Overcoming data scarcity in radiomics/radiogenomics using synthetic radiomic features.

PURPOSE: To evaluate the potential of synthetic radiomic data generation in addressing data scarcity in radiomics/radiogenomics models. METHODS: This study was conducted on a retrospectively collected cohort of 386 colorectal cancer patients (n = 2570 lesions) for whom matched contrast-enhanced CT images and gene TP53 mutational status were available. The full cohort data was divided into a training cohort (n = 2055 lesions) and an independent and fixed test set (n = 515 lesions). Differently sized training sets were subsampled from the training cohort to measure the impact of sample size on model performance and assess the added value of synthetic radiomic augmentation at different sizes. Five different tabular synthetic data generation models were used to generate synthetic radiomic data based on "real-world" radiomics data extracted from this cohort. The quality and reproducibility of the generated synthetic radiomic data were assessed. Synthetic radiomics were then combined with "real-world" radiomic training data to evaluate their impact on the predictive model's performance. RESULTS: A prediction model was generated using only "real-world" radiomic data, revealing the impact of data scarcity in this particular data set through a lack of predictive performance at low training sample numbers (n = 200, 400, 1000 lesions with average AUC = 0.52, 0.53, and 0.56 respectively, compared to 0.64 when using 2055 training lesions). Synthetic tabular data generation models created reproducible synthetic radiomic data with properties highly similar to "real-world" data (for n = 1000 lesions, average Chi-square = 0.932, average basic statistical correlation = 0.844). The integration of synthetic radiomic data consistently enhanced the performance of predictive models trained with small sample size sets (AUC enhanced by 9.6%, 11.3%, and 16.7% for models trained on n_samples = 200, 400, and 1000 lesions, respectively). In contrast, synthetic data generated from randomised/noisy radiomic data failed to enhance predictive performance underlining the requirement of true signal data to do so. CONCLUSION: Synthetic radiomic data, when combined with real radiomics, could enhance the performance of predictive models. Tabular synthetic data generation might help to overcome limitations in medical AI stemming from data scarcity.

Correlation of gene expression with magnetic resonance imaging features of retinoblastoma: a multi-center radiogenomics validation study.

OBJECTIVES: To validate associations between MRI features and gene expression profiles in retinoblastoma, thereby evaluating the repeatability of radiogenomics in retinoblastoma. METHODS: In this retrospective multicenter cohort study, retinoblastoma patients with gene expression data and MRI were included. MRI features (scored blinded for clinical data) and matched genome-wide gene expression data were used to perform radiogenomic analysis. Expression data from each center were first separately processed and analyzed. The end product normalized expression values from different sites were subsequently merged by their Z-score to permit cross-sites validation analysis. The MRI features were non-parametrically correlated with expression of photoreceptorness (radiogenomic analysis), a gene expression signature informing on disease progression. Outcomes were compared to outcomes in a previous described cohort. RESULTS: Thirty-six retinoblastoma patients were included, 15 were female (42%), and mean age was 24 (SD 18) months. Similar to the prior evaluation, this validation study showed that low photoreceptorness gene expression was associated with advanced stage imaging features. Validated imaging features associated with low photoreceptorness were multifocality, a tumor encompassing the entire retina or entire globe, and a diffuse growth pattern (all p < 0.05). There were a number of radiogenomic associations that were also not validated. CONCLUSIONS: A part of the radiogenomic associations could not be validated, underlining the importance of validation studies. Nevertheless, cross-center validation of imaging features associated with photoreceptorness gene expression highlighted the capability radiogenomics to non-invasively inform on molecular subtypes in retinoblastoma. CLINICAL RELEVANCE STATEMENT: Radiogenomics may serve as a surrogate for molecular subtyping based on histopathology material in an era of eye-sparing retinoblastoma treatment strategies. KEY POINTS: • Since retinoblastoma is increasingly treated using eye-sparing methods, MRI features informing on molecular subtypes that do not rely on histopathology material are important. • A part of the associations between retinoblastoma MRI features and gene expression profiles (radiogenomics) were validated. • Radiogenomics could be a non-invasive technique providing information on the molecular make-up of retinoblastoma.

The Prediction of Biological Features Using Magnetic Resonance Imaging in Head and Neck Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.

Magnetic resonance imaging (MRI) is an indispensable, routine technique that provides morphological and functional imaging sequences. MRI can potentially capture tumor biology and allow for longitudinal evaluation of head and neck squamous cell carcinoma (HNSCC). This systematic review and meta-analysis evaluates the ability of MRI to predict tumor biology in primary HNSCC. Studies were screened, selected, and assessed for quality using appropriate tools according to the PRISMA criteria. Fifty-eight articles were analyzed, examining the relationship between (functional) MRI parameters and biological features and genetics. Most studies focused on HPV status associations, revealing that HPV-positive tumors consistently exhibited lower ADCmean (SMD: 0.82; p < 0.001) and ADCminimum (SMD: 0.56; p < 0.001) values. On average, lower ADCmean values are associated with high Ki-67 levels, linking this diffusion restriction to high cellularity. Several perfusion parameters of the vascular compartment were significantly associated with HIF-1α. Analysis of other biological factors (VEGF, EGFR, tumor cell count, p53, and MVD) yielded inconclusive results. Larger datasets with homogenous acquisition are required to develop and test radiomic-based prediction models capable of capturing different aspects of the underlying tumor biology. Overall, our study shows that rapid and non-invasive characterization of tumor biology via MRI is feasible and could enhance clinical outcome predictions and personalized patient management for HNSCC.

