Medicine Imaging Research Articles

Ovarian Cancer Detection in MRI Images Using Feature Space and Classification Method (ABC-CNN)

The most common disease has an adverse effect on women is ovarian cancer. The female generative organ that is placed in the pelvis is similar to the size of the almond. The production of eggs for the reproduction is the part of the ovaries. Ovarian cancer mainly started from the ovaries, ovaries are the reproductive glands that mainly found in the women. The main aim of this paper is detection of the ovarian cancer and is done in stage wise manner. At every stage the cancer images are trained and cancer is detected using ABC- Convolutional Neural Network. The quality of the MRI cancer images are enhanced and selected in accordance to the performance parameters which are accuracy, error rate and processing time. The images are selected by extracting the features to increase the accuracy rate and reduce the cost and the time of the processing. The MRI cancer images are used for detection, classification and extraction algorithms. The selection of the extracted features of the medical images is done through the optimized ABC algorithm. After the extracting features in medicinal images using kernel PCA method. The selected features removes zero values and then optimized the feature vector .The classification process based on the convolutional neural network for training and testing the cancer images in each stage also detecting the quality of the cancer images. The method is evaluated using performance parameter which is signaling to noise ratio. The dataset is created by collecting the medical images from skims (sher-i-kashmir institute of Medical sciences) and Hospital Kashmir. The number of cancer images used 250. There is two kind of images used. Individual is normal image means without or cancer free images the 2nd one are malignant cancer images. Complete number of images used 250 which have 50 medical images of each dataset (Normal, Stage I, Stage II, Stage II and Stage III). The dataset pictures usually include the MRI scan image of PELVIS. The detection and selection of the images through MRI cancer images is in stage wise approach. The quality of the cancer images is improved with peak signal to noise ratio. The evaluated parameters used to increase the accuracy rate and decrease the time ofprocessing.

Preoperative Ultrasound Radiomics Signatures for Noninvasive Evaluation of Biological Characteristics of Intrahepatic Cholangiocarcinoma

The purpose of this study was to establish and validate radiomics signatures based on ultrasound (US) medicine images to assess the biological behaviors of intrahepatic cholangiocarcinoma (ICC) in a noninvasive manner. This study consisted of 128 ICC patients. We focused on evaluating six pathological features: microvascular invasion, perineural invasion, differentiation, Ki-67, vascular endothelial growth factor, and cytokeratin 7. Region of interest (ROI) of ICC was identified by manually plotting the tumor contour on the grayscale US image. We extracted radiomics features from medical US imaging. Then, dimensionality reduction methods and classifiers were used to develop radiomic signatures for evaluating six pathological features in ICC. Finally, independent validation datasets were used to assess the radiomic signatures performance. We extracted 1076 quantitative characteristic parameters on the US medicine images. Based on extracted radiomics features, the best performing radiomic signatures for evaluating microvascular invasion features were produced by hypothetical test + support vector machine (SVM), perineural invasion subgroup were least absolute shrinkage and selection operator + principal component analysis + support vector machine, differentiation subgroup were hypothetical test + decision tree, Ki-67 subgroup were hypothetical test + logistic regression, vascular endothelial growth factor subgroup were hypothetical test + Gradient Boosting Decision Tree (GBDT), and cytokeratin 7 subgroup were hypothetical test + bagging, respectively. Through the high-throughput radiomics analysis based on US medicine images, we proposed radiomics signatures that have moderate efficiency in predicting the biological behaviors of ICC noninvasively.

Web-Based GPU-Accelerated Application for Multiplanar Reconstructions from Conventional 2D Ultrasound.

In ultrasound education there is a need for interactive web-based learning resources. The purpose of this project was to develop a web-based application that enables the generation and exploration of volumetric datasets from cine loops obtained with conventional 2D ultrasound. JavaScript code for ultrasound video loading and the generation of volumetric datasets was created and merged with an existing web-based imaging viewer based on JavaScript and HTML5. The Web Graphics Library was utilized to enable hardware-accelerated image rendering. The result is a web application that works in most major browsers without any plug-ins. It allows users to load a conventional 2D ultrasound cine loop which can subsequently be manipulated with on-the-fly multiplanar reconstructions as in a Digital Imaging and Communications in Medicine (DICOM) viewer. The application is freely accessible at (http://www.castlemountain.dk/atlas/index.php?page=mulrecon&mulreconPage=sonoviewer) where a demonstration of web-based sharing of generated cases can also be found. The developed web-based application is unique in its ability to easily perform loading of one's own ultrasound clips and conduct multiplanar reconstructions where interactive cases can be shared on the Internet.

