Classification Of Different Stages Research Articles

A novel dense-net deep neural network with enhanced feature selection method for classification of different stages of tuberculosis using chest X-ray images

A novel dense-net deep neural network with enhanced feature selection method for classification of different stages of tuberculosis using chest X-ray images

Self-supervised learning with self-distillation on COVID-19 medical image classification

Background and objectiveCurrently, COVID-19 is a highly infectious disease that can be clinically diagnosed based on diagnostic radiology. Deep learning is capable of mining the rich information implied in inpatient imaging data and accomplishing the classification of different stages of the disease process. However, a large amount of training data is essential to train an excellent deep-learning model. Unfortunately, due to factors such as privacy and labeling difficulties, annotated data for COVID-19 is extremely scarce, which encourages us to propose a more effective deep learning model that can effectively assist specialist physicians in COVID-19 diagnosis. MethodsIn this study,we introduce Masked Autoencoder (MAE) for pre-training and fine-tuning directly on small-scale target datasets. Based on this, we propose Self-Supervised Learning with Self-Distillation on COVID-19 medical image classification (SSSD-COVID). In addition to the reconstruction loss computation on the masked image patches, SSSD-COVID further performs self-distillation loss calculations on the latent representation of the encoder and decoder outputs. The additional loss calculation can transfer the knowledge from the global attention of the decoder to the encoder which acquires only local attention. ResultsOur model achieves 97.78 % recognition accuracy on the SARS-COV-CT dataset containing 2481 images and is further validated on the COVID-CT dataset containing 746 images, which achieves 81.76 % recognition accuracy. Further introduction of external knowledge resulted in experimental accuracies of 99.6% and 95.27 % on these two datasets, respectively. ConclusionsSSSD-COVID can obtain good results on the target dataset alone, and when external information is introduced, the performance of the model can be further improved to significantly outperform other models.Overall, the experimental results show that our method can effectively mine COVID-19 features from rare data and can assist professional physicians in decision-making to improve the efficiency of COVID-19 disease detection.

Earlier detection of rop and rop sub-classification using TA-CHD-DNN and UD-TFCM from ultrasound digital B-Scan images

The growth of the retinal blood vessels of the baby begins at 16 weeks and even after the birth of the baby, they don’t grow completely. For the effective analysis of Retinopathy of Prematurity (ROP), diverse methodologies are employed. Owing to the insufficient growth of tangled patterns, greater retinal layer thickness, and the presence of hyperreflective material, the majority of the traditional methodologies were unsuccessful in classifying the Choroidal Neovascularization (CNV), Diabetic Macular Edema (DME), and DRUSEN stages of ROP. Thus, for the classification of different stages of the ROP, an effective Twin Active- Cosine-Hausdorff Distance-Deep Neural Network (TA-CHD-DNN) is proposed in this paper. Chiefly, the image obtained from the retinal image dataset is pre-processed and fed into TA- CHD-DNN. After the extraction of critical features, the segmentation of the retinal layer, choroid layer, and vascular layer occurs in TA-CHD- DNN. The classifier is trained to make decisions for the classification of diverse stages of ROP centered on the extracted features. The normal or abnormal stages of CNV, DME, and DRUSEN are classified by the classifier during testing. By utilizing the Uniformly Distributed-Trapezoidal Fuzzy C Means (UD-TFCM) technique, the decision regarding the severity stage of CNV, DME, and DRUSEN is made in the abnormal stage. Thus, centered on the experimental outcomes, the proposed system performance will be analogized to the conventional techniques to confirm the proposed system’s efficiency.

