluation through an unsupervised-learning analysis that incorporates the whole radiation dose distribution on the mandible.

METHODS AND MATERIALS

The analysis was conducted on retrospective data of 1259 patients with head and neck cancer treated at The University of Texas MD Anderson Cancer Center between 2005 and 2015. During a minimum 12-month posttherapy follow-up period, 173 patients in this cohort (13.7%) developed ORN (grades I to IV). The (structural) clusters of mandibular dose-volume histograms (DVHs) for these patients were identified using the K-means clustering method. A soft-margin support vector machine was used to determine the cluster borders and partition the dose-volume space. The risk of ORN for each dose-volume region was calculated based on incidence rates and other clinical risk factors.

RESULTS

The K-means clustering method identified 6 clusters among the DVHs. Based on the first 5 clusters, the dose-volume space was partitioned by the soft-margin support vector machine into distinct regions with different risk indices. The sixth cluster entirely overlapped with the others; the region of this cluster was determined by its envelopes. For each region, the ORN incidence rate per preradiation dental extraction status (a statistically significant, nondose related risk factor for ORN) was reported as the corresponding risk index.

CONCLUSIONS

This study presents an unsupervised-learning analysis of a large-scale data set to evaluate the risk of mandibular ORN among patients with head and neck cancer. The results provide a visual risk-assessment tool for ORN (based on the whole DVH and preradiation dental extraction status) as well as a range of constraints for dose optimization under different risk levels.

Dynamic Contrast Enhanced MRI as a Biomarker of Tumor Response and Oncologic Outcomes in Head and Neck Cancer: Results of a Single Institution Prospective Imaging Study

PURPOSE/OBJECTIVE(S)

We aim to determine the correlation between vascular parameters of Dynamic contrast enhanced (DCE) MRIs and tumor response and outcomes in head and neck (HNC) patients treated with definitive radiation therapy (RT).

MATERIALS/METHODS

Eighty-two HNC patients are included in this prospective study in one institute. All patients had malignant head and neck neoplasm indicative of curative- intent treatment. Patients were imaged using MRIs pre-, mid-, and post-RT completion at 8-12 weeks. T2-weighted sequences were used for tumor contouring then it was co-registered to respective DCE images. The response to treatment was checked at mid-radiotherapy (mid-RT) and at the end of RT. Mid-RT MRI was co-registered to baseline images and the manually segmented baseline primary tumor regions of interest were propagated to mid-RT images. Quantitative maps (Ktrans, Kep, Ve and Vp) were generated with the extended Tofts pharmacokinetic models and were used for analysis. These vascular parameters were presented as a mean value and percentile using histogram analysis and the following parameters were extracted using an in-house programming environment script: mean, 5th, 10th, 20th, 30th, 40th, 50th (i.e., median), 60th, 70th, 80th, 90th, 95th percentile. The non-parametric Wilcoxon signed-rank test was used to assess the changes of mid-RT DCE parameters compared to baseline. Recursive partitioning analysis (RPA) was used to identify the delta DCE threshold associated with relapse. We assessed the identified thresholds' correlation with oncological and survival endpoints using Cox regression with and without standard clinical variables.

RESULTS

The median age for patients is 61 years old (33-78 range). Never smokers are 39 (47%), 35 (43%) are former smoker and 8 (10%) are current smoker with a mean value of 14 pack per year and 26 standard deviations. Using AJCC 8th edition, 39 (47%) are stage I and 19 (23%) are stage II and stage III and IV are 15 (18%) and 9 (10%) respectively. HPV positive are 72 (88%). For patients with GTV-P at baseline (n = 60), 11 (18%) had mid-RT CR at the primary site which increased to 50 (83%) post-RT. The LC and RFS for the entire cohort were 91.4%, and 79.2% respectively. In GTV-P, none of the pre-radiotherapy DCE parameters were correlated with LC or RFS. Wilcoxon signed rank test was statistically significant in 80, 90 and 95 percentiles with (p<0.05). RPA analysis identified different thresholds for each DCE parameter, and its inclusions to the multivariate model improved its performance. In GTV-P, RPA analysis identified ΔKtrans 40 percentiles >15.6% at mid-RT as the most significant point. When this value of ΔKtrans added to the multivariate analysis it was associated with a significantly better model performance in RFS (p = 0.00001).

CONCLUSION

DCE parameters are a very promising tool to correlate with response and outcomes in H&N cancer patients. Future work is warranted for external validation of our findings.