MRI Features for Identifying MYCN-amplified RB1 Wild-type Retinoblastoma.

Background MYCN-amplified RB1 wild-type (MYCNARB1+/+) retinoblastoma is a rare but clinically important subtype of retinoblastoma due to its aggressive character and relative resistance to typical therapeutic approaches. Because biopsy is not indicated in retinoblastoma, specific MRI features might be valuable to identify children with this genetic subtype. Purpose To define the MRI phenotype of MYCNARB1+/+ retinoblastoma and evaluate the ability of qualitative MRI features to help identify this specific genetic subtype. Materials and Methods In this retrospective, multicenter, case-control study, MRI scans in children with MYCNARB1+/+ retinoblastoma and age-matched children with RB1-/- subtype retinoblastoma were included (case-control ratio, 1:4; scans acquired from June 2001 to February 2021; scans collected from May 2018 to October 2021). Patients with histopathologically confirmed unilateral retinoblastoma, genetic testing (RB1/MYCN status), and MRI scans were included. Associations between radiologist-scored imaging features and diagnosis were assessed with the Fisher exact test or Fisher-Freeman-Halton test, and Bonferroni-corrected P values were calculated. Results A total of 110 patients from 10 retinoblastoma referral centers were included: 22 children with MYCNARB1+/+ retinoblastoma and 88 control children with RB1-/- retinoblastoma. Children in the MYCNARB1+/+ group had a median age of 7.0 months (IQR, 5.0-9.0 months) (13 boys), while children in the RB1-/- group had a median age of 9.0 months (IQR, 4.6-13.4 months) (46 boys). MYCNARB1+/+ retinoblastomas were typically peripherally located (in 10 of 17 children; specificity, 97%; P < .001) and exhibited plaque or pleomorphic shape (in 20 of 22 children; specificity, 51%; P = .011) with irregular margins (in 16 of 22 children; specificity, 70%; P = .008) and extensive retina folding with vitreous enclosure (specificity, 94%; P < .001). MYCNARB1+/+ retinoblastomas showed peritumoral hemorrhage (in 17 of 21 children; specificity, 88%; P < .001), subretinal hemorrhage with a fluid-fluid level (in eight of 22 children; specificity, 95%; P = .005), and strong anterior chamber enhancement (in 13 of 21 children; specificity, 80%; P = .008). Conclusion MYCNARB1+/+ retinoblastomas show distinct MRI features that could enable early identification of these tumors. This may improve patient selection for tailored treatment in the future. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Rollins in this issue.

External validation of an MR-based radiomic model predictive of locoregional control in oropharyngeal cancer.

OBJECTIVES: To externally validate a pre-treatment MR-based radiomics model predictive of locoregional control in oropharyngeal squamous cell carcinoma (OPSCC) and to assess the impact of differences between datasets on the predictive performance. METHODS: Radiomic features, as defined in our previously published radiomics model, were extracted from the primary tumor volumes of 157 OPSCC patients in a different institute. The developed radiomics model was validated using this cohort. Additionally, parameters influencing performance, such as patient subgroups, MRI acquisition, and post-processing steps on prediction performance will be investigated. For this analysis, matched subgroups (based on human papillomavirus (HPV) status of the tumor, T-stage, and tumor subsite) and a subgroup with only patients with 4-mm slice thickness were studied. Also the influence of harmonization techniques (ComBat harmonization, quantile normalization) and the impact of feature stability across observers and centers were studied. Model performances were assessed by area under the curve (AUC), sensitivity, and specificity. RESULTS: Performance of the published model (AUC/sensitivity/specificity: 0.74/0.75/0.60) drops when applied on the validation cohort (AUC/sensitivity/specificity: 0.64/0.68/0.60). The performance of the full validation cohort improves slightly when the model is validated using a patient group with comparable HPV status of the tumor (AUC/sensitivity/specificity: 0.68/0.74/0.60), using patients acquired with a slice thickness of 4 mm (AUC/sensitivity/specificity: 0.67/0.73/0.57), or when quantile harmonization was performed (AUC/sensitivity/specificity: 0.66/0.69/0.60). CONCLUSION: The previously published model shows its generalizability and can be applied on data acquired from different vendors and protocols. Harmonization techniques and subgroup definition influence performance of predictive radiomics models. KEY POINTS: • Radiomics, a noninvasive quantitative image analysis technique, can support the radiologist by enhancing diagnostic accuracy and/or treatment decision-making. • A previously published model shows its generalizability and could be applied on data acquired from different vendors and protocols.

