Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Medical Imaging”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Survey of Image Denoising Methods for Medical Image Classification

Medical imaging devices, such as X-ray machines, inherently produce images that suffer from visual noise. Our objectives were to (i.) determine the effect of image denoising on a medical image classification task, and (ii.) determine if there exists a correlation between image denoising performance and medical image classification performance. We performed the medical image classification task on chest X-rays using the DenseNet-121 convolutional neural network (CNN) and used the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics as the image denoising performance measures. We first found that different denoising methods can make a statistically significant difference in classification performance for select labels. We also found that denoising methods affect fine-tuned models more than randomly-initialized models and that fine-tuned models have significantly higher and more uniform performance than randomly-initialized models. Lastly, we found that there is no significant correlation between PSNR and SSIM values and classification performance for our task.

Michael, Peter↗
DOE OSTI2024

MedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis

Deep neural networks have demonstrated impressive results in medical image analysis, but designing suitable architectures for each specific task is expertise dependent and time consuming. Neural architecture search (NAS) offers an effective means of discovering architectures. It has been highly successful in numerous applications, particularly in natural image classification. Yet, medical images possess unique characteristics, such as small regions and a wide variety of lesion sizes, that differentiate them from natural images. Furthermore, most current NAS methods struggle with high computational costs, especially when dealing with high-resolution image datasets. In this article, we present a novel evolutionary NAS method called multiscale training-free neural architecture search (MSTF-NAS) to address these challenges. Specifically, to accommodate the broad range of lesion region sizes in disease diagnosis, we develop a new reduction cell search space that enables the search algorithm to explicitly identify the optimal scale combination for multiscale feature extraction. Further, to overcome the issue of high computational costs, we utilize training-free indicators as performance measures for candidate architectures, which allows us to search for the optimal architecture more efficiently. More specifically, by considering the capability and simplicity of various networks, we formulate a multiobjective optimization problem that involves two training-free indicators and model complexity for candidate architectures. Extensive experiments on a large medical image benchmark and a publicly available breast cancer detection dataset are conducted. The empirical results demonstrate that our MSTF-NAS outperforms both human-designed architectures and current state-of-the-art NAS algorithms on both datasets, indicating the effectiveness of our proposed method.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics

Abstract Background The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report. Purpose The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain‐relevant assessments via the analysis of relevant image statistics. Methods As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis. To create the training dataset, an established 3D virtual breast phantom was adapted. The resulting dataset comprised about 108 000 images of size 512 512. For the evaluation of submissions to the Challenge, an ensemble of 10 000 DGM‐generated images from each submission was employed. The evaluation procedure consisted of two stages. In the first stage, a preliminary check for memorization and image quality (via the Fréchet Inception Distance [FID]) was performed. Submissions that passed the first stage were then evaluated for the reproducibility of image statistics corresponding to several feature families including texture, morphology, image moments, fractal statistics, and skeleton statistics. A summary measure in this feature space was employed to rank the submissions. Additional analyses of submissions was performed to assess DGM performance specific to individual feature families, the four classes in the training data, and also to identify various artifacts. Results Fifty‐eight submissions from 12 unique users were received for this Challenge. Out of these 12 submissions, 9 submissions passed the first stage of evaluation and were eligible for ranking. The top‐ranked submission employed a conditional latent diffusion model, whereas the joint runners‐up employed a generative adversarial network, followed by another network for image superresolution. In general, we observed that the overall ranking of the top 9 submissions according to our evaluation method (i) did not match the FID‐based ranking, and (ii) differed with respect to individual feature families. Another important finding from our additional analyses was that different DGMs demonstrated similar kinds of artifacts. Conclusions This Grand Challenge highlighted the need for domain‐specific evaluation to further DGM design as well as deployment. It also demonstrated that the specification of a DGM may differ depending on its intended use.