Deep Learning Based Prognostic Prediction in Oropharyngeal Cancer Patients Using Multiparametric MRI Inputs

PURPOSE/OBJECTIVE(S)

While prognostic outcomes for oropharyngeal cancer (OPC) patients have improved in recent years, patients still face a non-negligible risk of disease recurrence or death. Accurately predicting post-therapy prognosis would be highly valuable for risk stratification and treatment guidance for OPC patients. Recent studies using PET/CT data have demonstrated the effectiveness of large-scale, end-to-end image-based deep learning (DL) models for predicting progression-free survival (PFS) in OPC patients. Multiparametric MRI (mpMRI), which combines anatomical and functional MRI sequences, has the potential to offer similar results, and has the added advantage of high-frequency longitudinal imaging capabilities, such as through MR-Linac devices. Therefore, this study aimed to develop a DL model using mpMRI data to predict PFS, and to evaluate the impact of anatomical and functional input channels on model performance.

MATERIALS/METHODS

From a large-scale head and neck cancer database at MD Anderson Cancer Center, treatment-naïve OPC patients with available pre-radiotherapy mpMRI imaging were selected for this study. mpMRI images used for this study included T2-weighted images (T2) and apparent diffusion coefficient (ADC) maps. PFS event status was defined as having either a local, regional, or distant failure, and/or death; data were right censored if an event had not occurred. Images were resampled to the T2 resolution, normalized to a [-1,1] scale, and cropped to the field of view of the ADC image for use in DL models. A DL convolutional neural network model based on the DenseNet121 architecture from the Medical Open Network for AI (MONAI) Python package using a negative log-likelihood loss function was implemented. The model used mpMRI images as input channels and 20 output channels representing the different time intervals of the predicted PFS conditional probabilities of surviving that time interval; final PFS in days was obtained by summing the cumulative probability of surviving each interval times the interval duration. A 5-fold cross validation approach was used for model training and evaluation. Separate models using only T2, only ADC, and T2 + ADC channel inputs were compared. Model performance was measured using the C-index.

RESULTS

Out of 1154 patients, 404 met inclusion criteria. The overall PFS event rate was 16%. Median C-index values from the 5-fold cross validation were 0.62, 0.67, and 0.69 for the ADC, T2, and T2+ADC models, respectively.

CONCLUSION

Using large-scale datasets and open-source DL implementations, we find that OPC PFS prediction models using mpMRI data yield modest but comparable performance to existing models (i.e., state-of-the-art reference performance using PET/CT). Moreover, combining mpMRI channels may increase the performance of models for OPC prognostic prediction. Future work will involve integration of additional timepoints, additional mpMRI images, clinical variables, and saliency maps.

Assessment of Dynamic Contrast Enhanced (DCE) MRI for Detection of Radiotherapy Induced Alteration in Mandibular Vasculature

PURPOSE/OBJECTIVE(S)

We aim to determine the kinetics of DCE-MRI changes in various mandibular risk volumes based on radiation (RT) dose received.

MATERIALS/METHODS

Eighty-eight head and neck cancer (HNC) patients (Pts) who underwent definitive RT were enrolled in this prospective study after IRB approval and informed consent. Images were acquired at pre-RT (Baseline), 3 weeks after RT start date (Mid-RT), 3 mos post-RT (PostRT1), and 6 mos post-RT (PostRT2). Manually segmented mandibular volumes on T2-weighted images were propagated to co-registered DCE-MRIs. Planning CTs and dose grids were also co-registered to corresponding baseline T2 images to create 3-D dose subvolumes. These were used to create 3 risk subvolumes; <30 Gy, 30-50 Gy, and >50 Gy ROIs. DCE images of different timepoints (TPs) were deformably co-registered and the dose subvolumes were propagated to each TP. We used the extended-Tofts model to generate the vascular quantitative maps (Ktrans and Ve). Each subvolume histogram parameters were extracted at each TP. Wilcoxon Signed Rank test was used to compare the changes at different TPs compared to baseline. We classified Pts' delta parameters at different TPs -based on our prior extensive QA assessment- into Pts with stable vascular profile (±25% change), Pts with significant increase (>25% change) and Pts with significant decrease (<-25%). Chi-square test was used to assess the change at different TPs.

