Noninvasive Molecular Subtyping of Pediatric Low-Grade Glioma with Self-Supervised Transfer Learning.

Purpose To develop and externally test a scan-to-prediction deep learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma. Materials and Methods This retrospective study included two pediatric low-grade glioma datasets with linked genomic and diagnostic T2-weighted MRI data of patients: Dana-Farber/Boston Children's Hospital (development dataset, n = 214 [113 (52.8%) male; 104 (48.6%) BRAF wild type, 60 (28.0%) BRAF fusion, and 50 (23.4%) BRAF V600E]) and the Children's Brain Tumor Network (external testing, n = 112 [55 (49.1%) male; 35 (31.2%) BRAF wild type, 60 (53.6%) BRAF fusion, and 17 (15.2%) BRAF V600E]). A deep learning pipeline was developed to classify BRAF mutational status (BRAF wild type vs BRAF fusion vs BRAF V600E) via a two-stage process: (a) three-dimensional tumor segmentation and extraction of axial tumor images and (b) section-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary end point of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, a novel metric, center of mass distance, was developed to quantify the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with an AUC of 0.82 (95% CI: 0.72, 0.91), 0.87 (95% CI: 0.61, 0.97), and 0.85 (95% CI: 0.66, 0.95) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively, on internal testing. On external testing, the pipeline yielded an AUC of 0.72 (95% CI: 0.64, 0.86), 0.78 (95% CI: 0.61, 0.89), and 0.72 (95% CI: 0.64, 0.88) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pediatric low-grade glioma mutational status prediction in a limited data scenario. Keywords: Pediatrics, MRI, CNS, Brain/Brain Stem, Oncology, Feature Detection, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

Automatic Head and Neck Tumor segmentation and outcome prediction relying on FDG-PET/CT images: Findings from the second edition of the HECKTOR challenge.

By focusing on metabolic and morphological tissue properties respectively, FluoroDeoxyGlucose (FDG)-Positron Emission Tomography (PET) and Computed Tomography (CT) modalities include complementary and synergistic information for cancerous lesion delineation and characterization (e.g. for outcome prediction), in addition to usual clinical variables. This is especially true in Head and Neck Cancer (HNC). The goal of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge was to develop and compare modern image analysis methods to best extract and leverage this information automatically. We present here the post-analysis of HECKTOR 2nd edition, at the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2021. The scope of the challenge was substantially expanded compared to the first edition, by providing a larger population (adding patients from a new clinical center) and proposing an additional task to the challengers, namely the prediction of Progression-Free Survival (PFS). To this end, the participants were given access to a training set of 224 cases from 5 different centers, each with a pre-treatment FDG-PET/CT scan and clinical variables. Their methods were subsequently evaluated on a held-out test set of 101 cases from two centers. For the segmentation task (Task 1), the ranking was based on a Borda counting of their ranks according to two metrics: mean Dice Similarity Coefficient (DSC) and median Hausdorff Distance at 95th percentile (HD95). For the PFS prediction task, challengers could use the tumor contours provided by experts (Task 3) or rely on their own (Task 2). The ranking was obtained according to the Concordance index (C-index) calculated on the predicted risk scores. A total of 103 teams registered for the challenge, for a total of 448 submissions and 29 papers. The best method in the segmentation task obtained an average DSC of 0.759, and the best predictions of PFS obtained a C-index of 0.717 (without relying on the provided contours) and 0.698 (using the expert contours). An interesting finding was that best PFS predictions were reached by relying on DL approaches (with or without explicit tumor segmentation, 4 out of the 5 best ranked) compared to standard radiomics methods using handcrafted features extracted from delineated tumors, and by exploiting alternative tumor contours (automated and/or larger volumes encompassing surrounding tissues) rather than relying on the expert contours. This second edition of the challenge confirmed the promising performance of fully automated primary tumor delineation in PET/CT images of HNC patients, although there is still a margin for improvement in some difficult cases. For the first time, the prediction of outcome was also addressed and the best methods reached relatively good performance (C-index above 0.7). Both results constitute another step forward toward large-scale outcome prediction studies in HNC.

