A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in [Formula: see text]F]FDG PET/CT.

PURPOSE: PET-derived metabolic tumor volume (MTV) and total lesion glycolysis of the primary tumor are known to be prognostic of clinical outcome in head and neck cancer (HNC). Including evaluation of lymph node metastases can further increase the prognostic value of PET but accurate manual delineation and classification of all lesions is time-consuming and prone to interobserver variability. Our goal, therefore, was development and evaluation of an automated tool for MTV delineation/classification of primary tumor and lymph node metastases in PET/CT investigations of HNC patients. METHODS: Automated lesion delineation was performed with a residual 3D U-Net convolutional neural network (CNN) incorporating a multi-head self-attention block. 698 [Formula: see text]F]FDG PET/CT scans from 3 different sites and 5 public databases were used for network training and testing. An external dataset of 181 [Formula: see text]F]FDG PET/CT scans from 2 additional sites was employed to assess the generalizability of the network. In these data, primary tumor and lymph node (LN) metastases were interactively delineated and labeled by two experienced physicians. Performance of the trained network models was assessed by 5-fold cross-validation in the main dataset and by pooling results from the 5 developed models in the external dataset. The Dice similarity coefficient (DSC) for individual delineation tasks and the primary tumor/metastasis classification accuracy were used as evaluation metrics. Additionally, a survival analysis using univariate Cox regression was performed comparing achieved group separation for manual and automated delineation, respectively. RESULTS: In the cross-validation experiment, delineation of all malignant lesions with the trained U-Net models achieves DSC of 0.885, 0.805, and 0.870 for primary tumor, LN metastases, and the union of both, respectively. In external testing, the DSC reaches 0.850, 0.724, and 0.823 for primary tumor, LN metastases, and the union of both, respectively. The voxel classification accuracy was 98.0% and 97.9% in cross-validation and external data, respectively. Univariate Cox analysis in the cross-validation and the external testing reveals that manually and automatically derived total MTVs are both highly prognostic with respect to overall survival, yielding essentially identical hazard ratios (HR) ([Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in cross-validation and [Formula: see text]; [Formula: see text] vs. [Formula: see text]; [Formula: see text] in external testing). CONCLUSION: To the best of our knowledge, this work presents the first CNN model for successful MTV delineation and lesion classification in HNC. In the vast majority of patients, the network performs satisfactory delineation and classification of primary tumor and lymph node metastases and only rarely requires more than minimal manual correction. It is thus able to massively facilitate study data evaluation in large patient groups and also does have clear potential for supervised clinical application.

Radiotherapy in oligometastatic prostate cancer-a pattern of care survey among members of the German Society for Radiation Oncology (DEGRO).

PURPOSE: Due to improved imaging, oligometastatic prostate cancer (OMPC) is diagnosed more frequently. Growing evidence shows that patients with a limited number of metastases benefit from primary-directed radiotherapy (PDT) as well as from metastasis-directed radiotherapy (MDT). This survey investigates the current treatment practice for OMPC among German-speaking radiation oncologists. METHODS: Members of the German Society for Radiation Oncology (Deutsche Gesellschaft für Radioonkologie [DEGRO]) were surveyed regarding their current treatment practice via an anonymous online questionnaire sent by email. The survey included six general items and 14 specific items regarding treatment characteristics. Questionnaires with at least 50% of questions completed were considered for further analysis. RESULTS: A total of 204 responses were received (15% response rate), 167 were considered for further analysis. Most respondents stated to be specialized in treating prostate cancer patients and to treat 10-30 patients with OMPC per annum; 97% considered PSMA-PET/CT necessary to define oligometastatic disease. Opinions differed regarding the use of systemic therapies: 63% of the respondents aimed to defer systemic therapy using radiotherapy in OMPC, whereas 37% considered systemic therapy necessary. In the setting of synchronous OMPC, 97% recommended PDT with or without a combination of MDT and/or systemic therapy. For metachronous nodal or bone oligometastatic recurrence, 98 and 99%, respectively, would opt for MDT. The majority would combine MDT with systemic therapy in patients with metachronous oligorecurrence. Respondents recommended normofractionation, hypofractionation, and SBRT for lymph node metastases in 49, 27, and 24%, respectively. No consensus existed regarding the field size for MDT of lymph node metastases. Most respondents preferred > 5 fractions for treatment of bone metastases. CONCLUSION: Local radiotherapy for PDT and MDT is routinely used among respondents of this survey, representing 12% of all German-speaking radiation oncologists. The timing of systemic therapy, fractionation schedules, and field sizes are handled differently and remain an area of active investigation.

