Medical Imaging Detection Research Articles

Design of broadband impedance-matching Bessel lens with acoustic metamaterials

In this paper, a gradient-index lens is designed to implement an acoustic Bessel beam. Here, the wave from the point source is reshaped to the Bessel beam with the energy concentrated near the axial direction and almost no divergence. The two-dimensional distribution of the gradient refractive index is obtained based on the analysis of the impedance matching theory. The interface reflection is reduced significantly due to the impedance matching with air. The effect of the acoustic Bessel lens is found to work in a broadband with the use of the subwavelength unit cell and the finite-element simulations. Our results may provide the potential applications for medical ultrasound imaging and signal detection.

Development of a technology for the fabrication of Low-Gain Avalanche Diodes at BNL

Low-Gain Avalanche Detectors are gathering interest in the High-Energy Physics community thanks to their fast-timing and radiation-hardness properties, which are planned to be exploited, for example, in timing detectors for the upgrades of the ATLAS and CMS detectors at the High Luminosity LHC. This new technology has also raised interest for its possible application for photon detection in medical physics, imaging and photon science. The main characteristic of this type of device is a thin and highly-doped layer that provides internal and moderate gain, in the order of 10-20, that enhances the signal amplitude. Furthermore, the thin substrate of a few tens of microns allows fast carrier collection. This paper details on the fabrication technology, specifically developed at Brookhaven National Laboratory for the detection of minimum ionizing particles. The static electrical characterization and the gain measurements on prototypes will be reported, too.

Direct detection of high intensity X-ray fluxes with silicon photomultipliers

Silicon Photomultipliers (SiPM) are photodetectors optimized for the detection of infrared to ultraviolet photons and employed in a wide range of fast timing applications for medical imaging and particle detectors. SiPMs are used to detect the passage of ionizing radiation into matter via the collection of secondary photons emitted by the radiator material. In this work, we have investigated the possibility to detect high intensity X-ray fluxes using the DC current produced by SiPMs exposed directly to the X-ray beam, in absence of any passive converter material, to demonstrate the possibility to measure intense radiation fluxes without saturation of the SiPM response. In our application, the signal-to-noise ratio of the SiPM current during the direct exposition to X-rays is typically larger than 100, providing a robust indication of a positive detection. We show that, for a wide range of operational parameters and X-ray flux intensities, the SiPM current can be correlated to the X-ray beam intensity using a parametrization that describes the data with an accuracy of the order or better than 1%. We also show that the SiPM signal current to dark current ratio is maximum for hundreds of mV above the breakdown voltage, with a weak dependence on temperature. These results open the prospects for interesting applications for monitoring intense X-ray beams, for example beam spatial profiling, and possibly real time dosimetry both in medical and industrial applications.

Probability analysis for grasp planning facing the field of medical robotics

Medical surgical robot is a fusion of medical image information matching fusion technology and robotic trajectory control technology. The medical image information matching fusion is to obtain two images of a certain range of the patient’s body by two cameras on the robot, and after matching fusion processing, an image is obtained. At present, surgical robots have been successfully applied in minimally invasive surgery such as pelvic organ prolapse, defects and other basin basement reconstruction operations. Previously, most of the robots used in medical surgery have only one arm, but with the development of robotics related fields, multi-fingered robots with binocular stereo vision become possible in completing complex minimally invasive surgery. This paper aims to promote the further integration of multi-fingered manipulator and medical image detection, focusing on the grasping probability of multi-fingered manipulator. When the three-dimensional information of the object is incomplete, the machine learning method performs better than the hard coding method in the object grasping point planning. At present, most known methods can obtain classification results but could not give the probability of this category. Aiming at the problem of grab point planning, this paper proposes a crawling planning method based on big data Gaussian process classification. In this paper, a planner based on Gaussian process classification is designed, and the hyper constant used in the Gaussian process to judge the probability of capture is calculated. Based on the determined crawling scheme, the feasibility distribution map of the grab points which obtained by the trained Gaussian process classifier is drawn in MATLAB. The results show that the trained Gaussian process classifier is biased towards the center of the object which is the point with high stability. This method can give classification results and corresponding probabilities, which represents the feasibility of grasping points.

