COVID-19 Stroke Apical Lung Examination Study 2: a national prospective CTA biomarker study of the lung apices, in patients presenting with suspected acute stroke (COVID SALES 2)

BACKGROUND

Apical ground-glass opacification (GGO) identified on CT angiography (CTA) performed for suspected acute stroke was developed in 2020 as a coronavirus-disease-2019 (COVID-19) diagnostic and prognostic biomarker in a retrospective study during the first wave of COVID-19.

OBJECTIVE

To prospectively validate whether GGO on CTA performed for suspected acute stroke is a reliable COVID-19 diagnostic and prognostic biomarker and whether it is reliable for COVID-19 vaccinated patients.

METHODS

In this prospective, pragmatic, national, multi-center validation study performed at 13 sites, we captured study data consecutively in patients undergoing CTA for suspected acute stroke from January-March 2021. Demographic and clinical features associated with stroke and COVID-19 were incorporated. The primary outcome was the likelihood of reverse-transcriptase-polymerase-chain-reaction swab-test-confirmed COVID-19 using the GGO biomarker. Secondary outcomes investigated were functional status at discharge and survival analyses at 30 and 90 days. Univariate and multivariable statistical analyses were employed.

RESULTS

CTAs from 1,111 patients were analyzed, with apical GGO identified in 8.5 % during a period of high COVID-19 prevalence. GGO showed good inter-rater reliability (Fleiss κ = 0.77); and high COVID-19 specificity (93.7 %, 91.8-95.2) and negative predictive value (NPV; 97.8 %, 96.5-98.6). In subgroup analysis of vaccinated patients, GGO remained a good diagnostic biomarker (specificity 93.1 %, 89.8-95.5; NPV 99.7 %, 98.3-100.0). Patients with COVID-19 were more likely to have higher stroke score (NIHSS (mean +/- SD) 6.9 +/- 6.9, COVID-19 negative, 9.7 +/- 9.0, COVID-19 positive; p = 0.01), carotid occlusions (6.2 % negative, 14.9 % positive; p = 0.02), and larger infarcts on presentation CT (ASPECTS 9.4 +/- 1.5, COVID-19 negative, 8.6 +/- 2.4, COVID-19 positive; p = 0.00). After multivariable logistic regression, GGO (odds ratio 15.7, 6.2-40.1), myalgia (8.9, 2.1-38.2) and higher core body temperature (1.9, 1.1-3.2) were independent COVID-19 predictors. GGO was associated with worse functional outcome on discharge and worse survival after univariate analysis. However, after adjustment for factors including stroke severity, GGO was not independently predictive of functional outcome or mortality.

CONCLUSION

Apical GGO on CTA performed for patients with suspected acute stroke is a reliable diagnostic biomarker for COVID-19, which in combination with clinical features may be useful in COVID-19 triage.

Optimising brain age estimation through transfer learning: A suite of pre-trained foundation models for improved performance and generalisability in a clinical setting

Estimated age from brain MRI data has emerged as a promising biomarker of neurological health. However, the absence of large, diverse, and clinically representative training datasets, along with the complexity of managing heterogeneous MRI data, presents significant barriers to the development of accurate and generalisable models appropriate for clinical use. Here, we present a deep learning framework trained on routine clinical data (N up to 18,890, age range 18-96 years). We trained five separate models for accurate brain age prediction (all with mean absolute error ≤4.0 years, R2  ≥ .86) across five different MRI sequences (T2 -weighted, T2 -FLAIR, T1 -weighted, diffusion-weighted, and gradient-recalled echo T2 *-weighted). Our trained models offer dual functionality. First, they have the potential to be directly employed on clinical data. Second, they can be used as foundation models for further refinement to accommodate a range of other MRI sequences (and therefore a range of clinical scenarios which employ such sequences). This adaptation process, enabled by transfer learning, proved effective in our study across a range of MRI sequences and scan orientations, including those which differed considerably from the original training datasets. Crucially, our findings suggest that this approach remains viable even with limited data availability (as low as N = 25 for fine-tuning), thus broadening the application of brain age estimation to more diverse clinical contexts and patient populations. By making these models publicly available, we aim to provide the scientific community with a versatile toolkit, promoting further research in brain age prediction and related areas.

Brain Tumor Imaging without Gadolinium-based Contrast Agents: Feasible or Fantasy?

Gadolinium-based contrast agents (GBCAs) form the cornerstone of current primary brain tumor MRI protocols at all stages of the patient journey. Though an imperfect measure of tumor grade, GBCAs are repeatedly used for diagnosis and monitoring. In practice, however, radiologists will encounter situations where GBCA injection is not needed or of doubtful benefit. Reducing GBCA administration could improve the patient burden of (repeated) imaging (especially in vulnerable patient groups, such as children), minimize risks of putative side effects, and benefit costs, logistics, and the environmental footprint. On the basis of the current literature, imaging strategies to reduce GBCA exposure for pediatric and adult patients with primary brain tumors will be reviewed. Early postoperative MRI and fixed-interval imaging of gliomas are examples of GBCA exposure with uncertain survival benefits. Half-dose GBCAs for gliomas and T2-weighted imaging alone for meningiomas are among options to reduce GBCA use. While most imaging guidelines recommend using GBCAs at all stages of diagnosis and treatment, non-contrast-enhanced sequences, such as the arterial spin labeling, have shown a great potential. Artificial intelligence methods to generate synthetic postcontrast images from decreased-dose or non-GBCA scans have shown promise to replace GBCA-dependent approaches. This review is focused on pediatric and adult gliomas and meningiomas. Special attention is paid to the quality and real-life applicability of the reviewed literature.

Glioblastoma and Radiotherapy: a multi-center AI study for Survival Predictions from MRI (GRASP study)

BACKGROUND

The aim was to predict survival of glioblastoma at eight months after radiotherapy (a period allowing for completing a typical course of adjuvant temozolomide), by applying deep learning to the first brain MRI after radiotherapy completion.

METHODS

Retrospective and prospective data were collected from 206 consecutive glioblastoma, IDH-wildtype patients diagnosed between March 2014-February 2022 across 11 UK centers. Models were trained on 158 retrospective patients from three centers. Holdout test sets were retrospective (n=19; internal validation), and prospective (n=29; external validation from eight distinct centers).Neural network branches for T2-weighted and contrast-enhanced T1-weighted inputs were concatenated to predict survival. A non-imaging branch (demographics/MGMT/treatment data) was also combined with the imaging model. We investigated the influence of individual MR sequences; non-imaging features; and weighted dense blocks pretrained for abnormality detection.

RESULTS

The imaging model outperformed the non-imaging model in all test sets (area under the receiver-operating characteristic curve, AUC p=0.038) and performed similarly to a combined imaging/non-imaging model (p>0.05). Imaging, non-imaging, and combined models applied to amalgamated test sets gave AUCs of 0.93, 0.79, and 0.91. Initializing the imaging model with pretrained weights from 10,000s of brain MRIs improved performance considerably (amalgamated test sets without pretraining 0.64; p=0.003).

CONCLUSIONS

A deep learning model using MRI images after radiotherapy, reliably and accurately determined survival of glioblastoma. The model serves as a prognostic biomarker identifying patients who will not survive beyond a typical course of adjuvant temozolomide, thereby stratifying patients into those who might require early second-line or clinical trial treatment.