RESULTS

For <30 Gy subvolumes, there were no significant changes (p > 0.05) in the studied DCE parameters at all TPs except a significant decrease (p < 0.001) in median Ktrans at PostRT2. For 30-50 Gy subvolumes, there was a significant increase in median Ktrans that started at MidRT (p = 0.006) and continued at PostRT1 (p = 0.04) but recovered to baseline values at PostRT2. Median Ve on the other hand only showed significant increase at PostRT1 (p = 0.001), but other TPs were not significantly different compared to baseline. Similarly, subvolumes >50 Gy showed same kinetics as in 30-50 Gy with significant increase of Ktrans at MidRT and PostRT1 and significant increase in Ve in only PostRT1 (P <0.05). For <30 Gy, there was significant increase in the number of Pts with stable or decrease in Ktrans at PostRT2 compared to earlier TPs (70% vs. 60% at PostRT1 and 54% at MidRT p = 0.003). 30-50 Gy subvolumes showed similar profile like <30 Gy with significant increase in the percentage of Pts with recovery at PostRT2. However, for >50 Gy, there was no significant increase in the number of Pts who recovered at PostRT2 (p = 0.3). Ve showed no significant increase in the percentage of Pts with recovery at different TPs (p > 0.05).

CONCLUSION

Results showed that for all dose mandibular subvolumes, there is an acute vascular insult that tends to recover at +6 months post-RT except for a selective group of patients who continue to have persistence of the vascular insult at high dose subvolumes. These findings are of importance for future selection of high risk population for prophylactic intervention against osteoradionecrosis.

Temporal characterization of acute pain and toxicity kinetics during radiation therapy for head and neck cancer. A retrospective study

Objectives

Pain during Radiation Therapy (RT) for oral cavity/oropharyngeal cancer (OC/OPC) is a clinical challenge due to its multifactorial etiology and variable management. The objective of this study was to define complex pain profiles through temporal characterization of pain descriptors, physiologic state, and RT-induced toxicities for pain trajectories understanding.

Materials and methods

Using an electronic health record registry, 351 OC/OPC patients treated with RT from 2013 to 2021 were included. Weekly numeric scale pain scores, pain descriptors, vital signs, physician-reported toxicities, and analgesics were analyzed using linear mixed effect models and Spearman's correlation. Area under the pain curve (AUCpain) was calculated to measure pain burden over time.

Results

Median pain scores increased from 0 during the weekly visit (WSV)-1 to 5 during WSV-7. By WSV-7, 60% and 74% of patients reported mouth and throat pain, respectively, with a median pain score of 5. Soreness and burning pain peaked during WSV-6/7 (51%). Median AUCpain was 16% (IQR (9.3-23)), and AUCpain significantly varied based on gender, tumor site, surgery, drug use history, and pre-RT pain. A temporal increase in mucositis and dermatitis, declining mean bodyweight (-7.1%; P < 0.001) and mean arterial pressure (MAP) 6.8 mmHg; P < 0.001 were detected. Pulse rate was positively associated while weight and MAP were negatively associated with pain over time (P < 0.001).

Conclusion

This study provides insight on in-depth characterization and associations between dynamic pain, physiologic, and toxicity kinetics. Our findings support further needs of optimized pain control through temporal data-driven clinical decision support systems for acute pain management.

Quality assurance assessment of intra-acquisition diffusion-weighted and T2-weighted magnetic resonance imaging registration and contour propagation for head and neck cancer radiotherapy

BACKGROUND/PURPOSE

Adequate image registration of anatomical and functional magnetic resonance imaging (MRI) scans is necessary for MR-guided head and neck cancer (HNC) adaptive radiotherapy planning. Despite the quantitative capabilities of diffusion-weighted imaging (DWI) MRI for treatment plan adaptation, geometric distortion remains a considerable limitation. Therefore, we systematically investigated various deformable image registration (DIR) methods to co-register DWI and T2-weighted (T2W) images.

MATERIALS/METHODS

We compared three commercial (ADMIRE, Velocity, Raystation) and three open-source (Elastix with default settings [Elastix Default], Elastix with parameter set 23 [Elastix 23], Demons) post-acquisition DIR methods applied to T2W and DWI MRI images acquired during the same imaging session in twenty immobilized HNC patients. In addition, we used the non-registered images (None) as a control comparator. Ground-truth segmentations of radiotherapy structures (tumour and organs at risk) were generated by a physician expert on both image sequences. For each registration approach, structures were propagated from T2W to DWI images. These propagated structures were then compared with ground-truth DWI structures using the Dice similarity coefficient and mean surface distance.

