An evaluation of performance measures for arterial brain vessel segmentation

Background Arterial brain vessel segmentation allows utilising clinically relevant information contained within the cerebral vascular tree. Currently, however, no standardised performance measure is available to evaluate the quality of cerebral vessel segmentations. Thus, we developed a performance measure selection framework based on manual visual scoring of simulated segmentation variations to find the most suitable measure for cerebral vessel segmentation. Methods To simulate segmentation variations, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation. In 10 patients, we generated a set of approximately 300 simulated segmentation variations for each ground truth image. Each segmentation was visually scored based on a predefined scoring system and segmentations were ranked based on 22 performance measures common in the literature. The correlation of visual scores with performance measure rankings was calculated using the Spearman correlation coefficient. Results The distance-based performance measures balanced average Hausdorff distance (rank = 1) and average Hausdorff distance (rank = 2) provided the segmentation rankings with the highest average correlation with manual rankings. They were followed by overlap-based measures such as Dice coefficient (rank = 7), a standard performance measure in medical image segmentation. Conclusions Average Hausdorff distance-based measures should be used as a standard performance measure in evaluating cerebral vessel segmentation quality. They can identify more relevant segmentation errors, especially in high-quality segmentations. Our findings have the potential to accelerate the validation and development of novel vessel segmentation approaches.

On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking

Average Hausdorff distance is a widely used performance measure to calculate the distance between two point sets. In medical image segmentation, it is used to compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average Hausdorff distance making it less suitable for applications in segmentation performance assessment. To mitigate this error, we present a modified calculation of this performance measure that we have coined “balanced average Hausdorff distance”. To simulate segmentations for ranking, we manually created non-overlapping segmentation errors common in magnetic resonance angiography cerebral vessel segmentation as our use-case. Adding the created errors consecutively and randomly to the ground truth, we created sets of simulated segmentations with increasing number of errors. Each set of simulated segmentations was ranked using both performance measures. We calculated the Kendall rank correlation coefficient between the segmentation ranking and the number of errors in each simulated segmentation. The rankings produced by balanced average Hausdorff distance had a significantly higher median correlation (1.00) than those by average Hausdorff distance (0.89). In 200 total rankings, the former misranked 52 whilst the latter misranked 179 segmentations. Balanced average Hausdorff distance is more suitable for rankings and quality assessment of segmentations than average Hausdorff distance.

Sustaining cerebral perfusion in intracranial atherosclerotic stenosis: The roles of antegrade residual flow and leptomeningeal collateral flow

We aimed to investigate the roles of antegrade residual flow and leptomeningeal collateral flow in sustaining cerebral perfusion distal to an intracranial atherosclerotic stenosis (ICAS). Patients with apparently normal cerebral perfusion distal to a symptomatic middle cerebral artery (MCA)-M1 stenosis were enrolled. Computational fluid dynamics models were built based on CT angiography to obtain a translesional pressure ratio (PR) to gauge the residual antegrade flow. Leptomeningeal collaterals (LMCs) were scaled on CT angiography. Cerebral perfusion metrics were obtained in CT perfusion maps. Among 83 patients, linear regression analyses revealed that both translesional PR and LMC scale were independently associated with relative ipsilesional mean transit time (rMTT). Subgroup analyses showed that ipsilesional rMTT was significantly associated with translesional PR ( p < 0.001) rather than LMC scale in those with a moderate (50–69%) MCA stenosis, which, however, was only significantly associated with LMC scale ( p = 0.051) in those with a severe (70–99%) stenosis. Antegrade residual flow and leptomeningeal collateral flow have complementary effects in sustaining cerebral perfusion distal to an ICAS, while cerebral perfusion may rely more on the collateral circulation in those with a severe stenosis.

Aneurysm growth after brain tumor removal: case report

A rare case of rapid growth of an aneurysm after a posterior fossa meningioma removal in a 69-year-old lady is reported. Serial angiography, cerebral computed tomography and magnetic resonance imaging are presented. The patient harbored risk factors to both aneurysm formation and growth as current cigarette smoking, arterial hypertension, female sex and reduction of intracranial hypertension. One-year follow up after the first surgical procedure is presented.