Ewout Vansteenkiste

Channelized Hotelling observers for the assessment of volumetric imaging data sets

Current clinical practice is rapidly moving in the direction of volumetric imaging. For two-dimensional (2D) images, task-based medical image quality is often assessed using numerical model observers. For three-dimensional (3D) images, however, these models have been little explored so far. In this work, first, two novel designs of a multislice channelized Hotelling observer (CHO) are proposed for the task of detecting 3D signals in 3D images. The novel designs are then compared and evaluated in a simulation study with five different CHO designs: a single-slice model, three multislice models, and a volumetric model. Four different random background statistics are considered, both gaussian (noncorrelated and correlated gaussian noise) and non-gaussian (lumpy and clustered lumpy backgrounds). Overall, the results show that the volumetric model outperforms the others, while the disparity between the models decreases for greater complexity of the detection task. Among the multislice models, the second proposed CHO could most closely approach the volumetric model, whereas the first new CHO seems to be least affected by the number of training samples.

Spatially Coherent Fuzzy Clustering for Accurate and Noise-Robust Image Segmentation

In this letter, we present a new FCM-based method for spatially coherent and noise-robust image segmentation. Our contribution is twofold: 1) the spatial information of local image features is integrated into both the similarity measure and the membership function to compensate for the effect of noise; and 2) an anisotropic neighborhood, based on phase congruency features, is introduced to allow more accurate segmentation without image smoothing. The segmentation results, for both synthetic and real images, demonstrate that our method efficiently preserves the homogeneity of the regions and is more robust to noise than related FCM-based methods.

Perceived image quality measurement of state-of-the-art noise reduction schemes

In this paper we compare the overall image quality of 7 state-of-the-art denoising schemes, based on human visual perception. A psycho-visual experiment was set up in which 37 subjects were asked to score and compare denoised images. A perceptual space is constructed from this experiment through multidimensional scaling (MDS) techniques using the perceived dissimilarity and quality preference between the images and the scaled perceptual attributes bluriness and artefacts. We found that a two-dimensional perceptual space adequately represents the processed images used in the experiment, and that the perceptual spaces obtained for all scenes are very similar. The interpretation of this space leads to a ranking of the filters in perceived overall image quality. We can show that the impairment vector, whose direction is opposite to that of the quality vector, lies between the attribute vectors for bluriness and artefacts, which on their account form an angle of about 35 degrees meaning they do interact. A follow-up experiment allowed us to determine even further why subjects preferred one filter over the other.

Measuring the wicking behavior of textiles by the combination of a horizontal wicking experiment and image processing

A horizontal wicking experiment is proposed to measure the wicking behavior of textiles. A syringe supplying a continuous flow of distilled water is in contact with the absorbing fabric resulting in a wicking region. The increase in wicking area or the wicking area after a certain time is recorded with a digital camera. The picture analyzing process is automated by the use of two complementary image segmentation algorithms: morphological segmentation and region merging. Where commercial image analyzing software fails due to the specific porous structure of textiles, the developed algorithms succeed in calculating the wicking area semiautomatically. It is shown that the newly developed technique is able to test the wicking behavior of, e.g., a cotton fabric and a plasma treated polyester nonwoven.

Evaluation of the wear label description in carpets by using local binary pattern techniques

Carpet manufacturers certify their products for end-use applications by evaluating the wear behavior of their carpets in mechanical experiments. Currently, this process is performed by visual inspection, suffering from subjective gathers that limit reliability. To automate this process, we propose the use of image processing techniques, specifically of local binary pattern (LBP) statistics. Such statistics are tolerant against illumination changes, can be easily implemented, and perform well when combined with a symmetrized adaptation of the Kullback—Leibler divergence. As a main innovation, we extend the existing rotationally invariant LBPs by including ‘mirror’ and ‘complement’ invariants. We show an accurately improved and more reliable estimation of the degree of wear in worn carpets. The evaluation is performed on four digital reference scales, each containing eight pairs of images comparing transitional degrees of wear to the original appearance. Additionally, the texture changes due to distortions of the pile yarn tufts are enhanced by choosing a suitable scale factor per reference. We validate the findings using six physical reference scales, each containing four pairs of images. In both references, linear correlations of over 0.89 are demonstrated between the degrees of wear and extracted features from the images. These findings justify the use of the proposed LBP extensions in a first approach towards an automated low-cost inspection system for carpet wear at low computation cost.

