Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN

Background

Imbalanced data classification is an inevitable problem in medical intelligent diagnosis. Most of real-world biomedical datasets are usually along with limited samples and high-dimensional feature. This seriously affects the classification performance of the model and causes erroneous guidance for the diagnosis of diseases. Exploring an effective classification method for imbalanced and limited biomedical dataset is a challenging task.

Methods

In this paper, we propose a novel multilayer extreme learning machine (ELM) classification model combined with dynamic generative adversarial net (GAN) to tackle limited and imbalanced biomedical data. Firstly, principal component analysis is utilized to remove irrelevant and redundant features. Meanwhile, more meaningful pathological features are extracted. After that, dynamic GAN is designed to generate the realistic-looking minority class samples, thereby balancing the class distribution and avoiding overfitting effectively. Finally, a self-adaptive multilayer ELM is proposed to classify the balanced dataset. The analytic expression for the numbers of hidden layer and node is determined by quantitatively establishing the relationship between the change of imbalance ratio and the hyper-parameters of the model. Reducing interactive parameters adjustment makes the classification model more robust.

Results

To evaluate the classification performance of the proposed method, numerical experiments are conducted on four real-world biomedical datasets. The proposed method can generate authentic minority class samples and self-adaptively select the optimal parameters of learning model. By comparing with W-ELM, SMOTE-ELM, and H-ELM methods, the quantitative experimental results demonstrate that our method can achieve better classification performance and higher computational efficiency in terms of ROC, AUC, G-mean, and F-measure metrics.

Conclusions

Our study provides an effective solution for imbalanced biomedical data classification under the condition of limited samples and high-dimensional feature. The proposed method could offer a theoretical basis for computer-aided diagnosis. It has the potential to be applied in biomedical clinical practice.

     

A methodology for elucidating regulatory mechanisms leading to changes in lipid profiles

Introduction

It is difficult to elucidate the metabolic and regulatory factors causing lipidome perturbations.

Objectives

This work simplifies this process.

Methods

A method has been developed to query an online holistic lipid metabolic network (of 7923 metabolites) to extract the pathways that connect the input list of lipids.

Results

The output enables pathway visualisation and the querying of other databases to identify potential regulators. When used to a study a plasma lipidome dataset of polycystic ovary syndrome, 14 enzymes were identified, of which 3 are linked to ELAVL1—an mRNA stabiliser.

Conclusion

This method provides a simplified approach to identifying potential regulators causing lipid-profile perturbations.

     

Our local experience with the surgical treatment of ampullary cancer

Background

The aim of this study is to report the outcome after surgical treatment of 32 patients with ampullary cancers from 1990 to 1999.

Methods

Twenty-one of them underwent pancreaticoduodenectomy and 9 local excision of the ampullary lesion. The remaining 2 patients underwent palliative surgery.

Results

When the final histological diagnosis was compared with the preoperative histological finding on biopsy, accurate diagnosis was preoperatively established in 24 patients. The hospital morbidity was 18.8% as 9 complications occurred in 6 patients. Following local excision of the ampullary cancer, the survival rate at 3 and 5 years was 77.7% and 33.3% respectively. Among the patients that underwent Whipple's procedure, the 3-year survival rate was 76.2% and the 5-year survival rate 62%.

Conclusion

In this series, local resection was a safe option in patients with significant co-morbidity or small ampullary tumors less than 2 cm in size, and was associated with satisfactory long-term survival rates.

     

Feature extraction for the analysis of colon status from the endoscopic images

Background

Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status.

Methods

Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA) and are evaluated using Backpropagation Neural Network (BPNN).

Results

Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (τ = 1%), is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, τ = 1%) or color (90.52%, τ = 1%) features.

Conclusion

In conclusion, novel methods for extracting new texture- and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.

     

Fungal Keratitis: Epidemiological Profile in Argentina

Purpose of Review

The purpose of this review is to describe the epidemiology and species distribution of fungi-causing keratitis in Argentina during the past 10 years.

Recent Findings

In Argentina, reports of distribution and frequency of fungal keratitis are scarce and little is known about its current epidemiology.In the present study, a review of the published data on fungal keratitis was done according to the global context focusing on the current situation in our country.

Summary

Data presented here were obtained in a reference ophthalmological hospital in the Autonomous city of Buenos Aires from 2007 to 2017 and represents an approach to the current status of fungal keratitis. However, larger national data is required to assess the actual epidemiological situation in Argentina.