Radiology, Nuclear Medicine & Medical Imaging↗
DOE OSTI2020

Deep medical image analysis with representation learning and neuromorphic computing

Deep learning is increasingly used in medical imaging, improving many steps of the processing chain, from acquisition to segmentation and anomaly detection to outcome prediction. Yet significant challenges remain: (i) image-based diagnosis depends on the spatial relationships between local patterns, something convolution and pooling often do not capture adequately; (ii) data augmentation, the de facto method for learning three-dimensional pose invariance, requires exponentially many points to achieve robust improvement; (iii) labelled medical images are much less abundant than unlabelled ones, especially for heterogeneous pathological cases; and (iv) scanning technologies such as magnetic resonance imaging can be slow and costly, generally without online learning abilities to focus on regions of clinical interest. To address these challenges, novel algorithmic and hardware approaches are needed for deep learning to reach its full potential in medical imaging.

60 APPLIED LIFE SCIENCES↗
NASA NTRS1991

Medical Imaging System

The MD Image System, a true-color image processing system that serves as a diagnostic aid and tool for storage and distribution of images, was developed by Medical Image Management Systems, Huntsville, AL, as a "spinoff from a spinoff." The original spinoff, Geostar 8800, developed by Crystal Image Technologies, Huntsville, incorporates advanced UNIX versions of ELAS (developed by NASA's Earth Resources Laboratory for analysis of Landsat images) for general purpose image processing. The MD Image System is an application of this technology to a medical system that aids in the diagnosis of cancer, and can accept, store and analyze images from other sources such as Magnetic Resonance Imaging.

Source record↗
NASA NTRS2003

Method and Apparatus for Virtual Interactive Medical Imaging by Multiple Remotely-Located Users

A virtual interactive imaging system allows the displaying of high-resolution, three-dimensional images of medical data to a user and allows the user to manipulate the images, including rotation of images in any of various axes. The system includes a mesh component that generates a mesh to represent a surface of an anatomical object, based on a set of data of the object, such as from a CT or MRI scan or the like. The mesh is generated so as to avoid tears, or holes, in the mesh, providing very high-quality representations of topographical features of the object, particularly at high- resolution. The system further includes a virtual surgical cutting tool that enables the user to simulate the removal of a piece or layer of a displayed object, such as a piece of skin or bone, view the interior of the object, manipulate the removed piece, and reattach the removed piece if desired. The system further includes a virtual collaborative clinic component, which allows the users of multiple, remotely-located computer systems to collaboratively and simultaneously view and manipulate the high-resolution, three-dimensional images of the object in real-time.

Ross, Muriel D.↗
NASA NTRS2011

Automation of PCXMC and ImPACT for NASA Astronaut Medical Imaging Dose and Risk Tracking

To automate astronaut organ and effective dose calculations from occupational X-ray and computed tomography (CT) examinations incorporating PCXMC and ImPACT tools and to estimate the associated lifetime cancer risk per the National Council on Radiation Protection & Measurements (NCRP) using MATLAB(R). Methods: NASA follows guidance from the NCRP on its operational radiation safety program for astronauts. NCRP Report 142 recommends that astronauts be informed of the cancer risks from reported exposures to ionizing radiation from medical imaging. MATLAB(R) code was written to retrieve exam parameters for medical imaging procedures from a NASA database, calculate associated dose and risk, and return results to the database, using the Microsoft .NET Framework. This code interfaces with the PCXMC executable and emulates the ImPACT Excel spreadsheet to calculate organ doses from X-rays and CTs, respectively, eliminating the need to utilize the PCXMC graphical user interface (except for a few special cases) and the ImPACT spreadsheet. Results: Using MATLAB(R) code to interface with PCXMC and replicate ImPACT dose calculation allowed for rapid evaluation of multiple medical imaging exams. The user inputs the exam parameter data into the database and runs the code. Based on the imaging modality and input parameters, the organ doses are calculated. Output files are created for record, and organ doses, effective dose, and cancer risks associated with each exam are written to the database. Annual and post-flight exposure reports, which are used by the flight surgeon to brief the astronaut, are generated from the database. Conclusions: Automating PCXMC and ImPACT for evaluation of NASA astronaut medical imaging radiation procedures allowed for a traceable and rapid method for tracking projected cancer risks associated with over 12,000 exposures. This code will be used to evaluate future medical radiation exposures, and can easily be modified to accommodate changes to the risk calculation procedure.