Optimizing the Analytical Value of Oncology-Related Data Based on an In-Memory Analysis Layer: Development and Assessment of the Munich Online Comprehensive Cancer Analysis Platform.

BACKGROUND: Many comprehensive cancer centers incorporate tumor documentation software supplying structured information from the associated centers' oncology patients for internal and external audit purposes. However, much of the documentation data included in these systems often remain unused and unknown by most of the clinicians at the sites. OBJECTIVE: To improve access to such data for analytical purposes, a prerollout of an analysis layer based on the business intelligence software QlikView was implemented. This software allows for the real-time analysis and inspection of oncology-related data. The system is meant to increase access to the data while simultaneously providing tools for user-friendly real-time analytics. METHODS: The system combines in-memory capabilities (based on QlikView software) with innovative techniques that compress the complexity of the data, consequently improving its readability as well as its accessibility for designated end users. Aside from the technical and conceptual components, the software's implementation necessitated a complex system of permission and governance. RESULTS: A continuously running system including daily updates with a user-friendly Web interface and real-time usage was established. This paper introduces its main components and major design ideas. A commented video summarizing and presenting the work can be found within the Multimedia Appendix. CONCLUSIONS: The system has been well-received by a focus group of physicians within an initial prerollout. Aside from improving data transparency, the system's main benefits are its quality and process control capabilities, knowledge discovery, and hypothesis generation. Limitations such as run time, governance, or misinterpretation of data are considered.

FET PET-based target volume delineation for the radiotherapy of glioblastoma: A pictorial guide to help overcome methodological pitfalls.

PET is increasingly used for target volume definition in the radiotherapy of glioblastoma, as endorsed by the 2023 ESTRO-EANO guidelines. In view of its growing adoption into clinical practice and upcoming PET-based multi-center trials, this paper aims to assist in overcoming common pitfalls of FET PET-based target delineation in glioblastoma.

The role of online MR-guided multi-fraction stereotactic ablative radiotherapy in lung tumours.

Background: The aim of this prospective observational study was to evaluate the dosimetry benefits, changes in pulmonary function, and clinical outcome of online adaptive MR-guided SBRT. Methods: From 11/2020-07/2022, 45 consecutive patients with 59 lesions underwent multi-fraction SBRT (3-8 fractions) at our institution. Patients were eligible if they had biopsy-proven NSCLC or lung cancer/metastases diagnosed via clinical imaging. Endpoints were local control (LC) and overall survival (OS). We evaluated PTV/GTV dose coverage, organs at risk exposure, and changes in pulmonary function (PF). Acute toxicity was classified per the National Cancer Institute-Common Terminology Criteria for Adverse Events version 5.0. Results: The median PTV was 14.4 cm3 (range: 3.4 - 96.5 cm3). In total 195/215 (91%) plans were reoptimised. In the reoptimised vs. predicted plans, PTV coverage by the prescribed dose increased in 94.6% of all fractions with a median increase in PTV VPD of 5.6% (range: -1.8 - 44.6%, p < 0.001), increasing the number of fractions with PTV VPD ≥ 95% from 33% to 98%. The PTV D95% and D98% (BED10) increased in 93% and 95% of all fractions with a median increase of 7.7% (p < 0.001) and 10.6% (p < 0.001). The PTV D95% (BED10) increased by a mean of 9.6 Gy (SD: 10.3 Gy, p < 0.001). At a median follow-up of 21.4 months (95% CI: 12.3-27.0 months), 1- and 2-year LC rates were 94.8% (95% CI: 87.6 - 100.0%) and 91.1% (95% CI: 81.3 - 100%); 1- and 2-year OS rates were 85.6% (95% CI: 75.0 - 96.3%) and 67.1 % (95% CI: 50.3 - 83.8%). One grade ≥ 3 toxicity and no significant reduction in short-term PF parameters were recorded. Conclusions: Online adaptive MR-guided SBRT is an effective, safe and generally well tolerated treatment option for lung tumours achieving encouraging local control rates with significantly improved target volume coverage.

