Multi-modality imaging parameters that predict rapid tumor regression in head and neck radiotherapy.

Background and purpose: Volume regression during radiotherapy can indicate patient-specific treatment response. We aimed to identify pre-treatment multimodality imaging (MMI) metrics from positron emission tomography (PET), magnetic resonance imaging (MRI), and computed tomography (CT) that predict rapid tumor regression during radiotherapy in human papilloma virus (HPV) associated oropharyngeal carcinoma. Materials and methods: Pre-treatment FDG PET-CT, diffusion-weighted MRI (DW-MRI), and intra-treatment (at 1, 2, and 3 weeks) MRI were acquired in 72 patients undergoing chemoradiation therapy for HPV+ oropharyngeal carcinoma. Nodal gross tumor volumes were delineated on longitudinal images to measure intra-treatment volume changes. Pre-treatment PET standardized uptake value (SUV), CT Hounsfield Unit (HU), and non-gaussian intravoxel incoherent motion DW-MRI metrics were computed and correlated with volume changes. Intercorrelations between MMI metrics were also assessed using network analysis. Validation was carried out on a separate cohort (N = 64) for FDG PET-CT. Results: Significant correlations with volume loss were observed for baseline FDG SUVmean (Spearman ρ = 0.46, p < 0.001), CT HUmean (ρ = 0.38, p = 0.001), and DW-MRI diffusion coefficient, Dmean (ρ = -0.39, p < 0.001). Network analysis revealed 41 intercorrelations between MMI and volume loss metrics, but SUVmean remained a statistically significant predictor of volume loss in multivariate linear regression (p = 0.01). Significant correlations were also observed for SUVmean in the validation cohort in both primary (ρ = 0.30, p = 0.02) and nodal (ρ = 0.31, p = 0.02) tumors. Conclusions: Multiple pre-treatment imaging metrics were correlated with rapid nodal gross tumor volume loss during radiotherapy. FDG-PET SUV in particular exhibited significant correlations with volume regression across the two cohorts and in multivariate analysis.

Evolutionary Strategies Enable Systematic and Reliable Uncertainty Quantification: A Proof-of-Concept Pilot Study on Resting-State Functional MRI Language Lateralization.

Reliable and trustworthy artificial intelligence (AI), particularly in high-stake medical diagnoses, necessitates effective uncertainty quantification (UQ). Existing UQ methods using model ensembles often introduce invalid variability or computational complexity, rendering them impractical and ineffective in clinical workflow. We propose a UQ approach based on deep neuroevolution (DNE), a data-efficient optimization strategy. Our goal is to replicate trends observed in expert-based UQ. We focused on language lateralization maps from resting-state functional MRI (rs-fMRI). Fifty rs-fMRI maps were divided into training/testing (30:20) sets, representing two labels: "left-dominant" and "co-dominant." DNE facilitated acquiring an ensemble of 100 models with high training and testing set accuracy. Model uncertainty was derived from distribution entropies over the 100 model predictions. Expert reviewers provided user-based uncertainties for comparison. Model (epistemic) and user-based (aleatoric) uncertainties were consistent in the independently and identically distributed (IID) testing set, mainly indicating low uncertainty. In a mostly out-of-distribution (OOD) holdout set, both model and user-based entropies correlated but displayed a bimodal distribution, with one peak representing low and another high uncertainty. We also found a statistically significant positive correlation between epistemic and aleatoric uncertainties. DNE-based UQ effectively mirrored user-based uncertainties, particularly highlighting increased uncertainty in OOD images. We conclude that DNE-based UQ correlates with expert assessments, making it reliable for our use case and potentially for other radiology applications.

A Phase II Study Assessing Long-term Response to Ibrutinib Monotherapy in Recurrent or Refractory CNS Lymphoma.