Radiotherapy for Primary Pediatric Central Nervous System Malignancies: Current Treatment Paradigms and Future Directions.

BACKGROUND: Central nervous system tumors are the most common solid tumors in childhood. Treatment paradigms for pediatric central nervous system malignancies depend on elements including tumor histology, age of patient, and stage of disease. Radiotherapy is an important modality of treatment for many pediatric central nervous system malignancies. SUMMARY: While radiation contributes to excellent overall survival rates for many patients, radiation also carries significant risks of long-term side effects including neurocognitive decline, hearing loss, growth impairment, neuroendocrine dysfunction, strokes, and secondary malignancies. In recent decades, clinical trials have demonstrated that with better imaging and staging along with more sophisticated radiation planning and treatment set-up verification, smaller treatment volumes can be utilized without decrement in survival. Furthermore, the development of intensity-modulated radiotherapy and proton-beam radiotherapy has greatly improved conformality of radiation. KEY MESSAGES: Recent changes in radiation treatment paradigms have decreased risks of short- and long-term toxicity for common histologies and in different age groups. Future studies will continue to develop novel radiation regimens to improve outcomes in aggressive central nervous system tumors, integrate molecular subtypes to tailor radiation treatment, and decrease radiation-associated toxicity for long-term survivors.

Noninvasive molecular subtyping of pediatric low-grade glioma with self-supervised transfer learning.

Purpose: To develop and externally validate a scan-to-prediction deep-learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pLGG. Materials and Methods: We conducted a retrospective study of two pLGG datasets with linked genomic and diagnostic T2-weighted MRI of patients: BCH (development dataset, n=214 [60 (28%) BRAF fusion, 50 (23%) BRAF V600E, 104 (49%) wild-type), and Child Brain Tumor Network (CBTN) (external validation, n=112 [60 (53%) BRAF-Fusion, 17 (15%) BRAF-V600E, 35 (32%) wild-type]). We developed a deep learning pipeline to classify BRAF mutational status (V600E vs. fusion vs. wildtype) via a two-stage process: 1) 3D tumor segmentation and extraction of axial tumor images, and 2) slice-wise, deep learning-based classification of mutational status. We investigated knowledge-transfer and self-supervised approaches to prevent model overfitting with a primary endpoint of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, we developed a novel metric, COMDist, that quantifies the accuracy of model attention around the tumor. Results: A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest macro-average AUC (0.82 [95% CI: 0.70-0.90]) and accuracy (77%) on internal validation, with an AUC improvement of +17.7% and a COMDist improvement of +6.4% versus training from scratch. On external validation, the TransferX model yielded AUC (0.73 [95% CI 0.68-0.88]) and accuracy (75%). Conclusion: Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pLGG mutational status prediction in a limited data scenario.

A genomic score to predict local control among patients with brain metastases managed with radiation.

BACKGROUND: Clinical predictors of local recurrence following radiation among patients with brain metastases (BrM) provide limited explanatory power. We developed a DNA-based signature of radiotherapeutic efficacy among patients with BrM to better characterize recurrence risk. METHODS: We identified 570 patients with 1487 BrM managed with whole-brain (WBRT) or stereotactic radiation therapy at Brigham and Women's Hospital/Dana-Farber Cancer Institute (2013-2020) for whom next-generation sequencing panel data (OncoPanel) were available. Fine/Gray's competing risks regression was utilized to compare local recurrence on a per-metastasis level among patients with versus without somatic alterations of likely biological significance across 84 genes. Genes with a q-value ≤ 0.10 were utilized to develop a "Brain-Radiation Prediction Score" ("Brain-RPS"). RESULTS: Genomic alterations in 11 (ATM, MYCL, PALB2, FAS, PRDM1, PAX5, CDKN1B, EZH2, NBN, DIS3, and MDM4) and 2 genes (FBXW7 and AURKA) were associated with decreased or increased risk of local recurrence, respectively (q-value ≤ 0.10). Weighted scores corresponding to the strength of association with local failure for each gene were summed to calculate a patient-level RPS. On multivariable Fine/Gray's competing risks regression, RPS [1.66 (1.44-1.91, P < .001)], metastasis-associated edema [1.60 (1.16-2.21), P = .004], baseline size [1.02 (1.01-1.03), P < .001] and receipt of WBRT without local therapy [4.04 (2.49-6.58), P < .001] were independent predictors of local failure. CONCLUSIONS: We developed a genomic score to quantify local recurrence risk following brain-directed radiation. To the best of our knowledge, this represents the first study to systematically correlate DNA-based alterations with radiotherapeutic outcomes in BrM. If validated, Brain-RPS has potential to facilitate clinical trials aimed at genome-based personalization of radiation in BrM.

