A multichannel watershed-based segmentation method for multispectral chromosome classification

Adaptive Segmentation of DAPI-stained, C-banded, Aggregated and Overlapping Chromosomes

Existing algorithms for automated segmentation of chromosomes and centromeres do not work well for condensed, C-banded and DAPI-stained chromosomes and centromeres. Overlapping and aggregation, which frequently occur in metaphase spreads, introduce additional challenges to the counting of chromosomes and centromeres in the Dicentrics Chromosome Assay (DCA). In this paper, we introduce adaptive algorithms, for segmentation of difficult metaphase spreads that include overlapping and aggregated chromosomes. In order to enhance and segment chromosomes, two optimizations are done: (1) the best algorithm among several options is automatically chosen based on predefined figures of merit, (2) the algorithm is automatically optimized with a binary search to modify its parameters to achieve predefined thresholds. These algorithms are designed to separate mildly or moderately aggregated chromosomal clusters. The clusters are segmented by skeleton junctions, reduction of the overall object thickness, and the watershed algorithm. The chromosomes are characterized by rules we establish, using minimal assumptions. Centromeres are detected by detecting bright spots on the surface of the chromosomes, and then using cluster analysis and shape and intensity profiles to identify them as centromeres. High sensitivity and specificity for chromosome and centromere detection were achieved.

Adversarial Multiscale Feature Learning Framework for Overlapping Chromosome Segmentation

Chromosome karyotype analysis is of great clinical importance in the diagnosis and treatment of diseases. Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis. However, the strip-shaped chromosomes easily overlap each other when imaged, significantly affecting the accuracy of the subsequent analysis and hindering the development of chromosome analysis instruments. In this paper, we present an adversarial, multiscale feature learning framework to improve the accuracy and adaptability of overlapping chromosome segmentation. We first adopt the nested U-shaped network with dense skip connections as the generator to explore the optimal representation of the chromosome images by exploiting multiscale features. Then we use the conditional generative adversarial network (cGAN) to generate images similar to the original ones; the training stability of the network is enhanced by applying the least-square GAN objective. Finally, we replace the common cross-entropy loss with the advanced Lovász-Softmax loss to improve the model's optimization and accelerate the model's convergence. Comparing with the established algorithms, the performance of our framework is proven superior by using public datasets in eight evaluation criteria, showing its great potential in overlapping chromosome segmentation.

Segmentation of overlapping chromosome images using U-Net with improved dilated convolutions

Chromosome visualization has been used in human chromosome analysis and is a crucial step in clinical diagnosis and drug development. An important step in chromosome visualization is the extraction of chromosomes from chromosome images obtained by light microscopy. Chromosomes often overlap in a complex and variable manner, resulting in significant challenges in chromosome segmentation. The process of chromosome visualization requires manual intervention and is tedious. A method based on a neural network is proposed for the automatic segmentation of overlapping chromosome images to speed up the workflow of visualizing chromosomes. Three improved dilated convolutions are used in the chromosome image segmentation models based on U-Net. The proposed models successfully segment overlapping chromosomes in two publicly available overlapping chromosome data sets. Our models have better performance than existing overlapping chromosome segmentation methods based on U-Net. In summary, it is demonstrated that the improved dilated convolutions can be used for the automatic segmentation of overlapping chromosome images. The proposed improved dilated convolutions have a stable performance improvement, can be easily extended to the segmentation of multiple overlapping chromosomes, and are suitable as general neural network operations to replace standard convolutions in any network.

Automated Ki-67 Quantification of Immunohistochemical Staining Image of Human Nasopharyngeal Carcinoma Xenografts

Nasopharyngeal carcinoma is one of the malignant neoplasm with high incidence in China and south-east Asia. Ki-67 protein is strictly associated with cell proliferation and malignant degree. Cells with higher Ki-67 expression are always sensitive to chemotherapy and radiotherapy, the assessment of which is beneficial to NPC treatment. It is still challenging to automatically analyze immunohistochemical Ki-67 staining nasopharyngeal carcinoma images due to the uneven color distributions in different cell types. In order to solve the problem, an automated image processing pipeline based on clustering of local correlation features is proposed in this paper. Unlike traditional morphology-based methods, our algorithm segments cells by classifying image pixels on the basis of local pixel correlations from particularly selected color spaces, then characterizes cells with a set of grading criteria for the reference of pathological analysis. Experimental results showed high accuracy and robustness in nucleus segmentation despite image data variance. Quantitative indicators obtained in this essay provide a reliable evidence for the analysis of Ki-67 staining nasopharyngeal carcinoma microscopic images, which would be helpful in relevant histopathological researches.

