This study aimed to develop a method for pulmonary artery and vein (PA/PV) separation in three-dimensional computed tomography (3DCT), using a dual reconstruction technique and the addition of CT images. The physical image properties of multiple reconstruction kernels (FC13; FC13 3D-Q03; FC30 3D-Q03; FC83; FC13 twofold addition; FC13 threefold addition; FC13 fourfold addition; FC13 [3D-Q03] twofold addition; FC13+FC30 (3D-Q03); FC13+FC83) were evaluated based on spatial resolution using a modulation transfer function. The lung kernel CT image (FC 83) had a high spatial resolution with a 10% modulation transfer function (0.847). The noise power spectrum of the additive CT images was measured, and the CT values for the PA/PV with and without addition were compared. The addition of CT images increased the CT values difference between the PA/PV. The PA/PV 3DCT angiography (PA/PV 3DCTA), even with a small difference in CT values, could be effectively separated using high spatial resolution kernel CT and the addition of CT images dedicated to subtraction. This novel, simple method could create PA/PV 3DCTA using a general CT scanner and 3D workstation that can be easily performed at any facility.
Rhino manometry is widely used for measuring nasal aerodynamic resistance, but its clinical use is still limited and needs further standardization. The main aim of the study is to determine the total nasal resistance and to locate the place and the reasons for nasal cavity obstruction. A scheme of modern hybrid computed Rhino manometry for functional diagnosis of upper respiratory disease is proposed. The role of the main parameters in nasal aerodynamics is described (the airflow, the pressure, different types of local resistances, and nasal respiratory energy efficiency). The hybrid approach is based on a CT study and the Rhino manometry data. The study discovers four new features in the nasal breathing graph, which help in discrimination between different types of breathing modes, and this increases the accuracy of calculating the pressure losses by 12%. Also, the method used for calculating the mucosal roughness, which used as a criterion for evaluating the airflow mode. The accuracy of the hybrid functional method in calculating the total nasal aerodynamic resistance is 30% higher than with previous methods.
Diabetes causes damage to the retinal blood vessel networks, resulting in Diabetic Retinopathy (DR). This is a serious vision-threatening condition for most diabetics. Color fundus photographs are utilized to diagnose DR, which necessitates the employment of qualified clinicians to detect the presence of lesions. It is difficult to identify DR in an automated method. Feature extraction is quite important in terms of automated sickness detection. Convolutional Neural Network (CNN) exceeds previous handcrafted feature-based image classification algorithms in terms of picture classification efficiency in the current environment. In order to improve classification accuracy, this work presents the CNN structure for extracting attributes from retinal fundus images. The output properties of CNN are given as input to different machine learning classifiers in this recommended strategy. This approach is evaluating using pictures from the EYEPACS datasets using Decision stump, J48 and Random Forest classifiers. To determine the effectiveness of a classifier, its accuracy, false positive rate (FPR), True positive Rate (TPR), precision, recall, F-measure, and Kappa-score are illustrated. The recommended feature extraction strategy paired with the Random forest classifier outperforms all other classifiers on the EYEPACS datasets, with average accuracy and Kappa-score (k-score) of 99% and 0.98 respectively.
In this paper, a time series data mining models is introduced for analysis of ECG data for prior identification of heart attacks. The ECG data sets extracted from Physionet are simulated in MATLAB. The Data used for model are preprocessed so that missing data are fulfilled. In this work cascade feedforward NN which is similar to Multilayer Perceptron (MLP) architecture is proposed along with Swarm Intelligence. A hybrid method combining cascade-Forward NN Classifier and Ant colony optimization is proposed in this paper. The swarm-based intelligence method optimizes the weight adjustment of neural network and enhances the convergence behavior. The novelty is on the optimization of the NN parameters for narrowing down the convergence with ACO implementation. Ant colony optimization is used here for choosing the optimized hidden node. The combined use of machine learning algorithm with neural network enhances the performance of the system. The performance is evaluated using parameters like True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN) respectively. The Improved accuracy of proposed Classifier model raises the speed. In addition, the proposed method uses minimum memory. The implementation was done in MATLAB tool. Real time data was used.