A fuzzy membership based comparison of the grey matter (GM) in cognitively normal (CN), mild cognitive impairment (MCI), and Alzheimer’s disease (AD) using brain images

Grey matter (GM) in human brain contains most of the important cells covering the regions involved in neurophysiological operations such as memory, emotions, decision making, etc. Alzheimer’s disease (AD) is a neurological disease that kills the brain cells in regions which are mostly involved in the neurophysiological operations. Mild Cognitive Impairment (MCI) is a stage between Cognitively Normal (CN) and AD, where a significant cognitive declination can be observed. The destruction of brain cells causes a reduction in the size of GM. Evaluation of changes in GM, may help in studying the overall brain transformations and accurate classification of different stages of AD. In this work, firstly skull of brain images is stripped for 5 different slices, then segmentation of GM is performed. Finally, the average number of pixels in grey region and the average atrophy in grey pixels per year is calculated and compared amongst CN, MCI, and AD patients of various ages and genders. It is observed that, for some subjects (in some particular ages) from different dementia stages, pattern of GM changes is almost identical. To solve this issue, we have used the concept of fuzzy membership functions to classify the dementia stages more accurately. It is observed from the comparison that average difference in the number of pixels between CN and MCI= 10.01%, CN and AD= 19.63%, MCI and AD= 10.72%. It can be also observed from the comparison that, the average atrophy in grey matter per year in CN= 1.92%, MCI= 3.13%, and AD= 4.33%.

Surface-enhanced Raman spectroscopy analysis of serum samples of typhoid patients of different stages

BackgroundSurface-enhanced Raman spectroscopy (SERS) of body fluids is considered a quick, simple and easy to use method for the diagnosis of disease. ObjectivesTo evaluate rapid, reliable, and non-destructive SERS-based diagnostic tool with multivariate data analysis including principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) for classification of different stages of typhoid on the basis of characteristic SERS spectral features. MethodsSERS has been used for analysis of serum samples of different stages of typhoid including early acute stage and late acute stage in comparison with healthy samples, in order to investigate capability of this technique for diagnosis of typhoid. SERS spectral features associated with the biochemical changes taking place during the development of the typhoid fever were analyzed and identified. ResultsThe value of area under the receiver operating characteristics (AUROC) for early acute stage versus healthy is 0.87 and that for healthy versus late acute stage is 0.52. PLS-DA classifier model gives values of 100 % for accuracy, sensitivity and specificity, respectively for the SERS spectral data sets of healthy versus early acute stage. Moreover, this classifier model gives values of 91 %, 89 % and 97 % for accuracy, sensitivity and specificity, respectively for the SERS spectral data sets of healthy versus late acute stage. ConclusionsBased on preliminary work it is concluded that SERS has potential to diagnose various stages of typhoid fever including early acute and late acute stage in comparison with healthy samples.

Comparison of surface enhanced Raman spectroscopy and Raman spectroscopy for the detection of breast cancer based on serum samples

In this study, surface enhanced Raman spectroscopy (SERS) and Raman spectroscopy (RS), are employed for the classification of different stages of breast cancer using clinically diagnosed serum samples from breast cancer patients and healthy individuals. These serum samples are compared for their spectral features acquired by SERS and RS to establish spectral features that can be considered as spectral markers of breast cancer diagnosis and classification. SERS features related to DNA, proteins and lipids were observed which are solely observed in the serum samples of patients at different stages of breast cancer as compared to healthy samples. In order to explore the capability of SERS and RS and their comparison as an analytical tool for the efficient understanding of the progression of breast cancer, Principal Component Analysis (PCA) is done for the SERS and RS spectra of control, stage 2, stage 3 and stage 4. Furthermore, the Partial Least Squares-Discriminant Analysis (PLS-DA) was performed to compare the diagnostic performance of SERS and Raman spectroscopy for the classification of disease positive samples and healthy ones. The sensitivity and specificity and area under receiver operating characteristic (AUROC) curve values for SERS data were 90%, 98.4%, and 94% respectively which were higher as compared to Raman spectral data for which these values were found to be 88.2%, 97.7%, and 83.4% respectively.

Exploration of a Framework for the Identification of Chronic Kidney Disease Based on 2D Ultrasound Images: A Survey.