An improved sparse representation model with structural information for Multicolour Fluorescence In-Situ Hybridization (M-FISH) image classification

Background

Multicolour Fluorescence In-Situ Hybridization (M-FISH) images are employed for detecting chromosomal abnormalities such as chromosomal translocations, deletions, duplication and inversions. This technique uses mixed colours of fluorochromes to paint the whole chromosomes for rapid detection of chromosome rearrangements. The M-FISH data sets used in our research are obtained from microscopic scanning of a metaphase cell labelled with five different fluorochromes and a DAPI staining. The reliability of the technique lies in accurate classification of chromosomes (24 classes for male and 23 classes for female) from M-FISH images. However, due to imaging noise, mis-alignment between multiple channels and many other imaging problems, there is always a classification error, leading to wrong detection of chromosomal abnormalities. Therefore, how to accurately classify different types of chromosomes from M-FISH images becomes a challenging problem.

Methods

This paper presents a novel sparse representation model considering structural information for the classification of M-FISH images. In our previous work a sparse representation based classification model was proposed. This model employed only individual pixel information for the classification. With the structural information of neighbouring pixels as well as the information of themselves simultaneously, the novel approach extended the previous one to the regional case. Based on Orthogonal Matching Pursuit (OMP), we developed simultaneous OMP algorithm (SOMP) to derive an efficient solution of the improved sparse representation model by incorporating the structural information.

Results

The p-value of two models shows that the newly proposed model incorporating the structural information is significantly superior to our previous one. In addition, we evaluated the effect of several parameters, such as sparsity level, neighbourhood size, and training sample size, on the of the classification accuracy.

Conclusions

The comparison with our previously used sparse model demonstrates that the improved sparse representation model is more effective than the previous one on the classification of the chromosome abnormalities.

A novel approach for efficient extrication of overlapping chromosomes in automated karyotyping

Since the introduction of the automated karyotyping systems, segmentation and classification of touching and overlapping chromosomes in the metaphase images are major challenges. The earlier reported techniques for disentangling the chromosome overlaps have limited success and use only color information in case of multispectral imaging. Most of them are restricted to separation of single overlap of two chromosomes. This paper introduces a novel algorithm to extricate overlapping chromosomes in a metaphase image. The proposed technique uses Delaunay triangulation to automatically identify the number of overlaps in a cluster followed by the detection of the appropriate cut-points. The banding information on the overlapped region further resolves the set of overlapping chromosomes with the identified cut-points. The proposed algorithm has been tested with four data sets of 60 overlapping cases, obtained from publically available databases and private genetic labs. The experimental results provide an overall accuracy of 75–100 % for resolving the cluster of 1–6 overlaps.

Classification of multicolor fluorescence in situ hybridization (M-FISH) images with sparse representation

There has been a considerable interest in sparse representation and compressive sensing in applied mathematics and signal processing in recent years but with limited success to medical image processing. In this paper we developed a sparse representation-based classification (SRC) algorithm based on L1-norm minimization for classifying chromosomes from multicolor fluorescence in situ hybridization (M-FISH) images. The algorithm has been tested on a comprehensive M-FISH database that we established, demonstrating improved performance in classification. When compared with other pixel-wise M-FISH image classifiers such as fuzzy c-means (FCM) clustering algorithms and adaptive fuzzy c-means (AFCM) clustering algorithms that we proposed earlier the current method gave the lowest classification error. In order to evaluate the performance of different SRC for M-FISH imaging analysis, three different sparse representation methods, namely, Homotopy method, Orthogonal Matching Pursuit (OMP), and Least Angle Regression (LARS), were tested and compared. Results from our statistical analysis have shown that Homotopy based method is significantly better than the other two methods. Our work indicates that sparse representations based classifiers with proper models can outperform many existing classifiers for M-FISH classification including those that we proposed before, which can significantly improve the multicolor imaging system for chromosome analysis in cancer and genetic disease diagnosis.

