Classification Of Cancer Tissues Research Articles

Cancer Tissue Classification, Associated Therapeutic Implications and PDT as an Alternative

Carcinogenesis occurs via mutation of critical genes conferring enhanced survival and protection to the ensuing tissue. Current therapies in use garner success due to their specificity for certain intracellular targets. This particularity, whist beneficial in identifying tumorigenic from normal tissue states, is limited by the variations in geno/phenotypic profiles displayed between tumor tissue types. As such, tissue-specific therapeutic combinations and adjuvants are often required for adequate effect, but present symptomatic complications and occasionally generate secondary carcinogenesis displaying multi-drug resistance (MDR). An accumulation of research over the recent years has suggested that photodynamic therapy (PDT) with macrocycle photosensitizers are a promising alternative. Its administration method and toxicity mechanism present attractive features for potentially overcoming MDR cancers of multiple tissue origins with limited symptomatic onsets. Herein, we highlight these potentials as referenced against existing therapeutics and consider the impact of macrocycle-PDT for broad spectrum application regardless of tumorigenic resistance profiles.

LDA vs. QDA for FT-MIR prostate cancer tissue classification

Discrimination/classification of biological material a ta molecular level is one of the key aims of chemometrics applied to biospectroscopic data. Two discriminant functions, namely Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), were considered in this study for prostate cancer classification based on FT-MIR data, and illustrated graphically as boundary methods. Principal Component Analysis (PCA) was applied as a variable/dimensionality reduction method and Genetic Algorithm (GA) as variable selection method, followed by LDA and QDA. The performance of each method was determined using 40–100 MIR spectra per tissue sample (n=45), previously classified according to Gleason traditional grading by pathologists. The methods were used to separate the two-category of prostate cancer: Low grade (Gleason grade 2) vs. High grade (Gleason grade 3 and 4). The models were optimized using a training set and their performance was evaluated using a test set. Classification rates and quality metrics (Sensitivity, Specificity, Positive (or Precision) and Negative Predictive Values, Youden's index, and Positive and Negative Likelihood Ratios) were computed for each model. QDA-based models obtained higher classification rates and quality performance than LDA-based models. The models studied identify that secondary protein structure variations and DNA/RNA alterations are the main biomolecular ‘difference markers’ for prostate cancer grades.

Microscopic medical image classification framework via deep learning and shearlet transform.

Cancer is the second leading cause of death in US after cardiovascular disease. Image-based computer-aided diagnosis can assist physicians to efficiently diagnose cancers in early stages. Existing computer-aided algorithms use hand-crafted features such as wavelet coefficients, co-occurrence matrix features, and recently, histogram of shearlet coefficients for classification of cancerous tissues and cells in images. These hand-crafted features often lack generalizability since every cancerous tissue and cell has a specific texture, structure, and shape. An alternative approach is to use convolutional neural networks (CNNs) to learn the most appropriate feature abstractions directly from the data and handle the limitations of hand-crafted features. A framework for breast cancer detection and prostate Gleason grading using CNN trained on images along with the magnitude and phase of shearlet coefficients is presented. Particularly, we apply shearlet transform on images and extract the magnitude and phase of shearlet coefficients. Then we feed shearlet features along with the original images to our CNN consisting of multiple layers of convolution, max pooling, and fully connected layers. Our experiments show that using the magnitude and phase of shearlet coefficients as extra information to the network can improve the accuracy of detection and generalize better compared to the state-of-the-art methods that rely on hand-crafted features. This study expands the application of deep neural networks into the field of medical image analysis, which is a difficult domain considering the limited medical data available for such analysis.