Quantitative Diffusion-Weighted Imaging Analyses to Predict Response to Neoadjuvant Immunotherapy in Patients with Locally Advanced Head and Neck Carcinoma.

BACKGROUND: Neoadjuvant immune checkpoint blockade (ICB) prior to surgery may induce early pathological responses in head and neck squamous cell carcinoma (HNSCC) patients. Routine imaging parameters fail to diagnose these responses early on. Magnetic resonance (MR) diffusion-weighted imaging (DWI) has proven to be useful for detecting HNSCC tumor mass after (chemo)radiation therapy. METHODS: 32 patients with stage II-IV, resectable HNSCC, treated at a phase Ib/IIa IMCISION trial (NCT03003637), were retrospectively analyzed using MR-imaging before and after two doses of single agent nivolumab (anti-PD-1) (n = 6) or nivolumab with ipilimumab (anti-CTLA-4) ICB (n = 26). The primary tumors were delineated pre- and post-treatment. A total of 32 features were derived from the delineation and correlated with the tumor regression percentage in the surgical specimen. RESULTS: MR-DWI data was available for 24 of 32 patients. Smaller baseline tumor diameter (p = 0.01-0.04) and higher sphericity (p = 0.03) were predictive of having a good pathological response to ICB. Post-treatment skewness and the change in skewness between MRIs were negatively correlated with the tumor's regression (p = 0.04, p = 0.02). CONCLUSION: Pre-treatment DWI tumor diameter and sphericity may be quantitative biomarkers for the prediction of an early pathological response to ICB. Furthermore, our data indicate that ADC skewness could be a marker for individual response evaluation.

Largest diameter delineations can substitute 3D tumor volume delineations for radiomics prediction of human papillomavirus status on MRI's of oropharyngeal cancer.

PURPOSE: Laborious and time-consuming tumor segmentations are one of the factors that impede adoption of radiomics in the clinical routine. This study investigates model performance using alternative tumor delineation strategies in models predictive of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC). METHODS: Of 153 OPSCC patients, HPV status was determined using p16/p53 immunohistochemistry. MR-based radiomic features were extracted within 3D delineations by an inexperienced observer, experienced radiologist or radiation oncologist, and within a 2D delineation of the largest axial tumor diameter and 3D spheres within the tumor. First, logistic regression prediction models were constructed and tested separately for each of these six delineation strategies. Secondly, the model trained on experienced delineations was tested using these delineation strategies. The latter methodology was repeated with the omission of shape features. Model performance was evaluated using area under the curve (AUC), sensitivity and specificity. RESULTS: Models constructed and tested using single-slice delineations (AUC/Sensitivity/Specificity: 0.84/0.75/0.84) perform better compared to 3D experienced observer delineations (AUC/Sensitivity/Specificity: 0.76/0.76/0.71), where models based on 4 mm sphere delineations (AUC/Sensitivity/Specificity: 0.77/0.59/0.71) show similar performance. Similar performance was found when experienced and largest diameter delineations (AUC/Sens/Spec: 0.76/0.75/0.65 vs 0.76/0.69/0.69) was used to test the model constructed using experienced delineations without shape features. CONCLUSION: Alternative delineations can substitute labor and time intensive full tumor delineations in a model that predicts HPV status in OPSCC. These faster delineations may improve adoption of radiomics in the clinical setting. Future research should evaluate whether these alternative delineations are valid in other radiomics models.

Magnetic Resonance Imaging Can Reliably Differentiate Optic Nerve Inflammation from Tumor Invasion in Retinoblastoma with Orbital Cellulitis.