Recurrent residual U-Net for medical image segmentation.

Deep learning (DL)-based semantic segmentation methods have been providing state-of-the-art performance in the past few years. More specifically, these techniques have been successfully applied in medical image classification, segmentation, and detection tasks. One DL technique, U-Net, has become one of the most popular for these applications. We propose a recurrent U-Net model and a recurrent residual U-Net model, which are named RU-Net and R2U-Net, respectively. The proposed models utilize the power of U-Net, residual networks, and recurrent convolutional neural networks. There are several advantages to using these proposed architectures for segmentation tasks. First, a residual unit helps when training deep architectures. Second, feature accumulation with recurrent residual convolutional layers ensures better feature representation for segmentation tasks. Third, it allows us to design better U-Net architectures with the same number of network parameters with better performance for medical image segmentation. The proposed models are tested on three benchmark datasets, such as blood vessel segmentation in retinal images, skin cancer segmentation, and lung lesion segmentation. The experimental results show superior performance on segmentation tasks compared to equivalent models, including a variant of a fully connected convolutional neural network called SegNet, U-Net, and residual U-Net.

Computer-assisted medical image classification for early diagnosis of oral cancer employing deep learning algorithm.

Oral cancer is a complex wide spread cancer, which has high severity. Using advanced technology and deep learning algorithm early detection and classification are made possible. Medical imaging technique, computer-aided diagnosis and detection can make potential changes in cancer treatment. In this research work, we have developed a deep learning algorithm for automated, computer-aided oral cancer detecting system by investigating patient hyperspectral images. To validate the proposed regression-based partitioned deep learning algorithm, we compare the performance with other techniques by its classification accuracy, specificity, and sensitivity. For the accurate medical image classification objective, we demonstrate a new structure of partitioned deep Convolution Neural Network (CNN) with two partitioned layers for labeling and classify by labeling region of interest in multidimensional hyperspectral image. The performance of the partitioned deep CNN was verified by classification accuracy. We have obtained classification accuracy of 91.4% with sensitivity 0.94 and a specificity of 0.91 for 100 image data sets training for task classification of cancerous tumor with benign and for task classification of cancerous tumor with normal tissue accuracy of 94.5% for 500 training patterns was obtained. We compared the obtained results from another traditional medical image classification algorithm. From the obtained result, we identify that the quality of diagnosis is increased by proposed regression-based partitioned CNN learning algorithm for a complex medical image of oral cancer diagnosis.

Evaluation of solid-state detectors in medical imaging with fuzzy PROMETHEE

Solid-state semiconductor detectors are radiation detectors which employs a semiconductor material as the detecting medium. These detectors produce pulse of electric current by means of pairs of charge carriers, electrons and holes, generated when the detectors come in contact with ionizing radiation. The type of semiconducting material used in the detectors determines the number of paired charge carriers generated, which is a very important parameter that affects the performance of the device. Other parameters to be considered in determining the performance of the solid-state detectors include energy resolution, atomic number, and density. The trend in development of new cameras for nuclear medicine applications is the principal reason behind the extensive research into detectors with superb spatial resolution. Semiconductor based detectors have received much attention due to their high energy and intrinsic spatial resolution, various types of such detectors exist, of which no study has categorically provided the “best” amongst the existing detectors. Fuzzy (Preference Ranking Organization Method for Enrichment Evaluations) PROMETHEE is a multi-criterion decision-making method (MCDM) that has been applied in many fields to solve selection problems involving multiple criteria. We applied this MCDM technique in order to evaluate the various semiconductor based detectors using their distinct physical parameters. Evaluation results showed that Cadmium Telluride, Cadmium Zinc Telluride, and Thallium Bromide are among the most suitable detector materials for high-sensitivity and high-resolution nuclear medicine devices. By using fuzzy PROMETHEE, one can determine the most suitable material based on the selected criteria and defined weight according to desired application.

