Phenotype recognition with combined features and random subspace classifier ensemble

MIC_Locator: a novel image-based protein subcellular location multi-label prediction model based on multi-scale monogenic signal representation and intensity encoding strategy

Background

Protein subcellular localization plays a crucial role in understanding cell function. Proteins need to be in the right place at the right time, and combine with the corresponding molecules to fulfill their functions. Furthermore, prediction of protein subcellular location not only should be a guiding role in drug design and development due to potential molecular targets but also be an essential role in genome annotation. Taking the current status of image-based protein subcellular localization as an example, there are three common drawbacks, i.e., obsolete datasets without updating label information, stereotypical feature descriptor on spatial domain or grey level, and single-function prediction algorithm’s limited capacity of handling single-label database.

Results

In this paper, a novel human protein subcellular localization prediction model MIC_Locator is proposed. Firstly, the latest datasets are collected and collated as our benchmark dataset instead of obsolete data while training prediction model. Secondly, Fourier transformation, Riesz transformation, Log-Gabor filter and intensity coding strategy are employed to obtain frequency feature based on three components of monogenic signal with different frequency scales. Thirdly, a chained prediction model is proposed to handle multi-label instead of single-label datasets. The experiment results showed that the MIC_Locator can achieve 60.56% subset accuracy and outperform the existing majority of prediction models, and the frequency feature and intensity coding strategy can be conducive to improving the classification accuracy.

Conclusions

Our results demonstrate that the frequency feature is more beneficial for improving the performance of model compared to features extracted from spatial domain, and the MIC_Locator proposed in this paper can speed up validation of protein annotation, knowledge of protein function and proteomics research.

Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis

Automated biomedical image classification could confront the challenges of high level noise, image blur, illumination variation and complicated geometric correspondence among various categorical biomedical patterns in practice. To handle these challenges, we propose a cascade method consisting of two stages for biomedical image classification. At stage 1, we propose a confidence score based classification rule with a reject option for a preliminary decision using the support vector machine (SVM). The testing images going through stage 1 are separated into two groups based on their confidence scores. Those testing images with sufficiently high confidence scores are classified at stage 1 while the others with low confidence scores are rejected and fed to stage 2. At stage 2, the rejected images from stage 1 are first processed by a subspace analysis technique called eigenfeature regularization and extraction (ERE), and then classified by another SVM trained in the transformed subspace learned by ERE. At both stages, images are represented based on two types of local features, i.e., SIFT and SURF, respectively. They are encoded using various bag-of-words (BoW) models to handle biomedical patterns with and without geometric correspondence, respectively. Extensive experiments are implemented to evaluate the proposed method on three benchmark real-world biomedical image datasets. The proposed method significantly outperforms several competing state-of-the-art methods in terms of classification accuracy.

Bioimage Classification with Handcrafted and Learned Features

Bioimage classification is increasingly becoming more important in many biological studies including those that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new General Purpose (GenP) bioimage classification method that can be applied to a large range of classification problems. The GenP system we propose is an ensemble that combines multiple texture features (both handcrafted and learned descriptors) for superior and generalizable discriminative power. Our ensemble obtains a boosting of performance by combining local features, dense sampling features, and deep learning features. Each descriptor is used to train a different Support Vector Machine that is then combined by sum rule. We evaluate our method on a diverse set of bioimage classification tasks each represented by a benchmark database, including some of those available in the IICBU 2008 database. Each bioimage classification task represents a typical subcellular, cellular, and tissue level classification problem. Our evaluation on these datasets demonstrates that the proposed GenP bioimage ensemble obtains state-of-the-art performance without any ad-hoc dataset tuning of the parameters (thereby avoiding any risk of overfitting/overtraining). To reproduce the experiments reported in this paper, the MATLAB code of all the descriptors is available at https://github.com/LorisNanni and https://www.dropbox.com/s/bguw035yrqz0pwp/ElencoCode.docx?dl=0.

Low Dimensional Representation of Fisher Vectors for Microscopy Image Classification

Microscopy image classification is important in various biomedical applications, such as cancer subtype identification, and protein localization for high content screening. To achieve automated and effective microscopy image classification, the representative and discriminative capability of image feature descriptors is essential. To this end, in this paper, we propose a new feature representation algorithm to facilitate automated microscopy image classification. In particular, we incorporate Fisher vector (FV) encoding with multiple types of local features that are handcrafted or learned, and we design a separation-guided dimension reduction method to reduce the descriptor dimension while increasing its discriminative capability. Our method is evaluated on four publicly available microscopy image data sets of different imaging types and applications, including the UCSB breast cancer data set, MICCAI 2015 CBTC challenge data set, and IICBU malignant lymphoma, and RNAi data sets. Our experimental results demonstrate the advantage of the proposed low-dimensional FV representation, showing consistent performance improvement over the existing state of the art and the commonly used dimension reduction techniques.

Bioimage classification with subcategory discriminant transform of high dimensional visual descriptors

BACKGROUND

Bioimage classification is a fundamental problem for many important biological studies that require accurate cell phenotype recognition, subcellular localization, and histopathological classification. In this paper, we present a new bioimage classification method that can be generally applicable to a wide variety of classification problems. We propose to use a high-dimensional multi-modal descriptor that combines multiple texture features. We also design a novel subcategory discriminant transform (SDT) algorithm to further enhance the discriminative power of descriptors by learning convolution kernels to reduce the within-class variation and increase the between-class difference.