Chronic kidney disease (CKD) is a fatal disease that ultimately results in kidney failure. The primary threat is the aetiology of CKD. Over the years, researchers have proposed various techniques and methods to detect and diagnose the disease. The conventional method of detecting CKD is the determination of the estimated glomerular filtration rate by measuring creatinine levels in blood or urine. Conventional methods for the detection and classification of CKD are tedious; therefore, several researchers have suggested various alternative methods. Recently, the research community has shown keen interest in developing methods for the early detection of this disease using imaging modalities such as ultrasound, magnetic resonance imaging, and computed tomography. The study aimed to conduct a systematic review of various existing techniques for the detection and classification of different stages of CKD using 2D ultrasound imaging of the kidney. The review was confined to 2D ultrasound images alone, considering the feasibility of implementation even in underdeveloped countries because 2D ultrasound scans are more cost effective than other modalities. The techniques and experimentation in each work were thoroughly studied and discussed in this review. This review displayed the cutting-age research, challenges, and possibilities of further research and development in the detection and classification of CKD.

Probabilistic modeling of Diabetic Nephropathy progression.

Diabetic Nephropathy (DN) progression is stratified into several stages with different levels of proteinuria, albuminuria, and physical characteristics as observed by pathologists. These physical changes are primarily visible within a patient's glomeruli which function as filtration units for blood returning for oxygenation. As DN stage increases, it is possible to observe the thickening of the glomerular basement membrane, expansion of the mesangium, and development of nodular sclerosis. Classification of different stages of DN by pathologists is based on semi-qualitative assessments of these characteristics on an individual glomerulus basis. Being able to probabilistically infer stage membership of individual glomeruli based on a combination of easily observable and hidden image features would be an invaluable tool for furthering our understanding of the drivers of DN progression. Markov Particle filters, included in the bnlearn package in R, were used to query a Bayesian Network (BN) constructed using the structural Hill-Climbing algorithm on a set of glomerular features. These features included both traditional characteristics such as glomerular area and number of mesangial nuclei as well as more abstract features derived from Minimum Spanning Trees (MST) to quantify spatial distribution of mesangial nuclei. Our results using images from multiple institutions suggest that these abstract features exercise a variable influence on DN stage membership over the course of disease progression. Further research incorporating clinical data will give nephrologists a "white box" visual of quantitative factors present in DN patients.

Fourier transform infrared spectroscopic imaging of colon tissues: evaluating the significance of amide I and C\u2013H stretching bands in diagnostic applications with machine learning

Fourier transform infrared (FTIR) spectroscopic imaging of colon biopsy tissues in transmission combined with machine learning for the classification of different stages of colon malignancy was carried out in this study. Two different approaches, an optical and a computational one, were applied for the elimination of the scattering background during the measurements and compared with the results of the machine learning model without correction for the scattering. Several different data processing pathways were implemented in order to obtain a high accuracy of the prediction model. This study demonstrates, for the first time, that C–H stretching and amide I bands are of little to no significance in the classification of the colon malignancy, based on the Gini importance values by random forest (RF). The best prediction outcome is found when supervised RF classification was carried out in the fingerprint region of the spectral data between 1500 and 1000 cm−1 (excluding the contribution of amide I and II bands). An overall prediction accuracy higher than 90% is achieved through the RF. The results also show that dysplastic and hyperplastic tissues are well distinguished. This leads to the insight that the important differences between hyperplastic and dysplastic colon tissues lie within the fingerprint region of FTIR spectra. In this study, computational correction performed better than optical correction, but the findings show that the disease states of colon biopsies can be distinguished effectively without elimination of Mie scattering effect.Graphical abstract

Olfactory Function is Affected in Patients with Cirrhosis Depending on the Severity of Hepatic Encephalopathy