PURPOSE: To investigate the prevalence and magnetic resonance imaging (MRI) phenotype of retinoblastoma-associated orbital cellulitis. Additionally, this study aimed to identify postlaminar optic nerve enhancement (PLONE) patterns differentiating between inflammation and tumor invasion. DESIGN: A monocenter cohort study assessed the prevalence of orbital cellulitis features on MRI in retinoblastoma patients. A multicenter case-control study compared MRI features of the retinoblastoma-associated orbital cellulitis cases with retinoblastoma controls. PARTICIPANTS: A consecutive retinoblastoma patient cohort of 236 patients (311 eyes) was retrospectively investigated. Subsequently, 30 retinoblastoma cases with orbital cellulitis were compared with 30 matched retinoblastoma controls without cellulitis. METHODS: In the cohort study, retinoblastoma MRI scans were scored on presence of inflammatory features. In the case-control study, MRI scans were scored on intraocular features and PLONE patterns. Postlaminar enhancement patterns were compared with histopathologic assessment of postlaminar tumor invasion. Interreader agreement was assessed, and exact tests with Bonferroni correction were adopted for statistical comparisons. MAIN OUTCOME MEASURES: Prevalence of retinoblastoma-associated orbital cellulitis on MRI was calculated. Frequency of intraocular MRI features was compared between cases and controls. Sensitivity and specificity of postlaminar optic nerve patterns for detection of postlaminar tumor invasion were assessed. RESULTS: The MRI prevalence of retinoblastoma-associated orbital cellulitis was 6.8% (16/236). Retinoblastoma with orbital cellulitis showed significantly more tumor necrosis, uveal abnormalities (inflammation, hemorrhage, and necrosis), lens luxation (all P < 0.001), and a larger eye size (P = 0.012). The inflammatory pattern of optic nerve enhancement (strong enhancement similar to adjacent choroid) was solely found in orbital cellulitis cases, of which none (0/16) showed tumor invasion on histopathology. Invasive pattern enhancement was found in both cases and controls, of which 50% (5/10) showed tumor invasion on histopathology. Considering these different enhancement patterns suggestive for either inflammation or tumor invasion increased specificity for detection of postlaminar tumor invasion in orbital cellulitis cases from 32% (95% confidence interval [CI], 16-52) to 89% (95% CI, 72-98). CONCLUSIONS: Retinoblastoma cases presenting with orbital cellulitis show MRI findings of a larger eye size, extensive tumor necrosis, uveal abnormalities, and lens luxation. Magnetic resonance imaging contrast-enhancement patterns within the postlaminar optic nerve can differentiate between tumor invasion and inflammatory changes.

Early Response Prediction of Multiparametric Functional MRI and 18F-FDG-PET in Patients with Head and Neck Squamous Cell Carcinoma Treated with (Chemo)Radiation.

BACKGROUND: Patients with locally-advanced head and neck squamous cell carcinoma (HNSCC) have variable responses to (chemo)radiotherapy. A reliable prediction of outcomes allows for enhancing treatment efficacy and follow-up monitoring. METHODS: Fifty-seven histopathologically-proven HNSCC patients with curative (chemo)radiotherapy were prospectively included. All patients had an MRI (DW,-IVIM, DCE-MRI) and 18F-FDG-PET/CT before and 10 days after start-treatment (intratreatment). Primary tumor functional imaging parameters were extracted. Univariate and multivariate analysis were performed to construct prognostic models and risk stratification for 2 year locoregional recurrence-free survival (LRFFS), distant metastasis-free survival (DMFS) and overall survival (OS). Model performance was measured by the cross-validated area under the receiver operating characteristic curve (AUC). RESULTS: The best LRFFS model contained the pretreatment imaging parameters ADC_kurtosis, Kep and SUV_peak, and intratreatment imaging parameters change (Δ) Δ-ADC_skewness, Δ-f, Δ-SUV_peak and Δ-total lesion glycolysis (TLG) (AUC = 0.81). Clinical parameters did not enhance LRFFS prediction. The best DMFS model contained pretreatment ADC_kurtosis and SUV_peak (AUC = 0.88). The best OS model contained gender, HPV-status, N-stage, pretreatment ADC_skewness, D, f, metabolic-active tumor volume (MATV), SUV_mean and SUV_peak (AUC = 0.82). Risk stratification in high/medium/low risk was significantly prognostic for LRFFS (p = 0.002), DMFS (p < 0.001) and OS (p = 0.003). CONCLUSIONS: Intratreatment functional imaging parameters capture early tumoral changes that only provide prognostic information regarding LRFFS. The best LRFFS model consisted of pretreatment, intratreatment and Δ functional imaging parameters; the DMFS model consisted of only pretreatment functional imaging parameters, and the OS model consisted ofHPV-status, gender and only pretreatment functional imaging parameters. Accurate clinically applicable risk stratification calculators can enable personalized treatment (adaptation) management, early on during treatment, improve counseling and enhance patient-specific post-therapy monitoring.

Simple delineations cannot substitute full 3d tumor delineations for MR-based radiomics prediction of locoregional control in oropharyngeal cancer.

BACKGROUND AND PURPOSE: Manual delineation of head and neck tumor contours for radiomics analyses is tedious and time consuming. This study investigates if fast or readily available tumor contours can substitute full tumor contours by an experienced observer for an MR-based radiomics model to predict locoregional control (LRC) in oropharyngeal squamous cell carcinoma (OPSCC) tumors. MATERIALS AND METHODS: Radiomic features were extracted from postcontrast T1-weighted MRIs of 177 OPSCC primary tumors using six different manual delineation strategies. LRC prediction models based on recursive feature elimination combined with logistic regression were built. Models were trained and tested on data from each separate delineation. Additionally, the model derived from segmentations from the experienced reader was tested by each of the alternative delineations. Complementary, this was repeated with removal of size and shape features. Model performance was evaluated using area under the curve (AUC). RESULTS: Prediction performance of the experienced radiologist tumor delineation (AUC: 0.74) was superior compared to all other delineations when trained and tested (AUCs: 0.41-0.56) or trained on experienced delineations and tested (AUC: 0.56-0.67) on alternative segmentations. Removal of size and shape features considerably decreases prediction performance (AUC: 0.54). Applying the model based on expert delineations to spherical or single slice delineations makes prediction worthless since these models predict one class. CONCLUSION: Fast or readily available contours cannot substitute full expert tumor delineations in radiomics models predictive of LRC in OPSCC.