Factors influencing local control after MR-guided stereotactic body radiotherapy (MRgSBRT) for adrenal metastases.

Purpose: Stereotactic body radiotherapy (SBRT) is an effective treatment for adrenal gland metastases, but it is technically challenging and there are concerns about toxicity. We performed a multi-institutional pooled retrospective analysis to study clinical outcomes and toxicities after MR-guided SBRT (MRgSBRT) using for adrenal gland metastases. Methods and Materials: Clinical and dosimetric data of patients treated with MRgSBRT on a 0.35 T MR-Linac at 11 institutions between 2016 and 2022 were analyzed. Local control (LC), local progression-free survival (LPFS), distant progression-free survival (DPFS) and overall survival (OS) were estimated using Kaplan-Meier method and log-rank test. Results: A total of 255 patients (269 adrenal metastases) were included. Metastatic pattern was solitary in 25.9 % and oligometastatic in 58.0 % of patients. Median total dose was 45 Gy (range, 16-60 Gy) in a median of 5 fractions, and the median BED10 was 100 Gy (range, 37.5-132.0 Gy). Adaptation was done in 87.4 % of delivered fractions based on the individual clinicians' judgement. The 1- and 2- year LPFS rates were 94.0 % (95 % CI: 90.7-97.3 %) and 88.3 % (95 % CI: 82.4-94.2 %), respectively and only 2 patients (0.8 %) experienced grade 3 + toxicity. No local recurrences were observed after treatment to a total dose of BED10 > 100 Gy, with single fraction or fractional dose of > 10 Gy. Conclusions: This is a large retrospective multi-institutional study to evaluate the treatment outcomes and toxicities with MRgSBRT in over 250 patients, demonstrating the need for frequent adaptation in 87.4 % of delivered fractions to achieve a 1- year LPFS rate of 94 % and less than 1 % rate of grade 3 + toxicity. Outcomes analysis in 269 adrenal lesions revealed improved outcomes with delivery of a BED10 > 100 Gy, use of single fraction SBRT and with fraction doses > 10 Gy, providing benchmarks for future clinical trials.

Metabolic pathway-based subtypes associate glycan biosynthesis and treatment response in head and neck cancer.

Head and Neck Squamous Cell Carcinoma (HNSCC) is a heterogeneous malignancy that remains a significant challenge in clinical management due to frequent treatment failures and pronounced therapy resistance. While metabolic dysregulation appears to be a critical factor in this scenario, comprehensive analyses of the metabolic HNSCC landscape and its impact on clinical outcomes are lacking. This study utilized transcriptomic data from four independent clinical cohorts to investigate metabolic heterogeneity in HNSCC and define metabolic pathway-based subtypes (MPS). In HPV-negative HNSCCs, MPS1 and MPS2 were identified, while MPS3 was enriched in HPV-positive cases. MPS classification was associated with clinical outcome post adjuvant radio(chemo)therapy, with MPS1 consistently exhibiting the highest risk of therapeutic failure. MPS1 was uniquely characterized by upregulation of glycan (particularly chondroitin/dermatan sulfate) metabolism genes. Immunohistochemistry and pilot mass spectrometry imaging analyses confirmed this at metabolite level. The histological context and single-cell RNA sequencing data identified the malignant cells as key contributors. Globally, MPS1 was distinguished by a unique transcriptomic landscape associated with increased disease aggressiveness, featuring motifs related to epithelial-mesenchymal transition, immune signaling, cancer stemness, tumor microenvironment assembly, and oncogenic signaling. This translated into a distinct histological appearance marked by extensive extracellular matrix remodeling, abundant spindle-shaped cancer-associated fibroblasts, and intimately intertwined populations of malignant and stromal cells. Proof-of-concept data from orthotopic xenotransplants replicated the MPS phenotypes on the histological and transcriptome levels. In summary, this study introduces a metabolic pathway-based classification of HNSCC, pinpointing glycan metabolism-enriched MPS1 as the most challenging subgroup that necessitates alternative therapeutic strategies.

A Multicenter Evaluation of Different Chemotherapy Regimens in Older Adults With Head and Neck Squamous Cell Carcinoma Undergoing Definitive Chemoradiation.