Introduction and aim. Olfactory functions are altered to a variable degree by chronic liver disease. Few studies including only small populations of patients emphasized the possibility of hepatic encephalopathy (HE) influencing olfactory nervous tasks. So far, no study has explicitly focused on olfactory function depending on the severity of HE as assessed by objective diagnostic procedures. Thus we performed a study using the “Sniffin’ Sticks” test system, critical flicker-fusion frequency (CFF) and clinical West Haven criteria.Material and methods. 54 cirrhotic patients with liver cirrhosis were included. Furthermore, 43 adult volunteers participating as a non-cirrhotic control group. Olfactory testing was performed using the “Sniffin’ Stick” test battery (Burghart Medizintechnik, Wedel, Germany) which renders a widely-used tool both in clinical and research settings for the assessment of olfactory threshold, odor identification and discrimination. Several complications of cirrhosis were diagnosed by reference methods. Statistical analysis of cirrhosis-associated complications and their relation to olfactory function was performed. Assessment of HE and classification of different stages were performed according to clinical criteria (West- Haven criteria) and according to CFF, which was determined using a portable analyzer.Results. Olfactory function was significantly reduced in cirrhotic patients (in 61.1%) compared to controls (p < 0.001). Among cirrhotics patients, the prevalence of olfactory deficits (hyposmia, anosmia) increased with the severity of HE as assessed by CFF and clinical criteria (p = 0.008 and p = 0.097, respectively). No correlation was observed between olfactory deficits and severity of liver disease as assessed by Child-Pugh-Score, etiology of cirrhosis and complications of cirrhosis such as ascites and portal venous hypertension.Conclusions. Olfactory testing serves as a screening tool for HE and may faciliate grading of HE-severity.

Assessment of the quality of brain regions and neuroimaging metrics as biomarkers of Alzheimer's Disease.

Alzheimer Disease (AD) is characterized by progressive cognitive decline and dementia. Earlier diagnosis and classification of different stages of the disease are currently the main challenges and can be assessed by neuroimaging. With this work we aim to evaluate the quality of brain regions and neuroimaging metrics as biomarkers of AD. Multimodal Imaging Brain Connectivity Analysis (MIBCA) toolbox functionalities were used to study AD by T1weighted, Diffusion Tensor Imaging and 18FAV45 PET, with data obtained from the AD Neuroimaging Initiative database, specifically 12healthy controls (CTRL) and 33 patients with early mild cognitive impairment (EMCI), late MCI (LMCI) and AD (11 patients/group). The metrics evaluated were gray-matter volume (GMV), cortical thickness (CThk), mean diffusivity (MD), fractional anisotropy (FA), fiber count (FiberConn), node degree (Deg), cluster coefficient (ClusC) and relative standard-uptake-values (rSUV). Receiver Operating Characteristic (ROC) curves were used to evaluate and compare the diagnostic accuracy of the most significant metrics and brain regions and expressed as area under the curve (AUC). Comparisons were performed between groups. The RH-Accumbens/Deg demonstrated the highest AUC when differentiating between CTRLEMCI (82%), whether rSUV presented it in several brain regions when distinguishing CTRL-LMCI (99%). Regarding CTRL-AD, highest AUC were found with LH-STG/FiberConn and RH-FP/FiberConn (~100%). A larger number of neuroimaging metrics related with cortical atrophy with AUC>70% was found in CTRL-AD in both hemispheres, while in earlier stages, cortical metrics showed in more confined areas of the temporal region and mainly in LH, indicating an increasing of the spread of cortical atrophy that is characteristic of disease progression. In CTRL-EMCI several brain regions and neuroimaging metrics presented AUC>70% with a worst result in later stages suggesting these indicators as biomarkers for an earlier stage of MCI, although further research is necessary.

Contrast-Enhanced Ultrasound in Different Stages of Pyogenic Liver Abscess

To enable sonographic classification of different stages of pyogenic liver abscesses, sonographic findings in 86 patients with 113 pyogenic liver abscesses were retrospectively analyzed and compared with established pathomorphologic descriptions of the disease. The typical findings in contrast-enhanced ultrasound were sub-segmental hyperemia (93/113, 82%) and necrosis with a hyperemic margin (109/113, 96%) in the arterial phase and a washout of liver tissue surrounding necrosis in the late phase (101/113, 89%). Four different sonomorphologic stages of pyogenic liver abscess were identified. Stage I was defined by focal inflammation without necrosis (n = 2); stage II by focal clusters of micro-abscesses appearing to coalesce (n = 41); and stage III by a single cavity with or without capsule (n = 64). Stage IV was defined as numerous small abscesses scattered all over the liver (n = 6). The results indicate that contrast-enhanced ultrasound is suitable for classifying different stages of pyogenic liver abscesses. Knowledge of the described morphologic patterns influences therapeutic decisions and helps distinguish abscesses from other liver masses.