Prognostic functional MR imaging parameters in head and neck squamous cell carcinoma: A systematic review.

OBJECTIVE: Functional MR imaging has demonstrated potential for predicting treatment response. This systematic review gives an extensive overview of the current level of evidence for pre-treatment MR-based perfusion and diffusion imaging parameters that are prognostic for treatment outcome in head and neck squamous cell carcinoma (HNSCC) (PROSPERO registrationCRD42020210689). MATERIALS AND METHODS: According to the PRISMA statements, Medline, Embase and Scopus were queried for articles with a maximum date of October 19th, 2020. Studies investigating the predictive performance of pre-treatment MR-based perfusion and/or diffusion imaging parameters in HNSCC treatment response were included. All prognosticators were extracted from the primary tumor. Risk of bias was assessed using the QUIPS tool. Results were summarized in tables and forest plots. RESULTS: 31 unique studies met the inclusion criteria; among them, 11 articles described perfusion (n = 529 patients) and 28 described diffusion (n = 1626 patients) MR-imaging, eight studies were included in both categories. Higher Ktrans and Kep were associated with better treatment response for OS and DFS, respectively. Study findings for Vp and Ve were inconsistent or not significant. High-level controversy was observed between studies examining the MR diffusion parameters mean and median ADC. CONCLUSION: For HNSCC patients, the accurate and consistent results of pre-treatment MR-based perfusion parameters Ktrans and Kep are potential for clinical applicability predictive of OS and DFS and treatment decision guidance. Significant heterogeneity in study designs might affect high discrepancy in study results for parameters extracted from diffusion imaging. Furthermore, recommendations for future research were summarized.

Improved outcome prediction of oropharyngeal cancer by combining clinical and MRI features in machine learning models.

OBJECTIVES: New markers are required to predict chemoradiation response in oropharyngeal squamous cell carcinoma (OPSCC) patients. This study evaluated the ability of magnetic resonance (MR) radiomics to predict locoregional control (LRC) and overall survival (OS) after chemoradiation and aimed to determine whether this has added value to traditional clinical outcome predictors. METHODS: 177 OPSCC patients were eligible for this study. Radiomic features were extracted from the primary tumor region in T1-weighted postcontrast MRI acquired before chemoradiation. Logistic regression models were created using either clinical variables (clinical model), radiomic features (radiomic model) or clinical and radiomic features combined (combined model) to predict LRC and OS 2-years posttreatment. Model performance was evaluated using area under the curve (AUC), 95 % confidence intervals were calculated using 500 iterations of bootstrap. All analyses were performed for the total population and the Human papillomavirus (HPV) negative tumor subgroup. RESULTS: A combined model predicted treatment outcome with a higher AUC (LRC: 0.745 [0.734-0.757], OS: 0.744 [0.735-0.753]) than the clinical model (LRC: 0.607 [0.594-0.620], OS: 0.708 [0.697-0.719]). Performance of the radiomic model was comparable to the combined model for LRC (AUC: 0.740 [0.729-0.750]), but not for OS prediction (AUC: 0.654 [0.646-0.662]). In HPV negative patients, the performance of all models was not sufficient with AUCs ranging from 0.587 to 0.660 for LRC and 0.559 to 0.600 for OS prediction. CONCLUSION: Predictive models that include clinical variables and radiomic tumor features derived from MR images of OPSCC better predict LRC after chemoradiation than models based on only clinical variables. Predictive models that include clinical variables perform better than models based on only radiomic features for the prediction of OS.

Clinical variables and magnetic resonance imaging-based radiomics predict human papillomavirus status of oropharyngeal cancer.

BACKGROUND: Human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) have better prognosis and treatment response compared to HPV-negative OPSCC. This study aims to noninvasively predict HPV status of OPSCC using clinical and/or radiological variables. METHODS: Seventy-seven magnetic resonance radiomic features were extracted from T1-weighted postcontrast images of the primary tumor of 153 patients. Logistic regression models were created to predict HPV status, determined with immunohistochemistry, based on clinical variables, radiomic features, and its combination. Model performance was evaluated using area under the curve (AUC). RESULTS: Model performance showed AUCs of 0.794, 0.764, and 0.871 for the clinical, radiomic, and combined models, respectively. Smoking, higher T-classification (T3 and T4), larger, less round, and heterogeneous tumors were associated with HPV-negative tumors. CONCLUSION: Models based on clinical variables and/or radiomic tumor features can predict HPV status in OPSCC patients with good performance and can be considered when HPV testing is not available.

