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

Review of In Situ Hybridization (ISH) Stain Images Using Computational Techniques

Recent advancements in medical imaging have greatly enhanced the application of computational techniques in digital pathology, particularly for the classification of breast cancer using in situ hybridization (ISH) imaging. HER2 amplification, a key prognostic marker in 20-25% of breast cancers, can be assessed through alterations in gene copy number or protein expression. However, challenges persist due to the heterogeneity of nuclear regions and complexities in cancer biomarker detection. This review examines semi-automated and fully automated computational methods for analyzing ISH images with a focus on HER2 gene amplification. Literature from 1997 to 2023 is analyzed, emphasizing silver-enhanced in situ hybridization (SISH) and its integration with image processing and machine learning techniques. Both conventional machine learning approaches and recent advances in deep learning are compared. The review reveals that automated ISH analysis in combination with bright-field microscopy provides a cost-effective and scalable solution for routine pathology. The integration of deep learning techniques shows promise in improving accuracy over conventional methods, although there are limitations related to data variability and computational demands. Automated ISH analysis can reduce manual labor and increase diagnostic accuracy. Future research should focus on refining these computational methods, particularly in handling the complex nature of HER2 status evaluation, and integrate best practices to further enhance clinical adoption of these techniques.

Processes shaping cancer genomes - From mitotic defects to chromosomal rearrangements

Sequencing of cancer genomes revealed a rich landscape of somatic single nucleotide variants, structural changes of chromosomes, as well as chromosomal copy number alterations. These chromosome changes are highly variable, and simple translocations, deletions or duplications have been identified, as well as complex events that likely arise through activity of several interconnected processes. Comparison of the cancer genome sequencing data with our knowledge about processes important for maintenance of genome stability, namely DNA replication, repair and chromosome segregation, provides insights into the mechanisms that may give rise to complex chromosomal patterns, such as chromothripsis, a complex form of multiple focal chromosome rearrangements. In addition, observations gained from model systems that recapitulate the rearrangements patterns under defined experimental conditions suggest that mitotic errors and defective DNA replication and repair contribute to their formation. Here, we review the molecular mechanisms that contribute to formation of chromosomal aberrations observed in cancer genomes.

Feature extraction method for proteins based on Markov tripeptide by compressive sensing

BACKGROUND

In order to capture the vital structural information of the original protein, the symbol sequence was transformed into the Markov frequency matrix according to the consecutive three residues throughout the chain. A three-dimensional sparse matrix sized 20 × 20 × 20 was obtained and expanded to one-dimensional vector. Then, an appropriate measurement matrix was selected for the vector to obtain a compressed feature set by random projection. Consequently, the new compressive sensing feature extraction technology was proposed.

RESULTS

Several indexes were analyzed on the cell membrane, cytoplasm, and nucleus dataset to detect the discrimination of the features. In comparison with the traditional methods of scale wavelet energy and amino acid components, the experimental results suggested the advantage and accuracy of the features by this new method.

CONCLUSIONS

The new features extracted from this model could preserve the maximum information contained in the sequence and reflect the essential properties of the protein. Thus, it is an adequate and potential method in collecting and processing the protein sequence from a large sample size and high dimension.

Semantic segmentation of mFISH images using convolutional networks

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry.

Segmentation of multicolor fluorescence in situ hybridization images using an improved fuzzy C-means clustering algorithm by incorporating both spatial and spectral information

Multicolor fluorescence in situ hybridization (M-FISH) is a multichannel imaging technique for rapid detection of chromosomal abnormalities. It is a critical and challenging step to segment chromosomes from M-FISH images toward better chromosome classification. Recently, several fuzzy C-means (FCM) clustering-based methods have been proposed for M-FISH image segmentation or classification, e.g., adaptive fuzzy C-means (AFCM) and improved AFCM (IAFCM), but most of these methods used only one channel imaging information with limited accuracy. To improve the segmentation for better accuracy and more robustness, we proposed an FCM clustering-based method, denoted by spatial- and spectral-FCM. Our method has the following advantages: (1) it is able to exploit information from neighboring pixels (spatial information) to reduce the noise and (2) it can incorporate pixel information across different channels simultaneously (spectral information) into the model. We evaluated the performance of our method by comparing with other FCM-based methods in terms of both accuracy and false-positive detection rate on synthetic, hybrid, and real images. The comparisons on 36 M-FISH images have shown that our proposed method results in higher segmentation accuracy ([Formula: see text]) and a lower false-positive ratio ([Formula: see text]) than conventional FCM (accuracy: [Formula: see text], and false-positive ratio: [Formula: see text]) and the IAFCM (accuracy: [Formula: see text] and false-positive ratio: [Formula: see text]) methods by incorporating both spatial and spectral information from M-FISH images.

Two-phase greedy pursuit algorithm for automatic detection and characterization of transient calcium signaling

Ca(2+) plays an important role in the regulation of cellular functions. Local calcium events, e.g., calcium sparks, not only bring insights into Ca(2+) signaling but also contribute to the understanding of various cellular processes. However, it is challenging to detect calcium sparks, due to their transient properties and high level of nonstationary noises in microscopic images. Most of existing algorithms tend to have limitations for the detection of calcium sparks, e.g., empirically defined hard thresholds or poor applicability to nonstationary conditions. This paper presents a novel two-phase greedy pursuit (TPGP) algorithm for automatic detection and characterization of calcium sparks. In Phase I, a coarse-grained search is conducted across the whole image to identify the predominant sparks. In Phase II, adaptive basis function model is developed for the fine-grained representation of detected sparks. It may be noted that the proposed TPGP algorithms overcome the drawback of hard thresholding in most of previous approaches. Furthermore, the morphology of detected sparks is effectively modeled with multiscale basis functions in Phase II, thereby facilitating the analysis of physiological features. We evaluated and validated the TPGP algorithms using both real-word and synthetic images with multiple noise levels and varying baselines. Experimental results show that TPGP algorithms yield better performances than previous hard-thresholding approaches in terms of both sensitivities and positive predicted values. The present research provides the community a robust tool for the automatic detection and characterization of transient calcium signaling.