RESULTS

We evaluate our method on eight different bioimage classification tasks using the publicly available IICBU 2008 database. Each task comprises a separate dataset, and the collection represents typical subcellular, cellular, and tissue level classification problems. Our method demonstrates improved classification accuracy (0.9 to 9%) on six tasks when compared to state-of-the-art approaches. We also find that SDT outperforms the well-known dimension reduction techniques, with for example 0.2 to 13% improvement over linear discriminant analysis.

CONCLUSIONS

We present a general bioimage classification method, which comprises a highly descriptive visual feature representation and a learning-based discriminative feature transformation algorithm. Our evaluation on the IICBU 2008 database demonstrates improved performance over the state-of-the-art for six different classification tasks.

Spatial uncertainty modeling of fuzzy information in images for pattern classification

The modeling of the spatial distribution of image properties is important for many pattern recognition problems in science and engineering. Mathematical methods are needed to quantify the variability of this spatial distribution based on which a decision of classification can be made in an optimal sense. However, image properties are often subject to uncertainty due to both incomplete and imprecise information. This paper presents an integrated approach for estimating the spatial uncertainty of vagueness in images using the theory of geostatistics and the calculus of probability measures of fuzzy events. Such a model for the quantification of spatial uncertainty is utilized as a new image feature extraction method, based on which classifiers can be trained to perform the task of pattern recognition. Applications of the proposed algorithm to the classification of various types of image data suggest the usefulness of the proposed uncertainty modeling technique for texture feature extraction.

Computer-aided diagnosis system for classifying benign and malignant thyroid nodules in multi-stained FNAB cytological images

An automated computer-aided diagnosis system is developed to classify benign and malignant thyroid nodules using multi-stained fine needle aspiration biopsy (FNAB) cytological images. In the first phase, the image segmentation is performed to remove the background staining information and retain the appropriate foreground cell objects in cytological images using mathematical morphology and watershed transform segmentation methods. Subsequently, statistical features are extracted using two-level discrete wavelet transform (DWT) decomposition, gray level co-occurrence matrix (GLCM) and Gabor filter based methods. The classifiers k-nearest neighbor (k-NN), Elman neural network (ENN) and support vector machine (SVM) are tested for classifying benign and malignant thyroid nodules. The combination of watershed segmentation, GLCM features and k-NN classifier results a lowest diagnostic accuracy of 60 %. The highest diagnostic accuracy of 93.33 % is achieved by ENN classifier trained with the statistical features extracted by Gabor filter bank from the images segmented by morphology and watershed transform segmentation methods. It is also observed that SVM classifier results its highest diagnostic accuracy of 90 % for DWT and Gabor filter based features along with morphology and watershed transform segmentation methods. The experimental results suggest that the developed system with multi-stained thyroid FNAB images would be useful for identifying thyroid cancer irrespective of staining protocol used.

Functional genomic and high-content screening for target discovery and deconvolution

INTRODUCTION

Functional genomic screens apply knowledge gained from the sequencing of the human genome toward rapid methods of identifying genes involved in cellular function based on a specific phenotype. This approach has been made possible through advances in both molecular biology and automation. The utility of this approach has been further enhanced through the application of image-based high-content screening: an automated microscopy and quantitative image analysis platform. These approaches can significantly enhance the acquisition of novel targets for drug discovery.

AREAS COVERED

Both the utility and potential issues associated with functional genomic screening approaches are discussed in this review, along with examples that illustrate both. The considerations for high-content screening applied to functional genomics are also presented.

EXPERT OPINION

Functional genomic screening and high-content screening are extremely useful in the identification of new drug targets. However, the technical, experimental, and computational parameters have an enormous influence on the results. Thus, although new targets are identified, caution should be applied to the interpretation of screening data in isolation. Genomic screens should be viewed as an integral component of a target identification campaign that requires both the acquisition of orthogonal data, as well as a rigorous validation strategy.

VEHICLE TYPE AND MAKE RECOGNITION BY COMBINED FEATURES AND ROTATION FOREST ENSEMBLE

Vehicle type/make recognition based on images captured by surveillance cameras is a challenging task in intelligent transportation system and automatic surveillance. In this paper, we comparatively studied two feature extraction methods for image description, i.e. a new multiresolution analysis tool called Fast Discrete Curvelet Transform and the pyramid histogram of oriented gradients (PHOG). Curvelet Transform has better directional and edge representation abilities than widely used wavelet transform, which is particularly appropriate for the description of images rich with edges. PHOG represents the local shape by a histogram of edge orientations computed for each image sub-region, quantized into a number of bins, thus has the ascendency in its description of more discriminating information. A composite feature description from PHOG and Curvelet can further increase the accuracy of classification by taking their complementary information. We also investigated the applicability of the Rotation Forest (RF) ensemble method for vehicle classification based on the combined features. The RF ensemble contains a set of base multilayer perceptrons which are trained using principal component analysis to rotate the original axes of combined features of vehicle images. The class label is assigned by the ensemble via majority voting. Experimental results using more than 600 images from 21 makes of cars/vans show the effectiveness of the proposed approach. The composite feature is better than any single feature in the classification accuracy and the ensemble model produces better performance compared to any of the individual neural network base classifier. With a moderate ensemble size of 20, the Rotation Forest ensembles offers a classification rate close to 96.5%, exhibiting promising potentials for real-life applications.