Brain Tumour is a one of the most threatful disease in the world. It reduces the life span of human beings. Computer vision is advantageous for human health research because it eliminates the need for human judgement to get accurate data. The most reliable and secure imaging techniques for magnetic resonance imaging are CT scans, X-rays, and MRI scans (MRI). MRI can locate tiny objects. The focus of our paper will be the many techniques for detecting brain cancer using brain MRI. Early detection of tumour and diagnosis is might essential to radiologist to initiate better treatment. MRI is a competent and speedy method of examining a brain tumour. Resonance in Magnetic Fields Imaging technology is a non-invasive technique that aids in the segmentation of brain tumour images. Deep learning algorithm delivers good outcomes in terms of reducing time consumption and precise tumour diagnosis (solution). This research proposed that a Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) Supervised Deep Learning model be used to automatically find and split brain tumours. The RNN Model outperforms the CNN Model by 98.91 percentage. These models categorize brain images as normal or pathological, and their performance was evaluated.
Facial expression recognition has been more essential in artificial machine intelligence systems in recent years. Recognizing facial expressions automatically has constantly been considered as a challenging task since people significantly vary the way of exhibiting their facial expressions. Numerous researchers established diverse approaches to analyze the facial expressions automatically but there arise few imprecision issues during facial recognition. To address such shortcomings, our proposed approach recognizes the facial expressions of humans in an effective manner. The suggested method is divided into three stages: pre-processing, feature extraction, and classification. The inputs are pre-processed at the initial stage and CNN-BO algorithm is used to extract the best feature in the feature extraction step. Then the extracted feature is provided to the classification stage where MNN-SR algorithm is employed in classifying the face expression as joyful, miserable, normal, annoyance, astonished and frightened. Also, the parameters are tuned effectively to obtain high recognition accuracy. In addition to this, the performances of the proposed approach are computed by employing three various datasets namely; CMU/VASC, Caltech faces 1999, JAFFE and XM2VTS. The performance of the proposed system is calculated and comparative analysis is made with few other existing approaches and its concluded that the proposed method provides superior performance with optimal recognition rate.
In practical radiology, early diagnosis and precise categorization of liver cancer are difficult issues. Manual segmentation is also a time-consuming process. So, utilizing various methodologies based on an embedded system, we detect liver cancer from abdominal CT images using automated liver cancer segmentation and classification. The objective is to categorize CT scan images of primary and secondary liver disease using a Back Propagation Neural Network (BPNN) classifier, which has greater accuracy than previous approaches. In this work, a newly proposed method is shown which has four phases: image preprocessing, image segmentation, extraction of the features, and classification of the liver. Level set segmentation for segmenting the liver from abdominal CT images and Practical Swarm Optimization (PSO) for the tumor segmentation. Then the features from the liver are extracted and given to the BPNN classifier to classify the liver cancer. These algorithms are implemented on the Raspberry Pi. Then it serially interfaces with the MAX3232 protocol via serial communication. The GSM 800C module is connected to the system to send SMS as primary or secondary cancer. The BPNN classification technique achieved an excellent accuracy of 97.98%. The experimental results demonstrate the efficiency of this proposed approach, which provides excellent accuracy with good results.
Segmentation of breast tumors with more accuracy using computerized methods is essential for breast cancer monitoring and quantification. Both segmentation and classification of breast tumors using a fully automated or Computer-Aided Diagnosis system poses various problems in terms of imaging properties. In this work, a new hybrid algorithm is proposed for segmentation with a two-step process. Initially, a watershed transformation is applied to separate all basins based on pixel density variation from the mass present in tumors, since it has been quite booming in the presence of tumors in all circumstances. Though this is very perceptive to tiny fluctuations in the size of the image, large numbers of areas are produced unacceptably, and the boundaries after segmentations are also quite hard. The second level set is an effective method of segmenting all types of medical images because; it easily flows with, cavities, folds, splits, and merges. To make the recognition step easier and more accurate, the result of segmentation is considered the beginning position of the curve, and the same will be used at the next step of the level set. This produces a closed, smooth, and accurately placed contour or surface. As a result, the present research uses watershed segmentation to isolate tumor regions and performs classification using Feed Forward Neural Network (FNN) to extract features for classification. Experimental results are evaluated based on performance and quality analysis. In the classification process, the study obtained an accuracy rate of 91.2% in the learning model and 71.8% in a testing model.