Automatic Classification of Initial Categories of Alzheimer's Disease from Structural MRI Phase Images: A Comparison of PSVM, KNN and ANN Methods

An early and accurate detection of Alzheimer’s disease (AD) is an important stage in the treatment of individuals suffering from AD. We present an approach based on the use of structural magnetic resonance imaging (sMRI) phase images to distinguish between normal controls (NC), mild cognitive impairment (MCI) and AD patients with clinical dementia rating (CDR) of 1. Independent component analysis (ICA) technique is used for extracting useful features which form the inputs to the support vector machines (SVM), K nearest neighbour (kNN) and multilayer artificial neural network (ANN) classifiers to discriminate between the three classes. The obtained results are encouraging in terms of classification accuracy and effectively ascertain the usefulness of phase images for the classification of different stages of Alzheimer’s disease. Keywords—Biomedical image processing, classification algorithms, feature extraction, statistical learning.

The Expression Patterns and Clinical Significance of microRNAs in Liver Diseases and Hepatocellular Carcinoma

MicroRNAs (miRNAs) are approximately 22-nucleotide noncoding RNAs that constitute silencers of target gene expression and have emerged as key regulatory molecules of mammalian cell functions. Aberrant miRNA expression promotes pathologic conditions including hepatocellular carcinoma (HCC) and a variety of precancerous liver diseases, especially chronic hepatitis B and C, and liver cirrhosis. miRNAs may contribute to HCC development by acting as oncogenes or tumor suppressors. Specific alterations of miRNA expression have also been related to clinical features of HCC, such as stage, differentiation, prognosis, and response to adjuvant therapy. miRNA signatures may help define molecular profiles of liver diseases as biomarkers, and allow classification of different stages of cirrhosis and HCC progression. Either miRNAs, or anti-miRNA oligonucleotides (antagomirs) could be used for in vivo modulation of miRNA actions, and thus have significant potential in molecularly targeted therapy.

Machine learning approach for automated screening of malaria parasite using light microscopic images

The aim of this paper is to address the development of computer assisted malaria parasite characterization and classification using machine learning approach based on light microscopic images of peripheral blood smears. In doing this, microscopic image acquisition from stained slides, illumination correction and noise reduction, erythrocyte segmentation, feature extraction, feature selection and finally classification of different stages of malaria (Plasmodium vivax and Plasmodium falciparum) have been investigated. The erythrocytes are segmented using marker controlled watershed transformation and subsequently total ninety six features describing shape-size and texture of erythrocytes are extracted in respect to the parasitemia infected versus non-infected cells. Ninety four features are found to be statistically significant in discriminating six classes. Here a feature selection-cum-classification scheme has been devised by combining F-statistic, statistical learning techniques i.e., Bayesian learning and support vector machine (SVM) in order to provide the higher classification accuracy using best set of discriminating features. Results show that Bayesian approach provides the highest accuracy i.e., 84% for malaria classification by selecting 19 most significant features while SVM provides highest accuracy i.e., 83.5% with 9 most significant features. Finally, the performance of these two classifiers under feature selection framework has been compared toward malaria parasite classification.

English

There has been a steady rise in the number of patients suffering from Alzheimer's disease (AD) all over the world. Medical diagnosis is an important but complicated task that should be performed accurately and efficiently and its automation would be very useful. The patient's records are collected from National Institute on Aging, USA. The Sample consisted of initial visits of 496 subjects seen either as control or as patients. Patients were concerned about their memory at the National Institute on Aging. It also consisted of patients and caregiver interviews. This research work presents different models for the classification of different stages of Alzheimer's disease using various machine learning methods such as Neural Networks, Multilayer Perceptron, Bagging, Decision tree, CANFIS and Genetic algorithms. The classification accuracy for CANFIS was found to be 99.55% which was found to be better when compared to other classification methods. Based on the outcome of classification accuracies, various management and treatment strategies such as pharmacotherapeutic and non pharmacotherapeutic interventions for mild, moderate and severe AD were elucidated, which can be of enormous use for the medical professionals in diagnosis and treatment of AD.