PURPOSE: The number of older adults with head and neck squamous cell carcinoma (HNSCC) is increasing, and treatment of these patients is challenging. Although cisplatin-based chemotherapy concomitantly with radiation therapy is considered the standard regimen for patients with locoregionally advanced HNSCC, there is substantial real-world heterogeneity regarding concomitant chemotherapy in older patients with HNSCC. METHODS AND MATERIALS: The SENIOR study is an international multicenter cohort study including older patients (≥65 years) with HNSCC treated with definitive radiation therapy at 13 academic centers in the United States and Europe. Patients with concomitant chemoradiation were analyzed regarding overall survival (OS) and progression-free survival (PFS) via Kaplan-Meier analyses. Fine-Gray competing risk regressions were performed regarding the incidence of locoregional failures and distant metastases. RESULTS: Six hundred ninety-seven patients with a median age of 71 years were included in this analysis. Single-agent cisplatin was the most common chemotherapy regimen (n = 310; 44%), followed by cisplatin plus 5-fluorouracil (n = 137; 20%), carboplatin (n = 73; 10%), and mitomycin C plus 5-fluorouracil (n = 64; 9%). Carboplatin-based regimens were associated with diminished PFS (hazard ratio [HR], 1.39 [1.03-1.89]; P < .05) and a higher incidence of locoregional failures (subdistribution HR, 1.54 [1.00-2.38]; P = .05) compared with single-agent cisplatin, whereas OS (HR, 1.15 [0.80-1.65]; P = .46) was comparable. There were no oncological differences between single-agent and multiagent cisplatin regimens (all P > .05). The median cumulative dose of cisplatin was 180 mg/m2 (IQR, 120-200 mg/m2). Cumulative cisplatin doses ≥200 mg/m2 were associated with increased OS (HR, 0.71 [0.53-0.95]; P = .02), increased PFS (HR, 0.66 [0.51-0.87]; P = .003), and lower incidence of locoregional failures (subdistribution HR, 0.50 [0.31-0.80]; P = .004). Higher cumulative cisplatin doses remained an independent prognostic variable in the multivariate regression analysis for OS (HR, 0.996 [0.993-0.999]; P = .009). CONCLUSIONS: Single-agent cisplatin can be considered in the standard chemotherapy regimen for older patients with HNSCC who can tolerate cisplatin. Cumulative cisplatin doses are prognostically relevant in older patients with HNSCC.

Deep learning based automatic segmentation of organs-at-risk for 0.35 T MRgRT of lung tumors.

BACKGROUND AND PURPOSE: Magnetic resonance imaging guided radiotherapy (MRgRT) offers treatment plan adaptation to the anatomy of the day. In the current MRgRT workflow, this requires the time consuming and repetitive task of manual delineation of organs-at-risk (OARs), which is also prone to inter- and intra-observer variability. Therefore, deep learning autosegmentation (DLAS) is becoming increasingly attractive. No investigation of its application to OARs in thoracic magnetic resonance images (MRIs) from MRgRT has been done so far. This study aimed to fill this gap. MATERIALS AND METHODS: 122 planning MRIs from patients treated at a 0.35 T MR-Linac were retrospectively collected. Using an 80/19/23 (training/validation/test) split, individual 3D U-Nets for segmentation of the left lung, right lung, heart, aorta, spinal canal and esophagus were trained. These were compared to the clinically used contours based on Dice similarity coefficient (DSC) and Hausdorff distance (HD). They were also graded on their clinical usability by a radiation oncologist. RESULTS: Median DSC was 0.96, 0.96, 0.94, 0.90, 0.88 and 0.78 for left lung, right lung, heart, aorta, spinal canal and esophagus, respectively. Median 95th percentile values of the HD were 3.9, 5.3, 5.8, 3.0, 2.6 and 3.5 mm, respectively. The physician preferred the network generated contours over the clinical contours, deeming 85 out of 129 to not require any correction, 25 immediately usable for treatment planning, 15 requiring minor and 4 requiring major corrections. CONCLUSIONS: We trained 3D U-Nets on clinical MRI planning data which produced accurate delineations in the thoracic region. DLAS contours were preferred over the clinical contours.