Systematic Review of Artificial Intelligence for Abnormality Detection in High-volume Neuroimaging and Subgroup Meta-analysis for Intracranial Hemorrhage Detection

PURPOSE

Most studies evaluating artificial intelligence (AI) models that detect abnormalities in neuroimaging are either tested on unrepresentative patient cohorts or are insufficiently well-validated, leading to poor generalisability to real-world tasks. The aim was to determine the diagnostic test accuracy and summarise the evidence supporting the use of AI models performing first-line, high-volume neuroimaging tasks.

METHODS

Medline, Embase, Cochrane library and Web of Science were searched until September 2021 for studies that temporally or externally validated AI capable of detecting abnormalities in first-line computed tomography (CT) or magnetic resonance (MR) neuroimaging. A bivariate random effects model was used for meta-analysis where appropriate. This study was registered on PROSPERO as CRD42021269563.

RESULTS

Out of 42,870 records screened, and 5734 potentially eligible full texts, only 16 studies were eligible for inclusion. Included studies were not compromised by unrepresentative datasets or inadequate validation methodology. Direct comparison with radiologists was available in 4/16 studies and 15/16 had a high risk of bias. Meta-analysis was only suitable for intracranial hemorrhage detection in CT imaging (10/16 studies), where AI systems had a pooled sensitivity and specificity 0.90 (95% confidence interval [CI] 0.85-0.94) and 0.90 (95% CI 0.83-0.95), respectively. Other AI studies using CT and MRI detected target conditions other than hemorrhage (2/16), or multiple target conditions (4/16). Only 3/16 studies implemented AI in clinical pathways, either for pre-read triage or as post-read discrepancy identifiers.

CONCLUSION

The paucity of eligible studies reflects that most abnormality detection AI studies were not adequately validated in representative clinical cohorts. The few studies describing how abnormality detection AI could impact patients and clinicians did not explore the full ramifications of clinical implementation.

Factors affecting the labelling accuracy of brain MRI studies relevant for deep learning abnormality detection

Unlocking the vast potential of deep learning-based computer vision classification systems necessitates large data sets for model training. Natural Language Processing (NLP)-involving automation of dataset labelling-represents a potential avenue to achieve this. However, many aspects of NLP for dataset labelling remain unvalidated. Expert radiologists manually labelled over 5,000 MRI head reports in order to develop a deep learning-based neuroradiology NLP report classifier. Our results demonstrate that binary labels (normal vs. abnormal) showed high rates of accuracy, even when only two MRI sequences (T2-weighted and those based on diffusion weighted imaging) were employed as opposed to all sequences in an examination. Meanwhile, the accuracy of more specific labelling for multiple disease categories was variable and dependent on the category. Finally, resultant model performance was shown to be dependent on the expertise of the original labeller, with worse performance seen with non-expert vs. expert labellers.

Association of partial T2-FLAIR mismatch sign and isocitrate dehydrogenase mutation in WHO grade 4 gliomas: results from the ReSPOND consortium

PURPOSE

While the T2-FLAIR mismatch sign is highly specific for isocitrate dehydrogenase (IDH)-mutant, 1p/19q-noncodeleted astrocytomas among lower-grade gliomas, its utility in WHO grade 4 gliomas is not well-studied. We derived the partial T2-FLAIR mismatch sign as an imaging biomarker for IDH mutation in WHO grade 4 gliomas.

METHODS

Preoperative MRI scans of adult WHO grade 4 glioma patients (n = 2165) from the multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium were analyzed. Diagnostic performance of the partial T2-FLAIR mismatch sign was evaluated. Subset analyses were performed to assess associations of imaging markers with overall survival (OS).

RESULTS

One hundred twenty-one (5.6%) of 2165 grade 4 gliomas were IDH-mutant. Partial T2-FLAIR mismatch was present in 40 (1.8%) cases, 32 of which were IDH-mutant, yielding 26.4% sensitivity, 99.6% specificity, 80.0% positive predictive value, and 95.8% negative predictive value. Multivariate logistic regression demonstrated IDH mutation was significantly associated with partial T2-FLAIR mismatch (odds ratio [OR] 5.715, 95% CI [1.896, 17.221], p = 0.002), younger age (OR 0.911 [0.895, 0.927], p < 0.001), tumor centered in frontal lobe (OR 3.842, [2.361, 6.251], p < 0.001), absence of multicentricity (OR 0.173, [0.049, 0.612], p = 0.007), and presence of cystic (OR 6.596, [3.023, 14.391], p < 0.001) or non-enhancing solid components (OR 6.069, [3.371, 10.928], p < 0.001). Multivariate Cox analysis demonstrated cystic components (p = 0.024) and non-enhancing solid components (p = 0.003) were associated with longer OS, while older age (p < 0.001), frontal lobe center (p = 0.008), multifocality (p < 0.001), and multicentricity (p < 0.001) were associated with shorter OS.

CONCLUSION

Partial T2-FLAIR mismatch sign is highly specific for IDH mutation in WHO grade 4 gliomas.

Robotically facilitated parafasicular microsurgery to a brain arteriovenous malformation in a paediatric patient

PURPOSE

We report what we believe is the first application of robotically constrained image-guided surgery to approach a fistulous micro-arteriovenous malformation in a highly eloquent location. Drawing on institutional experience with a supervisory-control robotic system, a series of steps were devised to deliver a tubular retractor system to a deeply situated micro-arteriovenous malformation. The surgical footprint of this procedure was minimised along with the neurological morbidity. We hope that our contribution will be of assistance to others in integrating such systems given a similar clinical problem.

CLINICAL PRESENTATION

A right-handed 9-year old girl presented to her local emergency department after a sudden onset of severe headache accompanied by vomiting. An intracranial haemorrhage centred in the right centrum semiovale with intraventricular extension was evident and she was transferred urgently to the regional paediatric neurosurgical centre, where an external ventricular drain (EVD) was sited. A digital subtraction angiogram demonstrated a small right hemispheric arteriovenous shunt irrigated by peripheral branches of the middle cerebral artery & a robotically facilitated parafasicular microsurgical approach was performed to disconnect the arteriovenous malformation.

CONCLUSION

We describe the successful microsurgical in-situ disconnection of a deeply-situated, fistulous micro-AVM via a port system itself delivered directly to the target with a supervisory-control robotic system. This minimised the surgical disturbance along a relatively long white matter trajectory and demonstrates the feasibility of this approach for deeply located arteriovenous fistulae or fistulous AVMs.

Artificial intelligence in the autonomous navigation of endovascular interventions: a systematic review

Background

Autonomous navigation of catheters and guidewires in endovascular interventional surgery can decrease operation times, improve decision-making during surgery, and reduce operator radiation exposure while increasing access to treatment.

Objective

To determine from recent literature, through a systematic review, the impact, challenges, and opportunities artificial intelligence (AI) has for the autonomous navigation of catheters and guidewires for endovascular interventions.

Methods

PubMed and IEEEXplore databases were searched to identify reports of AI applied to autonomous navigation methods in endovascular interventional surgery. Eligibility criteria included studies investigating the use of AI in enabling the autonomous navigation of catheters/guidewires in endovascular interventions. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), articles were assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). PROSPERO: CRD42023392259.