Relationship of EEG sources of neonatal seizures to acute perinatal brain lesions seen on MRI: A pilot study

Even though it is known that neonatal seizures are associated with acute brain lesions, the relationship of electroencephalographic (EEG) seizures to acute perinatal brain lesions visible on magnetic resonance imaging (MRI) has not been objectively studied. EEG source localization is successfully used for this purpose in adults, but it has not been sufficiently explored in neonates. Therefore, we developed an integrated method for ictal EEG dipole source localization based on a realistic head model to investigate the utility of EEG source imaging in neonates with postasphyxial seizures. We describe here our method and compare the dipole seizure localization results with acute perinatal lesions seen on brain MRI in 10 full‐term infants with neonatal encephalopathy. Through experimental studies, we also explore the sensitivity of our method to the electrode positioning errors and the variations in neonatal skull geometry and conductivity. The localization results of 45 focal seizures from 10 neonates are compared with the visual analysis of EEG and MRI data, scored by expert physicians. In 9 of 10 neonates, dipole locations showed good relationship with MRI lesions and clinical data. Our experimental results also suggest that the variations in the used values for skull conductivity or thickness have little effect on the dipole localization, whereas inaccurate electrode positioning can reduce the accuracy of source estimates. The performance of our fused method indicates that ictal EEG source imaging is feasible in neonates and with further validation studies, this technique can become a useful diagnostic tool. Hum Brain Mapp 34:2402–2417, 2013.

Generalized pixel profiling and comparative segmentation with application to arteriovenous malformation segmentation.

Extraction of structural and geometric information from 3-D images of blood vessels is a well known and widely addressed segmentation problem. The segmentation of cerebral blood vessels is of great importance in diagnostic and clinical applications, with a special application in diagnostics and surgery on arteriovenous malformations (AVM). However, the techniques addressing the problem of the AVM inner structure segmentation are rare. In this work we present a novel method of pixel profiling with the application to segmentation of the 3-D angiography AVM images. Our algorithm stands out in situations with low resolution images and high variability of pixel intensity. Another advantage of our method is that the parameters are set automatically, which yields little manual user intervention. The results on phantoms and real data demonstrate its effectiveness and potentials for fine delineation of AVM structure.

An improved fuzzy clustering approach for image segmentation

Fuzzy clustering techniques have been widely used in automated image segmentation. However, since the standard fuzzy c-means (FCM) clustering algorithm does not consider any spatial information, it is highly sensitive to noise. In this paper, we present an extension of the FCM algorithm to overcome this drawback, by incorporating spatial neighborhood information into a new similarity measure. We consider that spatial information depends on the relative location and features of the neighboring pixels. The performance of the proposed algorithm is tested on synthetic and real images with different noise levels. Experimental quantitative and qualitative segmentation results show that the proposed method is effective, more robust to noise and preserves the homogeneity of the regions better than other FCM-based methods.

Feature Extraction of the Wear Label of Carpets by Using a Novel 3D Scanner

In this paper we present a novel 3D scanner to capture the texture characteristics of worn carpets into images of the depth. We first compare our proposed scanner to a Metris scanner previously attempted for this application. Then, we scan the surface of samples from the standard EN1471 using our proposed scanner. We found that our proposed scanner offers additional benefits because it has been specifically designed for carpets, performing faster, cheaper, better and also a lot more suitable for darker carpets. The results of this approach give optimistic expectations in the automation of the label assessment dealing with multiple types of carpets.

The use of steerable channels for detecting asymmetrical signals with random orientations

In the optimization of medical imaging systems, there is a stringent need to shift from human observer studies to numerical observer studies, because of both cost and time limitations. Numerical models give an objective measure for the quality of displayed images for a given task and can be designed to predict the performance of medical specialists performing the same task. For the task of signal detection, the channelized Hotelling observer (CHO) has been successfully used, although several studies indicate an overefficiency of the CHO compared to human observers. One of the main causes of this overefficiency is attributed to the intrinsic uncertainty about the signal (such as its orientation) that a human observer is dealing with. Deeper knowledge of the discrepancies of the CHO and the human observer may provide extra insight in the processing of the human visual system and this knowledge can be utilized to better fine-tune medical imaging systems. In this paper, we investigate the optimal detection of asymmetrical signals with statistically known random orientation, based on joint detection and estimation theory. We derive the optimal channelized observer for this task and we show that the optimal detection in channel space requires the use of steerable channels, which are used in steerable pyramid transforms in image processing. Even though the use of CHOs for SKS tasks has not been studied so far, our findings indicate that CHO models can be further extended to incorporate intrinsic uncertainty about the signal to behave closer to humans. Experimental results are provided to illustrate these findings.