Adherence to pretreatment and intratreatment imaging of head and neck squamous cell carcinoma patients undergoing (chemo) radiotherapy in a research setting.

PURPOSE: The emerge of improved personalized treatment adaptations and outcome prediction is accompanied with increasing non-invasive assessments in early treatment phase, leading to increased patient burden. This study assessed the adherence of patients with head and neck squamous cell carcinoma (HNSCC) to undergo pretreatment and research-related intratreatment imaging, and assessed which factors caused drop-out. METHOD: Between 2013 and 2019, advanced-staged HNSCC patients were prospectively included, underwent (chemo) radiotherapy with curative intent and planned for both pre-treatment and intratreatment sequential 18F-FDG-PET/CT, 18F-FDG-PET/MRI and thereafter MRI (including DWI/DCE). Drop-out-factors were described as healthcare-related (logistics and imaging-system defects) and patient-related (psychological, physical, not-specified). Common Toxicity Criteria (CTC) were routinely scored by radiation/medical oncologists throughout the first 3 weeks, and compared between patient drop-outs and who complete imaging. RESULTS: Ninety-seven patients (mean age 61 ± 6.8 years) were included; 95 patients (97.9%) underwent pretreatment imaging and 63 (64.9%) intratreatment imaging. For 18F-FDG-PET/CT, 18F-FDG-PET/MRI and MRI pretreatment drop-outs were 2, 10 and 3 patients and for intratreatment drop-outs were 34, 39 and 35 patients, respectively. Patient-related drop-out-factors were physical (n = 16, e.g. dysphagia), psychological (n = 6, e.g. claustrophobia) and non-specified (n = 12). Healthcare-related drop-out-factors were logistics (n = 6) and 18F-FDG-PET/CT-/MRI-system defects (n = 2). The CTC mucosal toxicity was significantly higher (p = 0.023) at week 2 of (chemo)radiotherapy in patient drop-outs than with complete imaging. CONCLUSIONS: The drop-out frequency of advanced-staged HNSCC patients for imaging during (chemo)radiotherapy in a research-setting was high and mainly patient-related. Treatment of patient-related inconveniences, communication of rationale and healthcare-related imaging protocol efficiency improvements may contribute to improved adherence.

Multiparametric functional MRI and 18F-FDG-PET for survival prediction in patients with head and neck squamous cell carcinoma treated with (chemo)radiation.

OBJECTIVES: To assess (I) correlations between diffusion-weighted (DWI), intravoxel incoherent motion (IVIM), dynamic contrast-enhanced (DCE) MRI, and 18F-FDG-PET/CT imaging parameters capturing tumor characteristics and (II) their predictive value of locoregional recurrence-free survival (LRFS) and overall survival (OS) in patients with head and neck squamous cell carcinoma (HNSCC) treated with (chemo)radiotherapy. METHODS: Between 2014 and 2018, patients with histopathologically proven HNSCC, planned for curative (chemo) radiotherapy, were prospectively included. Pretreatment clinical, anatomical, and functional imaging parameters (obtained by DWI/IVIM, DCE-MRI, and 18F-FDG-PET/CT) were extracted for primary tumors (PT) and lymph node metastases. Correlations and differences between parameters were assessed. The predictive value of LRFS and OS was assessed, performing univariable, multivariable Cox and CoxBoost regression analyses. RESULTS: In total, 70 patients were included. Significant correlations between 18F-FDG-PET parameters and DWI-/DCE volume parameters were found (r > 0.442, p < 0.002). The combination of HPV (HR = 0.903), intoxications (HR = 1.065), PT ADCGTV (HR = 1.252), Ktrans (HR = 1.223), and Ve (HR = 1.215) was predictive for LRFS (C-index = 0.546; p = 0.023). N-stage (HR = 1.058), HPV positivity (HR = 0.886), hypopharyngeal tumor location (HR = 1.111), ADCGTV (HR = 1.102), ADCmean (HR = 1.137), D* (HR = 0.862), Ktrans (HR = 1.106), Ve (HR = 1.195), SUVmax (HR = 1.094), and TLG (HR = 1.433) were predictive for OS (C-index = 0.664; p = 0.046). CONCLUSIONS: Functional imaging parameters, performing DWI/IVIM, DCE-MRI, and 18F-FDG-PET/CT, yielded complementary value in capturing tumor characteristics. More specific, intoxications, HPV-negative status, large tumor volume-related parameters, high permeability (Ktrans), and high extravascular extracellular space (Ve) parameters were predictive for adverse locoregional recurrence-free survival and adverse overall survival. Low cellularity (high ADC) and high metabolism (high SUV) were additionally predictive for decreased overall survival. These different predictive factors added to estimated locoregional and overall survival. KEY POINTS: • Parameters of DWI/IVIM, DCE-MRI, and 18F-FDG-PET/CT were able to capture complementary tumor characteristics. • Multivariable analysis revealed that intoxications, HPV negativity, large tumor volume and high vascular permeability (Ktrans), and extravascular extracellular space (Ve) were complementary predictive for locoregional recurrence. • In addition to predictive parameters for locoregional recurrence, also high cellularity (low ADC) and high metabolism (high SUV) were complementary predictive for overall survival.