Evaluation of Concomitant Systemic Treatment in Older Adults With Head and Neck Squamous Cell Carcinoma Undergoing Definitive Radiotherapy.

Importance: The number of older adults with head and neck squamous cell carcinoma (HNSCC) is increasing, and these patients are underrepresented in clinical trials. It is unclear whether the addition of chemotherapy or cetuximab to radiotherapy is associated with improved survival in older adults with HNSCC. Objective: To examine whether the addition of chemotherapy or cetuximab to definitive radiotherapy is associated with improved survival in patients with locoregionally advanced (LA) HNSCC. Design, Setting, and Participants: The Special Care Patterns for Elderly HNSCC Patients Undergoing Radiotherapy (SENIOR) study is an international, multicenter cohort study including older adults (≥65 years) with LA-HNSCCs of the oral cavity, oropharynx/hypopharynx, or larynx treated with definitive radiotherapy, either alone or with concomitant systemic treatment, between January 2005 and December 2019 at 12 academic centers in the US and Europe. Data analysis was conducted from June 4 to August 10, 2022. Interventions: All patients underwent definitive radiotherapy alone or with concomitant systemic treatment. Main Outcomes and Measures: The primary outcome was overall survival. Secondary outcomes included progression-free survival and locoregional failure rate. Results: Among the 1044 patients (734 men [70.3%]; median [IQR] age, 73 [69-78] years) included in this study, 234 patients (22.4%) were treated with radiotherapy alone and 810 patients (77.6%) received concomitant systemic treatment with chemotherapy (677 [64.8%]) or cetuximab (133 [12.7%]). Using inverse probability weighting to attribute for selection bias, chemoradiation was associated with longer overall survival than radiotherapy alone (hazard ratio [HR], 0.61; 95% CI, 0.48-0.77; P < .001), whereas cetuximab-based bioradiotherapy was not (HR, 0.94; 95% CI, 0.70-1.27; P = .70). Progression-free survival was also longer after the addition of chemotherapy (HR, 0.65; 95% CI, 0.52-0.81; P < .001), while the locoregional failure rate was not significantly different (subhazard ratio, 0.62; 95% CI, 0.30-1.26; P = .19). The survival benefit of the chemoradiation group was present in patients up to age 80 years (65-69 years: HR, 0.52; 95% CI, 0.33-0.82; 70-79 years: HR, 0.60; 95% CI, 0.43-0.85), but was absent in patients aged 80 years or older (HR, 0.89; 95% CI, 0.56-1.41). Conclusions and Relevance: In this cohort study of older adults with LA- HNSCC, chemoradiation, but not cetuximab-based bioradiotherapy, was associated with longer survival compared with radiotherapy alone.

Dental management before radiotherapy of the head and neck region: 4-year single-center experience.

OBJECTIVE: To review our experience with a standardized dental management approach in patients with planned radiotherapy of the head and neck region based on preradiation and follow-up data. MATERIAL AND METHODS: Records of patients who underwent radiotherapy between June 2016 and November 2020 were reviewed. Data on dental findings and therapeutic recommendations were extracted from a prospectively managed database. Hospital records were used to obtain follow-up data. RESULTS: Two hundred eighty-one patient records were identified. After the exclusion of 81 patients because of incomplete data, 200 patients were included in the study. Dental findings relevant to radiotherapy were found in 144 cases (72.0%). Teeth extractions were recommended in 112 (56.0%) patients. Follow-up data were available for 172 (86.0%) patients (mean follow-up: 16.8 ± 10.7 months). Radiodermatitis was the most frequently observed sequela of radiotherapy (42.4%), followed by dysphagia (38.4%) and stomatitis (36.6%). Osteoradionecrosis was observed in only 2.3% of the patients. CONCLUSION: Dental findings relevant to planned radiotherapy were frequent and in many cases resulted in recommendations for teeth extraction. Based on our standardized dental management protocol, we observed low rates of late oral complications after radiotherapy of the head and neck region.

A deep image-to-image network organ segmentation algorithm for radiation treatment planning: principles and evaluation.