Results

Four hundred and sixty-two studies fulfilled the search criteria, of which 14 studies were included for analysis. Reinforcement learning (RL) (9/14, 64%) and learning from expert demonstration (7/14, 50%) were used as data-driven models for autonomous navigation. These studies evaluated models on physical phantoms (10/14, 71%) and in-silico (4/14, 29%) models. Experiments within or around the blood vessels of the heart were reported by the majority of studies (10/14, 71%), while non-anatomical vessel platforms "idealized" for simple navigation were used in three studies (3/14, 21%), and the porcine liver venous system in one study. We observed that risk of bias and poor generalizability were present across studies. No procedures were performed on patients in any of the studies reviewed. Moreover, all studies were limited due to the lack of patient selection criteria, reference standards, and reproducibility, which resulted in a low level of evidence for clinical translation.

Conclusion

Despite the potential benefits of AI applied to autonomous navigation of endovascular interventions, the field is in an experimental proof-of-concept stage, with a technology readiness level of 3. We highlight that reference standards with well-identified performance metrics are crucial to allow for comparisons of data-driven algorithms proposed in the years to come.

Systematic review registration

identifier: CRD42023392259.

The experience of interval scans for adults living with primary malignant brain tumors

PURPOSE

People with primary malignant brain tumors (PMBT) undergo anti-tumor treatment and are followed up with MRI interval scans. There are potential burdens and benefits to interval scanning, yet high-quality evidence to suggest whether scans are beneficial or alter outcomes of importance for patients is lacking. We aimed to gain an in-depth understanding of how adults living with PMBTs experience and cope with interval scanning.

METHODS

Twelve patients diagnosed with WHO grade III or IV PMBT from two sites in the UK took part. Using a semi-structured interview guide, they were asked about their experiences of interval scans. A constructivist grounded theory approach was used to analyze data.

RESULTS

Although most participants found interval scans uncomfortable, they accepted that scans were something that they had to do and were using various coping methods to get through the MRI scan. All participants said that the wait between their scan and results was the most difficult part. Despite the difficulties they experienced, all participants said that they would rather have interval scans than wait for a change in their symptoms. Most of the time, scans provided relief, gave participants some certainty in an uncertain situation, and a short-term sense of control over their lives.

CONCLUSION

The present study shows that interval scanning is important and highly valued by patients living with PMBT. Although interval scans are anxiety provoking, they appear to help people living with PMBT cope with the uncertainty of their condition.

Detection of cerebral aneurysms using artificial intelligence: a systematic review and meta-analysis

BACKGROUND

Subarachnoid hemorrhage from cerebral aneurysm rupture is a major cause of morbidity and mortality. Early aneurysm identification, aided by automated systems, may improve patient outcomes. Therefore, a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence (AI) algorithms in detecting cerebral aneurysms using CT, MRI or DSA was performed.

METHODS

MEDLINE, Embase, Cochrane Library and Web of Science were searched until August 2021. Eligibility criteria included studies using fully automated algorithms to detect cerebral aneurysms using MRI, CT or DSA. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy (PRISMA-DTA), articles were assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis included a bivariate random-effect model to determine pooled sensitivity, specificity, and area under the receiver operator characteristic curve (ROC-AUC).

PROSPERO

CRD42021278454.

RESULTS

43 studies were included, and 41/43 (95%) were retrospective. 34/43 (79%) used AI as a standalone tool, while 9/43 (21%) used AI assisting a reader. 23/43 (53%) used deep learning. Most studies had high bias risk and applicability concerns, limiting conclusions. Six studies in the standalone AI meta-analysis gave (pooled) 91.2% (95% CI 82.2% to 95.8%) sensitivity; 16.5% (95% CI 9.4% to 27.1%) false-positive rate (1-specificity); 0.936 ROC-AUC. Five reader-assistive AI studies gave (pooled) 90.3% (95% CI 88.0% - 92.2%) sensitivity; 7.9% (95% CI 3.5% to 16.8%) false-positive rate; 0.910 ROC-AUC.

CONCLUSION

AI has the potential to support clinicians in detecting cerebral aneurysms. Interpretation is limited due to high risk of bias and poor generalizability. Multicenter, prospective studies are required to assess AI in clinical practice.

Overcoming challenges of translating deep-learning models for glioblastoma: the ZGBM consortium

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.

Federated learning enables big data for rare cancer boundary detection

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

Imaging timing after glioblastoma surgery (INTERVAL-GB): protocol for a UK and Ireland, multicentre retrospective cohort study

INTRODUCTION

Glioblastoma is the most common malignant primary brain tumour with a median overall survival of 12-15 months (range 6-17 months), even with maximal treatment involving debulking neurosurgery and adjuvant concomitant chemoradiotherapy. The use of postoperative imaging to detect progression is of high importance to clinicians and patients, but currently, the optimal follow-up schedule is yet to be defined. It is also unclear how adhering to National Institute for Health and Care Excellence (NICE) guidelines-which are based on general consensus rather than evidence-affects patient outcomes such as progression-free and overall survival. The primary aim of this study is to assess MRI monitoring practice after surgery for glioblastoma, and to evaluate its association with patient outcomes.

METHODS AND ANALYSIS

ImagiNg Timing aftER surgery for glioblastoma: an eVALuation of practice in Great Britain and Ireland is a retrospective multicentre study that will include 450 patients with an operated glioblastoma, treated with any adjuvant therapy regimen in the UK and Ireland. Adult patients ≥18 years diagnosed with glioblastoma and undergoing surgery between 1 August 2018 and 1 February 2019 will be included. Clinical and radiological scanning data will be collected until the date of death or date of last known follow-up. Anonymised data will be uploaded to an online Castor database. Adherence to NICE guidelines and the effect of being concordant with NICE guidelines will be identified using descriptive statistics and Kaplan-Meier survival analysis.

ETHICS AND DISSEMINATION

Each participating centre is required to gain local institutional approval for data collection and sharing. Formal ethical approval is not required since this is a service evaluation. Results of the study will be reported through peer-reviewed presentations and articles, and will be disseminated to participating centres, patients and the public.

The changing landscape of cerebral revascularization surgery: A United Kingdom experience

Objective

We describe the chronological trends in cerebral revascularization surgery through a single-surgeon experience; and we review whether in the context of giant and fusiform cerebral aneurysms, flow-diverting stents have impacted on the use of cerebral revascularization surgery.

Methods

We review our single institution prospectively collected database of cerebral revascularization procedures between 2006 and 2018. Comparing this to our database of flow-diverting endovascular stent procedures, we compare the treatment of fusiform and giant aneurysms. We describe patient demographics, procedural incidence, complications, and outcomes.

Results

Between 2006 and 2018, 50 cerebral revascularization procedures were performed. The incidence of cerebral revascularization surgery is declining. In the context of giant/fusiform aneurysm treatment, the decline in cerebral revascularization is accompanied by a rise in the use of flow-diverting endovascular stents. Thirty cerebral revascularizations were performed for moyamoya disease and 11 for giant/fusiform aneurysm. Four (14%) direct bypass grafts occluded without neurological sequela. Other morbidity included hydrocephalus (2%), transient ischemic attacks (2%), and ischemic stroke (2%). There was one procedure-related mortality (2%). Flow-diverting stents were inserted for seven fusiform and seven giant aneurysms. Comparing the treatment of giant/fusiform aneurysms, there was no significant difference in morbidity and mortality between cerebral revascularization and flow-diverting endovascular stents.