RESULTS

19 left submandibular glands, 18 right submandibular glands, 20 left parotid glands, 20 right parotid glands, 20 spinal cords, and 12 tumours were delineated. Most DIR methods took <30 s to execute per case, with the exception of Elastix 23 which took ∼458 s to execute per case. ADMIRE and Elastix 23 demonstrated improved performance over None for all metrics and structures (Bonferroni-corrected p < 0.05), while the other methods did not. Moreover, ADMIRE and Elastix 23 significantly improved performance in individual and pooled analysis compared to all other methods.

CONCLUSIONS

The ADMIRE DIR method offers improved geometric performance with reasonable execution time so should be favoured for registering T2W and DWI images acquired during the same scan session in HNC patients. These results are important to ensure the appropriate selection of registration strategies for MR-guided radiotherapy.

Cluster-Based Toxicity Estimation of Osteoradionecrosis via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification

Purpose

Given the limitations of extant models for normal tissue complication probability estimation for osteoradionecrosis (ORN) of the mandible, the purpose of this study was to enrich statistical inference by exploiting structural properties of data and provide a clinically reliable model for ORN risk evaluation through an unsupervised-learning analysis.

Materials and Methods

The analysis was conducted on retrospective data of 1,259 head and neck cancer (HNC) patients treated at the University of Texas MD Anderson Cancer Center between 2005 and 2015. The (structural) clusters of mandibular dose-volume histograms (DVHs) were identified through the K-means clustering method. A soft-margin support vector machine (SVM) was used to determine the cluster borders and partition the dose-volume space. The risk of ORN for each dose-volume region was calculated based on the clinical risk factors and incidence rates.

Results

The K-means clustering method identified six clusters among the DVHs. Based on the first five clusters, the dose-volume space was partitioned almost perfectly by the soft-margin SVM into distinct regions with different risk indices. The sixth cluster overlapped the others entirely; the region of this cluster was determined by its envelops. These regions and the associated risk indices provide a range of constraints for dose optimization under different risk levels.

Conclusion

This study presents an unsupervised-learning analysis of a large-scale data set to evaluate the risk of mandibular ORN among HNC patients. The results provide a visual risk-assessment tool (based on the whole DVH) and a spectrum of dose constraints for radiation planning.

Dysphagia and shortness-of-breath as markers for treatment failure and survival in oropharyngeal cancer after radiation

BACKGROUND

Post-treatment symptoms are a focal point of follow-up visits for head and neck cancer patients. While symptoms such as dysphagia and shortness-of-breath early after treatment may motivate additional work up, their precise association with disease control and survival outcomes is not well established.

METHODS

This prospective data cohort study of 470 oropharyngeal cancer patients analyzed patient-reported swallowing, choking and shortness-of-breath symptoms at 3-to-6 months following radiotherapy to evaluate their association with overall survival and disease control. Associations between the presence of moderate-to-severe swallowing, choking and mild-to-severe shortness-of-breath and treatment outcomes were analyzed via Cox regression and Kaplan-Meier. The main outcome was overall survival (OS), and the secondary outcomes were local, regional, and distant disease control.

RESULTS

The majority of patients (91.3%) were HPV-positive. Median follow-up time was 31.7 months (IQR: 21.9-42.1). Univariable analysis showed significant associations between OS and all three symptoms of swallowing, choking, and shortness-of-breath. A composite variable integrating scores of all three symptoms was significantly associated with OS on multivariable Cox regression (p = 0.0018). Additionally, this composite symptom score showed the best predictive value for OS (c-index = 0.75). Multivariable analysis also revealed that the composite score was significantly associated with local (p = 0.044) and distant (p = 0.035) recurrence/progression. Notably, the same significant associations with OS were seen for HPV-positive only subset analysis (p < 0.01 for all symptoms).

CONCLUSIONS

Quantitative patient-reported measures of dysphagia and shortness-of-breath 3-to-6 months post-treatment are significant predictors of OS and disease recurrence/progression in OPC patients and in HPV-positive OPC only.