PURPOSE: Ibrutinib is a first-in-class inhibitor of Bruton tyrosine kinase. We previously reported the safety and short-term antitumor activity of ibrutinib in 20 patients with relapsed or refractory (r/r) primary central nervous system (CNS) lymphoma (PCNSL) or secondary CNS lymphoma (SCNSL). PATIENTS AND METHODS: We enrolled 26 additional patients with r/r PCNSL/SCNSL into the dose-expansion cohort of the trial into a combined cohort of 46 patients (31 with PCNSL and 15 with SCNSL). Patients received ibrutinib at 560 or 840 mg daily in the dose-escalation cohort and ibrutinib at 840 mg daily in the expansion cohort. The median follow-up was 49.9 and 62.1 months for patients with PCNSL and SCNSL, respectively. We sequenced DNA from available tumor biopsies and cerebrospinal fluid collected before and during ibrutinib therapy. RESULTS: Tumor responses were observed in 23/31 (74%) patients with PCNSL and 9/15 (60%) patients with SCNSL, including 12 complete responses in PCNSL and 7 in SCNSL. The median progression-free survival (PFS) for PCNSL was 4.5 months [95% confidence interval (CI), 2.8-9.2] with 1-year PFS at 23.7% (95% CI, 12.4%-45.1%). The median duration of response in the 23 PCNSL responders was 5.5 months. The median PFS in SCNSL was 5.3 months (95% CI, 1.3-14.5) with a median duration of response of 8.7 months for the 9 responders. Exploratory biomarker analysis suggests that mutations in TBL1XR1 may be associated with a long-term response to ibrutinib in PCNSL (P = 0.0075). Clearance of ctDNA from cerebrospinal fluid was associated with complete and long-term ibrutinib responses. CONCLUSIONS: Our study confirms single-agent activity of ibrutinib in r/r CNS lymphoma and identifies molecular determinants of response based on long-term follow-up.

Differentiating Low-Grade from High-Grade Intracranial Ependymomas: Comparison of Dynamic Contrast-Enhanced MRI and Diffusion-Weighted Imaging.

BACKGROUND AND PURPOSE: The aim of this study was to determine the diagnostic value of fractional plasma volume derived from dynamic contrast-enhanced perfusion MR imaging versus ADC, obtained from DWI in differentiating between grade 2 (low-grade) and grade 3 (high-grade) intracranial ependymomas. MATERIALS AND METHODS: A hospital database was created for the period from January 2013 through June 2022, including patients with histologically-proved ependymoma diagnosis with available dynamic contrast-enhanced MR imaging. Both dynamic contrast-enhanced perfusion and DWI were performed on each patient using 1.5T and 3T scanners. Fractional plasma volume maps and ADC maps were calculated. ROIs were defined by a senior neuroradiologist manually by including the enhancing tumor on every section and conforming a VOI to obtain the maximum value of fractional plasma volume (Vpmax) and the minimum value of ADC (ADCmin). A Mann-Whitney U test at a significance level of corrected P = .01 was used to evaluate the differences. Additionally, receiver operating characteristic curve analysis was applied to assess the sensitivity and specificity of Vpmax and ADCmin values. RESULTS: A total of 20 patients with ependymomas (10 grade 2 tumors and 10 grade 3 tumors) were included. Vpmax values for grade 3 ependymomas were significantly higher (P < .002) than those for grade 2. ADCmin values were overall lower in high-grade lesions. However, no statistically significant differences were found (P = .12114). CONCLUSIONS: As a dynamic contrast-enhanced perfusion MR imaging metric, fractional plasma volume can be used as an indicator to differentiate grade 2 and grade 3 ependymomas. Dynamic contrast-enhanced perfusion MR imaging plays an important role with high diagnostic value in differentiating low- and high-grade ependymoma.

Mixed histiocytic neoplasms: A multicentre series revealing diverse somatic mutations and responses to targeted therapy.

Histiocytic neoplasms are diverse clonal haematopoietic disorders, and clinical disease is mediated by tumorous infiltration as well as uncontrolled systemic inflammation. Individual subtypes include Langerhans cell histiocytosis (LCH), Rosai-Dorfman-Destombes disease (RDD) and Erdheim-Chester disease (ECD), and these have been characterized with respect to clinical phenotypes, driver mutations and treatment paradigms. Less is known about patients with mixed histiocytic neoplasms (MXH), that is two or more coexisting disorders. This international collaboration examined patients with biopsy-proven MXH with respect to component disease subtypes, oncogenic driver mutations and responses to conventional (chemotherapeutic or immunosuppressive) versus targeted (BRAF or MEK inhibitor) therapies. Twenty-seven patients were studied with ECD/LCH (19/27), ECD/RDD (6/27), RDD/LCH (1/27) and ECD/RDD/LCH (1/27). Mutations previously undescribed in MXH were identified, including KRAS, MAP2K2, MAPK3, non-V600-BRAF, RAF1 and a BICD2-BRAF fusion. A repeated-measure generalized estimating equation demonstrated that targeted treatment was statistically significantly (1) more likely to result in a complete response (CR), partial response (PR) or stable disease (SD) (odds ratio [OR]: 17.34, 95% CI: 2.19-137.00, p = 0.007), and (2) less likely to result in progression (OR: 0.08, 95% CI: 0.03-0.23, p < 0.0001). Histiocytic neoplasms represent an entity with underappreciated clinical and molecular diversity, poor responsiveness to conventional therapy and exquisite sensitivity to targeted therapy.