Spatially-aware clustering improves AJCC-8 risk stratification performance in oropharyngeal carcinomas.

OBJECTIVE: Evaluate the effectiveness of machine learning tools that incorporate spatial information such as disease location and lymph node metastatic patterns-of-spread, for prediction of survival and toxicity in HPV+ oropharyngeal cancer (OPC). MATERIALS & METHODS: 675 HPV+ OPC patients that were treated at MD Anderson Cancer Center between 2005 and 2013 with curative intent IMRT were retrospectively collected under IRB approval. Risk stratifications incorporating patient radiometric data and lymph node metastasis patterns via an anatomically-adjacent representation with hierarchical clustering were identified. These clusterings were combined into a 3-level patient stratification and included along with other known clinical features in a Cox model for predicting survival outcomes, and logistic regression for toxicity, using independent subsets for training and validation. RESULTS: Four groups were identified and combined into a 3-level stratification. The inclusion of patient stratifications in predictive models for 5-yr Overall survival (OS), 5-year recurrence free survival, (RFS) and Radiation-associated dysphagia (RAD) consistently improved model performance measured using the area under the curve (AUC). Test set AUC improvements over models with clinical covariates, was 9 % for predicting OS, and 18 % for predicting RFS, and 7 % for predicting RAD. For models with both clinical and AJCC covariates, AUC improvement was 7 %, 9 %, and 2 % for OS, RFS, and RAD, respectively. CONCLUSION: Including data-driven patient stratifications considerably improve prognosis for survival and toxicity outcomes over the performance achieved by clinical staging and clinical covariates alone. These stratifications generalize well to across cohorts, and sufficient information for reproducing these clusters is included.

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT.

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

Artificial Intelligence and Radiology Education.

Implementation of artificial intelligence (AI) applications into clinical practice requires AI-savvy radiologists to ensure the safe, ethical, and effective use of these systems for patient care. Increasing demand for AI education reflects recognition of the translation of AI applications from research to clinical practice, with positive trainee attitudes regarding the influence of AI on radiology. However, barriers to AI education, such as limited access to resources, predispose to insufficient preparation for the effective use of AI in practice. In response, national organizations have sponsored formal and self-directed learning courses to provide introductory content on imaging informatics and AI. Foundational courses, such as the National Imaging Informatics Course - Radiology and the Radiological Society of North America Imaging AI Certificate, lay a framework for trainees to explore the creation, deployment, and critical evaluation of AI applications. This report includes additional resources for formal programming courses, video series from leading organizations, and blogs from AI and informatics communities. Furthermore, the scope of "AI and radiology education" includes AI-augmented radiology education, with emphasis on the potential for "precision education" that creates personalized experiences for trainees by accounting for varying learning styles and inconsistent, possibly deficient, clinical case volume. © RSNA, 2022 Keywords: Use of AI in Education, Impact of AI on Education, Artificial Intelligence, Medical Education, Imaging Informatics, Natural Language Processing, Precision Education.

