Optimal Treatment Selection in Sequential Systemic and Locoregional Therapy of Oropharyngeal Squamous Carcinomas: Deep Q-Learning With a Patient-Physician Digital Twin Dyad.

BACKGROUND: Currently, selection of patients for sequential versus concurrent chemotherapy and radiation regimens lacks evidentiary support and it is based on locally optimal decisions for each step. OBJECTIVE: We aim to optimize the multistep treatment of patients with head and neck cancer and predict multiple patient survival and toxicity outcomes, and we develop, apply, and evaluate a first application of deep Q-learning (DQL) and simulation to this problem. METHODS: The treatment decision DQL digital twin and the patient's digital twin were created, trained, and evaluated on a data set of 536 patients with oropharyngeal squamous cell carcinoma with the goal of, respectively, determining the optimal treatment decisions with respect to survival and toxicity metrics and predicting the outcomes of the optimal treatment on the patient. Of the data set of 536 patients, the models were trained on a subset of 402 (75%) patients (split randomly) and evaluated on a separate set of 134 (25%) patients. Training and evaluation of the digital twin dyad was completed in August 2020. The data set includes 3-step sequential treatment decisions and complete relevant history of the patient cohort treated at MD Anderson Cancer Center between 2005 and 2013, with radiomics analysis performed for the segmented primary tumor volumes. RESULTS: On the test set, we found mean 87.35% (SD 11.15%) and median 90.85% (IQR 13.56%) accuracies in treatment outcome prediction, matching the clinicians' outcomes and improving the (predicted) survival rate by +3.73% (95% CI -0.75% to 8.96%) and the dysphagia rate by +0.75% (95% CI -4.48% to 6.72%) when following DQL treatment decisions. CONCLUSIONS: Given the prediction accuracy and predicted improvement regarding the medically relevant outcomes yielded by this approach, this digital twin dyad of the patient-physician dynamic treatment problem has the potential of aiding physicians in determining the optimal course of treatment and in assessing its outcomes.

The impact of induction and/or concurrent chemoradiotherapy on acute and late patient-reported symptoms in oropharyngeal cancer: Application of a mixed-model analysis of a prospective observational cohort registry.

BACKGROUND: The goal of this study was to comprehensively investigate the association of chemotherapy with trajectories of acute symptom development and late symptom recovery in patients with oropharyngeal cancer (OPC) by comparing symptom burden between induction chemotherapy followed by concurrent chemoradiotherapy (ICRT), concurrent chemo-radiotherapy (CRT), or radiotherapy (RT) alone. METHODS: Among a registry of 717 patients with OPC, the 28-item patient-reported MD Anderson Symptom Inventory-Head and Neck Module (MDASI-HN) symptoms were collected prospectively at baseline, weekly during RT, and 1.5, 3 to 6, 12, and 18 to 24 months after RT. The effect of the treatment regimen (ICRT, CRT, and RT alone) was examined with mixed-model analyses for the acute and late period. In the CRT cohort, the chemotherapy agent relationship with symptoms was investigated. RESULTS: Chemoradiation (ICRT/CRT) compared with RT alone resulted in significantly higher acute symptom scores in the majority of MDASI-HN symptoms (ie, 21 out of 28). No late symptom differences between treatment with or without chemotherapy were observed that were not attributable to ICRT. Nausea was lower for CRT with carboplatin than for CRT with cisplatin; cetuximab was associated with particularly higher scores for acute and late skin, mucositis, and 6 other symptoms. The addition of ICRT compared with CRT or RT alone was associated with a significant increase in numbness and shortness of breath. CONCLUSION: The addition of chemotherapy to definitive RT for OPC patients was associated with significantly worse acute symptom outcomes compared with RT alone, which seems to attenuate in the late posttreatment period. Moreover, induction chemotherapy was specifically associated with worse numbness and shortness of breath during and after treatment. LAY SUMMARY: Chemotherapy is frequently used in addition to radiotherapy cancer treatment, yet the (added) effect on treatment-induced over time is not comprehensively investigated This study shows that chemotherapy adds to the symptom severity reported by patients, especially during treatment.