Conclusion

We conclude that with the decline in the incidence of cerebral revascularization surgery, there is a need for centralization of services to allow high standards and outcomes to be maintained.

OS09.5.A The experience of interval scans for adults living with primary malignant brain tumours

Background

People living with primary malignant brain tumours (PMBT) face a complex and unpredictable illness. Throughout the disease course they undergo various treatments and follow-up with regular interval scanning. There are potential costs and benefits to interval scanning, however there is no high-quality evidence to suggest interval scanning is beneficial or whether scans alter outcomes of importance for people living with PMBTs. Yet, interval scanning may exacerbate issues such as uncertainty and anxiety - which impacts on patient quality of life. The aim of this study was to gain an in-depth understanding of how adults living with PMBTs experience and cope with interval scanning.

Material and Methods

Twelve patients with a diagnosis of PMBT (glioblastoma n=10; astrocytoma grade 3 n=1; solitary fibrous tumour of the dura grade 3 n=1) under the neuro-oncology teams at Leeds Teaching Hospital NHS Trust and King's College Hospital NHS Foundation Trust took part in the study. They were interviewed remotely about their experiences of interval scans, following a semi-structured interview guide. An abbreviated version of a constructionist grounded theory approach was used to analyse data.

Results

Five main themes were generated from the data: ‘Living with a PMBT’, ‘Interval scanning: the difficult times’, ‘MRI scan: accepting the discomfort’, ‘Waiting for results: coping with the uncertainty’ and ‘Results: providing some certainty in uncertainty’. Although most participants found interval scans uncomfortable, they accepted that they were something that they had to do and were using various coping methods to get through the MRI scan. All participants said that the wait between their scan and results was the most difficult part. Despite the difficulties they experienced, all participants said that they would prefer to have interval scans than wait for a change in their symptoms. Most of the time, scans provided relief, gave participants some certainty in an uncertain situation, and a short-term sense of control over their lives.

Conclusion

The present study shows that interval scanning is important and highly valued by patients living with PMBT. Although interval scans are anxiety provoking, they appear to help people living with PMBT cope with the uncertainty of their diagnosis.

Imaging in patients with glioblastoma: A national cohort study

Background

Glioblastoma is the most common malignant brain tumor in adults and has a poor prognosis. This cohort of patients is diverse and imaging is vital to formulate treatment plans. Despite this, there is relatively little data on patterns of use of imaging and imaging workload in routine practice.

Methods

We examined imaging patterns for all patients aged 15–99 years resident in England who were diagnosed with a glioblastoma between 1st January 2013 and 31st December 2014. Patients without imaging and death-certificate-only registrations were excluded.

Results

The analytical cohort contained 4,307 patients. There was no significant variation in pre- or postdiagnostic imaging practice by sex or deprivation quintile. Postdiagnostic imaging practice was varied. In the group of patients who were treated most aggressively (surgical debulking and chemoradiation) and were MRI compatible, only 51% had a postoperative MRI within 72 hours of surgery. In patients undergoing surgery who subsequently received radiotherapy, only 61% had a postsurgery and preradiotherapy MRI.

Conclusions

Prediagnostic imaging practice is uniform. Postdiagnostic imaging practice was variable. With increasing evidence and clearer recommendations regarding debulking surgery and planning radiotherapy imaging, the reason for this is unclear and will form the basis of further work.

Robotics in neurointerventional surgery: a systematic review of the literature

BACKGROUND

Robotically performed neurointerventional surgery has the potential to reduce occupational hazards to staff, perform intervention with greater precision, and could be a viable solution for teleoperated neurointerventional procedures.

OBJECTIVE

To determine the indication, robotic systems used, efficacy, safety, and the degree of manual assistance required for robotically performed neurointervention.

METHODS

We conducted a systematic review of the literature up to, and including, articles published on April 12, 2021. Medline, PubMed, Embase, and Cochrane register databases were searched using medical subject heading terms to identify reports of robotically performed neurointervention, including diagnostic cerebral angiography and carotid artery intervention.

RESULTS

A total of 8 articles treating 81 patients were included. Only one case report used a robotic system for intracranial intervention, the remaining indications being cerebral angiography and carotid artery intervention. Only one study performed a comparison of robotic and manual procedures. Across all studies, the technical success rate was 96% and the clinical success rate was 100%. All cases required a degree of manual assistance. No studies had clearly defined patient selection criteria, reference standards, or index tests, preventing meaningful statistical analysis.

CONCLUSIONS

Given the clinical success, it is plausible that robotically performed neurointerventional procedures will eventually benefit patients and reduce occupational hazards for staff; however, there is no high-level efficacy and safety evidence to support this assertion. Limitations of current robotic systems and the challenges that must be overcome to realize the potential for remote teleoperated neurointervention require further investigation.

Perfusion Imaging for Endovascular Thrombectomy in Acute Ischemic Stroke Is Associated With Improved Functional Outcomes in the Early and Late Time Windows

The impact on clinical outcomes of patient selection using perfusion imaging for endovascular thrombectomy (EVT) in patients with acute ischemic stroke presenting beyond 6 hours from onset remains undetermined in routine clinical practice.

Deep learning models for triaging hospital head MRI examinations

The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken to report head MRI scans in recent years. For many neurological conditions, this delay can result in poorer patient outcomes and inflated healthcare costs. Potentially, computer vision models could help reduce reporting times for abnormal examinations by flagging abnormalities at the time of imaging, allowing radiology departments to prioritise limited resources into reporting these scans first. To date, however, the difficulty of obtaining large, clinically-representative labelled datasets has been a bottleneck to model development. In this work, we present a deep learning framework, based on convolutional neural networks, for detecting clinically-relevant abnormalities in minimally processed, hospital-grade axial T2-weighted and axial diffusion-weighted head MRI scans. The models were trained at scale using a Transformer-based neuroradiology report classifier to generate a labelled dataset of 70,206 examinations from two large UK hospital networks, and demonstrate fast (< 5 s), accurate (area under the receiver operating characteristic curve (AUC) > 0.9), and interpretable classification, with good generalisability between hospitals (ΔAUC ≤ 0.02). Through a simulation study we show that our best model would reduce the mean reporting time for abnormal examinations from 28 days to 14 days and from 9 days to 5 days at the two hospital networks, demonstrating feasibility for use in a clinical triage environment.