Markerless Augmented Reality (MAR) is a superior technology that is currently used by the medical device assembler with aid in design, assembly, disassembly and maintenance operations. The medical assembler assembles the medical equipment based on the doctors requirement, they also maintains quality and sanitation of the equipment. The major research challenges in MAR are as follows: establish automatic registration parts, find and track the orientation of parts, and lack of depth and visual features. This work proposes a rapid dual feature tracking method i.e., combination of Visual Simultaneous Localization and Mapping (SLAM) and Matched Pairs Selection (MAPSEL). The main idea of this work is to attain high tracking accuracy using the combined method. To get a good depth image map, a Graph-Based Joint Bilateral with Sharpening Filter (GRB-JBF with SF) is proposed since depth images are noisy due to the dynamic change of environmental factors that affects tracking accuracy. Then, the best feature points are obtained for matching using Oriented Fast and Rotated Brief (ORB) as a feature detector, Fast Retina Key point with Histogram of Gradients (FREAK-HoG) as a feature descriptor, and Feature Matching using Rajsk’s distance. Finally, the virtual object is rendered based on 3D affine and projection transformation. This work computes the performance in terms of tracking accuracy, tracking time, and rotation error for different distances using MATLAB R2017b. From the observed results, it is perceived that the proposed method attained the least position error value about 0.1 cm to 0.3 cm. Also, rotation error is observed as minimal between 2.40 (Deg) to 3.10 and its average scale is observed as 2.7140. Further, the proposed combination consumes less time against frames compared with other combinations and obtained a higher tracking accuracy of about 95.14% for 180 tracked points. The witnessed outcomes from the proposed scheme display superior performance compared with existing methods.
Cardiovascular disease (CVD) is most dreadful disease that results in fatal-threats like heart attacks. Accurate disease prediction is very essential and machine-learning techniques contribute a major part in predicting occurrence. In this paper, a novel machine learning based model for accurate prediction of cardiovascular disease is developed that applies unique feature selection technique called Chronic Fatigue Syndrome Best Known Method (CFSBKM). Each feature is ranked based on the feature importance scores. The new learning model eliminates the most irrelevant and low importance features from the datasets thereby resulting in the robust heart disease risk prediction model. The multi-nominal Naive Bayes classifier is used for the classification. The performance of the CFSBKM model is evaluated using the Benchmark dataset Cleveland dataset from UCI repository and the proposed models out-perform the existing techniques.
As medical image processing research has progressed, image fusion has emerged as a realistic solution, automatically extracting relevant data from many images before fusing them into a single, unified image. Medical imaging techniques, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), etc., play a crucial role in the diagnosis and classification of brain tumors (BT). A single imaging technique is not sufficient for correct diagnosis of the disease. In case the scans are ambiguous, it can lead doctors to incorrect diagnoses, which can be unsafe to the patient. The solution to this problem is fusing images from different scans containing complementary information to generate accurate images with minimum uncertainty. This research presents a novel method for the automated identification and classification of brain tumors using multi-modal deep learning (AMDL-BTDC). The proposed AMDL-BTDC model initially performs image pre-processing using bilateral filtering (BF) technique. Next, feature vectors are generated using a pair of pre-trained deep learning models called EfficientNet and SqueezeNet. Slime Mold Algorithm is used to acquire the DL models’ optimal hyperparameter settings (SMA). In the end, an autoencoder (AE) model is used for BT classification once features have been fused. The suggested model’s superior performance over other techniques under diverse measures was validated by extensive testing on the benchmark medical imaging dataset.
Early detection of cataract is considered as an important solution to prevent vision loss. An automatic detection of cataract is proposed in this work with the help of histogram approach. In the beginning, noises occur in an image which is also referred to as impulse noise. To eliminate this noise a non-linear type of median filter is matched especially for the morphological filter. These filtering methods help to extract the content of the image by edge detection and segmentation. The quality of the image is evaluated the image enhancing can be obtained by a histogram approach. A normalization method can be used to enhance the image which is also called Contrast stretching. To make morphological functions effective a top-hat filter is used to segment the cataract part in the given image. Nakagami distributions are usually used for extracting required important information of ultrasound details by matching histograms from the radio frequency signals. The extracted information from the Nakagami distribution is obtained by parameter values. The recent techniques used to improve the given image quality in histogram modification method are done by Intentional Camera Movement (ICM) and Unintentional Camera Movement (UCM) to recognize the real image more precisely. In the proposed method the result shows the noise reduction and a better contrast in the output image through parameters values such as Mean Squared Error (MSE) obtained as 17.23 and Peak-Signal-to-Noise Ratio (PSNR) obtained as 35.8.