The effect of certolizumab drug concentration and anti-drug antibodies on TNF neutralisation.

OBJECTIVES: Tumour necrosis factor (TNF) inhibitors like certolizumab, elicit an immunogenic response leading to the formation of anti-drug antibodies (ADAs). We sought to mechanistically investigate the relationship between certolizumab concentrations, ADAs, and the effective TNF neutralising capacity in sera of rheumatoid arthritis (RA) patients. TNF neutralising capacity of certolizumab was compared to the neutralising capacity of adalimumab. METHODS: Serum samples were collected from 40 consecutive certolizumab-treated RA patients at baseline and 4, 16, 28 and 52 weeks after treatment initiation [Dutch Trial Register NTR (Nederlands Trial Register) Trial NL2824 no. 2965]. Certolizumab concentration and ADA titre were measured with a certolizumab bridging enzyme-linked immunosorbent assay (ELISA) and a drug-tolerant radioimmunoassay (RIA), respectively. TNF neutralisation by certolizumab and adalimumab, in presence or absence of ADAs, was analysed with the TNF-sensitive WEHI bioassay. RESULTS: Despite a high incidence of ADAs during one year of follow-up (65%; 26/40 patients), certolizumab levels of >10 µg/ml were measured in most patients. The capacity for TNF neutralisation highly correlated with certolizumab serum concentration, whereas no association with ADAs was observed. Similar results were obtained for adalimumab. The relative in vitro neutralising potency was higher for certolizumab compared to adalimumab. CONCLUSIONS: Anti-certolizumab antibodies were detected in a large proportion of patients, but in most cases where ADAs were detected, certolizumab was also present in high concentrations, directly correlating with in vitro neutralising capacity. These results indicate that measurement of certolizumab drug levels, rather than ADAs, have direct clinical significance.

Deep learning-based outcome prediction using PET/CT and automatically predicted probability maps of primary tumor in patients with oropharyngeal cancer.

BACKGROUND AND OBJECTIVE: Recently, deep learning (DL) algorithms showed to be promising in predicting outcomes such as distant metastasis-free survival (DMFS) and overall survival (OS) using pre-treatment imaging in head and neck cancer. Gross Tumor Volume of the primary tumor (GTVp) segmentation is used as an additional channel in the input to DL algorithms to improve model performance. However, the binary segmentation mask of the GTVp directs the focus of the network to the defined tumor region only and uniformly. DL models trained for tumor segmentation have also been used to generate predicted tumor probability maps (TPM) where each pixel value corresponds to the degree of certainty of that pixel to be classified as tumor. The aim of this study was to explore the effect of using TPM as an extra input channel of CT- and PET-based DL prediction models for oropharyngeal cancer (OPC) patients in terms of local control (LC), regional control (RC), DMFS and OS. METHODS: We included 399 OPC patients from our institute that were treated with definitive (chemo)radiation. For each patient, CT and PET scans and GTVp contours, used for radiotherapy treatment planning, were collected. We first trained a previously developed 2.5D DL framework for tumor probability prediction by 5-fold cross validation using 131 patients. Then, a 3D ResNet18 was trained for outcome prediction using the 3D TPM as one of the possible inputs. The endpoints were LC, RC, DMFS, and OS. We performed 3-fold cross validation on 168 patients for each endpoint using different combinations of image modalities as input. The final prediction in the test set (100) was obtained by averaging the predictions of the 3-fold models. The C-index was used to evaluate the discriminative performance of the models. RESULTS: The models trained replacing the GTVp contours with the TPM achieved the highest C-indexes for LC (0.74) and RC (0.60) prediction. For OS, using the TPM or the GTVp as additional image modality resulted in comparable C-indexes (0.72 and 0.74). CONCLUSIONS: Adding predicted TPMs instead of GTVp contours as an additional input channel for DL-based outcome prediction models improved model performance for LC and RC.

Probability maps for deep learning-based head and neck tumor segmentation: Graphical User Interface design and test.

