Protein subcellular localization of fluorescence microscopy images: Employing new statistical and Texton based image features and SVM based ensemble classification

Rebalance Weights AdaBoost-SVM Model for Imbalanced Data

Classification of imbalanced data is a challenging task that has captured considerable interest in numerous scientific fields by virtue of the great practical value of minority accuracy. Some methods for improving generalization performance have been developed to address this classification situation. Here, we propose a cost-sensitive ensemble learning method using a support vector machine as a base learner of AdaBoost for classifying imbalanced data. Considering that the existing methods are not well studied in terms of how to precisely control the classification accuracy of the minority class, we developed a novel way to rebalance the weights of AdaBoost, and the weights influence the base learner training. This weighting strategy increases the sample weight of the misclassified minority while decreasing the sample weight of the misclassified majority until their distributions are even in each round. Furthermore, we included P-mean as one of the assessment markers and discussed why it is necessary. Experiments were conducted to compare the proposed and comparison 10 models on 18 datasets in terms of six different metrics. Through comprehensive experimental findings, the statistical study is performed to verify the efficacy and usability of the proposed model.

Multi-scale deep learning for the imbalanced multi-label protein subcellular localization prediction based on immunohistochemistry images

MOTIVATION

The development of microscopic imaging techniques enables us to study protein subcellular locations from the tissue level down to the cell level, contributing to the rapid development of image-based protein subcellular location prediction approaches. However, existing methods suffer from intrinsic limitations, such as poor feature representation ability, data imbalanced issue, and multi-label classification problem, greatly impacting the model performance and generalization.

RESULTS

In this study, we propose MSTLoc, a novel multi-scale end-to-end deep learning model to identify protein subcellular locations in the imbalanced multi-label immunohistochemistry (IHC) images dataset. In our MSTLoc, we deploy a deep convolution neural network to extract multi-scale features from the IHC images, aggregate the high-level features and low-level features via feature fusion to sufficiently exploit the dependencies amongst various subcellular locations, and utilize Vision Transformer (ViT) to model the relationship amongst the features and enhance the feature representation ability. We demonstrate that the proposed MSTLoc achieves better performance than current state-of-the-art models in multi-label subcellular location prediction. Through feature visualization and interpretation analysis, we demonstrate that as compared with the hand-crafted features, the multi-scale deep features learnt from our model exhibit better ability in capturing discriminative patterns underlying protein subcellular locations, and the features from different scales are complementary for the improvement in performance. Finally, case study results indicate that our MSTLoc can successfully identify some biomarkers from proteins that are closely involved with cancer development. For the convenient use of our method, we establish a user-friendly webserver available at http://server.wei-group.net/ MSTLoc.

AVAILABILITY AND IMPLEMENTATION

http://server.wei-group.net/ MSTLoc.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Accurate prediction of multi-label protein subcellular localization through multi-view feature learning with RBRL classifier

Multi-label proteins can participate in carrier transportation, enzyme catalysis, hormone regulation and other life activities. Meanwhile, they play a key role in the fields of biopharmaceuticals, gene and cell therapy. This article proposes a prediction method called Mps-mvRBRL to predict the subcellular localization (SCL) of multi-label protein. Firstly, pseudo position-specific scoring matrix, dipeptide composition, position specific scoring matrix-transition probability composition, gene ontology and pseudo amino acid composition algorithms are used to obtain numerical information from different views. Based on the contribution of five individual feature extraction methods, differential evolution is used for the first time to learn the weight of single feature, and then these original features use a weighted combination method to fuse multi-view information. Secondly, the fused high-dimensional features use a weighted linear discriminant analysis framework based on binary weight form to eliminate irrelevant information. Finally, the best feature vector is input into the joint ranking support vector machine and binary relevance with robust low-rank learning classifier to predict the SCL. After applying leave-one-out cross-validation, the overall actual accuracy (OAA) and overall location accuracy (OLA) of Mps-mvRBRL on the training set of Gram-positive bacteria are both 99.81%. The OAA on the test sets of plant, virus and Gram-negative bacteria datasets are 97.24%, 98.55% and 98.20%, respectively, and the OLA are 97.16%, 97.62% and 98.28%, respectively. The results show that the model achieves good prediction performance for predicting the SCL of multi-label protein.

Hybrid diffusion tensor imaging feature-based AD classification

BACKGROUND

Effective detection of Alzheimer's disease (AD) is still difficult in clinical practice. Therefore, establishment of AD detection model by means of machine learning is of great significance to assist AD diagnosis.

OBJECTIVE

To investigate and test a new detection model aiming to help doctors diagnose AD more accurately.

METHODS

Diffusion tensor images and the corresponding T1w images acquired from subjects (AD = 98, normal control (NC) = 100) are used to construct brain networks. Then, 9 types features (198×90×9 in total) are extracted from the 3D brain networks by a graph theory method. Features with low correction in both groups are selected through the Pearson correlation analysis. Finally, the selected features (198×33, 198×26, 198×30, 198×42, 198×36, 198×23, 198×29, 198×14, 198×25) are separately used into train 3 machine learning classifier based detection models in which 60% of study subjects are used for training, 20% for validation and 20% for testing.