Left ventricular myocardium segmentation on delayed phase of multi-detector row computed tomography

RATIONALE AND OBJECTIVES

Advanced ischemic heart disease is usually accompanied by left ventricular (LV) myocardial volume loss and an abnormal enhancing pattern on delayed phase of multi-detector row computed tomography (MDCT). To assist radiologists and physicians in estimating the LV myocardial volume on delayed phase, this paper proposes an adaptive segmentation method for contouring the myocardial region in the delayed-phase MDCT and for computing the volume.

MATERIALS AND METHODS

The proposed method uses an anisotropic diffusion filter as a preprocessing procedure to enhance contrast and reduce specks in MDCT imaging. This work picks the middle of mid-ventricular level image slices as the lead slice. The proposed method develops two contouring modes to sketch the myocardium contour on the lead slice. By establishing the obtained contours as the initial contours, the region-growing method is employed to identify the contour of the myocardial region for each slice. The convex-hull finding algorithm is then used to refine the extracted contour. Finally, the width properties of the myocardial region and the morphological operators are used to obtain the entire LV myocardial volume.

RESULTS

Twenty-seven healthy patients who had no symptoms of ischemic heart disease are examined to evaluate the performance of the proposed method. Compared with manual contours delineated by two experienced experts, the contouring results using computer simulation reveal that the proposed method reliably identifies contours similar to those obtained using manual sketching.

CONCLUSION

The proposed method provides robust contouring for the LV myocardium on delayed-phase MDCT. The potential role of this technique may substantially reduce the time required to sketch manually a precise contour with high stability.

An edge embedded marker-based watershed algorithm for high spatial resolution remote sensing image segmentation

This correspondence proposes an edge embedded marker-based watershed algorithm for high spatial resolution remote sensing image segmentation. Two improvement techniques are proposed for the two key steps of maker extraction and pixel labeling, respectively, to make it more effective and efficient for high spatial resolution image segmentation. Moreover, the edge information, detected by the edge detector embedded with confidence, is used to direct the two key steps for detecting objects with weak boundary and improving the positional accuracy of the objects boundary. Experiments on different images show that the proposed method has a good generality in producing good segmentation results. It performs well both in retaining the weak boundary and reducing the undesired over-segmentation.

Enhancement of the classification of multichannel chromosome images using support vector machines

Color chromosome classification (karyotyping) allows simultaneous analysis of numerical and structural chromosome abnormalities. The success of the technique largely depends on the accuracy of pixel classification. In this paper we present a method for multichannel chromosome image classification based on support vector machines. First, the image is segmented using a multichannel watershed segmentation method. Classification of the pixels of the segmented regions using support vector machines is then employed. The method has been tested on images from normal cells, showing the improvement in classification accuracy by 10.16% when compared to a Bayesian classifier. The increased classification improves the reliability of the M-FISH imaging technique in identifying subtle and cryptic chromosomal abnormalities for cancer diagnosis and genetic disorders research.

Automatic chromosome pairing using mutual information

Cytogenetics is a key tool in the detection of acquired chromosomal abnormalities and in the diagnosis of genetic diseases such as leukemia. The karyotyping is a set of procedures, in the scope of the cytogenetics, that produces a visual representation of the 46 chromosomes (called karyogram), paired and arranged in decreasing order of size. The pairing procedure aims to identify all pairs of homologous chromosomes.The pairing criterion is based on dimensional, morphological,and textural features similarity. This process is time consuming when performed manually, and demanding from a technical point of view. An automatic pairing algorithm would thus bring benefits, but it remains an open problem to date.In this paper a new strategy for automatic pairing of homologous chromosomes is proposed. Besides the traditional features described in the literature, the Mutual Information (MI) is used to discriminate chromosome textural differences. A supervised non-linear classifier is trained by using manual classifications provided by expert technicians, combining the different features computed from each pair.Simulations using 836 real chromosome images, obtained with a Leica Optical Microscope DM 2500, in a leave-one-out cross validation fashion, were performed for training and testing the algorithm.Promising and relevant results were found, despite the poor quality of the original chromosome images, contrasting with state-of the-art algorithms and datasets found in the literature.