BACKGROUND: The different tumor appearance of head and neck cancer across imaging modalities, scanners, and acquisition parameters accounts for the highly subjective nature of the manual tumor segmentation task. The variability of the manual contours is one of the causes of the lack of generalizability and the suboptimal performance of deep learning (DL) based tumor auto-segmentation models. Therefore, a DL-based method was developed that outputs predicted tumor probabilities for each PET-CT voxel in the form of a probability map instead of one fixed contour. The aim of this study was to show that DL-generated probability maps for tumor segmentation are clinically relevant, intuitive, and a more suitable solution to assist radiation oncologists in gross tumor volume segmentation on PET-CT images of head and neck cancer patients. METHOD: A graphical user interface (GUI) was designed, and a prototype was developed to allow the user to interact with tumor probability maps. Furthermore, a user study was conducted where nine experts in tumor delineation interacted with the interface prototype and its functionality. The participants' experience was assessed qualitatively and quantitatively. RESULTS: The interviews with radiation oncologists revealed their preference for using a rainbow colormap to visualize tumor probability maps during contouring, which they found intuitive. They also appreciated the slider feature, which facilitated interaction by allowing the selection of threshold values to create single contours for editing and use as a starting point. Feedback on the prototype highlighted its excellent usability and positive integration into clinical workflows. CONCLUSIONS: This study shows that DL-generated tumor probability maps are explainable, transparent, intuitive and a better alternative to the single output of tumor segmentation models.

PET/CT based transformer model for multi-outcome prediction in oropharyngeal cancer.

BACKGROUND AND PURPOSE: To optimize our previously proposed TransRP, a model integrating CNN (convolutional neural network) and ViT (Vision Transformer) designed for recurrence-free survival prediction in oropharyngeal cancer and to extend its application to the prediction of multiple clinical outcomes, including locoregional control (LRC), Distant metastasis-free survival (DMFS) and overall survival (OS). MATERIALS AND METHODS: Data was collected from 400 patients (300 for training and 100 for testing) diagnosed with oropharyngeal squamous cell carcinoma (OPSCC) who underwent (chemo)radiotherapy at University Medical Center Groningen. Each patient's data comprised pre-treatment PET/CT scans, clinical parameters, and clinical outcome endpoints, namely LRC, DMFS and OS. The prediction performance of TransRP was compared with CNNs when inputting image data only. Additionally, three distinct methods (m1-3) of incorporating clinical predictors into TransRP training and one method (m4) that uses TransRP prediction as one parameter in a clinical Cox model were compared. RESULTS: TransRP achieved higher test C-index values of 0.61, 0.84 and 0.70 than CNNs for LRC, DMFS and OS, respectively. Furthermore, when incorporating TransRP's prediction into a clinical Cox model (m4), a higher C-index of 0.77 for OS was obtained. Compared with a clinical routine risk stratification model of OS, our model, using clinical variables, radiomics and TransRP prediction as predictors, achieved larger separations of survival curves between low, intermediate and high risk groups. CONCLUSION: TransRP outperformed CNN models for all endpoints. Combining clinical data and TransRP prediction in a Cox model achieved better OS prediction.

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.

3D deep learning Normal Tissue Complication Probability model to predict late xerostomia in head and neck cancer patients.

BACKGROUND AND PURPOSE: Conventional normal tissue complication probability (NTCP) models for head and neck cancer (HNC) patients are typically based on single-value variables, which for radiation-induced xerostomia are baseline xerostomia and mean salivary gland doses. This study aims to improve the prediction of late xerostomia by utilizing 3D information from radiation dose distributions, CT imaging, organ-at-risk segmentations, and clinical variables with deep learning (DL). MATERIALS AND METHODS: An international cohort of 1208 HNC patients from two institutes was used to train and twice validate DL models (DCNN, EfficientNet-v2, and ResNet) with 3D dose distribution, CT scan, organ-at-risk segmentations, baseline xerostomia score, sex, and age as input. The NTCP endpoint was moderate-to-severe xerostomia 12 months post-radiotherapy. The DL models' prediction performance was compared to a reference model: a recently published xerostomia NTCP model that used baseline xerostomia score and mean salivary gland doses as input. Attention maps were created to visualize the focus regions of the DL predictions. Transfer learning was conducted to improve the DL model performance on the external validation set. RESULTS: All DL-based NTCP models showed better performance (AUCtest=0.78 - 0.79) than the reference NTCP model (AUCtest=0.74) in the independent test. Attention maps showed that the DL model focused on the major salivary glands, particularly the stem cell-rich region of the parotid glands. DL models obtained lower external validation performance (AUCexternal=0.63) than the reference model (AUCexternal=0.66). After transfer learning on a small external subset, the DL model (AUCtl, external=0.66) performed better than the reference model (AUCtl, external=0.64). CONCLUSION: DL-based NTCP models performed better than the reference model when validated in data from the same institute. Improved performance in the external dataset was achieved with transfer learning, demonstrating the need for multicenter training data to realize generalizable DL-based NTCP models.