Accurate brain-age models for routine clinical MRI examinations

Convolutional neural networks (CNN) can accurately predict chronological age in healthy individuals from structural MRI brain scans. Potentially, these models could be applied during routine clinical examinations to detect deviations from healthy ageing, including early-stage neurodegeneration. This could have important implications for patient care, drug development, and optimising MRI data collection. However, existing brain-age models are typically optimised for scans which are not part of routine examinations (e.g., volumetric T1-weighted scans), generalise poorly (e.g., to data from different scanner vendors and hospitals etc.), or rely on computationally expensive pre-processing steps which limit real-time clinical utility. Here, we sought to develop a brain-age framework suitable for use during routine clinical head MRI examinations. Using a deep learning-based neuroradiology report classifier, we generated a dataset of 23,302 'radiologically normal for age' head MRI examinations from two large UK hospitals for model training and testing (age range = 18-95 years), and demonstrate fast (< 5 s), accurate (mean absolute error [MAE] < 4 years) age prediction from clinical-grade, minimally processed axial T2-weighted and axial diffusion-weighted scans, with generalisability between hospitals and scanner vendors (Δ MAE < 1 year). The clinical relevance of these brain-age predictions was tested using 228 patients whose MRIs were reported independently by neuroradiologists as showing atrophy 'excessive for age'. These patients had systematically higher brain-predicted age than chronological age (mean predicted age difference = +5.89 years, 'radiologically normal for age' mean predicted age difference = +0.05 years, p < 0.0001). Our brain-age framework demonstrates feasibility for use as a screening tool during routine hospital examinations to automatically detect older-appearing brains in real-time, with relevance for clinical decision-making and optimising patient pathways.

High-Grade Glioma Treatment Response Monitoring Biomarkers: A Position Statement on the Evidence Supporting the Use of Advanced MRI Techniques in the Clinic, and the Latest Bench-to-Bedside Developments. Part 1: Perfusion and Diffusion Techniques

Objective

Summarize evidence for use of advanced MRI techniques as monitoring biomarkers in the clinic, and highlight the latest bench-to-bedside developments.

Methods

Experts in advanced MRI techniques applied to high-grade glioma treatment response assessment convened through a European framework. Current evidence regarding the potential for monitoring biomarkers in adult high-grade glioma is reviewed, and individual modalities of perfusion, permeability, and microstructure imaging are discussed (in Part 1 of two). In Part 2, we discuss modalities related to metabolism and/or chemical composition, appraise the clinic readiness of the individual modalities, and consider post-processing methodologies involving the combination of MRI approaches (multiparametric imaging) or machine learning (radiomics).

Results

High-grade glioma vasculature exhibits increased perfusion, blood volume, and permeability compared with normal brain tissue. Measures of cerebral blood volume derived from dynamic susceptibility contrast-enhanced MRI have consistently provided information about brain tumor growth and response to treatment; it is the most clinically validated advanced technique. Clinical studies have proven the potential of dynamic contrast-enhanced MRI for distinguishing post-treatment related effects from recurrence, but the optimal acquisition protocol, mode of analysis, parameter of highest diagnostic value, and optimal cut-off points remain to be established. Arterial spin labeling techniques do not require the injection of a contrast agent, and repeated measurements of cerebral blood flow can be performed. The absence of potential gadolinium deposition effects allows widespread use in pediatric patients and those with impaired renal function. More data are necessary to establish clinical validity as monitoring biomarkers. Diffusion-weighted imaging, apparent diffusion coefficient analysis, diffusion tensor or kurtosis imaging, intravoxel incoherent motion, and other microstructural modeling approaches also allow treatment response assessment; more robust data are required to validate these alone or when applied to post-processing methodologies.

Conclusion

Considerable progress has been made in the development of these monitoring biomarkers. Many techniques are in their infancy, whereas others have generated a larger body of evidence for clinical application.

High-Grade Glioma Treatment Response Monitoring Biomarkers: A Position Statement on the Evidence Supporting the Use of Advanced MRI Techniques in the Clinic, and the Latest Bench-to-Bedside Developments. Part 2: Spectroscopy, Chemical Exchange Saturation, Multiparametric Imaging, and Radiomics

Objective

To summarize evidence for use of advanced MRI techniques as monitoring biomarkers in the clinic, and to highlight the latest bench-to-bedside developments.

Methods

The current evidence regarding the potential for monitoring biomarkers was reviewed and individual modalities of metabolism and/or chemical composition imaging discussed. Perfusion, permeability, and microstructure imaging were similarly analyzed in Part 1 of this two-part review article and are valuable reading as background to this article. We appraise the clinic readiness of all the individual modalities and consider methodologies involving machine learning (radiomics) and the combination of MRI approaches (multiparametric imaging).

Results

The biochemical composition of high-grade gliomas is markedly different from healthy brain tissue. Magnetic resonance spectroscopy allows the simultaneous acquisition of an array of metabolic alterations, with choline-based ratios appearing to be consistently discriminatory in treatment response assessment, although challenges remain despite this being a mature technique. Promising directions relate to ultra-high field strengths, 2-hydroxyglutarate analysis, and the use of non-proton nuclei. Labile protons on endogenous proteins can be selectively targeted with chemical exchange saturation transfer to give high resolution images. The body of evidence for clinical application of amide proton transfer imaging has been building for a decade, but more evidence is required to confirm chemical exchange saturation transfer use as a monitoring biomarker. Multiparametric methodologies, including the incorporation of nuclear medicine techniques, combine probes measuring different tumor properties. Although potentially synergistic, the limitations of each individual modality also can be compounded, particularly in the absence of standardization. Machine learning requires large datasets with high-quality annotation; there is currently low-level evidence for monitoring biomarker clinical application.

Conclusion

Advanced MRI techniques show huge promise in treatment response assessment. The clinical readiness analysis highlights that most monitoring biomarkers require standardized international consensus guidelines, with more facilitation regarding technique implementation and reporting in the clinic.

Imaging Biomarkers of Glioblastoma Treatment Response: A Systematic Review and Meta-Analysis of Recent Machine Learning Studies

OBJECTIVE

Monitoring biomarkers using machine learning (ML) may determine glioblastoma treatment response. We systematically reviewed quality and performance accuracy of recently published studies.

METHODS

Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy, we extracted articles from MEDLINE, EMBASE and Cochrane Register between 09/2018-01/2021. Included study participants were adults with glioblastoma having undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide), and follow-up imaging to determine treatment response status (specifically, distinguishing progression/recurrence from progression/recurrence mimics, the target condition). Using Quality Assessment of Diagnostic Accuracy Studies Two/Checklist for Artificial Intelligence in Medical Imaging, we assessed bias risk and applicability concerns. We determined test set performance accuracy (sensitivity, specificity, precision, F1-score, balanced accuracy). We used a bivariate random-effect model to determine pooled sensitivity, specificity, area-under the receiver operator characteristic curve (ROC-AUC). Pooled measures of balanced accuracy, positive/negative likelihood ratios (PLR/NLR) and diagnostic odds ratio (DOR) were calculated. PROSPERO registered (CRD42021261965).

RESULTS

Eighteen studies were included (1335/384 patients for training/testing respectively). Small patient numbers, high bias risk, applicability concerns (particularly confounding in reference standard and patient selection) and low level of evidence, allow limited conclusions from studies. Ten studies (10/18, 56%) included in meta-analysis gave 0.769 (0.649-0.858) sensitivity [pooled (95% CI)]; 0.648 (0.749-0.532) specificity; 0.706 (0.623-0.779) balanced accuracy; 2.220 (1.560-3.140) PLR; 0.366 (0.213-0.572) NLR; 6.670 (2.800-13.500) DOR; 0.765 ROC-AUC.

