Medical Analysis Applications Research Articles

Confidence Calibration of a Medical Imaging Classification System That is Robust to Label Noise.

A classification model is calibrated if its predicted probabilities of outcomes reflect their accuracy. Calibrating neural networks is critical in medical analysis applications where clinical decisions rely upon the predicted probabilities. Most calibration procedures, such as temperature scaling, operate as a post processing step by using holdout validation data. In practice, it is difficult to collect medical image data with correct labels due to the complexity of the medical data and the considerable variability across experts. This study presents a network calibration procedure that is robust to label noise. We draw on the fact that the confusion matrix of the noisy labels can be expressed as the matrix product between the confusion matrix of the clean labels and the label noises. The method is based on estimating the noise level as part of a noise-robust training method. The noise level is then used to estimate the network accuracy required by the calibration procedure. We show that despite the unreliable labels, we can still achieve calibration results that are on a par with the results of a calibration procedure using data with reliable labels.

Cost-Effective Droplet Generator for Portable Bio-Applications.

The convenient division of aqueous samples into droplets is necessary for many biochemical and medical analysis applications. In this article, we propose the design of a cost-effective droplet generator for potential bio-chemical application, featuring two symmetric tubes. The new droplet generator revisits the relationship between capillary components and liquid flow rates. The size of generated droplets by prototype depends only on generator dimensions, without precisely needing to control external flow conditions or driving pressure, even when the relative extreme difference in flow rate for generating nL level droplets is over 57.79%, and the relative standard deviation (RSD) of the volume of droplets is barely about 9.80%. A dropper working as a pressure resource is used to verify the rapidity and robustness of this principle of droplet generation, which shows great potential for a wide range of droplet-based applications.

Fluid control with hydrophobic pillars in paper-based microfluidics

Paper-based microfluidics has been widely used in chemical and medical analysis applications. In the conventional paper-based microfluidic approach, fluid is propagating inside the porous structure, and the flow direction of the fluid propagation is usually controlled with the pre-defined hydrophobic barrier (e.g. wax). However, the fluid propagation velocity inside the paper-based microfluidic devices largely depends on the material properties of paper and fluid, the relative control method is rarely reported. In this study, a fluid propagation velocity control method is proposed for paper-based microfluidics: hydrophobic pillar arrays with different configurations were deposited in the microchannels in paper-based microfluidics for flow speed control, the result indicates the deposited hydrophobic pillar arrays can effectively slow down the fluid propagation at different levels and can be used to passively control the fluid propagation inside microchannels for paper-based microfluidics. For the demonstration of the proposed fluid control methods, a paper-based microfluidic device for nitrite test in water was also fabricated. The proposed fluid control method for paper-based microfluidics may have significant importance for applications that involve sequenced reactions and more actuate fluid manipulation.

An Advanced Arithmetic Approach to GTIFNs and Its Application in Medical Analysis

Intuitionistic fuzzy set (IFS) is the straight simplification of fuzzy set theory (FST). Nevertheless, estimation of the arithmetic operation on generalized intuitionistic fuzzy number (GIFNs) is a critical apprehension. This paper presents an attempt to set up a novel method for effectively resolving the drawbacks of conform arithmetic operations on generalized triangular intuitionistic fuzzy numbers (GTIFNs). For this purpose, decomposition theorems for generalized trapezoidal intuitionistic fuzzy numbers (GTrFNs) are studied. Numerical examples are illustrated herewith. Finally, to validate the requirement of a novel elucidation, an application in medical analysis has been carried out under this setting.

Biomedical Image Denoising Based on Hybrid Optimization Algorithm and Sequential Filters.

Background: Nowadays, image de-noising plays a very important role in medical analysis applications and pre-processing step. Many filters were designed for image processing, assuming a specific noise distribution, so the images which are acquired by different medical imaging modalities must be out of the noise.Objectives: This study has focused on the sequence filters which are selected by a hybrid genetic algorithm and particle swarm optimizationMaterial and Methods: In this analytical study, we have applied the composite of different types of noise such as salt and pepper noise, speckle noise and Gaussian noise to images to make them noisy. The Median, Max and Min filters, Gaussian filter, Average filter, Unsharp filter, Wiener filter, Log filter and Sigma filter, are the nine filters that were used in this study for the denoising of medical images as digital imaging and communications in medicine (DICOM) format.Results: The model has been implemented on medical noisy images and the performances have been determined by the statistical analyses such as peak signal to noise ratio (PSNR), Root Mean Square error (RMSE) and Structural similarity (SSIM) index. The PSNR values were obtained between 59 to 63 and 63 to 65 for MRI and CT images. Also, the RMSE values were obtained between 36 to 47 and 12 to 20 for MRI and CT images.Conclusion: The proposed denoising algorithm showed the significantly increment of visual quality of the images and the statistical assessment

An Efficient MRI Brain Image Registration and Wavelet Based Fusion

Over last few decades, 3D reconstruction of medical images becomes advance technique in medical image processing. Reconstruction of 2D images of such data sets into 3D volumes, via registration of 2D sections had become a most interesting topic. In current years, MRI has been used for many medical analysis applications. The proposed system considered MRI images are taken from the same view, different times or acquired by different imaging modalities to increase the information. T1, T2 and PD MRI are taken as an input; T2 image is registered with a reference of T1 image using affine transformation, the registered T2 image is fused with T1 using DWT. The Fused T1T2 image is taken as reference image to register PD image using B-Spline transformation. DT-CWT technique is used to fuse the T1T2 image with registered PD image. The performance of the system shows that the proposed system gives more information by fusing T1T2PD images.

Jensen-Tsalli’s Intuitionistic Fuzzy Divergence Measure and Its Applications in Medical Analysis and Pattern Recognition

Vagueness in scientific studies poses a challenge. Intuitionistic Fuzzy Set (IFS) theory has emerged as a powerful and flexible tool to counter such challenge. So, there is a need to develop such measures which can not only measure the vagueness but also quantify the differences in underlying IFSs. The aim of this communication is to introduce one such divergence measure called Intuitionistic Fuzzy Jensen-Tsalli Divergence measure in the settings of IFS theory. The presence of parameters makes the proposed divergence measure flexible and competent for applications. Besides discussing some of its major properties, the findings are applied in pattern recognition problem and in medical diagnosis of some diseases with same set of symptoms. The performance of the proposed measure is genuinely compared with some other existing measures in literature through numerical examples based on medical diagnosis and pattern recognition.

Research in Clustering Algorithm for Diseases Analysis

The clustering algorithm play s a very important role in the applications of medical analysis, it can effective analysis the log of disease. It can accurately analyze the characteristics of various diseases, thus providing accurate basis for the doctor's diagnosis. In this paper, we will analysis the cluster algorithm--Fuzzy C-Means Algorithm (FCM). The traditional FCM is liable to trap into the problem of local optimum. We propose an improved algorithm of FCM based on the smooth technology. It will consider the sample points in different positions have different effects on cluster and cluster number has a great influence on the clustering results , so the new algorithm combines the point density and the method of determining the optimal number of clusters , finally use the effective evaluation function to evaluate the effective of the algorithm. Finally, we will use the case of Parkinson's disease to do the experimental verification, the results showed that the new clustering algorithms have better clustering effect, and it can more accurate analysis the characteristics of the disease, and it is using in some applications