Late-xerostomia prediction model based on 18F-FDG PET image biomarkers of the main salivary glands.

BACKGROUND AND PURPOSE: Recently, a comprehensive xerostomia prediction model was published, based on baseline xerostomia, mean dose to parotid glands (PG) and submandibular glands (SMG). Previously, PET imaging biomarkers (IBMs) of PG were shown to improve xerostomia prediction. Therefore, this study aimed to explore the potential improvement of the additional PET-IBMs from both PG and SMG to the recent comprehensive xerostomia prediction model (i.e., the reference model). MATERIALS AND METHODS: Totally, 540 head and neck cancer patients were split into training and validation cohorts. PET-IBMs from the PG and SMG, were selected using bootstrapped forward selection based on the reference model. The IBMs from both the PG and SMG with the highest selection frequency were added to the reference model, resulting in a PG-IBM model and a SMG-IBM model which were combined into a composite model. Model performance was assessed using the area under the curve (AUC). Likelihood ratio test compared the predictive performance between the reference model and models including IBMs. RESULTS: The final selected PET-IBMs were 90th percentile of the PG SUV and total energy of the SMG SUV. The additional two PET-IBMs in the composite model improved the predictive performance of the reference model significantly. The AUC of the reference model and the composite model were 0.67 and 0.69 in the training cohort, and 0.71 and 0.73 in the validation cohort, respectively. CONCLUSION: The composite model including two additional PET-IBMs from PG and SMG improved the predictive performance of the reference xerostomia model significantly, facilitating a more personalized prediction approach.

Reducing and controlling metabolic active tumor volume prior to CAR T-cell infusion can improve survival outcomes in patients with large B-cell lymphoma.

Bridging therapy before CD19-directed chimeric antigen receptor (CAR) T-cell infusion is frequently applied in patients with relapsed or refractory Large B-cell lymphoma (r/r LBCL). This study aimed to assess the influence of quantified MATV and MATV-dynamics, between pre-apheresis (baseline) and pre-lymphodepleting chemotherapy (pre-LD) MATV, on CAR T-cell outcomes and toxicities in patients with r/r LBCL. MATVs were calculated semi-automatically at baseline (n = 74) and pre-LD (n = 68) in patients with r/r LBCL who received axicabtagene ciloleucel. At baseline, patients with a low MATV (< 190 cc) had a better time to progression (TTP) and overall survival (OS) compared to high MATV patients (p < 0.001). High MATV patients who remained stable or reduced upon bridging therapy showed a significant improvement in TTP (p = 0.041) and OS (p = 0.015), compared to patients with a high pre-LD MATV (> 480 cc). Furthermore, high MATV baseline was associated with severe cytokine release syndrome (CRS, p = 0.001). In conclusion, patients with low baseline MATV had the best TTP/OS and effective reduction or controlling MATV during bridging improved survival outcomes in patients with a high baseline MATV, providing rationale for the use of more aggressive bridging regimens.

Belimumab concentration measurements using a homologous anti-idiotype immunoassay.

Monitoring belimumab concentrations in patients can be a valuable tool for assessing treatment response and for personalizing drug doses. Various assay formats may be used to measure concentrations of therapeutic monoclonal antibodies. A particularly useful format involves the use of anti-idiotype monoclonal antibodies, selected to be highly specific to the antibody of interest. Here, we describe the development of a specific, high-affinity anti-idiotype antibody to belimumab, and the application of this antibody in a homologous sandwich ELISA to measure belimumab concentrations.

METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII.

PURPOSE: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies. METHODS: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated. RESULT: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community. CONCLUSION: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers. CRITICAL RELEVANCE STATEMENT: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning. KEY POINTS: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score ( https://metricsscore.github.io/metrics/METRICS.html ) and a repository created to collect feedback from the radiomics community ( https://github.com/metricsscore/metrics ).

Drug-tolerant detection of anti-drug antibodies in an antigen-binding assay using europium chelate fluorescence.

Accurate anti-drug antibody (ADA) measurements in patient sera requires dissociation of ADA-drug complexes combined with sensitive and specific ADA detection. Bridging type immunoassays are often used despite several disadvantages associated with this approach. A good drug-tolerant alternative is the acid-dissociation radioimmunoassay (ARIA), but this method is not easily implemented in most labs as specialized facilities are required for working with radioactive materials. We describe an innovative method for ADA detection that combines the advantages of antigen binding tests like the ARIA with the convenience of regular immunoassays. This acid-dissociation lanthanide-fluorescence immunoassay (ALFIA) involves dissociation of ADA-drug complexes, followed by binding to an europium-labeled drug derivative and subsequently an IgG pulldown on Sepharose beads. After europium elution, detection is achieved by measuring time-resolved fluorescence originating from europium chelate complexes. We measured anti-adalimumab ADA levels in sera of 94 rheumatoid arthritis patients using the ALFIA and showed this method to be highly drug tolerant, sensitive and specific for anti-adalimumab ADAs.

Semi-automated 18F-FDG PET segmentation methods for tumor volume determination in Non-Hodgkin lymphoma patients: a literature review, implementation and multi-threshold evaluation.

In the treatment of Non-Hodgkin lymphoma (NHL), multiple therapeutic options are available. Improving outcome predictions are essential to optimize treatment. The metabolic active tumor volume (MATV) has shown to be a prognostic factor in NHL. It is usually retrieved using semi-automated thresholding methods based on standardized uptake values (SUV), calculated from 18F-Fluorodeoxyglucose Positron Emission Tomography (18F-FDG PET) images. However, there is currently no consensus method for NHL. The aim of this study was to review literature on different segmentation methods used, and to evaluate selected methods by using an in house created software tool. A software tool, MUltiple SUV Threshold (MUST)-segmenter was developed where tumor locations are identified by placing seed-points on the PET images, followed by subsequent region growing. Based on a literature review, 9 SUV thresholding methods were selected and MATVs were extracted. The MUST-segmenter was utilized in a cohort of 68 patients with NHL. Differences in MATVs were assessed with paired t-tests, and correlations and distributions figures. High variability and significant differences between the MATVs based on different segmentation methods (p < 0.05) were observed in the NHL patients. Median MATVs ranged from 35 to 211 cc. No consensus for determining MATV is available based on the literature. Using the MUST-segmenter with 9 selected SUV thresholding methods, we demonstrated a large and significant variation in MATVs. Identifying the most optimal segmentation method for patients with NHL is essential to further improve predictions of toxicity, response, and treatment outcomes, which can be facilitated by the MUST-segmenter.

Comparison of Machine-Learning and Deep-Learning Methods for the Prediction of Osteoradionecrosis Resulting From Head and Neck Cancer Radiation Therapy.

Purpose: Deep-learning (DL) techniques have been successful in disease-prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine-learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of patients with HNC. Methods and Materials: Patients who received HNC radiation therapy at the University of Texas MD Anderson Cancer Center from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. The ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. The DL models were based on ResNet, DenseNet, and autoencoder-based architectures. The DL models used each participant's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models' prediction performance was evaluated by training the DL models using increasing ratios of the original training data. Results: The F1 score for the logistic regression model, the best-performing ML model, was 0.3. The best-performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training. Conclusions: The ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data are needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task.

Deep learning aided oropharyngeal cancer segmentation with adaptive thresholding for predicted tumor probability in FDG PET and CT images.

