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.

Dural arteriovenous fistula causing reversible cognitive impairment.

A previously independent 82-year-old woman presented with 5 months of worsening confusion, mobility and cognitive decline, with deficits in orientation, language and executive function. A cerebral dural arteriovenous fistula was identified and successfully embolised, after which her cognitive ability and independence dramatically improved. Although rare, a dural arteriovenous fistula may mimic a rapidly progressive dementia, but its early recognition and treatment can completely reverse the dementia.

Improving stroke pathways using an adhesive ambulatory ECG patch: reducing time for patients to ECGs and subsequent results.

Three south-London hospital trusts undertook a feasibility study, comparing data from 93 patients who received the 14-day adhesive ambulatory electrocardiography (ECG) patch Zio XT with retrospective data from 125 patients referred for 24-hour Holter for cryptogenic stroke and transient ischaemic attack following negative 12-lead ECG. As the ECG patch was fitted the same day as the clinical decision for ambulatory ECG monitoring was made, median time to the patient having the monitor fitted was significantly reduced in all three hospital trusts compared with 24-hour Holter being ordered and fitted. Hospital visits reduced by a median of two for patients receiving Zio XT. This project supports that it is feasible to use a patch as part of routine clinical care with a positive impact on care pathways.

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.

Acute ischaemic brain lesions in intracerebral haemorrhage: multicentre cross-sectional magnetic resonance imaging study.

Subclinical acute ischaemic lesions on brain magnetic resonance imaging have recently been described in spontaneous intracerebral haemorrhage, and may be important to understand pathophysiology and guide treatment. The underlying mechanisms are uncertain. We tested the hypothesis that ischaemic lesions are related to magnetic resonance imaging markers of the severity and type of small-vessel disease (hypertensive arteriopathy or cerebral amyloid angiopathy) in a multicentre, cross-sectional study. We studied consecutive patients with intracerebral haemorrhage from four specialist stroke centres, and age-matched stroke service referrals without intracerebral haemorrhage. Acute ischaemic lesions were assessed on magnetic resonance imaging (<3 months after intracerebral haemorrhage) using diffusion-weighted imaging. White matter changes and cerebral microbleeds were rated with validated scales. We investigated associations between diffusion-weighted imaging lesions, clinical and radiological characteristics. We included 114 patients with intracerebral haemorrhage (39 with clinically probable cerebral amyloid angiopathy) and 47 age-matched controls. The prevalence of diffusion-weighted imaging lesions was 9/39 (23%) in probable cerebral amyloid angiopathy-related intracerebral haemorrhage versus 6/75 (8%) in the remaining patients with intracerebral haemorrhage (P = 0.024); no diffusion-weighted imaging lesions were found in controls. Diffusion-weighted imaging lesions were mainly cortical and were associated with mean white matter change score (odds ratio 1.14 per unit increase, 95% confidence interval 1.02-1.28, P = 0.024) and the presence of strictly lobar cerebral microbleeds (odds ratio 3.85, 95% confidence interval 1.15-12.93, P = 0.029). Acute, subclinical ischaemic brain lesions are frequent but previously underestimated after intracerebral haemorrhage, and are three times more common in cerebral amyloid angiopathy-related intracerebral haemorrhage than in other intracerebral haemorrhage types. Ischaemic brain lesions are associated with white matter changes and cerebral microbleeds, suggesting that they result from an occlusive small-vessel arteriopathy. Diffusion-weighted imaging lesions contribute to the overall burden of vascular-related brain damage in intracerebral haemorrhage, and may be a useful surrogate marker of ongoing ischaemic injury from small-vessel damage.