Diabetic Retinopathy (DR) is a complicated disease of diabetes, which specifically affects the retina. The human-intensive analysis mechanism of DR infected retina are likely to diagnose wrongly compared to computer-intensive diagnosis systems. In this paper, in order to aid the computer based approach for the diagnosis of DR, a model based on machine learning algorithm is proposed. The nucleotides of the human retina are processed with the help of signal processing methodologies. A speed efficient Fast Fourier transform is proposed to work out the FFT of huge amount of samples with higher pace. The improvement in speed is achieved in 98% of the samples. The prediction parameters, derived from these samples are utilized to classify the healthy retina sequence and an infected retina. In this study, Fine Tree, KNN Fine, Weighted KNN, Ensemble Bagged Trees and Ensemble Subspace KNN classifiers are employed to build the models. The simulated results using MATLAB software show that the accuracy is 98% which is better than image processing based methods which were used earlier. The performance parameters such as sensitivity and specificity are determined for each model. The faithfulness of the model is studied by deriving the ROC Curve.
Diabetic Retinopathy (DR) is a critical abnormality in the retina mainly caused by diabetes. The early diagnosis of DR is essential to avoid painless blindness. The conventional DR diagnosis is manual and requires skilled Ophthalmologists. The Ophthalmologist’s analyses are subjective to inconsistency and record maintenance issues. Hence, there is a need for other DR diagnosis methods. In this paper, we proposed an AdaBoost algorithm-based ensemble classification approach to classify DR grades. The major objective of the proposed approach is an enhancement of DR classification performance by using optimized features and ensemble machine learning techniques. The proposed method classifies different grades of DR using the Meyer wavelet and retinal vessel-based features extracted from multiple regions of interest of the retina. To improve the predictive accuracy, we used a Bayesian algorithm to optimize the hyper-parameters of the proposed ensemble classifier. The proposed DR grading model was constructed and evaluated by using the MESSIDOR fundus image dataset. In evaluation experiment, the classification outcome of the proposed approach was evaluated by the confusion matrix and receiver operating characteristic (ROC) based metrics. The evaluation experiments show that the proposed approach attained 99.2% precision, 98.2% recall, 99% accuracy, and 0.99 AUC. The experimental findings also indicate that the proposed approach’s classification outcome is significantly better than that of state of art DR classification methods.
Ventricular Segmentation or Delineation of Cardiac Magnetic Resonance Imaging (CMRI) is significant in obtaining the cardiac contractile function, which in turn is taken as input for diagnosing Cardio Vascular Diseases (CVD). Many automatic and semi-automatic methods were evolved to meet the constraints of diagnosing CVDs. Among these, semi-automatic methods require user intervention for delineation of ventricles, which consumes time and leads to intra and inter-observability, as with manual delineation. Thus, the automatic method is suggested by most of the researchers to address the above-stated problem. We proposed Saliency-based Active contour U-Net (SACU-Net) for automatic bi-ventricular segmentation which is found to surpass the existing highest developed methods regarding closeness to the gold standard. Three schemes are used by our proposed algorithm, namely 1. Saliency Detection Scheme for Region of Interest (ROI) Localization to concentrate only on Object of Interest, 2. Drop-out embedded U-net for Initial Contour evolution that performs initial segmentation and 3. Local-Global-based Regional active Contour (LGRAC) to fine-tune and avoid leaking, merging of ventricles during Delineation. We used three datasets namely Automatic Cardiac Diagnosing Challenge (ACDC) of MICCAI 2017, Right Ventricular Segmentation Challenge (RVSC) of MICCAI 2012, and Sunny Brook (SB) of MICCAI 2009 dataset to test the adaptability nature of our algorithm over different scanner resolutions and protocols. 100 and 50 CMRI Images of ACDC were used for training and testing respectively which obtained average Dice Coefficient (DC) metric of 0.963, 0.934, and 0.948 for Left Ventricular Cavity (LVC), Left Ventricular Myocardium (LVM), and Right Ventricular Cavity (RVC) respectively. 32 and 16 CMRI Images of RVSC are used for preparing and experimenting respectively, which obtained an average DC metric of 0.95 for RVC.30 and 15 CMRI Images of SB are used for preparing and experimenting respectively, which obtained average DC metric of 0.96 and 0.97 for LVC and LVM, respectively. Hausdorff Distance (HD) Metrics are also calculated to learn the distance of proposed delineated ventricles to reach the gold standard. The above resultant metrics show the robustness of our proposed SACU-Net in the segmentation of ventricles of CMRI than previous methods.