CONCLUSION

ML models using MRI features to distinguish between progression and mimics appear to demonstrate good diagnostic performance. However, study quality and design require improvement.

NIMG-39. RADIOMIC ANALYSIS FOR NON-INVASIVE IN VIVO PROGNOSTIC STRATIFICATION OF DE NOVO GLIOBLASTOMA PATIENTS: A MULTI-INSTITUTIONAL EVALUATION FOR GENERALIZABILITY IN THE RESPOND CONSORTIUM

PURPOSE

Multi-parametric MRI based radiomic signatures have highlighted the promise of artificial intelligence (AI) in neuro-oncology. However, inter-institution heterogeneity hinders generalization to data from unseen clinical institutions. To this end, we formulated the ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium for glioblastoma. Here, we seek non-invasive generalizable radiomic signatures from routine clinically-acquired MRI for prognostic stratification of glioblastoma patients.

METHODS

We identified a retrospective cohort of 606 patients with near/gross total tumor resection ( &gt;90%), from 13 geographically-diverse institutions. All pre-operative structural MRI scans (T1,T1-Gd,T2,T2-FLAIR) were aligned to a common anatomical atlas. An automatic algorithm segmented the whole tumors (WTs) into 3 sub-compartments, i.e., enhancing (ET), necrotic core (NC), and peritumoral T2-FLAIR signal abnormality (ED). The combination of ET+NC defines the tumor core (TC). Quantitative radiomic features were extracted to generate our AI model to stratify patients into short- (&lt; 14mts) and long-survivors ( &gt;14mts). The model trained on 276 patients from a single institution was independently validated on 330 unseen patients from 12 left-out institutions, using the area-under-the-receiver-operating-characteristic-curve (AUC).

RESULTS

Each feature individually offered certain (limited but reproducible) value for identifying short-survivors: 1) TC closer to lateral ventricles (AUC=0.62); 2) larger ET/brain (AUC=0.61); 3) larger TC/brain (AUC=0.59); 4) larger WT/brain (AUC=0.55); 5) larger ET/WT (AUC=0.59); 6) smaller ED/WT (AUC=0.57); 7) larger ventricle deformations (AUC=0.6). Integrating all features and age, through a multivariate AI model, resulted in higher accuracy (AUC=0.7; 95% C.I.,0.64-0.77).

CONCLUSION

Prognostic stratification using basic radiomic features is highly reproducible across diverse institutions and patient populations. Multivariate integration yields relatively more accurate and generalizable radiomic signatures, across institutions. Our results offer promise for generalizable non-invasive in vivo signatures of survival prediction in patients with glioblastoma. Extracted features from clinically-acquired imaging, renders these signatures easier for clinical translation. Large-scale evaluation could contribute to improving patient management and treatment planning.

*Indicates equal authorship.

NIMG-22. PREDICTION OF GLIOBLASTOMA CELLULAR INFILTRATION AND RECURRENCE USING MACHINE LEARNING AND MULTI-PARAMETRIC MRI ANALYSIS: RESULTS FROM THE MULTI-INSTITUTIONAL RESPOND CONSORTIUM

PURPOSE

Multi-parametric MRI and artificial intelligence (AI) methods were previously used to predict peritumoral neoplastic cell infiltration and risk of future recurrence in glioblastoma, in single-institution studies. We hypothesize that important characteristics of peritumoral tissue heterogeneity captured, engineered/selected, and quantified by these methods relate to predictions generalizable in the multi-institutional ReSPOND (Radiomics Signatures for PrecisiON Diagnostics) consortium.

METHODS

To support further development, generalization, and clinical translation of our proposed method, we trained the AI model on a retrospective cohort of 29 de novo glioblastoma patients from the Hospital of the University of Pennsylvania (UPenn) (Male/Female:20/9, age:22-78 years) followed by evaluation on a prospective multi-institutional cohort of 84 glioblastoma patients (Male/Female:51/33, age:34-89 years) from Case Western Reserve University/University Hospitals (CWRU/UH, 25), New York University (NYU, 13), Ohio State University (OSU, 13), University Hospital Río Hortega (RH, 2), and UPenn (31). Features extracted from pre-resection MRI (T1, T1-Gd, T2, T2-FLAIR, ADC) were used to build our model predicting the spatial pattern of subsequent tumor recurrence. These predictions were evaluated against regions of pathology-confirmed post-resection recurrence.

RESULTS

Our model predicted the locations that later harbored tumor recurrence with sensitivity 83%, AUC 0.83 (99% CI, 0.73-0.93), and odds ratio 7.23 (99% CI, 7.09-7.37) in the prospective cohort. Odds ratio (99% CI)/AUC(99% CI) per institute were: CWRU/UH, 7.8(7.6-8.1)/0.82(0.75-0.89); NYU, 3.5(3.3-3.6)/0.84(074-0.93); OSU, 7.9(7.6-8.3)/0.8(0.67-0.94); RH, 22.7(20-25.1)/0.94(0.27-1); UPenn, 7.1(6.8-7.3)/0.83(0.76-0.91).

CONCLUSION

This is the first study that provides relatively extensive multi-institutional validated evidence that AI can provide good predictions of peritumoral neoplastic cell infiltration and future recurrence, by dissecting the MRI signal heterogeneity in peritumoral tissue. Our analyses leveraged the unique dataset of the ReSPOND consortium, which aims to develop and evaluate AI-based biomarkers for individualized prediction and prognostication, by moving from single-institution studies to generalizable, well-validated multi-institutional predictive biomarkers.

OS08.6.A Glioblastoma treatment response machine learning monitoring biomarkers: a systematic review and meta-analysis

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.

Deep learning to automate the labelling of head MRI datasets for computer vision applications

Objectives

The purpose of this study was to build a deep learning model to derive labels from neuroradiology reports and assign these to the corresponding examinations, overcoming a bottleneck to computer vision model development.

Methods

Reference-standard labels were generated by a team of neuroradiologists for model training and evaluation. Three thousand examinations were labelled for the presence or absence of any abnormality by manually scrutinising the corresponding radiology reports (‘reference-standard report labels’); a subset of these examinations (n = 250) were assigned ‘reference-standard image labels’ by interrogating the actual images. Separately, 2000 reports were labelled for the presence or absence of 7 specialised categories of abnormality (acute stroke, mass, atrophy, vascular abnormality, small vessel disease, white matter inflammation, encephalomalacia), with a subset of these examinations (n = 700) also assigned reference-standard image labels. A deep learning model was trained using labelled reports and validated in two ways: comparing predicted labels to (i) reference-standard report labels and (ii) reference-standard image labels. The area under the receiver operating characteristic curve (AUC-ROC) was used to quantify model performance. Accuracy, sensitivity, specificity, and F1 score were also calculated.

Results

Accurate classification (AUC-ROC > 0.95) was achieved for all categories when tested against reference-standard report labels. A drop in performance (ΔAUC-ROC > 0.02) was seen for three categories (atrophy, encephalomalacia, vascular) when tested against reference-standard image labels, highlighting discrepancies in the original reports. Once trained, the model assigned labels to 121,556 examinations in under 30 min.

Conclusions

Our model accurately classifies head MRI examinations, enabling automated dataset labelling for downstream computer vision applications.