Incidence proportion and prognosis of leptomeningeal disease among patients with breast vs. non-breast primaries.

BACKGROUND: Leptomeningeal disease (LMD) is a relatively uncommon manifestation of advanced cancer. Patients with LMD carry a poor prognosis and often decline rapidly, complicating inclusion in clinical trials. Identification of LMD subsets of greater incidence and more favorable prognosis might facilitate dedicated clinical trials in the future. We hypothesized that patients with breast cancer may represent such a population and sought to assess the relative incidence and prognosis of LMD secondary to breast vs. non-breast primaries. METHODS: We identified 2411 patients with intracranial metastases secondary to breast (N = 501) and non-breast (N = 1910) primaries at Brigham and Women's Hospital/Dana-Farber Cancer Institute between 1996 and 2020, of whom 112 presented with and an additional 161 subsequently developed LMD. A log-rank test and Cox modeling were used to compare outcomes in patients with breast vs. non-breast primaries. RESULTS: Among patients with newly diagnosed intracranial disease, the incidence proportion of concurrent LMD was 11.4% vs. 2.9% among patients with breast vs. non-breast primaries (P < .001). Development of LMD among initially LMD-naïve patients was also more common among patients with breast vs. non-breast primaries (HR = 1.49 [1.05-2.11], P = .03). Patients with LMD secondary to breast vs. non-breast primaries displayed lower all-cause mortality (HR 0.70 [0.52-0.93], P = .01; median survival: 5.2 vs. 2.4 months, respectively), with a greater numerical difference observed in patients with LMD at intracranial involvement (7.4 vs. 2.6 months, respectively). CONCLUSIONS: Patients with breast cancer and LMD may represent an ideal population for clinical trials given the higher incidence and potentially more favorable prognosis seen in this population.

Neutrophil-to-lymphocyte ratio trend: A novel prognostic predictor in patients with nasopharyngeal carcinoma receiving radiotherapy.

BACKGROUND: Peripheral neutrophil-lymphocyte ratio (NLR), reflecting immune-inflammation status, shows great potential for tumor progression and outcome. Pre-treatment NLR does not fully reflect the immune-inflammatory response to treatment. This study aimed to introduce the NLR trend as a new indicator and to investigate its prognostic value in patients with nasopharyngeal carcinoma receiving radiotherapy. METHODS: This retrospective study evaluated patients with nasopharyngeal carcinoma treated with radiotherapy. The NLR trend value was calculated from the fitted line gradient via the NLRs before, during (at least once), and after each patient's first radiotherapy. The Kaplan-Meier curve and log-rank test were used to calculate and compare survival outcomes of different pretreatment NLRs and NLR trends for progression-free survival, locoregional recurrence-free survival (LRFS), and overall survival at 3 and 5 years. Multivariate Cox regression analyses were performed to assess the association between the NLR trend plus 3- and 5-year overall survival. RESULTS: The study included 528 patients. A lower NLR trend predicted worse progression-free survival, LRFS, plus 3- and 5-year overall survival. Multivariate Cox regression analysis showed that the NLR trend independently predicted 3- and 5-year overall survival. Sub-group analysis showed that the prognosis of patients with a low pretreatment NLR and a high NLR trend were superior to those of other groups. CONCLUSION: The NLR trend independently predicted the prognosis of patients with nasopharyngeal carcinoma receiving radiotherapy. The NLR trend and the pretreatment NLR combination is more precise than pretreatment NLR in predicting prognosis. A high NLR trend may be evidence of a positive immune response to radiotherapy in patients with nasopharyngeal carcinoma.

Graded Prognostic Assessment (GPA) for Patients With Lung Cancer and Brain Metastases: Initial Report of the Small Cell Lung Cancer GPA and Update of the Non-Small Cell Lung Cancer GPA Including the Effect of Programmed Death Ligand 1 and Other Prognostic Factors.