     

Case report of optic atrophy in Dentatorubropallidoluysian Atrophy (DRPLA)

Background

Dentatorubropallidoluysian atrophy (DRPLA) is a rare autosomal dominant neurodegenerative disease that is associated with numerous movement disorders. Ocular problems also occur with DRPLA with reports of corneal endothelial degeneration in some patients living with the disease. We report a new visual problem associated with DRPLA, optic atrophy.

Case presentation

A 47 year-old man presented complaining of progressive visual loss associated with optic atrophy on ophthalmological evaluation. He gradually developed a progressive ataxia with dystonia. Brain MRI revealed a diffuse leukoencephalopathy. Genetic analysis revealed 62 CAG repeats in one allele of the DRPLA gene and he was diagnosed with DRPLA.

Conclusion

Optic atrophy should be included in the clinical spectrum of DRPLA.

     

Urinary metabolite markers characterizing tuberculosis treatment failure

Background

Considering that approximately 15% of the nine million new tuberculosis (TB) cases reported per annum are not treated successfully, new, distinctive and specific biomarkers are needed to better characterize the biological basis of a poor treatment outcome.

Methods

Urine samples from 41 active pulmonary TB patients were collected at baseline (time of diagnosis), during treatment (weeks 1, 2 and 4) and 2 weeks after treatment completion (week 26). These samples were divided into successful (cured) and unsuccessful (failed) treatment outcome groups and analyzed using a GCxGC-TOFMS metabolomics research approach.

Results

The metabolite data collected showed clear differentiation of the cured and failed treatment outcome groups using the samples collected at the time of diagnosis, i.e. before any treatment was administered.

Conclusions

The treatment failure group was characterized by an imbalanced gut microbiome, in addition to elevated levels of metabolites associated with abnormalities in the long-chain fatty acid β-oxidation pathway, accompanied by reduced l-carnitine and short-chain fatty acids, indicative of a mitochondrial trifunctional protein defect in particular. Furthermore, an altered amino acid metabolism was also observed in these patients, which confirms previous findings and associations to increased interferon gamma due to the host’s immune response to M. tuberculosis and a compromised insulin secretion.

     

Bridge processes: a solution for LCI datasets independent of background databases

Introduction

New platforms are emerging that enable more data providers to publish life cycle inventory data.

Background

Providing datasets that are not complete LCA models results in fragments that are difficult for practitioners to integrate and use for LCA modeling. Additionally, when proxies are used to provide a technosphere input to a process that was not originally intended by the process authors, in most LCA software, this requires modifying the original process.

Results

The use of a bridge process, which is a process created to link two existing processes, is proposed as a solution.

Discussion

Benefits to bridge processes include increasing model transparency, facilitating dataset sharing and integration without compromising original dataset integrity and independence, providing a structure with which to make the data quality associated with process linkages explicit, and increasing model flexibility in the case that multiple bridges are provided. A drawback is that they add additional processes to existing LCA models which will increase their size.

Conclusions

Bridge processes can be an enabler in allowing users to integrate new datasets without modifying them to link to background databases or other processes they have available. They may not be the ideal long-term solution but provide a solution that works within the existing LCA data model.

     

Optimization of fecal sample preparation for untargeted LC-HRMS based metabolomics

Introduction

Collecting feces is easy. It offers direct outcome to endogenous and microbial metabolites.

Objectives

In a context of lack of consensus about fecal sample preparation, especially in animal species, we developed a robust protocol allowing untargeted LC-HRMS fingerprinting.

Methods

The conditions of extraction (quantity, preparation, solvents, dilutions) were investigated in bovine feces.

Results

A rapid and simple protocol involving feces extraction with methanol (1/3, M/V) followed by centrifugation and a step filtration (10 kDa) was developed.

Conclusion

The workflow generated repeatable and informative fingerprints for robust metabolome characterization.

     

<Emphasis Type="Italic">massPix</Emphasis>: an R package for annotation and interpretation of mass spectrometry imaging data for lipidomics

Introduction

Mass spectrometry imaging (MSI) experiments result in complex multi-dimensional datasets, which require specialist data analysis tools.

Objectives

We have developed massPix—an R package for analysing and interpreting data from MSI of lipids in tissue.

Methods

massPix produces single ion images, performs multivariate statistics and provides putative lipid annotations based on accurate mass matching against generated lipid libraries.

Results

Classification of tissue regions with high spectral similarly can be carried out by principal components analysis (PCA) or k-means clustering.