MR Imaging Features to Differentiate Retinoblastoma from Coats' Disease and Persistent Fetal Vasculature.

Retinoblastoma mimickers, or pseudoretinoblastoma, are conditions that show similarities with the pediatric cancer retinoblastoma. However, false-positive retinoblastoma diagnosis can cause mistreatment, while false-negative diagnosis can cause life-threatening treatment delay. The purpose of this study is to identify the MR imaging features that best differentiate between retinoblastoma and the most common pseudoretinoblastoma diagnoses: Coats' disease and persistent fetal vasculature (PFV). Here, six expert radiologists performed retrospective assessments (blinded for diagnosis) of MR images of patients with a final diagnosis based on histopathology or clinical follow-up. Associations between 20 predefined imaging features and diagnosis were assessed with exact tests corrected for multiple hypothesis testing. Sixty-six patients were included, of which 33 (50%) were retinoblastoma and 33 (50%) pseudoretinoblastoma patients. A larger eye size, vitreous seeding, and sharp-V-shaped retinal detachment were almost exclusively found in retinoblastoma (p < 0.001-0.022, specificity 93-97%). Features that were almost exclusively found in pseudoretinoblastoma included smaller eye size, ciliary/lens deformations, optic nerve atrophy, a central stalk between optic disc and lens, Y-shaped retinal detachment, and absence of calcifications (p < 0.001-0.022, specificity 91-100%). Additionally, three newly identified imaging features were exclusively present in pseudoretinoblastoma: intraretinal macrocysts (p < 0.001, 38% [9/24] in Coats' disease and 20% [2/10] in PFV), contrast enhancement outside the solid lesion (p < 0.001, 30% [7/23] in Coats' disease and 57% [4/7] in PFV), and enhancing subfoveal nodules (38% [9/24] in Coats' disease). An assessment strategy was proposed for MR imaging differentiation between retinoblastoma and pseudoretinoblastoma, including three newly identified differentiating MR imaging features.

The Additional Value of Ultrafast DCE-MRI to DWI-MRI and 18F-FDG-PET to Detect Occult Primary Head and Neck Squamous Cell Carcinoma.

To evaluate diagnostic accuracy of qualitative analysis and interobserver agreement of single ultrafast-DCE, DWI or 18F-FDG-PET and the combination of modalities for the detection of unknown primary tumor (UPT) in patients presenting with cervical lymph node metastasis from squamous cell carcinoma (SCC). Between 2014-2019, patients with histologically proven cervical lymph node metastasis of UPT SCC were prospectively included and underwent DWI, ultrafast-DCE, and 18F-FDG-PET/CT. Qualitative assessment was performed by two observers per modality. Interobserver agreement was calculated using the proportion specific agreement. Diagnostic accuracy of combined use of DWI, ultrafast-DCE and 18F-FDG-PET/CT was assessed. Twenty-nine patients were included (20 males. [68%], median age 60 years). Nine (31%) primary tumors remained occult. Ultrafast-DCE added reader confidence for suspicious locations (one additional true positive (5%), 2 decisive true malignant (10%). The per-location analysis showed highest specific positive agreement for ultrafast-DCE (77.6%). The per-location rating showed highest sensitivity (95%, 95%CI = 75.1-99.9, YI = 0.814) when either one of all modalities was scored positive, and 97.4% (95%CI = 93.5-99.3, YI = 0.774) specificity when co-detected on all. The per-patient analysis showed highest sensitivity (100%) for 18F-FDG-PET/CT (YI = 0.222) and either DWI or PET (YI = 0.111). Despite highest trends, no significant differences were found. The per-patient analysis showed highest specific positive agreement when co-detected on all modalities (55.6%, 95%CI = 21.2-86.3, YI = 0.456). Ultrafast-DCE showed potential to improve detection of unknown primary tumors in addition to DWI and 18F-FDG-PET/CT in patients with cervical squamous cell carcinoma lymph node metastasis. The combined use of ultrafast-DCE, DWI and 18F-FDG-PET/CT yielded highest sensitivity.

Predictive value of quantitative 18F-FDG-PET radiomics analysis in patients with head and neck squamous cell carcinoma.