Automated Breast Cancer Detection Using FISH Spectral Linear Unmixing

Fluorescence microscopy plays an important role in the classification of cancerous Tissue. The dramatic increase in multicolor fluorescence microscopy applications witnessed over the past decade is due, in part, to the significant advances in instrument and detector design. A number of advanced microscopy techniques have been applied using multi-color fluorescence labeling, including fluorescence recovery after photo bleaching (FRAP), fluorescence correlation spectroscopy (FCS), fluorescence resonance energy transfer (FRET), fluorescence in situ hybridization (FISH), and fluorescence lifetime imaging (FLIM). Many of these methods benefit significantly from the ability to use specifically targeted fluorescent proteins in live-cell imaging experiments. In addition, live-cell imaging has been revolutionized by the introduction of ever increasingly useful genetically encoded fluorescent proteins spanning the entire visible spectral region. However, the problem of fluorescence microscopy is the crosstalk between the channels caused by the overlap of the emission spectra of the different fluorophores, The crosstalk cannot be solved on the filter level, and not by specialized florophores. To eliminate the crosstalk the hyperspectral imaging using the spectra unmixing (algorithmically reduce the overlap of spectra) can be the possible way to reduce the errors in the classification of the tissue. Spectral imaging is the combination of commuter vision and spectroscopy. In addition, because every object of interest consists of more than one pixels, every pixel is dependent on its neighboring pixels. Thus, the spatial context of the image contains useful information for a classification and increase the sensitivity and specificity of a spectral classification.

Multi-objective semi-supervised clustering of tissue samples for cancer diagnosis

In the domain of bioinformatics, the clustering of gene expression profiles of different tissue samples over different experimental conditions has gained importance with the invention of micro-array based technology. This study also has some impact on cancer diagnosis. The proper classification of cancer tissue samples generated using the micro-array technology helps in detecting cancers in an automated way. In the current paper we have developed a semi-supervised clustering technique for proper partitioning of these gene expression data sets. Semi-supervised clustering is a combination of unsupervised and supervised classification techniques. It uses some amount of supervised information and a large collection of unsupervised data. Here a multi-objective based semi-supervised clustering technique is developed for solving the cancer tissue classification problem. Different combinations of objective functions are used. As the supervised information we assume that class labels of 10 % data are available. The proposed technique is evaluated for three open source benchmark cancer data sets (brain tumor data set, adult malignancy and small round blood cell tumors). Two classification quality measures, viz., Adjusted Rand Index and Classification Accuracy are used to measure the goodness of the obtained partitionings. Obtained results are compared with several state-of-the-art clustering techniques. Moreover, significant gene markers have been identified and demonstrated visually from the clustering solutions obtained.

Development of an image pre-processor for operational hyperspectral laryngeal cancer detection.

Hyperspectral imaging (HSI) is a technology with high potential in the field of non-invasive detection of cancer. However, in complex imaging situations like HSI of the larynx with a rigid endoscope, various image interferences can disable a proper classification of cancerous tissue. We identified three main problems: i) misregistration of single images in a HS cube due to patient heartbeat ii) image noise and iii) specular reflections (SR). Consequently, an image pre-processor is developed in the current paper to overcome these image interferences. It encompasses i) image registration ii) noise removal by minimum noise fraction (MNF) transformation and iii) a novel SR detection method. The results reveal that the pre-processor improves classification performance, while the newly developed SR detection method outperforms global thresholding technique hitherto used by 46%. The novel pre-processor will be used for future studies towards the development of an operational scheme for HS-based larynx cancer detection. RGB image of the larynx derived from the hyperspectral cube and corresponding specular reflections (a) manually segmented and (b) detected by a novel specular reflection detection method.

Characterization of biomechanical properties of agar based tissue mimicking phantoms for ultrasound stiffness imaging techniques

Pathological changes of the body have been observed to change the mechanical properties of soft tissue types which can be imaged by ultrasound elastography. Though initial clinical results using ultrasound elastography in detection of tumors are promising, quantification of signal to noise ratio, resolution and strain image patterns are the best achieved under a controlled study using phantoms with similar biomechanical properties of normal and abnormal tissues. The purpose of this work is to characterize the biomechanical properties of agar based tissue mimicking phantoms by varying the agar concentration from 1.7 to 6.6% by weight and identify the optimum property to be used in classification of cancerous tissues. We performed quasi-static uniaxial compression test under a strain rate of 0.5mm/min up to 15% strain and measured Young's modulus of phantom samples which are from 50kPa to 450kPa. Phantoms show nonlinear stress–strain characteristics at finite strain which were characterized using hyperelastic parameters by fitting Neo-Hookean, Mooney Rivlin, Ogden and Veronda Westmann models. We also investigated viscoelastic parameters of the samples by conducting oscillatory shear rheometry at various precompression levels (2–5%). Loss modulus values are always less than storage modulus which represents the behavior of soft tissues. The increase in agar concentration increases the shear modulus of the samples as well as decreases the linear viscoelastic region. The results suggest that dynamic shear modul are more promising than linear and nonlinear elastic modul in differentiation of various classes of abnormal tissues.