504 Classification of pigmentary lesions: Can a Computerized System Replace the Dermatologist?

The novel deep learning method is a computer based system that differentiates objects by morphological parameters such as colors, shape and other abstract features. The augmented accuracy of deep convolutional neural networks and the accessibility of clinical pictures, have brought about the increasing use of this method for visual recognision of images in medicine. In melanoma, deep convolutional nets may be implicated for early identification of suspicious lesions, therefore may reduce melanoma mortality and improve survival. This study examines the capability of a computerized system to visually diagnose melanoma, and to compare these results to other diagnostic measures. To address these goals, we trained a deep convolutional neural network on the International Skin Imaging Collaboration (ISIC) Archive dataset of melanoma and benign lesion images. The system was than further fine- tuned. Using InceptionV3 network architecture, the system achieves high scores in diagnosing melanoma (sensitivity and accuracy values of 84.8% and 84.5%, respectively). These values are comparable to published accuracy of dermatologists. In conclusion, computerized systems may have an accuracy level similar to dermatologists in diagnosing melanoma. However, for the system to become applicable, larger cohorts of higher-quality, clinically annotated skin lesion imaging as well as dermatoscopic images should be collected.

Synthesis and Study of Fluorescent Forest-like Carbon Nanotubes Doped with Oxides of Rare-earth Elements

Background: Methods for obtaining the hybrids of multi-wall carbon nanotubes (MWCNTs) and rare earths are in progress. Such composites may possess luminescent properties, which could be of interest for various areas, in particular, medicine (imaging), engineering (fluorescent polymers, LED and relative materials), among other applications. Lanthanide oxides, additionally, can serve as catalysts for MWCNTs formation and catalysts of several organic reactions. Objective: The goal of this work is to obtain the composites of MWCNTs with strontium aluminate, doped with several lanthanides (Eu, Ce, La, Nd, and Sm), via the spray pyrolysis method and to study the properties of the formed hybrids. Methods: The spray pyrolysis method in the temperature range from 780 to 850oC, starting from toluene as a carbon source and ferrocene as a catalyst precursor. SrAl12O19 doped with rare-earths were added to carbon matter in the ultrasonic field. Methods: Among various structures, the forest-like nanostructures have been observed in some cases. The formed coated carbon nanotubes possess fluorescent properties due to the attachment of lanthanide- doped ceramic compound (SrAl12O19) to their surface, allowing the emission control for each dopant: yellow (Nd2O3), blue (Eu2O3 and Sm2O3), intense orange (La2O3), light orange (Ce2O3). Conclusion: MWCNTs decorated with strontium aluminate (SrAl12O19), doped with a series of lanthanide oxides (Nd2O3, Eu2O3, La2O3, Ce2O3, Sm2O3), were obtained by the spray pyrolysis technique on the surface of optical fibers. Lanthanum- and cerium-containing coatings were found to show a better deposition on the MWCNTs surface, exhibiting uniform coating. MWCNTs, coated with Nd-, Ce-, and Eu-doped SrAl12O19 were shown to reveal the best conductive properties.

Abstracts for the Society of Nuclear Medicine and Molecular Imaging, Greater New York and New England Chapters, 32nd Annual Northeast Regional Scientific Meeting, Newport, RI

Abstracts for the Society of Nuclear Medicine and Molecular Imaging, Greater New York and New England Chapters, 32nd Annual Northeast Regional Scientific Meeting, Newport, RI

Geometrically invariant watermarking for medical images based on digital holography and three-level DWT-SVD.

Digital imaging and communications in medicine are being applied widely to improve health care for people, and their security attracted our attention when they are transmitted through the Internet. The paper proposes a digital watermarking method for medical images based on digital holography and three-level discrete wavelength transform (DWT) singular value decomposition (SVD), where a live code including privacy information is transformed into digital holography by an improved computer-generated hologram method. The holography then is embedded into the singular values of the LL3 subband wavelet of the medical image. Experimental results show that the proposed method provides sufficient security results against various attacks, especially geometrical attacks.

Evaluation of an Adrenal Incidentaloma.

Given the frequent use of cross-sectional imaging in medicine, adrenal masses are discovered at an increasing rate. Once detected, it is critical to ensure the patient undergoes the appropriate biochemical/hormonal workup to rule out any aberrant activity and ensure imaging features do not raise suspicion for a malignant neoplasm. Patients with hormonal overactivity, concerning size, and/or imaging characteristics must be referred for surgical consideration. For those not requiring adrenalectomy, it is important to determine which patients mandate follow-up to ensure no further growth or development of hormonal production. It is also critical to understand what is the appropriate follow-up.