Conclusion

massPix is an open-source tool for the analysis and statistical interpretation of MSI data, and is particularly useful for lipidomics applications.

     

NS-kNN: a modified <Emphasis Type="Italic">k</Emphasis>-nearest neighbors approach for imputing metabolomics data

Introduction

A common problem in metabolomics data analysis is the existence of a substantial number of missing values, which can complicate, bias, or even prevent certain downstream analyses. One of the most widely-used solutions to this problem is imputation of missing values using a k-nearest neighbors (kNN) algorithm to estimate missing metabolite abundances. kNN implicitly assumes that missing values are uniformly distributed at random in the dataset, but this is typically not true in metabolomics, where many values are missing because they are below the limit of detection of the analytical instrumentation.

Objectives

Here, we explore the impact of nonuniformly distributed missing values (missing not at random, or MNAR) on imputation performance. We present a new model for generating synthetic missing data and a new algorithm, No-Skip kNN (NS-kNN), that accounts for MNAR values to provide more accurate imputations.

Methods

We compare the imputation errors of the original kNN algorithm using two distance metrics, NS-kNN, and a recently developed algorithm KNN-TN, when applied to multiple experimental datasets with different types and levels of missing data.

Results

Our results show that NS-kNN typically outperforms kNN when at least 20–30% of missing values in a dataset are MNAR. NS-kNN also has lower imputation errors than KNN-TN on realistic datasets when at least 50% of missing values are MNAR.

Conclusion

Accounting for the nonuniform distribution of missing values in metabolomics data can significantly improve the results of imputation algorithms. The NS-kNN method imputes missing metabolomics data more accurately than existing kNN-based approaches when used on realistic datasets.

     

Automatic non-proliferative diabetic retinopathy screening system based on color fundus image

Background

Non-proliferative diabetic retinopathy is the early stage of diabetic retinopathy. Automatic detection of non-proliferative diabetic retinopathy is significant for clinical diagnosis, early screening and course progression of patients.

Methods

This paper introduces the design and implementation of an automatic system for screening non-proliferative diabetic retinopathy based on color fundus images. Firstly, the fundus structures, including blood vessels, optic disc and macula, are extracted and located, respectively. In particular, a new optic disc localization method using parabolic fitting is proposed based on the physiological structure characteristics of optic disc and blood vessels. Then, early lesions, such as microaneurysms, hemorrhages and hard exudates, are detected based on their respective characteristics. An equivalent optical model simulating human eyes is designed based on the anatomical structure of retina. Main structures and early lesions are reconstructed in the 3D space for better visualization. Finally, the severity of each image is evaluated based on the international criteria of diabetic retinopathy.

Results

The system has been tested on public databases and images from hospitals. Experimental results demonstrate that the proposed system achieves high accuracy for main structures and early lesions detection. The results of severity classification for non-proliferative diabetic retinopathy are also accurate and suitable.

Conclusions

Our system can assist ophthalmologists for clinical diagnosis, automatic screening and course progression of patients.

     

Evaluation of texture features at staging liver fibrosis based on phase contrast X-ray imaging

Background

The purpose of this study is to explore the potential of phase contrast imaging to detect fibrotic progress in its early stage; to investigate the feasibility of texture features for quantified diagnosis of liver fibrosis; and to evaluate the performance of back propagation (BP) neural net classifier for characterization and classification of liver fibrosis.

Methods

Fibrous mouse liver samples were imaged by X-ray phase contrast imaging, nine texture measures based on gray-level co-occurrence matrix were calculated and the feasibility of texture features in the characterization and discrimination of liver fibrosis at early stages was investigated. Furthermore, 36 or 18 features were applied to the input of BP classifier; the classification performance was evaluated using receiver operating characteristic curve.

Results

The phase contrast images displayed a vary degree of texture pattern from normal to severe fibrosis stages. The BP classifier could distinguish liver fibrosis among normal, mild, moderate and severe stages; the average accuracy was 95.1% for 36 features, and 91.1% for 18 features.

Conclusion

The study shows that early stages of liver fibrosis can be discriminated by the morphological features on the phase contrast images. BP network model based on combination of texture features is demonstrated effective for staging liver fibrosis.

     

Metal artifact reduction on cervical CT images by deep residual learning

Background

Cervical cancer is the fifth most common cancer among women, which is the third leading cause of cancer death in women worldwide. Brachytherapy is the most effective treatment for cervical cancer. For brachytherapy, computed tomography (CT) imaging is necessary since it conveys tissue density information which can be used for dose planning. However, the metal artifacts caused by brachytherapy applicators remain a challenge for the automatic processing of image data for image-guided procedures or accurate dose calculations. Therefore, developing an effective metal artifact reduction (MAR) algorithm in cervical CT images is of high demand.