Key Points

• Deep learning is poised to revolutionise image recognition tasks in radiology; however, a barrier to clinical adoption is the difficulty of obtaining large labelled datasets for model training.

• We demonstrate a deep learning model which can derive labels from neuroradiology reports and assign these to the corresponding examinations at scale, facilitating the development of downstream computer vision models.

• We rigorously tested our model by comparing labels predicted on the basis of neuroradiology reports with two sets of reference-standard labels: (1) labels derived by manually scrutinising each radiology report and (2) labels derived by interrogating the actual images.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-08132-0.

A Position Statement on the Utility of Interval Imaging in Standard of Care Brain Tumour Management: Defining the Evidence Gap and Opportunities for Future Research

Objectiv e

To summarise current evidence for the utility of interval imaging in monitoring disease in adult brain tumours, and to develop a position for future evidence gathering while incorporating the application of data science and health economics.

Methods

Experts in 'interval imaging' (imaging at pre-planned time-points to assess tumour status); data science; health economics, trial management of adult brain tumours, and patient representatives convened in London, UK. The current evidence on the use of interval imaging for monitoring brain tumours was reviewed. To improve the evidence that interval imaging has a role in disease management, we discussed specific themes of data science, health economics, statistical considerations, patient and carer perspectives, and multi-centre study design. Suggestions for future studies aimed at filling knowledge gaps were discussed.

Results

Meningioma and glioma were identified as priorities for interval imaging utility analysis. The "monitoring biomarkers" most commonly used in adult brain tumour patients were standard structural MRI features. Interval imaging was commonly scheduled to provide reported imaging prior to planned, regular clinic visits. There is limited evidence relating interval imaging in the absence of clinical deterioration to management change that alters morbidity, mortality, quality of life, or resource use. Progression-free survival is confounded as an outcome measure when using structural MRI in glioma. Uncertainty from imaging causes distress for some patients and their caregivers, while for others it provides an important indicator of disease activity. Any study design that changes imaging regimens should consider the potential for influencing current or planned therapeutic trials, ensure that opportunity costs are measured, and capture indirect benefits and added value.

Conclusion

Evidence for the value, and therefore utility, of regular interval imaging is currently lacking. Ongoing collaborative efforts will improve trial design and generate the evidence to optimise monitoring imaging biomarkers in standard of care brain tumour management.

COVID-19 Stroke Apical Lung Examination Study: A Diagnostic and Prognostic Imaging Biomarker in Suspected Acute Stroke

BACKGROUND AND PURPOSE

Diagnosis of coronavirus disease 2019 (COVID-19) relies on clinical features and reverse-transcriptase polymerase chain reaction testing, but the sensitivity is limited. Carotid CTA is a routine acute stroke investigation and includes the lung apices. We evaluated CTA as a potential COVID-19 diagnostic imaging biomarker.

MATERIALS AND METHODS

This was a multicenter, retrospective study (n = 225) including CTAs of patients with suspected acute stroke from 3 hyperacute stroke units (March-April 2020). We evaluated the reliability and accuracy of candidate diagnostic imaging biomarkers. Demographics, clinical features, and risk factors for COVID-19 and stroke were analyzed using univariate and multivariate statistics.

RESULTS

Apical ground-glass opacification was present in 22.2% (50/225) of patients. Ground-glass opacification had high interrater reliability (Fleiss κ = 0.81; 95% CI, 0.68-0.95) and, compared with reverse-transcriptase polymerase chain reaction, had good diagnostic performance (sensitivity, 75% [95% CI, 56-87]; specificity, 81% [95% CI, 71-88]; OR = 11.65 [95% CI, 4.14-32.78]; P < .001) on multivariate analysis. In contrast, all other contemporaneous demographic, clinical, and imaging features available at CTA were not diagnostic for COVID-19. The presence of apical ground-glass opacification was an independent predictor of increased 30-day mortality (18.0% versus 5.7%, P = .017; hazard ratio = 3.51; 95% CI, 1.42-8.66; P = .006).

CONCLUSIONS

We identified a simple, reliable, and accurate COVID-19 diagnostic and prognostic imaging biomarker obtained from CTA lung apices: the presence or absence of ground-glass opacification. Our findings have important implications in the management of patients presenting with suspected stroke through early identification of COVID-19 and the subsequent limitation of disease transmission.

Glioblastoma post-operative imaging in neuro-oncology: current UK practice (GIN CUP study)

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.

Woven Endobridge (WEB) Device as a Retreatment Strategy After Unsuccessful Surgical Clipping

BACKGROUND

Surgical clipping of intracranial aneurysms is typically robust and durable. However, residual aneurysmal components may be seen after clipping. Furthermore, there may be occasional aneurysmal recurrence. These factors are both clinically relevant because subarachnoid hemorrhage after clipping is a rare but important event. The rationale for any treatment is to substantially decrease the future risk of hemorrhage. Small series have shown coiling as a retreatment strategy after unsuccessful clipping, but none has explored the feasibility of Woven Endobridge (WEB) implantation.

CASE DESCRIPTION

We examined the feasibility of WEB implantation as second-line treatment for wide-necked residual aneurysms after unsuccessful clipping. We also recorded the safety and efficacy in this small series of 6 patients. To determine safety, we measured the modified Rankin Scale score before and after the procedure, and at 2 later time points (mean follow-up, 5 months and 15 months). To determine efficacy, we obtained radiographic aneurysm occlusion outcomes (including WEB Occlusion Scale) at these 2 time points. Four middle cerebral artery and 2 anterior communicating artery complex aneurysms were treated with WEB implantation, showing feasibility in 6/6 cases (100%). Follow-up at 15 months showed no change from preprocedural modified Rankin Scale score and there were no other complications. There was adequate occlusion in 5/6 cases (83%).

CONCLUSIONS

WEB implantation provided a feasible option in this challenging retreatment scenario. This is a small series and prospective data are required to make outcome inferences for this population. Nonetheless, we observed no complications and high adequate occlusion rates.

Machine learning and glioma imaging biomarkers

AIM

To review how machine learning (ML) is applied to imaging biomarkers in neuro-oncology, in particular for diagnosis, prognosis, and treatment response monitoring.

MATERIALS AND METHODS

The PubMed and MEDLINE databases were searched for articles published before September 2018 using relevant search terms. The search strategy focused on articles applying ML to high-grade glioma biomarkers for treatment response monitoring, prognosis, and prediction.

RESULTS

Magnetic resonance imaging (MRI) is typically used throughout the patient pathway because routine structural imaging provides detailed anatomical and pathological information and advanced techniques provide additional physiological detail. Using carefully chosen image features, ML is frequently used to allow accurate classification in a variety of scenarios. Rather than being chosen by human selection, ML also enables image features to be identified by an algorithm. Much research is applied to determining molecular profiles, histological tumour grade, and prognosis using MRI images acquired at the time that patients first present with a brain tumour. Differentiating a treatment response from a post-treatment-related effect using imaging is clinically important and also an area of active study (described here in one of two Special Issue publications dedicated to the application of ML in glioma imaging).

