Search

Objective: To report imaging protocol and scheduling variance in routine care of glioblastoma patients in order to demonstrate challenges of integrating deep-learning models in glioblastoma care pathways. Additionally, to understand the most common imaging studies and image contrasts to inform the development of potentially robust deep-learning models. Methods: MR imaging data were analysed from a random sample of five patients from the prospective cohort across five participating sites of the ZGBM consortium. Reported clinical and treatment data alongside DICOM header information were analysed to understand treatment pathway imaging schedules. Results: All sites perform all structural imaging at every stage in the pathway except for the presurgical study, where in some sites only contrast-enhanced T1-weighted imaging is performed. Diffusion MRI is the most common non-structural imaging type, performed at every site. Conclusion: The imaging protocol and scheduling varies across the UK, making it challenging to develop machine-learning models that could perform robustly at other centres. Structural imaging is performed most consistently across all centres. Advances in knowledge: Successful translation of deep-learning models will likely be based on structural post-treatment imaging unless there is significant effort made to standardise non-structural or peri-operative imaging protocols and schedules.

© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attri- bution 4.0 International License, which permits use, sharing, adapta- tion, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/., Purpose: There is limited data concerning neuroimaging findings and longitudinal evaluation of familial cerebral cavernous malformations (FCCM) in children. Our aim was to study the natural history of pediatric FCCM, with an emphasis on symptomatic hemorrhagic events and associated clinical and imaging risk factors. Methods: We retrospectively reviewed all children diagnosed with FCCM in four tertiary pediatric hospitals between January 2010 and March 2022. Subjects with first available brain MRI and [Formula: see text] 3 months of clinical follow-up were included. Neuroimaging studies were reviewed, and clinical data collected. Annual symptomatic hemorrhage risk rates and cumulative risks were calculated using survival analysis and predictors of symptomatic hemorrhagic identified using regression analysis. Results: Forty-one children (53.7% males) were included, of whom 15 (36.3%) presenting with symptomatic hemorrhage. Seven symptomatic hemorrhages occurred during 140.5 person-years of follow-up, yielding a 5-year annual hemorrhage rate of 5.0% per person-year. The 1-, 2-, and 5-year cumulative risks of symptomatic hemorrhage were 7.3%, 14.6%, and 17.1%, respectively. The latter was higher in children with prior symptomatic hemorrhage (33.3%), CCM2 genotype (33.3%), and positive family history (20.7%). Number of brainstem (adjusted hazard ratio [HR] = 1.37, P = 0.005) and posterior fossa (adjusted HR = 1.64, P = 0.004) CCM at first brain MRI were significant independent predictors of prospective symptomatic hemorrhage. Conclusion: The 5-year annual and cumulative symptomatic hemorrhagic risk in our pediatric FCCM cohort equals the overall risk described in children and adults with all types of CCM. Imaging features at first brain MRI may help to predict potential symptomatic hemorrhage at 5-year follow-up.

© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022, Purpose: The aim of the study was to assess the prevalence and characteristics of spinal cord cavernous malformations (SCCM) and intraosseous spinal vascular malformations (ISVM) in a pediatric familial cerebral cavernous malformation (FCCM) cohort and evaluate clinico-radiological differences between children with (SCCM +) and without (SCCM-) SCCM. Methods: All patients with a pediatric diagnosis of FCCM evaluated at three tertiary pediatric hospitals between January 2010 and August 2021 with [Formula: see text] 1 whole spine MR available were included. Brain and spine MR studies were retrospectively evaluated, and clinical and genetic data collected. Comparisons between SCCM + and SCCM- groups were performed using student-t/Mann-Whitney or Fisher exact tests, as appropriate. Results: Thirty-one children (55% boys) were included. Baseline spine MR was performed (mean age = 9.7 years) following clinical manifestations in one subject (3%) and as a screening strategy in the remainder. Six SCCM were detected in five patients (16%), in the cervico-medullary junction (n = 1), cervical (n = 3), and high thoracic (n = 2) regions, with one appearing during follow-up. A tendency towards an older age at first spine MR (P = 0.14) and [Formula: see text] 1 posterior fossa lesion (P = 0.13) was observed in SCCM + patients, lacking statistical significance. No subject demonstrated ISVM. Conclusion: Although rarely symptomatic, SCCM can be detected in up to 16% of pediatric FCCM patients using diverse spine MR protocols and may appear de novo. ISVM were instead absent in our cohort. Given the relative commonality of asymptomatic SCCM, serial screening spine MR should be considered in FCCM starting in childhood.

BACKGROUND The aim of the systematic review was to assess recently published studies on diagnostic test accuracy of glioblastoma treatment response monitoring biomarkers in adults, developed through machine learning (ML). MATERIAL AND METHODS PRISMA methodology was followed. Articles published 09/2018-01/2021 (since previous reviews) were searched for using MEDLINE, EMBASE, and the Cochrane Register by two reviewers independently. Included study participants were adult patients with high grade glioma who had undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide) and subsequently underwent follow-up imaging to determine treatment response status (specifically, distinguishing progression/recurrence from progression/recurrence mimics - the target condition). Risk of bias and applicability was assessed with QUADAS 2. A third reviewer arbitrated any discrepancy. Contingency tables were created for hold-out test sets and recall, specificity, precision, F1-score, balanced accuracy calculated. A meta-analysis was performed using a bivariate model for recall, false positive rate and area-under the receiver operator characteristic curve (AUC). RESULTS Eighteen studies were included with 1335 patients in training sets and 384 in test sets. To determine whether there was progression or a mimic, the reference standard combination of follow-up imaging and histopathology at re-operation was applied in 67% (13/18) of studies. The small numbers of patient included in studies, the high risk of bias and concerns of applicability in the study designs (particularly in relation to the reference standard and patient selection due to confounding), and the low level of evidence, suggest that limited conclusions can be drawn from the data. Ten studies (10/18, 56%) had internal or external hold-out test set data that could be included in a meta-analysis of monitoring biomarker studies. The pooled sensitivity was 0.77 (0.65–0.86). The pooled false positive rate (1-specificity) was 0.35 (0.25–0.47). The summary point estimate for the AUC was 0.77. CONCLUSION There is likely good diagnostic performance of machine learning models that use MRI features to distinguish between progression and mimics. The diagnostic performance of ML using implicit features did not appear to be superior to ML using explicit features. There are a range of ML-based solutions poised to become treatment response monitoring biomarkers for glioblastoma. To achieve this, the development and validation of ML models require large, well-annotated datasets where the potential for confounding in the study design has been carefully considered. Therefore, multidisciplinary efforts and multicentre collaborations are necessary.