Auto-segmentation of neck nodal metastases using self-distilled masked image transformer on longitudinal MR images.

Objectives: Auto-segmentation promises greater speed and lower inter-reader variability than manual segmentations in radiation oncology clinical practice. This study aims to implement and evaluate the accuracy of the auto-segmentation algorithm, "Masked Image modeling using the vision Transformers (SMIT)," for neck nodal metastases on longitudinal T2-weighted (T2w) MR images in oropharyngeal squamous cell carcinoma (OPSCC) patients. Methods: This prospective clinical trial study included 123 human papillomaviruses (HPV-positive [+]) related OSPCC patients who received concurrent chemoradiotherapy. T2w MR images were acquired on 3 T at pre-treatment (Tx), week 0, and intra-Tx weeks (1-3). Manual delineations of metastatic neck nodes from 123 OPSCC patients were used for the SMIT auto-segmentation, and total tumor volumes were calculated. Standard statistical analyses compared contour volumes from SMIT vs manual segmentation (Wilcoxon signed-rank test [WSRT]), and Spearman's rank correlation coefficients (ρ) were computed. Segmentation accuracy was evaluated on the test data set using the dice similarity coefficient (DSC) metric value. P-values <0.05 were considered significant. Results: No significant difference in manual and SMIT delineated tumor volume at pre-Tx (8.68 ± 7.15 vs 8.38 ± 7.01 cm3, P = 0.26 [WSRT]), and the Bland-Altman method established the limits of agreement as -1.71 to 2.31 cm3, with a mean difference of 0.30 cm3. SMIT model and manually delineated tumor volume estimates were highly correlated (ρ = 0.84-0.96, P < 0.001). The mean DSC metric values were 0.86, 0.85, 0.77, and 0.79 at the pre-Tx and intra-Tx weeks (1-3), respectively. Conclusions: The SMIT algorithm provides sufficient segmentation accuracy for oncological applications in HPV+ OPSCC. Advances in knowledge: First evaluation of auto-segmentation with SMIT using longitudinal T2w MRI in HPV+ OPSCC.

Hypoxia-Directed Treatment of Human Papillomavirus-Related Oropharyngeal Carcinoma.

PURPOSE: Standard curative-intent chemoradiotherapy for human papillomavirus (HPV)-related oropharyngeal carcinoma results in significant toxicity. Since hypoxic tumors are radioresistant, we posited that the aerobic state of a tumor could identify patients eligible for de-escalation of chemoradiotherapy while maintaining treatment efficacy. METHODS: We enrolled patients with HPV-related oropharyngeal carcinoma to receive de-escalated definitive chemoradiotherapy in a phase II study (ClinicalTrials.gov identifier: NCT03323463). Patients first underwent surgical removal of disease at their primary site, but not of gross disease in the neck. A baseline 18F-fluoromisonidazole positron emission tomography scan was used to measure tumor hypoxia and was repeated 1-2 weeks intratreatment. Patients with nonhypoxic tumors received 30 Gy (3 weeks) with chemotherapy, whereas those with hypoxic tumors received standard chemoradiotherapy to 70 Gy (7 weeks). The primary objective was achieving a 2-year locoregional control (LRC) of 95% with a 7% noninferiority margin. RESULTS: One hundred fifty-eight patients with T0-2/N1-N2c were enrolled, of which 152 patients were eligible for analyses. Of these, 128 patients met criteria for 30 Gy and 24 patients received 70 Gy. The 2-year LRC was 94.7% (95% CI, 89.8 to 97.7), meeting our primary objective. With a median follow-up time of 38.3 (range, 22.1-58.4) months, the 2-year progression-free survival (PFS) and overall survival (OS) rates were 94% and 100%, respectively, for the 30-Gy cohort. The 70-Gy cohort had similar 2-year PFS and OS rates at 96% and 96%, respectively. Acute grade 3-4 adverse events were more common in 70 Gy versus 30 Gy (58.3% v 32%; P = .02). Late grade 3-4 adverse events only occurred in the 70-Gy cohort, in which 4.5% complained of late dysphagia. CONCLUSION: Tumor hypoxia is a promising approach to direct dosing of curative-intent chemoradiotherapy for HPV-related carcinomas with preserved efficacy and substantially reduced toxicity that requires further investigation.