PURPOSE: Patients with lung cancer and brain metastases represent a markedly heterogeneous population. Accurate prognosis is essential to optimally individualize care. In prior publications, we described the graded prognostic assessment (GPA), but a GPA for patients with small cell lung cancer (SCLC) has never been reported, and in non-small cell lung cancer (NSCLC), the effect of programmed death ligand 1 (PD-L1) was unknown. The 3-fold purpose of this work is to provide the initial report of an SCLC GPA, to evaluate the effect of PD-L1 on survival in patients with NSCLC, and to update the Lung GPA accordingly. METHODS AND MATERIALS: A multivariable analysis of prognostic factors and treatments associated with survival was performed on 4183 patients with lung cancer (3002 adenocarcinoma, 611 nonadenocarcinoma, 570 SCLC) with newly diagnosed brain metastases between January 1, 2015, and December 31, 2020, using a multi-institutional retrospective database. Significant variables were used to update the Lung GPA. RESULTS: Overall median survival for lung adenocarcinoma, SCLC, and nonadenocarcinoma was 17, 10, and 8 months, respectively, but varied widely by GPA from 2 to 52 months. In SCLC, the significant prognostic factors were age, performance status, extracranial metastases, and number of brain metastases. In NSCLC, the distribution of molecular markers among patients with lung adenocarcinoma and known primary tumor molecular status revealed alterations/expression in PD-L1 50% to 100%, PD-L1 1% to 49%, epidermal growth factor receptor, and anaplastic lymphoma kinase in 32%, 31%, 30%, and 7%, respectively. Median survival of patients with lung adenocarcinoma and brain metastases with 0, 1% to 49%, and ≥50% PD-L1 expression was 17, 19, and 24 months, respectively (P < .01), confirming PD-L1 is a prognostic factor. Previously identified prognostic factors for NSCLC (epidermal growth factor receptor and anaplastic lymphoma kinase status, performance status, age, number of brain metastases, and extracranial metastases) were reaffirmed. These factors were incorporated into the updated Lung GPA with robust separation between subgroups for all histologies. CONCLUSIONS: Survival for patients with lung cancer and brain metastases has improved but varies widely. The initial report of a GPA for SCLC is presented. For patients with NSCLC-adenocarcinoma and brain metastases, PD-L1 is a newly identified significant prognostic factor, and the previously identified factors were reaffirmed. The updated indices establish unique criteria for SCLC, NSCLC-nonadenocarcinoma, and NSCLC-adenocarcinoma (incorporating PD-L1). The updated Lung GPA, available for free at brainmetgpa.com, provides an accurate tool to estimate survival, individualize treatment, and stratify clinical trials.

Head and neck tumor segmentation in PET/CT: The HECKTOR challenge.

This paper relates the post-analysis of the first edition of the HEad and neCK TumOR (HECKTOR) challenge. This challenge was held as a satellite event of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2020, and was the first of its kind focusing on lesion segmentation in combined FDG-PET and CT image modalities. The challenge's task is the automatic segmentation of the Gross Tumor Volume (GTV) of Head and Neck (H&N) oropharyngeal primary tumors in FDG-PET/CT images. To this end, the participants were given a training set of 201 cases from four different centers and their methods were tested on a held-out set of 53 cases from a fifth center. The methods were ranked according to the Dice Score Coefficient (DSC) averaged across all test cases. An additional inter-observer agreement study was organized to assess the difficulty of the task from a human perspective. 64 teams registered to the challenge, among which 10 provided a paper detailing their approach. The best method obtained an average DSC of 0.7591, showing a large improvement over our proposed baseline method and the inter-observer agreement, associated with DSCs of 0.6610 and 0.61, respectively. The automatic methods proved to successfully leverage the wealth of metabolic and structural properties of combined PET and CT modalities, significantly outperforming human inter-observer agreement level, semi-automatic thresholding based on PET images as well as other single modality-based methods. This promising performance is one step forward towards large-scale radiomics studies in H&N cancer, obviating the need for error-prone and time-consuming manual delineation of GTVs.

