Segmentation of medical images through competitive learning

Semi-automated image processing system for micro- to macro-scale analysis of immunohistopathology: application to ischemic brain tissue

Immunochemical staining techniques are commonly used to assess neuronal, astrocytic and microglial alterations in experimental neuroscience research, and in particular, are applied to tissues from animals subjected to ischemic stroke. Immunoreactivity of brain sections can be measured from digitized immunohistology slides so that quantitative assessment can be carried out by computer-assisted analysis. Conventional methods of analyzing immunohistology are based on image classification techniques applied to a specific anatomic location at high magnification. Such micro-scale localized image analysis limits one for further correlative studies with other imaging modalities on whole brain sections, which are of particular interest in experimental stroke research. This report presents a semi-automated image analysis method that performs convolution-based image classification on micro-scale images, extracts numerical data representing positive immunoreactivity from the processed micro-scale images and creates a corresponding quantitative macro-scale image. The present method utilizes several image-processing techniques to cope with variances in intensity distribution, as well as artifacts caused by light scattering or heterogeneity of antigen expression, which are commonly encountered in immunohistology. Micro-scale images are composed by a tiling function in a mosaic manner. Image classification is accomplished by the K-means clustering method at the relatively low-magnification micro-scale level in order to increase computation efficiency. The quantitative macro-scale image is suitable for correlative analysis with other imaging modalities. This method was applied to different immunostaining antibodies, such as endothelial barrier antigen (EBA), lectin, and glial fibrillary acidic protein (GFAP), on histology slides from animals subjected to middle cerebral artery occlusion by the intraluminal suture method. Reliability tests show that the results obtained from immunostained images at high magnification and relatively low magnification are virtually the same.

Automated cerebrum segmentation from three-dimensional sagittal brain MR images

We present a fully automated cerebrum segmentation algorithm for full three-dimensional sagittal brain MR images. First, cerebrum segmentation from a midsagittal brain MR image is performed utilizing landmarks, anatomical information, and a connectivity-based threshold segmentation algorithm as previously reported. Recognizing that cerebrum in laterally adjacent slices tends to have similar size and shape, we use the cerebrum segmentation result from the midsagittal brain MR image as a mask to guide cerebrum segmentation in adjacent lateral slices in an iterative fashion. This masking operation yields a masked image (preliminary cerebrum segmentation) for the next lateral slice, which may truncate brain region(s). Truncated regions are restored by first finding end points of their boundaries, by comparing the mask image and masked image boundaries, and then applying a connectivity-based algorithm. The resulting final extracted cerebrum image for this slice is then used as a mask for the next lateral slice. The algorithm yielded satisfactory fully automated cerebrum segmentations in three-dimensional sagittal brain MR images, and had performance superior to conventional edge detection algorithms for segmentation of cerebrum from 3D sagittal brain MR images.

Quantification and Segmentation of Brain Tissues from MR Images: A Probabilistic Neural Network Approach

This paper presents a probabilistic neural network based technique for unsupervised quantification and segmentation of brain tissues from magnetic resonance images. It is shown that this problem can be solved by distribution learning and relaxation labeling, resulting in an efficient method that may be particularly useful in quantifying and segmenting abnormal brain tissues where the number of tissue types is unknown and the distributions of tissue types heavily overlap. The new technique uses suitable statistical models for both the pixel and context images and formulates the problem in terms of model-histogram fitting and global consistency labeling. The quantification is achieved by probabilistic self-organizing mixtures and the segmentation by a probabilistic constraint relaxation network. The experimental results show the efficient and robust performance of the new algorithm and that it outperforms the conventional classification based approaches.

Segmentation of multivariate medical images via unsupervised clustering with "adaptive resolution"

The need for quantitative information is becoming increasingly important in the clinical field. In this paper we present an interactive X11 based system, devoted to segmentation of multivariate medical images, including an unsupervised neural network approach to clustering. The following steps are considered in the analysis sequence: feature extraction, reduction of dimensionality, unsupervised data clustering, voxel classification, interactive post-processing refinement. The environment turns out to be extremely interactive, thus making the user able to display and modify data during processing, to set parameters, to choose different methods and different tools for each step, and to define online the whole analysis sequence.

The application of competitive Hopfield neural network to medical image segmentation

In this paper, a parallel and unsupervised approach using the competitive Hopfield neural network (CHNN) is proposed for medical image segmentation. It is a kind of Hopfield network which incorporates the winner-takes-all (WTA) learning mechanism. The image segmentation is conceptually formulated as a problem of pixel clustering based upon the global information of the gray level distribution. Thus, the energy function for minimization is defined as the mean of the squared distance measures of the gray levels within each class. The proposed network avoids the onerous procedure of determining values for the weighting factors in the energy function. In addition, its training scheme enables the network to learn rapidly and effectively. For an image of n gray levels and c interesting objects, the proposed CHNN would consist of n by c neurons and be independent of the image size. In both simulation studies and practical medical image segmentation, the CHNN method shows promising results in comparison with two well-known methods: the hard and the fuzzy c-means (FCM) methods.