S-UNet: A Bridge-Style U-Net Framework With a Saliency Mechanism for Retinal Vessel Segmentation

Deep learning methods have been successfully applied in medical image classification, segmentation and detection tasks. The U-Net architecture has been widely applied for these tasks. In this paper, we propose a U-Net variant for improved vessel segmentation in retinal fundus images. Firstly, we design a minimal U-Net (Mi-UNet) architecture, which drastically reduces the parameter count to 0.07M compared to 31.03M for the conventional U-Net. Moreover, based on Mi-UNet, we propose Salient U-Net (S-UNet), a bridge-style U-Net architecture with a saliency mechanism and with only 0.21M parameters. S-UNet uses a cascading technique that employs the foreground features of one net block as the foreground attention information of the next net block. This cascading leads to enhanced input images, inheritance of the learning experience of previous net blocks, and hence effective solution of the data imbalance problem. S-UNet was tested on two benchmark datasets, DRIVE and CHASE_DB1, with image sizes of 584 × 565 and 960 × 999, respectively. S-UNet was tested on the TONGREN clinical dataset with image sizes of 1880 × 2816. The experimental results show superior performance in comparison to other state-of-theart methods. Especially, for whole-image input from the DRIVE dataset, S-UNet achieved a Matthews correlation coefficient (MCC), an area under curve (AUC), and an F1 score of 0.8055, 0.9821, and 0.8303, respectively. The corresponding scores for the CHASE_DB1 dataset were 0.8065, 0.9867, and 0.8242, respectively. Moreover, our model shows an excellent performance on the TONGREN clinical dataset. In addition, S-UNet segments images of low, medium, and high resolutions in just 33ms, 91ms and 0.49s, respectively. This shows the real-time applicability of the proposed model.

Novel Method for Lung Tumour Detection Using Wavelet Shrinkage-based Double Classifier Analysis

Medical image detection and classification play an important role in medical research. Tumour detection is a process of crucial importance in oncology. The aim of this paper is to devise an approach for efficient image enhancement, tumour detection, and classification on computed tomographic lung images. Three different application-related methods on computed tomography (CT) images have been designed and implemented in this work. The first method, which was based on image quality, enhances the performance of the medical images. Generally, the CT images are very sensitive to noise and are difficult to handle. Proper care may be taken by introducing some preprocessing algorithms like enhancement algorithms and filters. According to this, an image enhancement algorithm, Wavelet Shrinkage adaptive histogram Equalization (WSAHE), with anisotropic diffusion filter (ADF) was introduced to improve the contrast of the CT images and denoising. In the second method Seed Region growing with Random walk segmentation algorithm (SRGWRWS) is proposed for lung tumour segmentation. In the third method GLCM features, FOS features, structural features, and combinational features are calculated from the segmented lung images. After segmentation, the tumour classification is done by Multi-class support vector machine (MCSVM) and Descend RUSBOOST classifiers. Here, MCSVM classifier was used to find whether the input CT tumour image is suspicious, benign or malignant. Overall accuracy of 92% is obtained using Descend RUSBOOST classifier with GLCM features, FOS features, structural features, combinational features and overall accuracy of 97% is obtained using MCSVM classifier with GLCM feature in MATLAB 2017a software.

Applications of generative adversarial networks in medical image processing

In recent years, researchers have introduced various methods in many domains into medical image processing so that its effectiveness and efficiency can be improved to some extent. The applications of generative adversarial networks (GAN) in medical image processing are evolving very fast. In this paper, the state of the art in this area has been reviewed. Firstly, the basic concepts of the GAN were introduced. And then, from the perspectives of the medical image denoising, detection, segmentation, synthesis, reconstruction and classification, the applications of the GAN were summarized. Finally, prospects for further research in this area were presented.