Effectiveness of Deep Learning Algorithms to Determine Laterality in Radiographs

Develop a highly accurate deep learning model to reliably classify radiographs by laterality. Digital Imaging and Communications in Medicine (DICOM) data for nine body parts was extracted retrospectively. Laterality was determined directly if encoded properly or inferred using other elements. Curation confirmed categorization and identified inaccurate labels due to human error. Augmentation enriched training data to semi-equilibrate classes. Classification and object detection models were developed on a dedicated workstation and tested on novel images. Receiver operating characteristic (ROC) curves, sensitivity, specificity, and accuracy were calculated. Study-level accuracy was determined and both were compared to human performance. An ensemble model was tested for the rigorous use-case of automatically classifying exams retrospectively. The final classification model identified novel images with an ROC area under the curve (AUC) of 0.999, improving on previous work and comparable to human performance. A similar ROC curve was observed for per-study analysis with AUC of 0.999. The object detection model classified images with accuracy of 99% or greater at both image and study level. Confidence scores allow adjustment of sensitivity and specificity as needed; the ensemble model designed for the highly specific use-case of automatically classifying exams was comparable and arguably better than human performance demonstrating 99% accuracy with 1% of exams unchanged and no incorrect classification. Deep learning models can classify radiographs by laterality with high accuracy and may be applied in a variety of settings that could improve patient safety and radiologist satisfaction. Rigorous use-cases requiring high specificity are achievable.

Abstracts for the Society of Nuclear Medicine and Molecular Imaging, Greater New York and New England Chapters, 32nd Annual Northeast Regional Scientific Meeting

Abstracts for the Society of Nuclear Medicine and Molecular Imaging, Greater New York and New England Chapters, 32nd Annual Northeast Regional Scientific Meeting

Iron Carbide@Carbon Nanocomposites: A Tool Box of Functional Materials.

Iron carbide (Fe3C) is a ceramic magnetic material with high potential for applications in different fields, including catalysis, medicine imaging, coatings, and sensors. Despite its interesting properties, it is still somehow largely unexplored, probably due to challenging synthetic conditions. In this contribution, we present a sol-gel-based method that allows preparing different Fe3C@C nanocomposites with tailored properties for specific applications, in particular, we have focused on and discussed potential uses for adsorption of noxious gas and waste removal. Nanocomposites were prepared using readily available and “green” sources, such as urea, simple and complex sugars, and chitosan. The nanocomposite prepared from chitosan was found to be more efficient for CO2 uptake, while the sample synthetized from cellulose had optimal capability for dye absorption and waste oil removal from water.

A voxel-based method for designing a numerical biomechanical model patient-specific with an anatomical functional approach adapted to additive manufacturing

Here, we describe an original and efficient geometry design approach, based on voxels resulting in a validated model for printability in additive manufacturing. The proposed approach is also designed to be accessible to non-specialists as it does not require specialist skills in computer-assisted-design (CAD). It focuses on biomedical applications, particularly the geometry design of a configurable digital biomechanical model with selected anatomical features based on medical imaging compatible with customization, as might be needed for prosthetic elements. The methodology is based on two main steps. First, an accessible parametrization to medical employees of a configurable biomechanical model is matched specifically to the patient. The configurable model is designed to palliate any kind of potential lack of information from the Digital Imaging and Communication in Medicine (DICOM) file of the medical imaging or partial topological defects but with the least and sufficient number of parameters. For this purpose, the configurable model is segmented in topological areas with a complexity facing solely the desired specification, without regards of potential numerical errors prior AM such as boundary edges, intersecting faces and non-manifold edges. The second step is the voxel-based modelling, easily accessible for medical employees unfamiliar with CAD. Voxels stores the geometric information in a discrete format to facilitate customization by topological operations such as addition and subtraction. The voxelization representation coupled with a smoothing filter, results in a more realistic, robust and closed triangulated model, freed from errors of printability. This method is presented in the context of a trapezium replacement prosthesis prior to selective laser melting (SLM) and diverse post-treatments.

