Automatic extraction of the midsagittal surface from brain MR images using the Kullback-Leibler measure

Hugo J. Kuijf, Susanne J. van Veluw, Mirjam I. Geerlings, Max A. Viergever, Geert Jan Biessels, Koen L. Vincken

Full text (PDF – 2 MB)

The midsagittal surface separates the two hemispheres of the cerebrum. This surface is often typified as a geometrical plane: the midsagittal plane. However, in subjects with a considerable amount of naturally occurring brain torque, the midsagittal surface deviates to a large extent from a plane. In the present study, an automated method to extract the midsagittal surface is proposed, evaluated on a large dataset, and compared to a conventional midsagittal plane representation. The midsagittal plane was extracted from MR images with a technique based on the Kullback–Leibler measure. This plane was used to initialize a surface, that was deformed to represent the midsagittal surface. One hundred subjects were selected from the SMART-MR study: fifty subjects with brain torque and fifty random subjects. Manual delineations of the midsagittal surface were used for evaluation. The extracted midsagittal planes and surfaces were compared to the manual delineations by assessing the absolute volume of misclassified cerebrum tissue. The midsagittal surface resulted in significantly better separations of the hemispheres. In the randomly selected subjects, the error reduced from 2.71 ± 1.05 ml to 2.20 ± 0.66 ml and in subjects with brain torque from 4.85 ± 2.79 ml to 2.23 ± 0.77 ml, with improvements up to 16.6 ml in individual subjects with marked brain torque.

DOI: 10.1007/s12021-013-9215-0

How to assess the reliability of cerebral microbleed rating?

Hugo J. Kuijf, Susanne J. van Veluw, Max A. Viergever, Koen L. Vincken, Geert Jan Biessels

Interest in cerebral microbleeds has grown rapidly over the past years. The need for sensitive and reliable detection of microbleeds has spurred the development of new MR sequences and standardized visual rating scales (Cordonnier et al., 2009; Gregoire et al., 2009). The value of these rating scales is currently assessed by measuring the inter-rater agreement, which is commonly determined using Cohen’s kappa coefficient (κ) or the intraclass correlation coefficient (ICC). With the recent increase of MR scanner field strength to 3T and even 7T, the sensitivity of microbleed detection has grown significantly, whence often multiple microbleeds are found in a single subject. As a result of this, researchers no longer solely focus on the absence or presence of microbleeds, but aim at determining their exact count and location as well.

Our concern is that, with this shift of focus, the measures that are in use to validate the reliability of microbleed ratings are no longer up-to-date. If the interest is confined to the presence or absence of microbleeds, the inter-rater agreement can be adequately assessed using κ. However, with multiple microbleeds in an individual subject, determining the inter-rater agreement using a measure that does not consider the number and location of the microbleeds appears inadequate. In other words, raters who agree on the presence or absence of microbleeds in an individual subject might disagree on their count or distribution.

DOI: 10.3389/fnagi.2013.00057

See also: http://www.isi.uu.nl/People/Hugok/microbleeds/simulator/

Semi-Automated Detection of Cerebral Microbleeds on 3.0 T MR Images

H.J. Kuijf, M. Brundel, J. de Bresser, S.J. van Veluw, S.M. Heringa, M.A. Viergever, G.J. Biessels, K.L. Vincken

Cerebral microbleeds are associated with vascular disease and dementia. They can be detected on MRI and receive increasing attention. Visual rating is the current standard for microbleed detection, but is rater dependent, has limited reproducibility, modest sensitivity, and can be time-consuming. The goal of the current study is to present a tool for semi-automated detection of microbleeds that can assist human raters in the rating procedure.

The radial symmetry transform is originally a technique to highlight circular-shaped objects in two-dimensional images. In the current study, the three-dimensional radial symmetry transform was adapted to detect spherical microbleeds in a series of 72 patients from our hospital, for whom a ground truth visual rating was made by four raters. Potential microbleeds were automatically identified on T2*-weighted 3.0 T MRI scans and the results were visually checked to identify microbleeds. Final ratings of the radial symmetry transform were compared to human ratings.

After implementing and optimizing the radial symmetry transform, the method achieved a high sensitivity, while maintaining a modest number of false positives. Depending on the settings, sensitivities ranged from 65%-84% compared to the ground truth rating. Rating of the processed images required 1-2 minutes per participant, in which 20-96 false positive locations per participant were censored. Sensitivities of individual raters ranged from 39%-86% compared to the ground truth and required 5-10 minutes per participant per rater.

The sensitivities that were achieved by the radial symmetry transform are similar to those of individual experienced human raters, demonstrating its feasibility and usefulness for semi-automated microbleed detection.

DOI: 10.1371/journal.pone.0066610

Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform

Hugo J. Kuijf, Jeroen de Bresser, Mirjam I. Geerlings, Mandy M.A. Conijn, Max A. Viergever, Geert Jan Biessels, Koen L. Vincken

Full text (PDF – 11 MB)

Cerebral microbleeds (CMBs) are commonly detected on MRI and have recently received an increased interest, because they are associated with vascular disease and dementia. Identification and rating of CMBs on MRI images may be facilitated by semi-automatic detection, particularly on high-resolution images acquired at high field strength. For these images, visual rating is time-consuming and has limited reproducibility. We present the radial symmetry transform (RST) as an efficient method for semi-automated CMB detection on 7.0 T MR images, with a high sensitivity and a low number of false positives that have to be censored manually.

The RST was computed on both echoes of a dual-echo T2*-weighted gradient echo 7.0 T MR sequence in 18 participants from the Second Manifestations of ARTerial disease (SMART) study. Potential CMBs were identified by combining the output of the transform on both echoes. Each potential CMB identified through the RST was visually checked by two raters to identify probable CMBs. The scoring time needed to manually reject false positives was recorded.

The sensitivity of 71.2% is higher than that of individual human raters on 7.0 T scans and the required human rater time is reduced from 30 to 2 minutes per scan on average. The RST outperforms published semi-automated methods in terms of either a higher sensitivity or less false positives, and requires much less human rater time.

DOI: 10.1016/j.neuroimage.2011.09.061