Methods

A novel residual learning method based on convolutional neural network (RL-ARCNN) is proposed to reduce metal artifacts in cervical CT images. For MAR, a dataset is generated by simulating various metal artifacts in the first step, which will be applied to train the CNN. This dataset includes artifact-insert, artifact-free, and artifact-residual images. Numerous image patches are extracted from the dataset for training on deep residual learning artifact reduction based on CNN (RL-ARCNN). Afterwards, the trained model can be used for MAR on cervical CT images.

Results

The proposed method provides a good MAR result with a PSNR of 38.09 on the test set of simulated artifact images. The PSNR of residual learning (38.09) is higher than that of ordinary learning (37.79) which shows that CNN-based residual images achieve favorable artifact reduction. Moreover, for a 512?×?512 image, the average removal artifact time is less than 1 s.

Conclusions

The RL-ARCNN indicates that residual learning of CNN remarkably reduces metal artifacts and improves critical structure visualization and confidence of radiation oncologists in target delineation. Metal artifacts are eliminated efficiently free of sinogram data and complicated post-processing procedure.

     

Diagnosis of post-surgical fine-needle aspiration biopsies of thyroid lesions with indeterminate cytology using HRMAS NMR-based metabolomics

Introduction

Ultrasound examination coupled with fine-needle aspiration (FNA) cytology is the gold standard for the diagnosis of thyroid cancer. However, about 10–40% of these analyses cannot be conclusive on the malignancy of the lesions and lead to surgery. The cytological indeterminate FNA biopsies are mainly constituted of follicular—patterned lesions, which are benign in 80% of the cases.

Objectives

The development of a FNAB classification approach based on the metabolic phenotype of the lesions, complementary to cytology and other molecular tests in order to limit the number of patients undergoing unnecessary thyroidectomy.

Methods

We explored the potential of a NMR-based metabolomics approach to improve the quality of the diagnosis from FNABs, using thyroid tissues collected post-surgically.

Results

The NMR-detected metabolites were used to produce a robust OPLSDA model to discriminate between benign and malignant tumours. Malignancy was correlated with amino acids such as tyrosine, serine, alanine, leucine and phenylalanine and anti-correlated with myo-inositol, scyllo-inositol and citrate. Diagnosis accuracy was of 84.8% when only indeterminate lesions were considered.

Conclusion

These results on model FNAB indicate that there is a clear interest in exploring the possibility to export NMR metabolomics to pre-surgical diagnostics.

     

A lost opportunity for science: journals promote data sharing in metabolomics but do not enforce it

Introduction

Data sharing is being increasingly required by journals and has been heralded as a solution to the ‘replication crisis’.

Objectives

(i) Review data sharing policies of journals publishing the most metabolomics papers associated with open data and (ii) compare these journals’ policies to those that publish the most metabolomics papers.

Methods

A PubMed search was used to identify metabolomics papers. Metabolomics data repositories were manually searched for linked publications.

Results

Journals that support data sharing are not necessarily those with the most papers associated to open metabolomics data.

Conclusion

Further efforts are required to improve data sharing in metabolomics.

     

Amelioration of patients with chronic spontaneous urticaria in treatment with vitamin D supplement

Background

Spontaneous urticaria is a common allergic skin condition affecting 0.5–1% of individuals and may burden on health care expenditure or may be associated with remarkable morbidity.

Aim

In this study, we measured the effect of vitamin D supplementation in patients with a diagnosis of CSU. Furthermore, quality of life and cytokine changes were evaluated.

Methods

The clinical trial was conducted on 20 patients with idiopathic chronic urticaria. Vitamin D was administered orally for 8 weeks and disease activity was measured pre- and post-treatment using USS and DLQI. On the other hand expressions of IL-17, IL-10, Foxp3, and TGF-β by Real-time RT-PCR were assessed.

Results

USS questionnaire showed that severity of idiopathic urticaria after the intervention, which compared with the first day reached a significant 55% reduction. The DLQI quality of life questionnaire 2 months after treatment showed 55% improvement. Along with the significant improvement of clinical symptoms, use of vitamin D increase FOXP3 gene expression and downregulation of IL-10, TGF-B, and FOXP3, IL-17, but these changes were not statistically significant.