BACKGROUND: We describe and evaluate a deep network algorithm which automatically contours organs at risk in the thorax and pelvis on computed tomography (CT) images for radiation treatment planning. METHODS: The algorithm identifies the region of interest (ROI) automatically by detecting anatomical landmarks around the specific organs using a deep reinforcement learning technique. The segmentation is restricted to this ROI and performed by a deep image-to-image network (DI2IN) based on a convolutional encoder-decoder architecture combined with multi-level feature concatenation. The algorithm is commercially available in the medical products "syngo.via RT Image Suite VB50" and "AI-Rad Companion Organs RT VA20" (Siemens Healthineers). For evaluation, thoracic CT images of 237 patients and pelvic CT images of 102 patients were manually contoured following the Radiation Therapy Oncology Group (RTOG) guidelines and compared to the DI2IN results using metrics for volume, overlap and distance, e.g., Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD95). The contours were also compared visually slice by slice. RESULTS: We observed high correlations between automatic and manual contours. The best results were obtained for the lungs (DSC 0.97, HD95 2.7 mm/2.9 mm for left/right lung), followed by heart (DSC 0.92, HD95 4.4 mm), bladder (DSC 0.88, HD95 6.7 mm) and rectum (DSC 0.79, HD95 10.8 mm). Visual inspection showed excellent agreements with some exceptions for heart and rectum. CONCLUSIONS: The DI2IN algorithm automatically generated contours for organs at risk close to those by a human expert, making the contouring step in radiation treatment planning simpler and faster. Few cases still required manual corrections, mainly for heart and rectum.

DeepClassPathway: Molecular pathway aware classification using explainable deep learning.

OBJECTIVE: HPV-associated head and neck cancer is correlated with favorable prognosis; however, its underlying biology is not fully understood. We propose an explainable convolutional neural network (CNN) classifier, DeepClassPathway, that predicts HPV-status and allows patient-specific identification of molecular pathways driving classifier decisions. METHODS: The CNN was trained to classify HPV-status on transcriptome data from 264 (13% HPV-positive) and tested on 85 (25% HPV-positive) head and neck squamous carcinoma patients after transformation into 2D-treemaps representing molecular pathways. Grad-CAM saliency was used to quantify pathways contribution to individual CNN decisions. Model stability was assessed by shuffling pathways within 2D-images. RESULTS: The classification performance of the CNN-ensembles achieved ROC-AUC/PR-AUC of 0.96/0.90 for all treemap variants. Quantification of the averaged pathway saliency heatmaps consistently identified KRAS, spermatogenesis, bile acid metabolism, and inflammation signaling pathways as the four most informative for classifying HPV-positive patients and MYC targets, epithelial-mesenchymal transition, and protein secretion pathways for HPV-negative patients. CONCLUSION: We have developed and applied an explainable CNN classification approach to transcriptome data from an oncology cohort with typical sample size that allows classification while accounting for the importance of molecular pathways in individual-level decisions.

Deep learning based time-to-event analysis with PET, CT and joint PET/CT for head and neck cancer prognosis.

OBJECTIVES: Recent studies have shown that deep learning based on pre-treatment positron emission tomography (PET) or computed tomography (CT) is promising for distant metastasis (DM) and overall survival (OS) prognosis in head and neck cancer (HNC). However, lesion segmentation is typically required, resulting in a predictive power susceptible to variations in primary and lymph node gross tumor volume (GTV) segmentation. This study aimed at achieving prognosis without GTV segmentation, and extending single modality prognosis to joint PET/CT to allow investigating the predictive performance of combined- compared to single-modality inputs. METHODS: We employed a 3D-Resnet combined with a time-to-event outcome model to incorporate censoring information. We focused on the prognosis of DM and OS for HNC patients. For each clinical endpoint, five models with PET and/or CT images as input were compared: PET-GTV, PET-only, CT-GTV, CT-only, and PET/CT-GTV models, where -GTV indicates that the corresponding images were masked using the GTV contour. Publicly available delineated CT and PET scans from 4 different Canadian hospitals (293) and the MAASTRO clinic (74) were used for training by 3-fold cross-validation (CV). For independent testing, we used 110 patients from a collaborating institution. The predictive performance was evaluated via Harrell's Concordance Index (HCI) and Kaplan-Meier curves. RESULTS: In a 5-year time-to-event analysis, all models could produce CV HCIs with median values around 0.8 for DM and 0.7 for OS. The best performance was obtained with the PET-only model, achieving a median testing HCI of 0.82 for DM and 0.69 for OS. Compared with the PET/CT-GTV model, the PET-only still had advantages of up to 0.07 in terms of testing HCI. The Kaplan-Meier curves and corresponding log-rank test results also demonstrated significant stratification capability of our models for the testing cohort. CONCLUSION: Deep learning-based DM and OS time-to-event models showed predictive capability and could provide indications for personalized RT. The best predictive performance achieved by the PET-only model suggested GTV segmentation might be less relevant for PET-based prognosis.