Muscle and adipose tissue segmentations at the third cervical vertebral level in patients with head and neck cancer

The accurate determination of sarcopenia is critical for disease management in patients with head and neck cancer (HNC). Quantitative determination of sarcopenia is currently dependent on manually-generated segmentations of skeletal muscle derived from computed tomography (CT) cross-sectional imaging. This has prompted the increasing utilization of machine learning models for automated sarcopenia determination. However, extant datasets currently do not provide the necessary manually-generated skeletal muscle segmentations at the C3 vertebral level needed for building these models. In this data descriptor, a set of 394 HNC patients were selected from The Cancer Imaging Archive, and their skeletal muscle and adipose tissue was manually segmented at the C3 vertebral level using sliceOmatic. Subsequently, using publicly disseminated Python scripts, we generated corresponding segmentations files in Neuroimaging Informatics Technology Initiative format. In addition to segmentation data, additional clinical demographic data germane to body composition analysis have been retrospectively collected for these patients. These data are a valuable resource for studying sarcopenia and body composition analysis in patients with HNC.

Deep learning auto-segmentation of cervical skeletal muscle for sarcopenia analysis in patients with head and neck cancer

Background/Purpose

Sarcopenia is a prognostic factor in patients with head and neck cancer (HNC). Sarcopenia can be determined using the skeletal muscle index (SMI) calculated from cervical neck skeletal muscle (SM) segmentations. However, SM segmentation requires manual input, which is time-consuming and variable. Therefore, we developed a fully-automated approach to segment cervical vertebra SM.

Materials/Methods

390 HNC patients with contrast-enhanced CT scans were utilized (300-training, 90-testing). Ground-truth single-slice SM segmentations at the C3 vertebra were manually generated. A multi-stage deep learning pipeline was developed, where a 3D ResUNet auto-segmented the C3 section (33 mm window), the middle slice of the section was auto-selected, and a 2D ResUNet auto-segmented the auto-selected slice. Both the 3D and 2D approaches trained five sub-models (5-fold cross-validation) and combined sub-model predictions on the test set using majority vote ensembling. Model performance was primarily determined using the Dice similarity coefficient (DSC). Predicted SMI was calculated using the auto-segmented SM cross-sectional area. Finally, using established SMI cutoffs, we performed a Kaplan-Meier analysis to determine associations with overall survival.

Results

Mean test set DSC of the 3D and 2D models were 0.96 and 0.95, respectively. Predicted SMI had high correlation to the ground-truth SMI in males and females (r>0.96). Predicted SMI stratified patients for overall survival in males (log-rank p = 0.01) but not females (log-rank p = 0.07), consistent with ground-truth SMI.

Conclusion

We developed a high-performance, multi-stage, fully-automated approach to segment cervical vertebra SM. Our study is an essential step towards fully-automated sarcopenia-related decision-making in patients with HNC.

Progression Free Survival Prediction for Head and Neck Cancer Using Deep Learning Based on Clinical and PET/CT Imaging Data

Determining progression-free survival (PFS) for head and neck squamous cell carcinoma (HNSCC) patients is a challenging but pertinent task that could help stratify patients for improved overall outcomes. PET/CT images provide a rich source of anatomical and metabolic data for potential clinical biomarkers that would inform treatment decisions and could help improve PFS. In this study, we participate in the 2021 HECKTOR Challenge to predict PFS in a large dataset of HNSCC PET/CT images using deep learning approaches. We develop a series of deep learning models based on the DenseNet architecture using a negative log-likelihood loss function that utilizes PET/CT images and clinical data as separate input channels to predict PFS in days. Internal model validation based on 10-fold cross-validation using the training data (N = 224) yielded C-index values up to 0.622 (without) and 0.842 (with) censoring status considered in C-index computation, respectively. We then implemented model ensembling approaches based on the training data cross-validation folds to predict the PFS of the test set patients (N = 101). External validation on the test set for the best ensembling method yielded a C-index value of 0.694, placing 2^nd in the competition. Our results are a promising example of how deep learning approaches can effectively utilize imaging and clinical data for medical outcome prediction in HNSCC, but further work in optimizing these processes is needed.