CONCLUSION

Although pioneering, most of the evidence is of a low level, having been obtained retrospectively and in single centres. Studies applying ML to build neuro-oncology monitoring biomarker models have yet to show an overall advantage over those using traditional statistical methods. Development and validation of ML models applied to neuro-oncology require large, well-annotated datasets, and therefore multidisciplinary and multi-centre collaborations are necessary.

Outcome Study of the Pipeline Embolization Device with Shield Technology in Unruptured Aneurysms (PEDSU)

BACKGROUND AND PURPOSE

The recently introduced Pipeline Flex Embolization Device with Shield Technology (Pipeline Shield) is the third generation of Pipeline flow-diverter devices. It has a new stent-surface modification, which reduces thrombogenicity. We aimed to evaluate clinical and radiographic (safety and efficacy) outcomes of the Pipeline Shield.

MATERIALS AND METHODS

The 30-day and 1-year mortality and morbidity rates and the 6- and 18-month radiographic aneurysm occlusion outcomes for procedures performed between March 2016 and January 2018 were analyzed. 3D-TOF-MRA was used for follow-up.

RESULTS

Forty-four attempted Pipeline Shield procedures were performed for 41 patients with 44 target aneurysms (total of 52 aneurysms treated). A total of 88.5% of devices were inserted in the anterior circulation, and 11.5%, in the posterior circulation; 49/52 (94.2%) aneurysms were saccular; and 1/52 (1.9%) was fusiform. One (1.9%) aneurysm was an iatrogenic pseudoaneurysm, and 1 (1.9%) was a dissecting aneurysm. Seventy-one percent (35/49) of the saccular aneurysms were wide-neck (neck, >4 mm), 34.6% (18/52) were large (≥10 mm), and 3.8% (2/52) were giant (≥25 mm). The mean aneurysm sac maximal diameter was 9.0 mm, and the mean neck width was 5.0 mm. The cumulative mortality and morbidity rates were 2.3% and 6.8% at 1 year, respectively. The adequate occlusion rate was 78.8% at 6 months and 90.3% at 18 months.

CONCLUSIONS

In this pragmatic and non-industry-sponsored study, the occlusion rates and safety outcomes were similar to those seen in previously published studies with flow-diverter devices and earlier generation Pipeline Embolization Devices.

The Fellowship of the Royal College of Radiologists (FRCR) examination: a review of the evidence

The Fellowship of the Royal College of Radiologists (FRCR) examination is the professional qualification that is essential for career progression in clinical radiology within the UK. It is also important for career progression in many countries internationally. The FRCR has evolved and changed over the last decade. In this systematic review we appraise and summarise the available data relating to the FRCR emphasising the published evidence regarding the validity, reliability, and acceptability of this examination. Comparison is made to other equivalent medical examinations, as well as a more recently published commissioned external review of the FRCR examinations. The Clinical Radiology Part 2B (CR2B) examination in its pre-existing format is reliable, valid, and acceptable. Recommendations from the commissioned external review are based primarily on expert opinion, with a limited evidence base comprising data from a small sample acquired during a single examination sitting and without peer review. Unlike the CR2B examination, there is little evidence regarding assessment of the CR1 and CR2 examinations. Both the CR1 and CR2 examinations are currently in the process of undergoing major changes to their formats. Blueprinting items to the curriculum might improve acceptability. Other changes may improve transparency and reliability of these assessments. Our analysis and many aspects of the external review may provide pointers regarding how the upcoming data produced by the "automated" FRCR examinations can be further analysed to provide a more robust evaluation.

Analysis of heterogeneity in T2-weighted MR images can differentiate pseudoprogression from progression in glioblastoma

PURPOSE

To develop an image analysis technique that distinguishes pseudoprogression from true progression by analyzing tumour heterogeneity in T2-weighted images using topological descriptors of image heterogeneity called Minkowski functionals (MFs).

METHODS

Using a retrospective patient cohort (n = 50), and blinded to treatment response outcome, unsupervised feature estimation was performed to investigate MFs for the presence of outliers, potential confounders, and sensitivity to treatment response. The progression and pseudoprogression groups were then unblinded and supervised feature selection was performed using MFs, size and signal intensity features. A support vector machine model was obtained and evaluated using a prospective test cohort.

RESULTS

The model gave a classification accuracy, using a combination of MFs and size features, of more than 85% in both retrospective and prospective datasets. A different feature selection method (Random Forest) and classifier (Lasso) gave the same results. Although not apparent to the reporting radiologist, the T2-weighted hyperintensity phenotype of those patients with progression was heterogeneous, large and frond-like when compared to those with pseudoprogression.

CONCLUSION

Analysis of heterogeneity, in T2-weighted MR images, which are acquired routinely in the clinic, has the potential to detect an earlier treatment response allowing an early change in treatment strategy. Prospective validation of this technique in larger datasets is required.

Post Brexit: challenges and opportunities for radiology beyond the European Union

We aimed to review the challenges and opportunities that radiology may face once the UK leaves the European Union (EU). Even before the exit negotiations commence, uncertainty over future policies and funding within the UK may influence the National Health Service (NHS). We discuss the potential impact that financial, regulatory and social changes may have on healthcare, and radiology in particular. Current difficulties in recruitment and retention of radiologists and the challenges that Brexit present are considered. Uncertainty over the new immigration regulations and their impact on the NHS workforce is addressed. Challenges also apply to UK research, which has greatly benefited from EU funding and the free movement of staff. Appreciating the problems as well as the opportunities that Brexit presents will help prepare radiology in the UK for the next decade.

Evaluation of two selection tests for recruitment into radiology specialty training

BACKGROUND

This study evaluated whether two selection tests previously validated for primary care General Practice (GP) trainee selection could provide a valid shortlisting selection method for entry into specialty training for the secondary care specialty of radiology.

METHODS

We conducted a retrospective analysis of data from radiology applicants who also applied to UK GP specialty training or Core Medical Training. The psychometric properties of the two selection tests, a clinical problem solving (CPS) test and situational judgement test (SJT), were analysed to evaluate their reliability. Predictive validity of the tests was analysed by comparing them with the current radiology selection assessments, and the licensure examination results taken after the first stage of training (Fellowship of the Royal College of Radiologists (FRCR) Part 1).

RESULTS

The internal reliability of the two selection tests in the radiology applicant sample was good (α ≥ 0.80). The average correlation with radiology shortlisting selection scores was r = 0.26 for the CPS (with p < 0.05 in 5 of 11 shortlisting centres), r = 0.15 for the SJT (with p < 0.05 in 2 of 11 shortlisting centres) and r = 0.25 (with p < 0.05 in 5 of 11 shortlisting centres) for the two tests combined. The CPS test scores significantly correlated with performance in both components of the FRCR Part 1 examinations (r = 0.5 anatomy; r = 0.4 physics; p < 0.05 for both). The SJT did not correlate with either component of the examination.

CONCLUSIONS

The current CPS test may be an appropriate selection method for shortlisting in radiology but would benefit from further refinement for use in radiology to ensure that the test specification is relevant. The evidence on whether the SJT may be appropriate for shortlisting in radiology is limited. However, these results may be expected to some extent since the SJT is designed to measure non-academic attributes. Further validation work (e.g. with non-academic outcome variables) is required to evaluate whether an SJT will add value in recruitment for radiology specialty training and will further inform construct validity of SJTs as a selection methodology.