18FDG positron emission tomography mining for metabolic imaging biomarkers of radiation-induced xerostomia in patients with oropharyngeal cancer.

PURPOSE: Head and neck cancers radiotherapy (RT) is associated with inevitable injury to parotid glands and subsequent xerostomia. We investigated the utility of SUV derived from 18FDG-PET to develop metabolic imaging biomarkers (MIBs) of RT-related parotid injury. METHODS: Data for oropharyngeal cancer (OPC) patients treated with RT at our institution between 2005 and 2015 with available planning computed tomography (CT), dose grid, pre- & first post-RT 18FDG-PET-CT scans, and physician-reported xerostomia assessment at 3-6 months post-RT (Xero 3-6 ms) per CTCAE, was retrieved, following an IRB approval. A CT-CT deformable image co-registration followed by voxel-by-voxel resampling of pre & post-RT 18FDG activity and dose grid were performed. Ipsilateral (Ipsi) and contralateral (contra) parotid glands were sub-segmented based on the received dose in 5 Gy increments, i.e. 0-5 Gy, 5-10 Gy sub-volumes, etc. Median and dose-weighted SUV were extracted from whole parotid volumes and sub-volumes on pre- & post-RT PET scans, using in-house code that runs on MATLAB. Wilcoxon signed-rank and Kruskal-Wallis tests were used to test differences pre- and post-RT. RESULTS: 432 parotid glands, belonging to 108 OPC patients treated with RT, were sub-segmented & analyzed. Xero 3-6 ms was reported as: non-severe (78.7%) and severe (21.3%). SUV- median values were significantly reduced post-RT, irrespective of laterality (p = 0.02). A similar pattern was observed in parotid sub-volumes, especially ipsi parotid gland sub-volumes receiving doses 10-50 Gy (p < 0.05). Kruskal-Wallis test showed a significantly higher mean RT dose in the contra parotid in the patients with more severe Xero 3-6mo (p = 0.03). Multiple logistic regression showed a combined clinical-dosimetric-metabolic imaging model could predict the severity of Xero 3-6mo; AUC = 0.78 (95%CI: 0.66-0.85; p < 0.0001). CONCLUSION: We sought to quantify pre- and post-RT 18FDG-PET metrics of parotid glands in patients with OPC. Temporal dynamics of PET-derived metrics can potentially serve as MIBs of RT-related xerostomia in concert with clinical and dosimetric variables.

Computed Tomography Radiomics Kinetics as Early Imaging Correlates of Osteoradionecrosis in Oropharyngeal Cancer Patients.

Osteoradionecrosis (ORN) is a major side-effect of radiation therapy in oropharyngeal cancer (OPC) patients. In this study, we demonstrate that early prediction of ORN is possible by analyzing the temporal evolution of mandibular subvolumes receiving radiation. For our analysis, we use computed tomography (CT) scans from 21 OPC patients treated with Intensity Modulated Radiation Therapy (IMRT) with subsequent radiographically-proven ≥ grade II ORN, at three different time points: pre-IMRT, 2-months, and 6-months post-IMRT. For each patient, radiomic features were extracted from a mandibular subvolume that developed ORN and a control subvolume that received the same dose but did not develop ORN. We used a Multivariate Functional Principal Component Analysis (MFPCA) approach to characterize the temporal trajectories of these features. The proposed MFPCA model performs the best at classifying ORN vs. Control subvolumes with an area under curve (AUC) = 0.74 [95% confidence interval (C.I.): 0.61-0.90], significantly outperforming existing approaches such as a pre-IMRT features model or a delta model based on changes at intermediate time points, i.e., at 2- and 6-month follow-up. This suggests that temporal trajectories of radiomics features derived from sequential pre- and post-RT CT scans can provide markers that are correlates of RT-induced mandibular injury, and consequently aid in earlier management of ORN.

Real-world evaluation of the impact of radiotherapy and chemotherapy in elderly patients with glioblastoma based on age and performance status.