Objective. Tumor segmentation is a fundamental step for radiotherapy treatment planning. To define an accurate segmentation of the primary tumor (GTVp) of oropharyngeal cancer patients (OPC) each image volume is explored slice-by-slice from different orientations on different image modalities. However, the manual fixed boundary of segmentation neglects the spatial uncertainty known to occur in tumor delineation. This study proposes a novel deep learning-based method that generates probability maps which capture the model uncertainty in the segmentation task.Approach. We included 138 OPC patients treated with (chemo)radiation in our institute. Sequences of 3 consecutive 2D slices of concatenated FDG-PET/CT images and GTVp contours were used as input. Our framework exploits inter and intra-slice context using attention mechanisms and bi-directional long short term memory (Bi-LSTM). Each slice resulted in three predictions that were averaged. A 3-fold cross validation was performed on sequences extracted from the axial, sagittal, and coronal plane. 3D volumes were reconstructed and single- and multi-view ensembling were performed to obtain final results. The output is a tumor probability map determined by averaging multiple predictions.Main Results. Model performance was assessed on 25 patients at different probability thresholds. Predictions were the closest to the GTVp at a threshold of 0.9 (mean surface DSC of 0.81, median HD95of 3.906 mm).Significance. The promising results of the proposed method show that is it possible to offer the probability maps to radiation oncologists to guide them in a in a slice-by-slice adaptive GTVp segmentation.

Comparison of computed tomography image features extracted by radiomics, self-supervised learning and end-to-end deep learning for outcome prediction of oropharyngeal cancer.

Background and purpose: To compare the prediction performance of image features of computed tomography (CT) images extracted by radiomics, self-supervised learning and end-to-end deep learning for local control (LC), regional control (RC), locoregional control (LRC), distant metastasis-free survival (DMFS), tumor-specific survival (TSS), overall survival (OS) and disease-free survival (DFS) of oropharyngeal squamous cell carcinoma (OPSCC) patients after (chemo)radiotherapy. Methods and materials: The OPC-Radiomics dataset was used for model development and independent internal testing and the UMCG-OPC set for external testing. Image features were extracted from the Gross Tumor Volume contours of the primary tumor (GTVt) regions in CT scans when using radiomics or a self-supervised learning-based method (autoencoder). Clinical and combined (radiomics, autoencoder or end-to-end) models were built using multivariable Cox proportional-hazard analysis with clinical features only and both clinical and image features for LC, RC, LRC, DMFS, TSS, OS and DFS prediction, respectively. Results: In the internal test set, combined autoencoder models performed better than clinical models and combined radiomics models for LC, RC, LRC, DMFS, TSS and DFS prediction (largest improvements in C-index: 0.91 vs. 0.76 in RC and 0.74 vs. 0.60 in DMFS). In the external test set, combined radiomics models performed better than clinical and combined autoencoder models for all endpoints (largest improvements in LC, 0.82 vs. 0.71). Furthermore, combined models performed better in risk stratification than clinical models and showed good calibration for most endpoints. Conclusions: Image features extracted using self-supervised learning showed best internal prediction performance while radiomics features have better external generalizability.

Improving Prediction of Late Symptoms using LSTM and Patient-reported Outcomes for Head and Neck Cancer Patients.

Patient-Reported Outcomes (PRO) are collected directly from the patients using symptom questionnaires. In the case of head and neck cancer patients, PRO surveys are recorded every week during treatment with each patient's visit to the clinic and at different follow-up times after the treatment has concluded. PRO surveys can be very informative regarding the patient's status and the effect of treatment on the patient's quality of life (QoL). Processing PRO data is challenging for several reasons. First, missing data is frequent as patients might skip a question or a questionnaire altogether. Second, PROs are patient-dependent, a rating of 5 for one patient might be a rating of 10 for another patient. Finally, most patients experience severe symptoms during treatment which usually subside over time. However, for some patients, late toxicities persist negatively affecting the patient's QoL. These long-term severe symptoms are hard to predict and are the focus of this study. In this work, we model PRO data collected from head and neck cancer patients treated at the MD Anderson Cancer Center using the MD Anderson Symptom Inventory (MDASI) questionnaire as time series. We impute missing values with a combination of K nearest neighbor (KNN) and Long Short-Term Memory (LSTM) neural networks, and finally, apply LSTM to predict late symptom severity 12 months after treatment. We compare performance against clinical and ARIMA models. We show that the LSTM model combined with KNN imputation is effective in predicting late-stage symptom ratings for occurrence and severity under the AUC and F1 score metrics.