Objectives MRI remains the preferred imaging investigation for glioblastoma. Appropriate and timely neuroimaging in the follow-up period is considered to be important in making management decisions. There is a paucity of evidence-based information in current UK, European and international guidelines regarding the optimal timing and type of neuroimaging following initial neurosurgical treatment. This study assessed the current imaging practices amongst UK neuro-oncology centres, thus providing baseline data and informing future practice. Methods The lead neuro-oncologist, neuroradiologist and neurosurgeon from every UK neuro-oncology centre were invited to complete an online survey. Participants were asked about current and ideal imaging practices following initial treatment. Results Ninety-two participants from all 31 neuro-oncology centres completed the survey (100% response rate). Most centres routinely performed an early post-operative MRI (87%, 27/31), whereas only a third performed a pre-radiotherapy MRI (32%, 10/31). The number and timing of scans routinely performed during adjuvant TMZ treatment varied widely between centres. At the end of the adjuvant period, most centres performed an MRI (71%, 22/31), followed by monitoring scans at 3 monthly intervals (81%, 25/31). Additional short-interval imaging was carried out in cases of possible pseudoprogression in most centres (71%, 22/31). Routine use of advanced imaging was infrequent; however, the addition of advanced sequences was the most popular suggestion for ideal imaging practice, followed by changes in the timing of EPMRI. Conclusion Variations in neuroimaging practices exist after initial glioblastoma treatment within the UK. Multicentre, longitudinal, prospective trials are needed to define the optimal imaging schedule for assessment. Key Points • Variations in imaging practices exist in the frequency, timing and type of interval neuroimaging after initial treatment of glioblastoma within the UK. • Large, multicentre, longitudinal, prospective trials are needed to define the optimal imaging schedule for assessment.

The aim of the systematic review was to assess recently published studies on diagnostic test accuracy of glioblastoma treatment response monitoring biomarkers in adults, developed through machine learning (ML). Articles were searched for using MEDLINE, EMBASE, and the Cochrane Register. Included study participants were adult patients with high grade glioma who had undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide) and subsequently underwent follow-up imaging to determine treatment response status. Risk of bias and applicability was assessed with QUADAS 2 methodology. Contingency tables were created for hold-out test sets and recall, specificity, precision, F1-score, balanced accuracy calculated. Fifteen studies were included with 1038 patients in training sets and 233 in test sets. To determine whether there was progression or a mimic, the reference standard combination of follow-up imaging and histopathology at re-operation was applied in 67% of studies. The small numbers of patient included in studies, the high risk of bias and concerns of applicability in the study designs (particularly in relation to the reference standard and patient selection due to confounding), and the low level of evidence, suggest that limited conclusions can be drawn from the data. There is likely good diagnostic performance of machine learning models that use MRI features to distinguish between progression and mimics. The diagnostic performance of ML using implicit features did not appear to be superior to ML using explicit features. There are a range of ML-based solutions poised to become treatment response monitoring biomarkers for glioblastoma. To achieve this, the development and validation of ML models require large, well-annotated datasets where the potential for confounding in the study design has been carefully considered.

BACKGROUND Glioblastoma is a common and aggressive primary malignant brain tumour in adults associated with a poor prognosis and considerable symptom burden. Clinical review and serial neuroimaging remain the primary monitoring tools to assess for disease status. However, the evidence base for the existing surveillance imaging schedule is yet to be established. New models of follow up care are needed to demonstrate better patient outcomes in this patient cohort. There are indications that patient-reported outcome measures (PROMs) can contribute to improved survival and maintaining an optimal quality of life in other oncology populations. MATERIALS AND METHODS There are no standardised PROMs for the priority symptoms in glioblastoma patients, which can be used for evaluation in clinical care as a surrogate marker for disease progression. A broad set of symptoms were therefore initially identified in a targeted literature search and were further refined via Delphi methodology, with the aim to obtain consensus amongst a small expert panel involved in the care of glioblastoma patients. A three round Delphi email survey was conducted. Consensus was defined as 70% agreement. RESULTS Symptom and function constructs were assessed for relevance, relationship to disease and treatment, sensitivity to change, psychometric properties and patient acceptability. Consensus was reached on the red flag symptoms and symptom clusters to monitor, as well as the minimum severity thresholds needed to trigger an alert on an electronic symptom reporting system, which has been developed to allow patient self-reporting of symptoms during treatment. CONCLUSION The red flag symptoms to monitor, along with the symptom severity thresholds, informed an app-based symptom reporting system, which is currently being piloted in a feasibility study exploring triggered imaging using ePROMs. This has the potential to inform future clinical practice through development of patient reported biomarkers.