Article Text
PDF
Abstract
Background Early detection of intracranial aneurysms (IAs) is crucial for patient outcomes. Typically identified on angiographic scans such as CT angiography (CTA) or MR angiography (MRA), the sensitivity of experts in studies on small IAs (diameter <3 mm) was moderate (64–74.1% for CTAs and 70–92.8% for MRAs), and these figures could be lower in a routine clinical setting. Recent research shows that the expert level of sensitivity might be achieved using deep learning approaches.
Methods A large multisite dataset including 1054 MRA and 2174 CTA scans with expert IA annotations was collected. A novel modality-agnostic two-step IA detection approach was proposed. The first step used nnU-Net for segmenting vascular structures, with model training performed separately for each modality. In the second step, segmentations were converted to vascular surface that was parcellated by sampling point clouds and, using a PointNet++ model, each point was labeled as an aneurysm or vessel class.
Results Quantitative validation of the test data from different sites than the training data showed that the proposed approach achieved pooled sensitivity of 85% and 90% on 157 MRA scans and 1338 CTA scans, respectively, while the sensitivity for small IAs was 72% and 83%, respectively. The corresponding number of false findings per image was low at 1.54 and 1.57, and 0.4 and 0.83 on healthy subject data.
Conclusions The proposed approach achieved a state-of-the-art balance between the sensitivity and the number of false findings, matched the expert-level sensitivity to small (and other) IAs on external data, and therefore seems fit for computer-assisted detection of IAs in a clinical setting.
- aneurysm
- vascular malformation
- brain
Data availability statement
Data are available upon reasonable request. Data may be obtained from a third party and are not publicly available. In this paper we are using public and private datasets. Public datasets are available from the third party, while private datasets are not available, however upon reasonable request we can test different models on this dataset.
Statistics from Altmetric.com
Data availability statement
Data are available upon reasonable request. Data may be obtained from a third party and are not publicly available. In this paper we are using public and private datasets. Public datasets are available from the third party, while private datasets are not available, however upon reasonable request we can test different models on this dataset.
Footnotes
Contributors ŽB initiated the collaborative project, wrote the statistical analysis plan, cleaned and analysed the data, designed the study methodology and drafted and revised the paper. JHC designed the data collection protocol and collected data and revised the paper. WP monitored the data collection. FP revised the paper. ŽŠ was responsible for the overall content as the guarantor, monitored the data collection and helped with study design, revised the draft paper and revised the final version.
Funding This research was funded by the Slovenian Research Agency (Research Grants Nos J2-2500 and J2-3059, assigned to ŽŠ). The authors would like to acknowledge AP from University Medical Centre Ljubljana for collecting, annotating and sharing the datasets used for this study.
Competing interests None declared.
Provenance and peer review Not commissioned; externally peer reviewed.
Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.