Abstract ID: 368 Imaging radiologico a contrasto di fase e a conteggio fotonico

An introduction to novel imaging modalities, which take advantage of energy and phase characteristics of X-ray quanta will be here provided. X-ray detection in medical imaging typically involves an integration of the spectrum of X-rays exiting a patient, weighted by the detector’s energy response. This procedure yields information related to the average energy of the spectrum exiting the patient, which for many clinical applications is sufficient. The spectral imaging methods allow instead the form, or shape, of the X-ray distribution exiting the patient to be measured [1]. In particular, energy-sensitive photon-counting detectors allow for further improvements of the diagnostic information by optimising the signal-to-noise ratio, anatomical background subtraction or quantitative analysis of object constituents [2]. Phase-contrast imaging has had an undeniable impact in the field of X-ray imaging during the last decades, and one of the main advantages lies in the fact that the phase shifting effects are related to characteristic properties of materials that are different from the ones involved in conventional X-ray imaging (i.e. the well-known absorption-contrast imaging) [3]. The mechanism that allows one to produce and to detect images according to this physical phenomenon will be here discussed, together with a review of main phase-contrast imaging techniques. Finally, the potential of both phase-contrast and spectral imaging in diagnostic radiology will be presented by means of specific applications.

Two-stage laser-driven plasma acceleration with external injection for EuPRAXIA

The EuPRAXIA (European Particle Research Accelerator with excellence In Applications) project aims at producing a conceptual design for the worldwide plasma-based accelerator facility, capable of delivering multi-GeV electron beams with high quality. This accelerator facility will be used for various user applications such as compact X-ray sources for medical imaging and high-energy physics detector tests. EuPRAXIA explores different approaches to plasma acceleration techniques. Laser-driven plasma wakefield acceleration with external injection of an RF-generated electron beam is one of the basic research directions of EuPRAXIA. We present studies of electron beam acceleration to GeV energies by a two-stage laser wakefield acceleration with external injection from an RF accelerator. Electron beam injection, acceleration and extraction from the plasma, using particle-in-cell simulations, are investigated.

Ontology-Based Approach for Liver Cancer Diagnosis and Treatment

Liver cancer is the third deadliest cancer in the world. It characterizes a malignant tumor that develops through liver cells. The hepatocellular carcinoma (HCC) is one of these tumors. Hepatic primary cancer is the leading cause of cancer deaths. This article deals with the diagnostic process of liver cancers. In order to analyze a large mass of medical data, ontologies are effective; they are efficient to improve medical image analysis used to detect different tumors and other liver lesions. We are interested in the HCC. Hence, the main purpose of this paper is to offer a new ontology-based approach modeling HCC tumors by focusing on two major aspects: the first focuses on tumor detection in medical imaging, and the second focuses on its staging by applying different classification systems. We implemented our approach in Java using Jena API. Also, we developed a prototype OntHCC by the use of semantic aspects and reasoning rules to validate our work. To show the efficiency of our work, we tested the proposed approach on real datasets. The obtained results have showed a reliable system with high accuracies of recall (76%), precision (85%), and F-measure (80%).

SVM Pixel Classification on Colour Image Segmentation

The aim of image segmentation is to simplify the representation of an image with the help of cluster pixels into something meaningful to analyze. Segmentation is typically used to locate boundaries and curves in an image, precisely to label every pixel in an image to give each pixel an independent identity. SVM pixel classification on colour image segmentation is the topic highlighted in this paper. It holds useful application in the field of concept based image retrieval, machine vision, medical imaging and object detection. The process is accomplished step by step. At first we need to recognize the type of colour and the texture used as an input to the SVM classifier. These inputs are extracted via local spatial similarity measure model and Steerable filter also known as Gabon Filter. It is then trained by using FCM (Fuzzy C-Means). Both the pixel level information of the image and the ability of the SVM Classifier undergoes some sophisticated algorithm to form the final image. The method has a well developed segmented image and efficiency with respect to increased quality and faster processing of the segmented image compared with the other segmentation methods proposed earlier. One of the latest application result is the Light L16 camera.

Application of Deep Learning in Liver Pathological Image Diagnosis

Hepatopathy is a kind of disease with high incidence, so the progress in the field of liver disease research is highly valued. Medical image, as an important part of medical diagnosis, provides an important basis for doctors to make correct diagnosis. Pathological images play a significant role in clinical application because they can facilitate doctors to clearly observe the degree of lesions and make accurate judgments. As an important component of computer vision, deep learning has been paid more and more attention by researchers. The application of computer aided technology in medical image detection has become an important application of computer vision. In view of this situation, an automatic diagnosis method of liver pathological images based on deep learning method is proposed. We analyze the image features, then design and train the classification model. The final results confirmed that this method can effectively classify the pathological images of liver and has a high accuracy rate.