Integration of p16/HPV DNA Status with a 24-miRNA-Defined Molecular Phenotype Improves Clinically Relevant Stratification of Head and Neck Cancer Patients.

Human papillomavirus (HPV)-driven head and neck squamous cell carcinomas (HNSCC) generally have a more favourable prognosis. We hypothesized that HPV-associated HNSCC may be identified by an miRNA-signature according to their specific molecular pathogenesis, and be characterized by a unique transcriptome compared to HPV-negative HNSCC. We performed miRNA expression profiling of two p16/HPV DNA characterized HNSCC cohorts of patients treated by adjuvant radio(chemo)therapy (multicentre DKTK-ROG n = 128, single-centre LMU-KKG n = 101). A linear model predicting HPV status built in DKTK-ROG using lasso-regression was tested in LMU-KKG. LMU-KKG tumours (n = 30) were transcriptome profiled for differential gene expression and miRNA-integration. A 24-miRNA signature predicted HPV-status with 94.53% accuracy (AUC: 0.99) in DKTK-ROG, and 86.14% (AUC: 0.86) in LMU-KKG. The prognostic values of 24-miRNA- and p16/HPV DNA status were comparable. Combining p16/HPV DNA and 24-miRNA status allowed patient sub-stratification and identification of an HPV-associated patient subgroup with impaired overall survival. HPV-positive tumours showed downregulated MAPK, Estrogen, EGFR, TGFbeta, WNT signaling activity. miRNA-mRNA integration revealed HPV-specific signaling pathway regulation, including PD-L1 expression/PD-1 checkpoint pathway in cancer in HPV-associated HNSCC. Integration of clinically established p16/HPV DNA with 24-miRNA signature status improved clinically relevant risk stratification, which might be considered for future clinical decision-making with respect to treatment de-escalation in HPV-associated HNSCC.

18F-Fluorodeoxyglucose Positron Emission Tomography of Head and Neck Cancer: Location and HPV Specific Parameters for Potential Treatment Individualization.

Purpose: 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) is utilized for staging and treatment planning of head and neck squamous cell carcinomas (HNSCC). Some older publications on the prognostic relevance showed inconclusive results, most probably due to small study sizes. This study evaluates the prognostic and potentially predictive value of FDG-PET in a large multi-center analysis. Methods: Original analysis of individual FDG-PET and patient data from 16 international centers (8 institutional datasets, 8 public repositories) with 1104 patients. All patients received curative intent radiotherapy/chemoradiation (CRT) and pre-treatment FDG-PET imaging. Primary tumors were semi-automatically delineated for calculation of SUVmax, SUVmean, metabolic tumor volume (MTV) and total lesion glycolysis (TLG). Cox regression analyses were performed for event-free survival (EFS), overall survival (OS), loco-regional control (LRC) and freedom from distant metastases (FFDM). Results: FDG-PET parameters were associated with patient outcome in the whole cohort regarding clinical endpoints (EFS, OS, LRC, FFDM), in uni- and multivariate Cox regression analyses. Several previously published cut-off values were successfully validated. Subgroup analyses identified tumor- and human papillomavirus (HPV) specific parameters. In HPV positive oropharynx cancer (OPC) SUVmax was well suited to identify patients with excellent LRC for organ preservation. Patients with SUVmax of 14 or less were unlikely to develop loco-regional recurrence after definitive CRT. In contrast FDG PET parameters deliver only limited prognostic information in laryngeal cancer. Conclusion: FDG-PET parameters bear considerable prognostic value in HNSCC and potential predictive value in subgroups of patients, especially regarding treatment de-intensification and organ-preservation. The potential predictive value needs further validation in appropriate control groups. Further research on advanced imaging approaches including radiomics or artificial intelligence methods should implement the identified cut-off values as benchmark routine imaging parameters.