Design of three-dimensional visualization system for medical image based on magnetic resonance angiography data

Objectives: The objective of the study was to discuss the design method of medical image three-dimensional (3D) visualization system based on magnetic resonance angiography (MRA) data. Methods: Using 3D visualization of the carotid artery as an example, the three-position reconstruction algorithm on the basis of volume rendering was discussed. Moreover, if 3D carotid artery is extracted, based on this, we could combine Visualization Toolkit and Image Segmentation and Registration Toolkit with it to construct a 3D visualization system of medical images based on MRA data using C++. Results: The 3D visualization system of medical image data can be read on the MRA based on Digital Imaging and Communications in Medicine images and can be displayed completely. At the same time, a series of interactive operations can be carried out on the 3D image, and three-position blood vessel segmentation and enhancement on the basis of volume rendering can be realized. Conclusions: The medical image 3D visualization system based on MRA data can read and display 3D images and can realize a series of interactive operations, which can achieve better blood vessel enhancement effect and carotid artery extraction. It has important function and significance for a three-bit visualization of medical image.

Concha bullosa, nasal septal deviation, and their impacts on maxillary sinus volume among Emirati people: A cone-beam computed tomography study.

PurposeTo determine the prevalence of concha bullosa (CB) and nasal septal deviation (NSD) and their impact on maxillary sinus volume (MSV).Materials and MethodsCone-beam computed tomographic (CBCT) images of 106 Emirati people were used in this study. The direction and angle of septal deviation were calculated. The presence of CB, which could be unilateral, contralateral, or bilateral in relation to the direction of NSD, was also recorded. MSV was measured using reconstructed Digital Imaging and Communication in Medicine images on Dolphin 3D imaging software version 11.8 premium (Dolphin Imaging, Chatsworth, CA, USA). P values <0.05 were considered to indicate statistical significance.ResultsCB was detected in 37.7% of the sample; 20.7% of the sample showed single unilateral CB and 16.6% had single bilateral CB. NSD was seen in 74.5% of the sample. In the participants with CB, 45.5% showed mild deviation, 34.4% showed moderate deviation, and only 12.5% showed severe septal deviation. CB, but not NSD, was associated with significantly higher MSV on the affected side (P=0.001).ConclusionAlthough NSD was observed in more than two-thirds of the sample and CB was present in more than one-third of the sample, only CB had a significant impact on MSV.

Dupuytren's contracture: Concise approach to an enigmatic disease

Dupuytren's disease (DD) is a debilitating fibroproliferative disorder of the palmar fascia. The clinical approach and management of DD is often challenging for clinicians. The purpose of this image in academic medicine is to review the pathophysiology, diagnosis, and treatment of DD. The following core competencies are addressed in this article: Patient care, Medical knowledge.

66th Society of Nuclear Medicine and Molecular Imaging Annual Meeting. Anaheim, California, USA - June 22-25, 2019

66th Society of Nuclear Medicine and Molecular Imaging Annual Meeting. Anaheim, California, USA - June 22-25, 2019

66th Society of Nuclear Medicine and Molecular Imaging Annual Meeting. Anaheim, California, USA - June 22-25, 2019

66th Society of Nuclear Medicine and Molecular Imaging Annual Meeting. Anaheim, California, USA - June 22-25, 2019

Quality Control of Display Devices for Medical Radiodiagnosis Employing the Standard TG18, GSDF and JND

Introduction: This work presents a study on the procedures for evaluating the quality of imaging display devices in radiology, considering the characteristic luminance curve obtained experimentally versus the Just Noticeable Difference (JND) and the lifetime of digital display devices. Materials &amp; Methods: The evaluations were done using image patterns published by the American Association of Physicists in Medicine on Digital Imaging and Communication in Medicine (DICOM) and the Grayscale Standard Display Function (GSDF), viewed in DICOM software, with various shades of gray. A digital luximeter was used as the luminance meter. A correlation with the time of use of the devices was performed to classify the digital devices as primary (suitable for medical diagnosis) or secondary (suitable only for visualization of medical images). Results &amp; Discussion: Among the monitors evaluated, those with a resolution between 2 and 5 megapixels were classified as primary for up to 50, 000 hours of use, and some above that time limit present behavior equivalent to secondary monitors. Monitoring the temporal evolution of the use of devices is important to avoid errors in medical diagnosis. Conclusion: The use of a calibrated digital luximeter with an illuminance unit conversion factor in luminance defined by this equipment was shown to be an alternative to replace a photometer when this latter is not available.

Study on the Difference of Standardized Uptake Value in Fusion Image of Nuclear Medicine

Study on the Difference of Standardized Uptake Value in Fusion Image of Nuclear Medicine

Technological Advancements in Nuclear Medicine and Molecular Imaging

Technological Advancements in Nuclear Medicine and Molecular Imaging