Sparse models for correlative and integrative analysis of imaging and genetic data

The development of advanced medical imaging technologies and high-throughput genomic measurements has enhanced our ability to understand their interplay as well as their relationship with human behavior by integrating these two types of datasets. However, the high dimensionality and heterogeneity of these datasets presents a challenge to conventional statistical methods; there is a high demand for the development of both correlative and integrative analysis approaches. Here, we review our recent work on developing sparse representation based approaches to address this challenge. We show how sparse models are applied to the correlation and integration of imaging and genetic data for biomarker identification. We present examples on how these approaches are used for the detection of risk genes and classification of complex diseases such as schizophrenia. Finally, we discuss future directions on the integration of multiple imaging and genomic datasets including their interactions such as epistasis.

Sparse representation based biomarker selection for schizophrenia with integrated analysis of fMRI and SNPs

Integrative analysis of multiple data types can take advantage of their complementary information and therefore may provide higher power to identify potential biomarkers that would be missed using individual data analysis. Due to different natures of diverse data modality, data integration is challenging. Here we address the data integration problem by developing a generalized sparse model (GSM) using weighting factors to integrate multi-modality data for biomarker selection. As an example, we applied the GSM model to a joint analysis of two types of schizophrenia data sets: 759,075 SNPs and 153,594 functional magnetic resonance imaging (fMRI) voxels in 208 subjects (92 cases/116 controls). To solve this small-sample-large-variable problem, we developed a novel sparse representation based variable selection (SRVS) algorithm, with the primary aim to identify biomarkers associated with schizophrenia. To validate the effectiveness of the selected variables, we performed multivariate classification followed by a ten-fold cross validation. We compared our proposed SRVS algorithm with an earlier sparse model based variable selection algorithm for integrated analysis. In addition, we compared with the traditional statistics method for uni-variant data analysis (Chi-squared test for SNP data and ANOVA for fMRI data). Results showed that our proposed SRVS method can identify novel biomarkers that show stronger capability in distinguishing schizophrenia patients from healthy controls. Moreover, better classification ratios were achieved using biomarkers from both types of data, suggesting the importance of integrative analysis.

Integrating fMRI and SNP data for biomarker identification for schizophrenia with a sparse representation based variable selection method

Background

In recent years, both single-nucleotide polymorphism (SNP) array and functional magnetic resonance imaging (fMRI) have been widely used for the study of schizophrenia (SCZ). In addition, a few studies have been reported integrating both SNPs data and fMRI data for comprehensive analysis.

Methods

In this study, a novel sparse representation based variable selection (SRVS) method has been proposed and tested on a simulation data set to demonstrate its multi-resolution properties. Then the SRVS method was applied to an integrative analysis of two different SCZ data sets, a Single-nucleotide polymorphism (SNP) data set and a functional resonance imaging (fMRI) data set, including 92 cases and 116 controls. Biomarkers for the disease were identified and validated with a multivariate classification approach followed by a leave one out (LOO) cross-validation. Then we compared the results with that of a previously reported sparse representation based feature selection method.

Results

Results showed that biomarkers from our proposed SRVS method gave significantly higher classification accuracy in discriminating SCZ patients from healthy controls than that of the previous reported sparse representation method. Furthermore, using biomarkers from both data sets led to better classification accuracy than using single type of biomarkers, which suggests the advantage of integrative analysis of different types of data.

Conclusions

The proposed SRVS algorithm is effective in identifying significant biomarkers for complicated disease as SCZ. Integrating different types of data (e.g. SNP and fMRI data) may identify complementary biomarkers benefitting the diagnosis accuracy of the disease.

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.

Identification of genes for complex diseases using integrated analysis of multiple types of genomic data

Various types of genomic data (e.g., SNPs and mRNA transcripts) have been employed to identify risk genes for complex diseases. However, the analysis of these data has largely been performed in isolation. Combining these multiple data for integrative analysis can take advantage of complementary information and thus can have higher power to identify genes (and/or their functions) that would otherwise be impossible with individual data analysis. Due to the different nature, structure, and format of diverse sets of genomic data, multiple genomic data integration is challenging. Here we address the problem by developing a sparse representation based clustering (SRC) method for integrative data analysis. As an example, we applied the SRC method to the integrative analysis of 376821 SNPs in 200 subjects (100 cases and 100 controls) and expression data for 22283 genes in 80 subjects (40 cases and 40 controls) to identify significant genes for osteoporosis (OP). Comparing our results with previous studies, we identified some genes known related to OP risk (e.g., 'THSD4', 'CRHR1', 'HSD11B1', 'THSD7A', 'BMPR1B' 'ADCY10', 'PRL', 'CA8','ESRRA', 'CALM1', 'CALM1', 'SPARC', and 'LRP1'). Moreover, we uncovered novel osteoporosis susceptible genes ('DICER1', 'PTMA', etc.) that were not found previously but play functionally important roles in osteoporosis etiology from existing studies. In addition, the SRC method identified genes can lead to higher accuracy for the diagnosis/classification of osteoporosis subjects when compared with the traditional T-test and Fisher-exact test, which further validates the proposed SRC approach for integrative analysis.