A Quantitative Multiparametric MRI Analysis Platform for Estimation of Robust Imaging Biomarkers in Clinical Oncology.

There is a need to develop user-friendly imaging tools estimating robust quantitative biomarkers (QIBs) from multiparametric (mp)MRI for clinical applications in oncology. Quantitative metrics derived from (mp)MRI can monitor and predict early responses to treatment, often prior to anatomical changes. We have developed a vendor-agnostic, flexible, and user-friendly MATLAB-based toolkit, MRI-Quantitative Analysis and Multiparametric Evaluation Routines ("MRI-QAMPER", current release v3.0), for the estimation of quantitative metrics from dynamic contrast-enhanced (DCE) and multi-b value diffusion-weighted (DW) MR and MR relaxometry. MRI-QAMPER's functionality includes generating numerical parametric maps from these methods reflecting tumor permeability, cellularity, and tissue morphology. MRI-QAMPER routines were validated using digital reference objects (DROs) for DCE and DW MRI, serving as initial approval stages in the National Cancer Institute Quantitative Imaging Network (NCI/QIN) software benchmark. MRI-QAMPER has participated in DCE and DW MRI Collaborative Challenge Projects (CCPs), which are key technical stages in the NCI/QIN benchmark. In a DCE CCP, QAMPER presented the best repeatability coefficient (RC = 0.56) across test-retest brain metastasis data, out of ten participating DCE software packages. In a DW CCP, QAMPER ranked among the top five (out of fourteen) tools with the highest area under the curve (AUC) for prostate cancer detection. This platform can seamlessly process mpMRI data from brain, head and neck, thyroid, prostate, pancreas, and bladder cancer. MRI-QAMPER prospectively analyzes dose de-escalation trial data for oropharyngeal cancer, which has earned it advanced NCI/QIN approval for expanded usage and applications in wider clinical trials.

Artificial Intelligence in CT and MR Imaging for Oncological Applications.

Cancer care increasingly relies on imaging for patient management. The two most common cross-sectional imaging modalities in oncology are computed tomography (CT) and magnetic resonance imaging (MRI), which provide high-resolution anatomic and physiological imaging. Herewith is a summary of recent applications of rapidly advancing artificial intelligence (AI) in CT and MRI oncological imaging that addresses the benefits and challenges of the resultant opportunities with examples. Major challenges remain, such as how best to integrate AI developments into clinical radiology practice, the vigorous assessment of quantitative CT and MR imaging data accuracy, and reliability for clinical utility and research integrity in oncology. Such challenges necessitate an evaluation of the robustness of imaging biomarkers to be included in AI developments, a culture of data sharing, and the cooperation of knowledgeable academics with vendor scientists and companies operating in radiology and oncology fields. Herein, we will illustrate a few challenges and solutions of these efforts using novel methods for synthesizing different contrast modality images, auto-segmentation, and image reconstruction with examples from lung CT as well as abdome, pelvis, and head and neck MRI. The imaging community must embrace the need for quantitative CT and MRI metrics beyond lesion size measurement. AI methods for the extraction and longitudinal tracking of imaging metrics from registered lesions and understanding the tumor environment will be invaluable for interpreting disease status and treatment efficacy. This is an exciting time to work together to move the imaging field forward with narrow AI-specific tasks. New AI developments using CT and MRI datasets will be used to improve the personalized management of cancer patients.

Fast, light, and scalable: harnessing data-mined line annotations for automated tumor segmentation on brain MRI.