Therapy-Related Transcriptional Subtypes in Matched Primary and Recurrent Head and Neck Cancer.

PURPOSE: The genetic relatedness between primary and recurrent head and neck squamous cell carcinomas (HNSCC) reflects the extent of heterogeneity and therapy-driven selection of tumor subpopulations. Yet, current treatment of recurrent HNSCC ignores the molecular characteristics of therapy-resistant tumor populations. EXPERIMENTAL DESIGN: From 150 tumors, 74 primary HNSCCs were RNA sequenced and 38 matched primary/recurrent tumor pairs were both whole-exome and RNA sequenced. Transcriptome analysis determined the predominant classical (CL), basal (BA), and inflamed-mesenchymal (IMS) transcriptional subtypes according to an established classification. Genomic alterations and clonal compositions of tumors were evaluated from whole-exome data. RESULTS: Although CL and IMS subtypes were more common in primary HNSCC with low recurrence rates, the BA subtype was more prevalent and stable in recurrent tumors. The BA subtype was associated with a transcriptional signature of partial epithelial-to-mesenchymal transition (p-EMT) and early recurrence. In 44% of matched cases, the dominant subtype changed from primary to recurrent tumors, preferably from IMS to BA or CL. Expression analysis of prognostic gene sets identified upregulation of hypoxia, p-emt, and radiotherapy resistance signatures and downregulation of tumor inflammation in recurrences compared with index tumors. A relevant subset of primary/recurrent tumor pairs presented no evidence for a common clonal origin. CONCLUSIONS: Our study showed a high degree of genetic and transcriptional heterogeneity between primary/recurrent tumors, suggesting therapy-related selection of a transcriptional subtype with characteristics unfavorable for therapy. We conclude that therapy decisions should be based on genetic and transcriptional characteristics of recurrences rather than primary tumors to enable optimally tailored treatment strategies.

Risk Stratification Using 18F-FDG PET/CT and Artificial Neural Networks in Head and Neck Cancer Patients Undergoing Radiotherapy.

This study retrospectively analyzed the performance of artificial neural networks (ANN) to predict overall survival (OS) or locoregional failure (LRF) in HNSCC patients undergoing radiotherapy, based on 2-[18F]FDG PET/CT and clinical covariates. We compared predictions relying on three different sets of features, extracted from 230 patients. Specifically, (i) an automated feature selection method independent of expert rating was compared with (ii) clinical variables with proven influence on OS or LRF and (iii) clinical data plus expert-selected SUV metrics. The three sets were given as input to an artificial neural network for outcome prediction, evaluated by Harrell's concordance index (HCI) and by testing stratification capability. For OS and LRF, the best performance was achieved with expert-based PET-features (0.71 HCI) and clinical variables (0.70 HCI), respectively. For OS stratification, all three feature sets were significant, whereas for LRF only expert-based PET-features successfully classified low vs. high-risk patients. Based on 2-[18F]FDG PET/CT features, stratification into risk groups using ANN for OS and LRF is possible. Differences in the results for different feature sets confirm the relevance of feature selection, and the key importance of expert knowledge vs. automated selection.

Distant metastasis time to event analysis with CNNs in independent head and neck cancer cohorts.

Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient's image and perform a binary classification of the occurrence of a given clinical endpoint. In this work, a 2D-CNN and a 3D-CNN for the binary classification of distant metastasis (DM) occurrence in head and neck cancer patients were extended to perform time-to-event analysis. The newly built CNNs incorporate censoring information and output DM-free probability curves as a function of time for every patient. In total, 1037 patients were used to build and assess the performance of the time-to-event model. Training and validation was based on 294 patients also used in a previous benchmark classification study while for testing 743 patients from three independent cohorts were used. The best network could reproduce the good results from 3-fold cross validation [Harrell's concordance indices (HCIs) of 0.78, 0.74 and 0.80] in two out of three testing cohorts (HCIs of 0.88, 0.67 and 0.77). Additionally, the capability of the models for patient stratification into high and low-risk groups was investigated, the CNNs being able to significantly stratify all three testing cohorts. Results suggest that image-based deep learning models show good reliability for DM time-to-event analysis and could be used for treatment personalisation.