Deep Learning Applications in Medical Image Analysis

The tremendous success of machine learning algorithms at image recognition tasks in recent years intersects with a time of dramatically increased use of electronic medical records and diagnostic imaging. This review introduces the machine learning algorithms as applied to medical image analysis, focusing on convolutional neural networks, and emphasizing clinical aspects of the field. The advantage of machine learning in an era of medical big data is that significant hierarchal relationships within the data can be discovered algorithmically without laborious hand-crafting of features. We cover key research areas and applications of medical image classification, localization, detection, segmentation, and registration. We conclude by discussing research obstacles, emerging trends, and possible future directions.

Classification of materials for conducting spheroids based on the first order polarization tensor

Polarization tensor is an old terminology in mathematics and physics with many recent industrial applications including medical imaging, nondestructive testing and metal detection. In these applications, it is theoretically formulated based on the mathematical modelling either in electrics, electromagnetics or both. Generally, polarization tensor represents the perturbation in the electric or electromagnetic fields due to the presence of conducting objects and hence, it also desribes the objects. Understanding the properties of the polarization tensor is necessary and important in order to apply it. Therefore, in this study, when the conducting object is a spheroid, we show that the polarization tensor is positive-definite if and only if the conductivity of the object is greater than one. In contrast, we also prove that the polarization tensor is negative-definite if and only if the conductivity of the object is between zero and one. These features categorize the conductivity of the spheroid based on in its polarization tensor and can then help to classify the material of the spheroid.

A generalized entropy-based two-phase threshold algorithm for noisy medical image edge detection

Edge detection in medical imaging is a significant task for object recognition of human organs and it is considered a pre-processing step in medical image segmentation and reconstruction. This article proposes an efficient approach based on generalized Hill entropy to find a good solution for detecting edges under noisy conditions in medical images. The proposed algorithm uses a two-phase thresholding: firstly, a global threshold is calculated by means of generalized Hill entropy and used to separate the image into object and background. Afterwards, a local threshold value is determined for each part of the image. The final edge map image is a combination of these two separate images based on the three calculated thresholds. The performance of the proposed algorithm is compared against Canny and Tsallis entropy by using sets of medical images corrupted with various types of noise. We used Pratt’s Figure of Merit (PFOM) as a quantitative measure for an objective comparison. Experimental results indicate that the proposed algorithm displayed superior noise resilience and better edge detection than Canny and Tsallis entropy methods for the four different types of noise analyzed, and thus it can be considered as a very interesting edge detection algorithm on noisy medical images.

Fabrication and Evaluation of Bendable Phosphor Screen for Feasibility Study of Medical X-ray Imaging Detector

Fabrication and Evaluation of Bendable Phosphor Screen for Feasibility Study of Medical X-ray Imaging Detector

The current status of the Gas Electron Multiplier (GEM) research at Kasetsart University, Thailand

During the past decade, Gas Electron Multiplier (GEM) detectors have been greatly developed and utilized in numbers of applications including advanced nuclear and particle researches, medical imaging, astrophysics, and neutron detection for national security. Our GEM research group at the Department of Applied Radiation and Isotopes, Faculty of Science, Kasetsart University, Thailand, realized in its excellent properties/potentials and started extensive researches on GEM detectors. To build a strong foundation on our research group, two 10 cm × 10 cm triple GEM detectors were characterized on their important properties including absolute gains and detection uniformity. Moreover, to widen applications of the GEM detector, our group had modified the GEM detector by introducing either solid or gaseous neutron converters to the detector so that the detector could effectively detect neutrons. These modifications included coating a thin film of 10B and natB to the GEM drift cathode for thermal neutron detection and flowing a gas mixture of He/CO2 (80:20 and 70:30) and C4H10/He/CO2 (7:70:23) for fast neutron detection. Results showed that the modified GEM-based neutron detector could detect both types of neutrons with different relative efficiencies and gains depending on thicknesses and types of neutron converters. This article discusses basic knowledge of the GEM detector, construction and testing procedures, results, and discussion.