Background : Alzheimer’s disease (AD) is the primary reason for health problem. Motivation : Being degenerative and progressive with brain cells that can be intervened by health professionals in case of early recognition. Feature extraction is a technique employed for reduction of dimensionality. The features are generated for a image. The extraction of features has to be done accurately without any loss of information. Methods : In this work, a Cuckoo Search (CS) based Wavelet Filter Bank Selection algorithm for classification of Alzheimer’s has been proposed. The Ada Boost classifier, Random Forest (RF), and Classification and Regression Tree (CART) were used for the identification of the affected patient with Magnetic Resonance Imaging (MRI). Results : From results it can be found that proposed CS-based technique is used in classifying AD compared to conventional techniques.
Brain tumors have to be predicted earlier to avoid the risk of being mortal. For an effective detection an adaptive segmentation with two-tier tumors region extraction is needed. This framework offers preprocessing to avoid noise occurrence by fusing median and wiener filter also utilizes adaptive pillar C-means algorithm for obtaining the essential feature set thus the processing time is reduced. Thus the attained essential feature sets are then classified by means of unswerving PNN (Probabilistic Neural network) classifier where classification is done twice initially to classify whether benign or malignant, Sub sequently to classify different sorts of brain tumor such as Astrocytoma, Meningioma, Glioblastoma and Medulloblastoma. Since the non-linearity of PNN due to distance factor consumes more computation time which is tackled by intruding the radial basis function resulted in LS-SVM (Least Square-Support Vector Machine) as a distance factor which is linear one. Thus computation time is further reduced.
One of the major complicated issues for extensive term diabetic aspirant is diabetic retinopathy (DR) which is an eye retinal syndrome, leads to blindness. The presence of exudates detects the disease, which can be prevented in the early stages by regular screening. Exudates can be automatically detected through inspecting digital retinal image. To detect the exudates for diagnosis the author proposed an algorithm called K-means Kernel support vector machine Radial basis function (KKR) approach, by the following main stages: extracting vessel and removal of optic disc followed by pre-processing, exudates detection and post processing. Wavelet dependent edge enhancement is used for dark portion separation of exudates in the retinal image by optically designed Wideband bandpass filter. Wavelet toolbox of MATLAB 2018a is used in this KKR algorithm. Statistical and structural texture features can be obtained using K-means segmentation process by integrating Local Binary Pattern (LBP) with Region Of Interest (ROI). Some features are selected and used Neural Network along with Radial Basis Function (RBF) to classify further. The KKR algorithm uses 80 fundus images from DIARETDB1 database and parameters are analyzed such as specificity, sensitivity and accuracy. The results obtained from proposed KKR algorithm have specificity of 81.57%, sensitivity of 87.56% and accuracy of 97.94% respectively.
This article presents a new extension of the type I half-logistic inverse Weibull distribution. It is used as a base line to construct a new bivariate model that is called bivariate extended type I half-logistic inverse Weibull model. Statistical properties of the proposed distributions are derived in explicit forms. Maximum likelihood estimators are discussed. Simulation is employed to discuss theoretical properties, to investigate the performance of the new models and to elaborate the goodness of fit. The new models are applied to real data sets.
The establishment of a scientific and complete intelligent medical information analysis application model is of great significance to promote the application of intelligent medical information. Aiming at the deficiencies of Artificial Fish School Algorithm (AFSA) in iterative convergence speed, low optimization accuracy, and Particle Swarm Optimization (PSO) algorithm easily falling into local extremes, this paper combines AFSA and PSO algorithms. We use the fast local convergence ability of the PSO algorithm to overcome the shortcomings of the AFSA algorithm’s low solution accuracy and slow convergence speed. In the classification stage, we try to apply machine learning technology to classify the labeled feature vectors, evaluate and analyze the performance of these two machine learning algorithms in intelligent medical diagnosis auxiliary applications, and use today’s popular deep learning classification methods (i.e., intelligently optimized text classification model) and machine learning classification method to compare the classification effect, evaluate and analyze the applicability of the classification model in the auxiliary application of intelligent medical diagnosis. The experimental results show that the accuracy rate of applying the machine learning method to the judgment of the type of disease reaches more than 90%, which is fully in line with the disease judgment of the patient.