BACKGROUND: Radiomics is aimed at image-based tumor phenotyping, enabling application within clinical-decision-support-systems to improve diagnostic accuracy and allow for personalized treatment. The purpose was to identify predictive 18-fluor-fluoro-2-deoxyglucose (18F-FDG) positron-emission tomography (PET) radiomic features to predict recurrence, distant metastasis, and overall survival in patients with head and neck squamous cell carcinoma treated with chemoradiotherapy. METHODS: Between 2012 and 2018, 103 retrospectively (training cohort) and 71 consecutively included patients (validation cohort) underwent 18F-FDG-PET/CT imaging. The 434 extracted radiomic features were subjected, after redundancy filtering, to a projection resulting in outcome-independent meta-features (factors). Correlations between clinical, first-order 18F-FDG-PET parameters (e.g., SUVmean), and factors were assessed. Factors were combined with 18F-FDG-PET and clinical parameters in a multivariable survival regression and validated. A clinically applicable risk-stratification was constructed for patients' outcome. RESULTS: Based on 124 retained radiomic features from 103 patients, 8 factors were constructed. Recurrence prediction was significantly most accurate by combining HPV-status, SUVmean, SUVpeak, factor 3 (histogram gradient and long-run-low-grey-level-emphasis), factor 4 (volume-difference, coarseness, and grey-level-non-uniformity), and factor 6 (histogram variation coefficient) (CI = 0.645). Distant metastasis prediction was most accurate assessing metabolic-active tumor volume (MATV)(CI = 0.627). Overall survival prediction was most accurate using HPV-status, SUVmean, SUVmax, factor 1 (least-axis-length, non-uniformity, high-dependence-of-high grey-levels), and factor 5 (aspherity, major-axis-length, inversed-compactness and, inversed-flatness) (CI = 0.764). CONCLUSIONS: Combining HPV-status, first-order 18F-FDG-PET parameters, and complementary radiomic factors was most accurate for time-to-event prediction. Predictive phenotype-specific tumor characteristics and interactions might be captured and retained using radiomic factors, which allows for personalized risk stratification and optimizing personalized cancer care. TRIAL REGISTRATION: Trial NL3946 (NTR4111), local ethics commission reference: Prediction 2013.191 and 2016.498. Registered 7 August 2013, https://www.trialregister.nl/trial/3946.

Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures.

OBJECTIVES: Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. MATERIALS AND METHODS: Native T1-weighted images of four independent, retrospective (2005-2013), patient cohorts (n = 102, n = 76, n = 89, and n = 56) were used to delineate primary tumors, and to extract 545 quantitative features from. Subsequently, redundancy filtering and factor analysis were performed to handle collinearity in the data. Next, radiomic prognostic models were trained and validated to predict overall survival (OS) and relapse-free survival (RFS). Radiomic features were compared to and combined with prognostic models based on standard clinical parameters. Performance was assessed by integrated area under the curve (iAUC). RESULTS: In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p < 0.001). CONCLUSIONS: MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. KEY POINTS: • MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. • MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. • Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.

Screening for Pineal Trilateral Retinoblastoma Revisited: A Meta-analysis.

TOPIC: To determine the age up to which children are at risk of trilateral retinoblastoma (TRb) developing, whether its onset is linked to the age at which intraocular retinoblastomas develop, and the lead time from a detectable pineal TRb to symptoms. CLINICAL RELEVANCE: Approximately 45% of patients with retinoblastoma-those with a germline RB1 pathogenic variant-are at risk of pineal TRb developing. Early detection and treatment are essential for survival. Current evidence is unclear regarding the usefulness of screening for pineal TRb and, if useful, the age up to which screening should be continued. METHODS: We conducted a study according to the Meta-analysis of Observational Studies in Epidemiology guidelines for reporting meta-analyses of observational studies. We searched PubMed and Embase between January 1, 1966, and February 27, 2019, for published literature. We considered articles reporting patients with TRb with survival and follow-up data. Inclusion of articles was performed separately and independently by 2 authors, and 2 authors also independently extracted the relevant data. They resolved discrepancies by consensus. RESULTS: One hundred thirty-eight patients with pineal TRb were included. Of 22 asymptomatic patients, 21 (95%) were diagnosed before the age of 40 months (median, 16 months; interquartile range, 9-29 months). Age at diagnosis of pineal TRb in patients diagnosed with retinoblastoma at 6 months or younger versus older than 6 months were comparable (P = 0.44), suggesting independence between the ages at diagnosis of intraocular retinoblastoma and pineal TRb. The laterality of intraocular retinoblastoma and its treatment were not associated with the age at which pineal TRb was diagnosed. The lead time from asymptomatic to symptomatic pineal TRb was approximately 1 year. By performing a screening magnetic resonance imaging scan every 6 months after the diagnosis of heritable retinoblastoma (median age, 6 months) until 36 months of age, at least 311 and 776 scans would be required to detect 1 case of asymptomatic pineal TRb and to save a single life, respectively. CONCLUSIONS: Patients with retinoblastoma are at risk of pineal TRb developing for a shorter period than previously assumed, and the age at diagnosis of pineal TRb is independent of the age at diagnosis of retinoblastoma. The GRADE (Grading of Recommendations Assessment, Development and Evaluation) level of evidence for these conclusions remains low.