Combining Tumor Segmentation Masks with PET/CT Images and Clinical Data in a Deep Learning Framework for Improved Prognostic Prediction in Head and Neck Squamous Cell Carcinoma

PET/CT images provide a rich data source for clinical prediction models in head and neck squamous cell carcinoma (HNSCC). Deep learning models often use images in an end-to-end fashion with clinical data or no additional input for predictions. However, in the context of HNSCC, the tumor region of interest may be an informative prior in the generation of improved prediction performance. In this study, we utilize a deep learning framework based on a DenseNet architecture to combine PET images, CT images, primary tumor segmentation masks, and clinical data as separate channels to predict progression-free survival (PFS) in days for HNSCC patients. Through internal validation (10-fold cross-validation) based on a large set of training data provided by the 2021 HECKTOR Challenge, we achieve a mean C-index of 0.855 ± 0.060 and 0.650 ± 0.074 when observed events are and are not included in the C-index calculation, respectively. Ensemble approaches applied to cross-validation folds yield C-index values up to 0.698 in the independent test set (external validation), leading to a 1^st place ranking on the competition leaderboard. Importantly, the value of the added segmentation mask is underscored in both internal and external validation by an improvement of the C-index when compared to models that do not utilize the segmentation mask. These promising results highlight the utility of including segmentation masks as additional input channels in deep learning pipelines for clinical outcome prediction in HNSCC.

Evaluation of deep learning-based multiparametric MRI oropharyngeal primary tumor auto-segmentation and investigation of input channel effects: Results from a prospective imaging registry

BACKGROUND/PURPOSE

Oropharyngeal cancer (OPC) primary gross tumor volume (GTVp) segmentation is crucial for radiotherapy. Multiparametric MRI (mpMRI) is increasingly used for OPC adaptive radiotherapy but relies on manual segmentation. Therefore, we constructed mpMRI deep learning (DL) OPC GTVp auto-segmentation models and determined the impact of input channels on segmentation performance.

MATERIALS/METHODS

GTVp ground truth segmentations were manually generated for 30 OPC patients from a clinical trial. We evaluated five mpMRI input channels (T2, T1, ADC, Ktrans, Ve). 3D Residual U-net models were developed and assessed using leave-one-out cross-validation. A baseline T2 model was compared to mpMRI models (T2 + T1, T2 + ADC, T2 + Ktrans, T2 + Ve, all five channels [ALL]) primarily using the Dice similarity coefficient (DSC). False-negative DSC (FND), false-positive DSC, sensitivity, positive predictive value, surface DSC, Hausdorff distance (HD), 95% HD, and mean surface distance were also assessed. For the best model, ground truth and DL-generated segmentations were compared through a blinded Turing test using three physician observers.

RESULTS

Models yielded mean DSCs from 0.71 ± 0.12 (ALL) to 0.73 ± 0.12 (T2 + T1). Compared to the T2 model, performance was significantly improved for FND, sensitivity, surface DSC, HD, and 95% HD for the T2 + T1 model (p < 0.05) and for FND for the T2 + Ve and ALL models (p < 0.05). No model demonstrated significant correlations between tumor size and DSC (p > 0.05). Most models demonstrated significant correlations between tumor size and HD or Surface DSC (p < 0.05), except those that included ADC or Ve as input channels (p > 0.05). On average, there were no significant differences between ground truth and DL-generated segmentations for all observers (p > 0.05).

CONCLUSION

DL using mpMRI provides reasonably accurate segmentations of OPC GTVp that may be comparable to ground truth segmentations generated by clinical experts. Incorporating additional mpMRI channels may increase the performance of FND, sensitivity, surface DSC, HD, and 95% HD, and improve model robustness to tumor size.

RNA2DNAlign: nucleotide resolution allele asymmetries through quantitative assessment of RNA and DNA paired sequencing data

We introduce RNA2DNAlign, a computational framework for quantitative assessment of allele counts across paired RNA and DNA sequencing datasets. RNA2DNAlign is based on quantitation of the relative abundance of variant and reference read counts, followed by binomial tests for genotype and allelic status at SNV positions between compatible sequences. RNA2DNAlign detects positions with differential allele distribution, suggesting asymmetries due to regulatory/structural events. Based on the type of asymmetry, RNA2DNAlign outlines positions likely to be implicated in RNA editing, allele-specific expression or loss, somatic mutagenesis or loss-of-heterozygosity (the first three also in a tumor-specific setting). We applied RNA2DNAlign on 360 matching normal and tumor exomes and transcriptomes from 90 breast cancer patients from TCGA. Under high-confidence settings, RNA2DNAlign identified 2038 distinct SNV sites associated with one of the aforementioned asymetries, the majority of which have not been linked to functionality before. The performance assessment shows very high specificity and sensitivity, due to the corroboration of signals across multiple matching datasets. RNA2DNAlign is freely available from http://github.com/HorvathLab/NGS as a self-contained binary package for 64-bit Linux systems.