RESULTS

The best detection accuracy levels of 3 models are 90%, 98% and 90% with the corresponding sensitivity of 92%, 96%, and 72% and specificity of 88%, 100% and 94% when using a random forest classifier trained with the Shortest Path Length (SPL) features (198×14), a support vector machine trained with the Degree Centrality features (198×33), and a convolution neural network trained with SPL features, respectively.

CONCLUSIONS

This study demonstrates that the new method and models not only improve the accuracy of detecting AD, but also avoid bias caused by the method of direct dimensionality reduction from high dimensional data.

Protein subcellular localization based on deep image features and criterion learning strategy

The spatial distribution of proteome at subcellular levels provides clues for protein functions, thus is important to human biology and medicine. Imaging-based methods are one of the most important approaches for predicting protein subcellular location. Although deep neural networks have shown impressive performance in a number of imaging tasks, its application to protein subcellular localization has not been sufficiently explored. In this study, we developed a deep imaging-based approach to localize the proteins at subcellular levels. Based on deep image features extracted from convolutional neural networks (CNNs), both single-label and multi-label locations can be accurately predicted. Particularly, the multi-label prediction is quite a challenging task. Here we developed a criterion learning strategy to exploit the label-attribute relevancy and label-label relevancy. A criterion that was used to determine the final label set was automatically obtained during the learning procedure. We concluded an optimal CNN architecture that could give the best results. Besides, experiments show that compared with the hand-crafted features, the deep features present more accurate prediction with less features. The implementation for the proposed method is available at https://github.com/RanSuLab/ProteinSubcellularLocation.

Morphological Segmentation Analysis and Texture-based Support Vector Machines Classification on Mice Liver Fibrosis Microscopic Images

Background:

To reduce the intensity of the work of doctors, pre-classification work needs to be issued. In this paper, a novel and related liver microscopic image classification analysis method is proposed.

Objective:

For quantitative analysis, segmentation is carried out to extract the quantitative information of special organisms in the image for further diagnosis, lesion localization, learning and treating anatomical abnormalities and computer-guided surgery. </P><P> Methods: In the current work, entropy-based features of microscopic fibrosis mice’ liver images were analyzed using fuzzy c-cluster, k-means and watershed algorithms based on distance transformations and gradient. A morphological segmentation based on a local threshold was deployed to determine the fibrosis areas of images.

Results:

The segmented target region using the proposed method achieved high effective microscopy fibrosis images segmenting of mice liver in terms of the running time, dice ratio and precision. The image classification experiments were conducted using Gray Level Co-occurrence Matrix (GLCM). The best classification model derived from the established characteristics was GLCM which performed the highest accuracy of classification using a developed Support Vector Machine (SVM). The training model using 11 features was found to be accurate when only trained by 8 GLCMs.

Conclusion:

The research illustrated that the proposed method is a new feasible research approach for microscopy mice liver image segmentation and classification using intelligent image analysis techniques. It is also reported that the average computational time of the proposed approach was only 2.335 seconds, which outperformed other segmentation algorithms with 0.8125 dice ratio and 0.5253 precision.</P>

Evaluating green tea quality based on multisensor data fusion combining hyperspectral imaging and olfactory visualization systems

BACKGROUND

The instrumental evaluation of tea quality using digital sensors instead of human panel tests has attracted much attention globally. However, individual sensors do not meet the requirements of discriminant accuracy as a result of incomprehensive sensor information. Considering the major factors in the sensory evaluation of tea, the study integrated multisensor information, including spectral, image and olfaction feature information.

RESULTS

To investigate spectral and image information obtained from hyperspectral spectrometers of different bands, principal components analysis was used for dimension reduction and different types of supervised learning algorithms (linear discriminant analysis, K-nearest neighbour and support vector machine) were selected for comparison. Spectral feature information in the near infrared region and image feature information in the visible-near infrared/near infrared region achieved greater accuracy for classification. The results indicated that a support vector machine outperformed other methods with respect to multisensor data fusion, which improved the accuracy of evaluating green tea quality compared to using individual sensor data. The overall accuracy of the calibration set increased from 75% using optimal single sensor information to 92% using multisensor information, and the overall accuracy of the prediction set increased from 78% to 92%.

CONCLUSION

Overall, it can be concluded that multisensory data accurately identify six grades of tea. © 2018 Society of Chemical Industry.

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.

Comparative analysis of image classification methods for automatic diagnosis of ophthalmic images

There are many image classification methods, but it remains unclear which methods are most helpful for analyzing and intelligently identifying ophthalmic images. We select representative slit-lamp images which show the complexity of ocular images as research material to compare image classification algorithms for diagnosing ophthalmic diseases. To facilitate this study, some feature extraction algorithms and classifiers are combined to automatic diagnose pediatric cataract with same dataset and then their performance are compared using multiple criteria. This comparative study reveals the general characteristics of the existing methods for automatic identification of ophthalmic images and provides new insights into the strengths and shortcomings of these methods. The relevant methods (local binary pattern +SVMs, wavelet transformation +SVMs) which achieve an average accuracy of 87% and can be adopted in specific situations to aid doctors in preliminarily disease screening. Furthermore, some methods requiring fewer computational resources and less time could be applied in remote places or mobile devices to assist individuals in understanding the condition of their body. In addition, it would be helpful to accelerate the development of innovative approaches and to apply these methods to assist doctors in diagnosing ophthalmic disease.