A Minimum Spanning Forest Based Hyperspectral Image Classification Method for Cancerous Tissue Detection.

Hyperspectral imaging is a developing modality for cancer detection. The rich information associated with hyperspectral images allow for the examination between cancerous and healthy tissue. This study focuses on a new method that incorporates support vector machines into a minimum spanning forest algorithm for differentiating cancerous tissue from normal tissue. Spectral information was gathered to test the algorithm. Animal experiments were performed and hyperspectral images were acquired from tumor-bearing mice. In vivo imaging experimental results demonstrate the applicability of the proposed classification method for cancer tissue classification on hyperspectral images.

Bayesian binary kernel probit model for microarray based cancer classification and gene selection

With the arrival of gene expression microarrays a new challenge has opened up for identification or classification of cancer tissues. Due to the large number of genes providing valuable information simultaneously compared to very few available tissue samples the cancer staging or classification becomes very tricky. In this paper we introduce a hierarchical Bayesian probit model for two class cancer classification. Instead of assuming a linear structure for the function that relates the gene expressions with the cancer types we only assume that the relationship is explained by an unknown function which belongs to an abstract functional space like the reproducing kernel Hilbert space. Our formulation automatically reduces the dimension of the problem from the large number of covariates or genes to a small sample size. We incorporate a Bayesian gene selection scheme with the automatic dimension reduction to adaptively select important genes and classify cancer types under an unified model. Our model is highly flexible in terms of explaining the relationship between the cancer types and gene expression measurements and picking up the differentially expressed genes. The proposed model is successfully tested on three simulated data sets and three publicly available leukemia cancer, colon cancer, and prostate cancer real life data sets.

Detect Key Gene Information in Classification of Microarray Data

We detect key information of high-dimensional microarray profiles based on wavelet analysis and genetic algorithm. Firstly, wavelet transform is employed to extract approximation coefficients at 2nd level, which remove noise and reduce dimensionality. Genetic algorithm (GA) is performed to select the optimized features. Experiments are performed on four datasets, and experimental results prove that approximation coefficients are efficient way to characterize the microarray data. Furthermore, in order to detect the key genes in the classification of cancer tissue, we reconstruct the approximation part of gene profiles based on orthogonal approximation coefficients. The significant genes are selected based on reconstructed approximation information using genetic algorithm. Experiments prove that good performance of classification is achieved based on the selected key genes.

Varying Degrees of Malignancy in Cancer of the Breast

Differences in the degree of malignancy of malignant tumors have been recognized by pathologists for many years. Indeed, Virchow9s original conception of a malignant tumor was one composed of cells, derived from the tissue cells of the individual, but differing from the normal cells in the rapidity and independence of their growth. Hansemann (1) carried this idea somewhat further and introduced the word “anaplasia” to indicate the process by which cancer cells came to differ from the normal type cell of the body tissue concerned. Anaplasia involves a loss of differentiation and an increase of reproductive power, so that the anaplastic cell fulfils only in abortive fashion, if at all, its normal function, such as secretion or keratinization; while it shows by increased number of mitotic figures, and especially by the irregularity and abnormality of its nuclear chromatic elements and figures, the increase in rapidity of cell division and of cell growth which is characteristic of malignancy. A number of attempts have been made to grade the malignancy of different breast tumors by distinguishing their histological characteristics, such as adenocarcinoma, medullary, scirrhus, colloid, etc.; but with the exception of adenocarcinoma and colloid, these divisions have proved of little value in prognosis. There the matter rested till 1921, when, under the influence of MacCarty (2) of the Mayo Clinic, Broders published a paper suggesting the classification of cancer tissue according to the degree of malignancy, as estimated by loss of differentiation and increase of reproductive characteristics.