OBJECTIVES: While fully supervised learning can yield high-performing segmentation models, the effort required to manually segment large training sets limits practical utility. We investigate whether data mined line annotations can facilitate brain MRI tumor segmentation model development without requiring manually segmented training data. METHODS: In this retrospective study, a tumor detection model trained using clinical line annotations mined from PACS was leveraged with unsupervised segmentation to generate pseudo-masks of enhancing tumors on T1-weighted post-contrast images (9911 image slices; 3449 adult patients). Baseline segmentation models were trained and employed within a semi-supervised learning (SSL) framework to refine the pseudo-masks. Following each self-refinement cycle, a new model was trained and tested on a held-out set of 319 manually segmented image slices (93 adult patients), with the SSL cycles continuing until Dice score coefficient (DSC) peaked. DSCs were compared using bootstrap resampling. Utilizing the best-performing models, two inference methods were compared: (1) conventional full-image segmentation, and (2) a hybrid method augmenting full-image segmentation with detection plus image patch segmentation. RESULTS: Baseline segmentation models achieved DSC of 0.768 (U-Net), 0.831 (Mask R-CNN), and 0.838 (HRNet), improving with self-refinement to 0.798, 0.871, and 0.873 (each p < 0.001), respectively. Hybrid inference outperformed full image segmentation alone: DSC 0.884 (Mask R-CNN) vs. 0.873 (HRNet), p < 0.001. CONCLUSIONS: Line annotations mined from PACS can be harnessed within an automated pipeline to produce accurate brain MRI tumor segmentation models without manually segmented training data, providing a mechanism to rapidly establish tumor segmentation capabilities across radiology modalities. KEY POINTS: • A brain MRI tumor detection model trained using clinical line measurement annotations mined from PACS was leveraged to automatically generate tumor segmentation pseudo-masks. • An iterative self-refinement process automatically improved pseudo-mask quality, with the best-performing segmentation pipeline achieving a Dice score of 0.884 on a held-out test set. • Tumor line measurement annotations generated in routine clinical radiology practice can be harnessed to develop high-performing segmentation models without manually segmented training data, providing a mechanism to rapidly establish tumor segmentation capabilities across radiology modalities.

Quantitative Relaxometry Metrics for Brain Metastases Compared to Normal Tissues: A Pilot MR Fingerprinting Study.

The purpose of the present pilot study was to estimate T1 and T2 metric values derived simultaneously from a new, rapid Magnetic Resonance Fingerprinting (MRF) technique, as well as to assess their ability to characterize-brain metastases (BM) and normal-appearing brain tissues. Fourteen patients with BM underwent MRI, including prototype MRF, on a 3T scanner. In total, 108 measurements were analyzed: 42 from solid parts of BM's (21 each on T1 and T2 maps) and 66 from normal-appearing brain tissue (11 ROIs each on T1 and T2 maps for gray matter [GM], white matter [WM], and cerebrospinal fluid [CSF]). The BM's mean T1 and T2 values differed significantly from normal-appearing WM (p < 0.05). The mean T1 values from normal-appearing GM, WM, and CSF regions were 1205 ms, 840 ms, and 4233 ms, respectively. The mean T2 values were 108 ms, 78 ms, and 442 ms, respectively. The mean T1 and T2 values for untreated BM (n = 4) were 2035 ms and 168 ms, respectively. For treated BM (n = 17) the T1 and T2 values were 2163 ms and 141 ms, respectively. MRF technique appears to be a promising and rapid quantitative method for the characterization of free water content and tumor morphology in BMs.

Qualitative and Quantitative Performance of Magnetic Resonance Image Compilation (MAGiC) Method: An Exploratory Analysis for Head and Neck Imaging.

The present exploratory study investigates the performance of a new, rapid, synthetic MRI method for diagnostic image quality assessment and measurement of relaxometry metric values in head and neck (HN) tumors and normal-appearing masseter muscle. The multi-dynamic multi-echo (MDME) sequence was used for data acquisition, followed by synthetic image reconstruction on a 3T MRI scanner for 14 patients (3 untreated and 11 treated). The MDME enables absolute quantification of physical tissue properties, including T1 and T2, with a shorter scan time than the current state-of-the-art methods used for relaxation measurements. The vendor termed the combined package MAGnetic resonance imaging Compilation (MAGiC). In total, 48 regions of interest (ROIs) were analyzed, drawn on normal-appearing masseter muscle and tumors in the HN region. Mean T1 and T2 values obtained from normal-appearing muscle were 880 ± 52 ms and 46 ± 3 ms, respectively. Mean T1 and T2 values obtained from tumors were 1930 ± 422 ms and 77 ± 13 ms, respectively, for the untreated group, 1745 ± 410 ms and 107 ± 61 ms, for the treated group. A total of 1552 images from both synthetic MRI and conventional clinical imaging were assessed by the radiologists to provide the rating for T1w and T2w image contrasts. The synthetically generated qualitative T2w images were acceptable and comparable to conventional diagnostic images (93% acceptability rating for both). The acceptability ratings for MAGiC-generated T1w, and conventional images were 64% and 100%, respectively. The benefit of MAGiC in HN imaging is twofold, providing relaxometry maps in a clinically feasible time and the ability to generate a different combination of contrast images in a single acquisition.