Head and neck cancer predictive risk estimator to determine control and therapeutic outcomes of radiotherapy (HNC-PREDICTOR): development, international multi-institutional validation, and web implementation of clinic-ready model-based risk stratification for head and neck cancer.

BACKGROUND: Personalised radiotherapy can improve treatment outcomes of patients with head and neck cancer (HNC), where currently a 'one-dose-fits-all' approach is the standard. The aim was to establish individualised outcome prediction based on multi-institutional international 'big-data' to facilitate risk-based stratification of patients with HNC. METHODS: The data of 4611 HNC radiotherapy patients from three academic cancer centres were split into four cohorts: a training (n = 2241), independent test (n = 786), and external validation cohorts 1 (n = 1087) and 2 (n = 497). Tumour- and patient-related clinical variables were considered in a machine learning pipeline to predict overall survival (primary end-point) and local and regional tumour control (secondary end-points); serially, imaging features were considered for optional model improvement. Finally, patients were stratified into high-, intermediate-, and low-risk groups. RESULTS: Performance score, AJCC8thstage, pack-years, and Age were identified as predictors for overall survival, demonstrating good performance in both the training cohort (c-index = 0.72 [95% CI, 0.66-0.77]) and in all three validation cohorts (c-indices: 0.76 [0.69-0.83], 0.73 [0.68-0.77], and 0.75 [0.68-0.80]). Excellent stratification of patients with HNC into high, intermediate, and low mortality risk was achieved; with 5-year overall survival rates of 17-46% for the high-risk group compared to 92-98% for the low-risk group. The addition of morphological image feature further improved the performance (c-index = 0.73 [0.64-0.81]). These models are integrated in a clinic-ready interactive web interface: https://uic-evl.github.io/hnc-predictor/ CONCLUSIONS: Robust model-based prediction was able to stratify patients with HNC in distinct high, intermediate, and low mortality risk groups. This can effectively be capitalised for personalised radiotherapy, e.g., for tumour radiation dose escalation/de-escalation.

Optimized decision support for selection of transoral robotic surgery or (chemo)radiation therapy based on posttreatment swallowing toxicity.

BACKGROUND: A primary goal in transoral robotic surgery (TORS) for oropharyngeal squamous cell cancer (OPSCC) survivors is to optimize swallowing function. However, the uncertainty in the outcomes of TORS including postoperative residual positive margin (PM) and extranodal extension (ENE), may necessitate adjuvant therapy, which may cause significant swallowing toxicity to survivors. METHODS: A secondary analysis was performed on a prospective registry data with low- to intermediate-risk human papillomavirus-related OPSCC possibly resectable by TORS. Decision trees were developed to model the uncertainties in TORS compared with definitive radiation therapy (RT) and chemoradiation therapy (CRT). Swallowing toxicities were measured by Dynamic Imaging Grade of Swallowing Toxicity (DIGEST), MD Anderson Dysphagia Inventory (MDADI), and the MD Anderson Symptom Inventory-Head and Neck (MDASI-HN) instruments. The likelihoods of PM/ENE were varied to determine the thresholds within which each therapy remains optimal. RESULTS: Compared with RT, TORS resulted in inferior swallowing function for moderate likelihoods of PM/ENE (>60% in short term for all instruments, >75% in long term for DIGEST and MDASI) leaving RT as the optimal treatment. Compared with CRT, TORS remained the optimal therapy based on MDADI and MDASI but showed inferior swallowing outcomes based on DIGEST for moderate-to-high likelihoods of PM/ENE (>75% for short-term and >40% for long-term outcomes). CONCLUSION: In the absence of reliable estimation of postoperative PM/ENE concurrent with significant postoperative PM, the overall toxicity level in OPSCC patients undergoing TORS with adjuvant therapy may become more severe compared with patients receiving nonsurgical treatments thus advocating definitive (C)RT protocols.