Limitation

These might happen due to lack of enrolled population in the investigation.

Conclusion

Vitamin D can be used along with standard medical care and it’s a safe and cost-effective method for the treatment of chronic urticaria with deficiency of vitamin D.

     

Building of a composite virtual slide from contiguous tissue samples

Background

Currently available microscope slide scanners produce whole slide images at various resolutions from histological sections. Nevertheless, acquisition area and so visualization of large tissue samples are limited by the standardized size of glass slides, used daily in pathology departments. The proposed solution has been developed to build composite virtual slides from images of large tumor fragments.

Materials and methods

Images of HES or immunostained histological sections of carefully labeled fragments from a representative slice of breast carcinoma were acquired with a digital slide scanner at a magnification of 20×. The tiling program involves three steps: the straightening of tissue fragment images using polynomial interpolation method, and the building and assembling of strips of contiguous tissue sample whole slide images in × and y directions. The final image is saved in a pyramidal BigTiff file format. The program has been tested on several tumor slices. A correlation quality control has been done on five images artificially cut.

Results

Sixty tumor slices from twenty surgical specimens, cut into two to twenty six pieces, were reconstructed. A median of 98.71% is obtained by computing the correlation coefficients between native and reconstructed images for quality control.

Conclusions

The proposed method is efficient and able to adapt itself to daily work conditions of classical pathology laboratories.

     

Hypocapnia is a biological marker for orthostatic intolerance in some patients with chronic fatigue syndrome

Context

Patients with chronic fatigue syndrome and those with orthostatic intolerance share many symptoms, yet questions exist as to whether CFS patients have physiological evidence of orthostatic intolerance.

Objective

To determine if some CFS patients have increased rates of orthostatic hypotension, hypertension, tachycardia, or hypocapnia relative to age-matched controls.

Design

Assess blood pressure, heart rate, respiratory rate, end tidal CO2 and visual analog scales for orthostatic symptoms when supine and when standing for 8 minutes without moving legs.

Setting

Referral practice and research center.

Participants

60 women and 15 men with CFS and 36 women and 4 men serving as age matched controls with analyses confined to 62 patients and 35 controls showing either normal orthostatic testing or a physiological abnormal test.

Main outcome measures

Orthostatic tachycardia; orthostatic hypotension; orthostatic hypertension; orthostatic hypocapnia or combinations thereof.

Results

CFS patients had higher rates of abnormal tests than controls (53% vs 20%, p < .002), but rates of orthostatic tachycardia, orthostatic hypotension, and orthostatic hypertension did not differ significantly between patients and controls (11.3% vs 5.7%, 6.5% vs 2.9%, 19.4% vs 11.4%, respectively). In contrast, rates of orthostatic hypocapnia were significantly higher in CFS than in controls (20.6% vs 2.9%, p < .02). This CFS group reported significantly more feelings of illness and shortness of breath than either controls or CFS patients with normal physiological tests.

Conclusion

A substantial number of CFS patients have orthostatic intolerance in the form of orthostatic hypocapnia. This allows subgrouping of patients with CFS and thus reduces patient pool heterogeneity engendered by use of a clinical case definition.

     

Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer images

Background

Efficient computational recognition and segmentation of target organ from medical images are foundational in diagnosis and treatment, especially about pancreas cancer. In practice, the diversity in appearance of pancreas and organs in abdomen, makes detailed texture information of objects important in segmentation algorithm. According to our observations, however, the structures of previous networks, such as the Richer Feature Convolutional Network (RCF), are too coarse to segment the object (pancreas) accurately, especially the edge.

Method

In this paper, we extend the RCF, proposed to the field of edge detection, for the challenging pancreas segmentation, and put forward a novel pancreas segmentation network. By employing multi-layer up-sampling structure replacing the simple up-sampling operation in all stages, the proposed network fully considers the multi-scale detailed contexture information of object (pancreas) to perform per-pixel segmentation. Additionally, using the CT scans, we supply and train our network, thus get an effective pipeline.

Result

Working with our pipeline with multi-layer up-sampling model, we achieve better performance than RCF in the task of single object (pancreas) segmentation. Besides, combining with multi scale input, we achieve the 76.36% DSC (Dice Similarity Coefficient) value in testing data.

Conclusion

The results of our experiments show that our advanced model works better than previous networks in our dataset. On the other words, it has better ability in catching detailed contexture information. Therefore, our new single object segmentation model has practical meaning in computational automatic diagnosis.