Quantitative Synthetic Magnetic Resonance Imaging for Brain Metastases: A Feasibility Study.

The present preliminary study aims to characterize brain metastases (BM) using T1 and T2 maps generated from newer, rapid, synthetic MRI (MAGnetic resonance image Compilation; MAGiC) in a clinical setting. We acquired synthetic MRI data from 11 BM patients on a 3T scanner. A multiple-dynamic multiple-echo (MDME) sequence was used for data acquisition and synthetic image reconstruction, including post-processing. MDME is a multi-contrast sequence that enables absolute quantification of physical tissue properties, including T1 and T2, independent of the scanner settings. In total, 82 regions of interest (ROIs) were analyzed, which were obtained from both normal-appearing brain tissue and BM lesions. The mean values obtained from the 48 normal-appearing brain tissue regions and 34 ROIs of BM lesions (T1 and T2) were analyzed using standard statistical methods. The mean T1 and T2 values were 1143 ms and 78 ms, respectively, for normal-appearing gray matter, 701 ms and 64 ms for white matter, and 4206 ms and 390 ms for cerebrospinal fluid. For untreated BMs, the mean T1 and T2 values were 1868 ms and 100 ms, respectively, and 2211 ms and 114 ms for the treated group. The quantitative T1 and T2 values generated from synthetic MRI can characterize BM and normal-appearing brain tissues.

Semisupervised Training of a Brain MRI Tumor Detection Model Using Mined Annotations.

Background Artificial intelligence (AI) applications for cancer imaging conceptually begin with automated tumor detection, which can provide the foundation for downstream AI tasks. However, supervised training requires many image annotations, and performing dedicated post hoc image labeling is burdensome and costly. Purpose To investigate whether clinically generated image annotations can be data mined from the picture archiving and communication system (PACS), automatically curated, and used for semisupervised training of a brain MRI tumor detection model. Materials and Methods In this retrospective study, the cancer center PACS was mined for brain MRI scans acquired between January 2012 and December 2017 and included all annotated axial T1 postcontrast images. Line annotations were converted to boxes, excluding boxes shorter than 1 cm or longer than 7 cm. The resulting boxes were used for supervised training of object detection models using RetinaNet and Mask region-based convolutional neural network (R-CNN) architectures. The best-performing model trained from the mined data set was used to detect unannotated tumors on training images themselves (self-labeling), automatically correcting many of the missing labels. After self-labeling, new models were trained using this expanded data set. Models were scored for precision, recall, and F1 using a held-out test data set comprising 754 manually labeled images from 100 patients (403 intra-axial and 56 extra-axial enhancing tumors). Model F1 scores were compared using bootstrap resampling. Results The PACS query extracted 31 150 line annotations, yielding 11 880 boxes that met inclusion criteria. This mined data set was used to train models, yielding F1 scores of 0.886 for RetinaNet and 0.908 for Mask R-CNN. Self-labeling added 18 562 training boxes, improving model F1 scores to 0.935 (P < .001) and 0.954 (P < .001), respectively. Conclusion The application of semisupervised learning to mined image annotations significantly improved tumor detection performance, achieving an excellent F1 score of 0.954. This development pipeline can be extended for other imaging modalities, repurposing unused data silos to potentially enable automated tumor detection across radiologic modalities. © RSNA, 2022 Online supplemental material is available for this article.

Application of Community Detection Algorithm to Investigate the Correlation between Imaging Biomarkers of Tumor Metabolism, Hypoxia, Cellularity, and Perfusion for Precision Radiotherapy in Head and Neck Squamous Cell Carcinomas.