BACKGROUND: This retrospective study investigated the impact of, in addition to age, the management and outcomes of elderly patients with glioblastoma (GBM). METHODS: The National Cancer Database was queried between 2004 and 2015 for GBM patients age 60 years and older. Three age groups were created: 60 to 69, 70 to 79, and 80 years and older, and 4 age/KPS groups: "age ≥ 60/ KPS < 70" (group 1), "age 60 to 69/KPS ≥ 70" (group 2), "age 70 to 79/KPS ≥ 70" (group 3), and "age ≥ 80/KPS ≥ 70" (group 4). Multivariable (MVA) modeling with Cox regression determined predictors of survival (OS), and estimated average treatment effects analysis was performed. RESULTS: A total of 48 540 patients with a median age of 70 years (range, 60-90 years) at diagnosis, and a median follow-up of 6.8 months (range, 0-151 months) were included. Median survival was 5.0, 15.2, 9.6, and 6.8 months in groups 1, 2, 3, and 4, respectively (P < .001). On treatment effects analysis, all groups survived longer with combined chemotherapy (ChT) and radiation therapy (RT), except group 1, which survived longer with ChT alone (P < .001). RT alone was associated with the worst OS in all groups (P < .01). Across all groups, predictors of worse OS on MVA were older age, lower KPS, White, higher comorbidity score, worse socioeconomic status, community treatment, tumor multifocality, subtotal resection, and no adjuvant treatment (all P < .01). CONCLUSIONS: In elderly patients with newly diagnosed GBM, those with good KPS fared best with combined ChT and RT across all age groups. Performance status is a key prognostic factor that should be considered for management decisions in these patients.

Tobacco exposure as a major modifier of oncologic outcomes in human papillomavirus (HPV) associated oropharyngeal squamous cell carcinoma.

BACKGROUND: The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-virally mediated OPSCC, this effect is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients. METHODS: We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002-2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p < 0.05). RESULTS: Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p = 0.002, p = 0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ > 30 PY patients didn't differ significantly from HPV- patients (p = 0.72, p = 0.27, respectively). HPV+ > 30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p = 0.03, 76% vs 88.3%; p = 0.07, and 52.3% vs 74%; p = 0.05, for stages I, II, and III (AJCC 8th Edition Manual), respectively. CONCLUSIONS: Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV + OPSCC smokers should be avoided.

Simultaneously spatial and temporal Higher-Order Total Variations for noise suppression and motion reduction in DCE and IVIM.

In many applications based on kinetic evaluation analysis and model fitting, quantitative mapping retrieved on data series from modalites such as MRI is completed on a voxel-by-voxel basis, where motion and low signal to noise ratio (SNR) would considerably degenerate the reliability of estimations. The coherence of image series in space and time can be used as prior knowledge to mitigate this occurrence. In this study, spatial and temporal higher-order total variations (HOTVs) are applied on a data series of MRI signal (e.g. dynamic contrast-enhanced (DCE) MRI and intravoxel incoherent motion (IVIM) MRI) to exploit the coherence of signal in space and time to minimize the variabilities caused by motion as well as improving quality of images with low SNR while retaining the physical details of original data properly. Simultaneously applying spatial and temporal HOTVs on images is non-trivial in implementation since it is a non-smooth optimization problem with multiple regularizers. Therefore, we use the proximal gradient method as well as a primal-dual split proximal mechanism to address the problem properly. In addition to increase the reliability of quantitative parametric map estimations, this preprocessing procedure can be included into many existing map estimation algorithms and pipelines effortlessly. We demonstrate our method on the parametric maps estimation for DCE MRI and IVIM MRI.

PleThora: Pleural effusion and thoracic cavity segmentations in diseased lungs for benchmarking chest CT processing pipelines.

This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with non-small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive "NSCLC Radiomics" data collection. Four hundred and two thoracic segmentations were first generated automatically by a U-Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy-eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert-vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y-gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs - where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from "NSCLC Radiomics," pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.