Automatic identification of diabetic maculopathy stages using fundus images

Diabetes mellitus is a major cause of visual impairment and blindness. Twenty years after the onset of diabetes, almost all patients with type 1 diabetes and over 60% of patients with type 2 diabetes will have some degree of retinopathy. Prolonged diabetes retinopathy leads to maculopathy, which impairs the normal vision depending on the severity of damage of the macula. This paper presents a computer-based intelligent system for the identification of clinically significant maculopathy, non-clinically significant maculopathy and normal fundus eye images. Features are extracted from these raw fundus images which are then fed to the classifier. Our protocol uses feed-forward architecture in an artificial neural network classifier for classification of different stages. Three different kinds of eye disease conditions were tested in 350 subjects. We demonstrated a sensitivity of more than 95% for these classifiers with a specificity of 100%, and results are very promising. Our systems are ready to run clinically on large amounts of datasets.

Micromorphological studies in Dupuytren's disease

Based on histological and scan electron microscopic investigations the morphology of Dupuytren's disease was studied. For comparison normal samples from the palm of the hand were used. Because scan electron microscopy permits a three dimensional observation of surfaces, cut as well as break preparations of cases in stages II, III and IV as well as from relapse cases were furnished and examined. The findings were as follows: 1) The border between cutis and underlying tissue was not distinct any more. 2) The subcutaneous fat tissue has been thrust aside and replaced by newly formed collagen. 3) Starting from the aponeurosis thickened net-like collagen fibers stretch across into the cutis causing skin retractions 4) Within the aponeurosis palmaris collagen bundles exhibit considerable deviation in diameter and structure. 5) A classification of different stages of the disease according to morphological findings proves to be impossible.

Colorectal cancer progression correlates with upregulation of S100A11 expression in tumor tissues

Early detection and treatment of human colorectal cancers remain a challenge. Identification of new potential markers may help in the diagnosis of colorectal cancer. By comparative two-dimensional gel electrophoresis using extracts from colorectal tumor and adjacent normal tissues, we identified a calcium-binding protein, S100A11, which was highly expressed in colorectal cancer compared with adjacent normal tissues. We expanded our study in 89 clinical colorectal tumor samples to validate this finding and correlates S100A11 expression in human colorectal cancer tissues with various stages of the tumor by Western blotting and immunohistochemical staining. We identified a calcium-binding protein, S100A11, which was highly expressed in colorectal cancer compared with adjacent normal tissues. S100A protein was expressed predominantly in the cytoplasm of normal tissue; however, it was expressed in both the nuclei and cytoplasm of colorectal cancer. S100A11 level in colorectal cancer tissue was increased following stage progression of the disease. These findings suggest S100A11 could be helpful in the pathological study of colorectal cancer, especially for the classification of different stages in colorectal cancer.

MicroRNA expression profiling in cancer from a bioinformatics prospective

A new type of noncoding short single-stranded RNA molecules, microRNA (miRNA), has recently emerged as one of the most important new classes of cellular regulators. Recent advances in miRNA research have provided evidence that aberrant expression of specific miRNAs is associated with a broad spectrum of human diseases, such as cancer, diabetes, cardiovascular diseases, psychological disorders and others. Global microRNAome profiling has demonstrated drastic changes in expression of multiple miRNAs in many common human cancers. miRNA expression signatures have been shown to provide a more accurate method of classifying cancer subtypes than transcriptome profiling of an entire set of known protein-coding genes. miRNA profiling also allows classification of different stages in tumor progression and can predict disease outcome in some cases. Further characterization of these abnormal miRNA expression signatures and identification of the most significant and informative aberrantly expressed miRNAs could lead to the development of tissue- and biofluid-specific diagnostic markers, as well as a new type of oligonucleotide-based therapeutics. As researchers continue to study miRNA expression in cancer and focus on most relevant miRNAs, the further advancement of miRNA-detection technologies and bioinformatics algorithms is critical for successful identification of the most informative diagnostics markers among the tissue-specific miRNAs.