The present study aimed to investigate the correlation at pre-treatment (TX) between quantitative metrics derived from multimodality imaging (MMI), including 18F-FDG-PET/CT, 18F-FMISO-PET/CT, DW- and DCE-MRI, using a community detection algorithm (CDA) in head and neck squamous cell carcinoma (HNSCC) patients. Twenty-three HNSCC patients with 27 metastatic lymph nodes underwent a total of 69 MMI exams at pre-TX. Correlations among quantitative metrics derived from FDG-PET/CT (SUL), FMSIO-PET/CT (K1, k3, TBR, and DV), DW-MRI (ADC, IVIM [D, D*, and f]), and FXR DCE-MRI [Ktrans, ve, and τi]) were investigated using the CDA based on a "spin-glass model" coupled with the Spearman's rank, ρ, analysis. Mean MRI T2 weighted tumor volumes and SULmean values were moderately positively correlated (ρ = 0.48, p = 0.01). ADC and D exhibited a moderate negative correlation with SULmean (ρ ≤ -0.42, p < 0.03 for both). K1 and Ktrans were positively correlated (ρ = 0.48, p = 0.01). In contrast, Ktrans and k3max were negatively correlated (ρ = -0.41, p = 0.03). CDA revealed four communities for 16 metrics interconnected with 33 edges in the network. DV, Ktrans, and K1 had 8, 7, and 6 edges in the network, respectively. After validation in a larger population, the CDA approach may aid in identifying useful biomarkers for developing individual patient care in HNSCC.

Reproducibility of radiomic features using network analysis and its application in Wasserstein k-means clustering.

Purpose: The goal of this study is to develop innovative methods for identifying radiomic features that are reproducible over varying image acquisition settings. Approach: We propose a regularized partial correlation network to identify reliable and reproducible radiomic features. This approach was tested on two radiomic feature sets generated using two different reconstruction methods on computed tomography (CT) scans from a cohort of 47 lung cancer patients. The largest common network component between the two networks was tested on phantom data consisting of five cancer samples. To further investigate whether radiomic features found can identify phenotypes, we propose a k -means clustering algorithm coupled with the optimal mass transport theory. This approach following the regularized partial correlation network analysis was tested on CT scans from 77 head and neck squamous cell carcinoma (HNSCC) patients in the Cancer Imaging Archive (TCIA) and validated using an independent dataset. Results: A set of common radiomic features was found in relatively large network components between the resultant two partial correlation networks resulting from a cohort of lung cancer patients. The reliability and reproducibility of those radiomic features were further validated on phantom data using the Wasserstein distance. Further analysis using the network-based Wasserstein k -means algorithm on the TCIA HNSCC data showed that the resulting clusters separate tumor subsites as well as HPV status, and this was validated on an independent dataset. Conclusion: We showed that a network-based analysis enables identifying reproducible radiomic features and use of the selected set of features can enhance clustering results.

Prognostic value of [18F]FDG PET/CT in patients with CNS lymphoma receiving ibrutinib-based therapies.

PURPOSE: Current clinical and imaging tools remain suboptimal for predicting treatment response and prognosis in CNS lymphomas. We investigated the prognostic value of baseline [18F]FDG PET in patients with CNS lymphoma receiving ibrutinib-based treatments. METHODS: Fifty-three patients enrolled in a prospective clinical trial and underwent brain PET before receiving single-agent ibrutinib or ibrutinib in combination with methotrexate with or without rituximab. [18F]FDG uptake in these lesions was quantified by drawing PET volumes of interest around up to five [18F]FDG-avid lesions per patient (with uptake greater than surrounding brain). We measured standardized uptake values (SUVmax), metabolic tumor volumes, total lesion glycolysis (TLG), and the sum thereof in these lesions. We analyzed the relationship between PET parameters and mutation status, overall response rates, and progression-free survival (PFS). RESULTS: Thirty-eight patients underwent single-agent therapy and 15 received combination therapy. On PET, 15/53 patients had no measurable disease. In the other 38 patients, a total of 71 lesions were identified on PET. High-intensity [18F]FDG uptake and a larger volume of [18F]FDG-avid disease were inversely related to treatment outcome (p ≤ 0.005). In univariable analysis, PFS was linearly correlated with all PET parameters, with stronger association when sum-values were used. A multivariable model showed that risk of progression increased by 9% for every 5-unit increase in sumSUVmax (hazard ratio = 1.09 [95% CI: 1.04 to 1.14]). CONCLUSION: Higher lesional metabolic parameters are inversely related to outcome in patients undergoing ibrutinib-based therapies, and sumSUVmax emerged as a strong independent prognostic factor. TRIAL REGISTRATION: NCT02315326; https://clinicaltrials.gov/ct2/show/NCT02315326?term=NCT02315326&draw=2&rank=1.