Bahadori, Amir↗
DOE OSTI2024

High-Throughput Computing: Case Study of Medical Image Processing Applications

HPC is designed for large-scale simulations using monolithic codes of tightly coupled processes highly optimized to deliver decreased time to solution. Medical image processing is not a traditional field of HPC. Similar to AI applications, medical image processing parses large datasets, typically multiple times, to support a variety of studies for classification, diagnosis or monitoring purposes. The convergence of AI, HPC and Big Data encouraged more fields using image processing to transition to HPC. However, not all applications benefit from the same optimizations. In this paper we focus on high throughput medical image processing applications that analyze a huge dataset of small MRI images and that require HPC systems to decrease the time of parsing the entire dataset and not individual MRIs. We show in this research the performance of running SLANT, an image processing application for a whole brain segmentation, on large-scale systems and highlight performance limitations. We present optimizations prioritizing throughput that exhibit a 3.5x speed-up on the Summit Supercomputer that can be used as a baseline for building a high-throughput execution framework for other HPC systems.

Predescu, Maria↗
DOE OSTI2024

Medical Imaging Equipment Energy Efficiency

The energy use of medical imaging equipment (MIE) in healthcare facilities is estimated to be about 5% of total site energy use. MIE energy use is only expected to increase as technology advances and more patients seek services from MIE, enabling more facilities to install additional MIE. Healthcare organizations need reliable information regarding comprehensive energy use or lifetime energy costs with which to make energy-efficient MIE procurement decisions, and there are currently no MIE energy or efficiency standards in the United States (U.S.). This fact sheet provides background on MIE energy consumption, key terms, and guidance on why and how to meter MIE, helping stakeholders make informed decisions to enhance their facility's performance.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION↗
NASA NTRS2003

Improved Interactive Medical-Imaging System

An improved computational-simulation system for interactive medical imaging has been invented. The system displays high-resolution, three-dimensional-appearing images of anatomical objects based on data acquired by such techniques as computed tomography (CT) and magnetic-resonance imaging (MRI). The system enables users to manipulate the data to obtain a variety of views for example, to display cross sections in specified planes or to rotate images about specified axes. Relative to prior such systems, this system offers enhanced capabilities for synthesizing images of surgical cuts and for collaboration by users at multiple, remote computing sites.

Ross, Muriel D.↗
DOE OSTI2020

Improving the performance of medical imaging applications using SYCL

As opposed to the Open Computing Language (OpenCL) programming model, in which host and device codes are generally written in different programming languages, SYCL can combine host and device codes for an application in a type-safe way to improve development productivity and performance portability. Hence, this report shows the experimental results of applying the SYCL programming model to medical imaging applications for a study on performance portability and programming productivity between OpenCL and SYCL. Rodinia is a widely used open-source benchmark suite for heterogeneous computing. We choose two medical imaging applications (Heart Wall and Particle Filter) in the benchmark suite, migrate the OpenCL implementations of the applications to the SYCL implementations, and evaluate their performance and productivity on Intel® microprocessors that contain a central processing unit (CPU) and an integrated graphics processing unit (GPU). The maturing SYCL compilers, which are based on a conformant implementation of the SYCL 1.2.1 Khronos specification, have been actively optimized for Intel® computing platforms. The experimental results are promising in terms of the raw performance and productivity. Although the SYCL implementation of the Heart Wall application does not execute successfully on a CPU, the SYCL implementations of the application can achieve comparable or better performance than the OpenCL implementation on Intel® integrated GPUs. For the Particle Filter application, the performance difference between the SYCL and OpenCL implementations is comparable on the GPUs for most cases, but the SYCL implementations are on average 4X faster than the OpenCL implementations on Intel® Xeon® CPUs. For programming productivity, we arguably use lines of code as a way to measure programming productivity in software. The SYCL programs reduce the lines of code of the OpenCL programs by 52% and 38% for the Heart Wall and Particle Filter, respectively. The results indicate that SYCL is a promising programming model for heterogeneous computing with the maturing compilers. We organize the remainder of the report as follows. Section II introduces the SYCL programming model, compares the major differences between an OpenCL program and a SYCL program, and describes the characteristics of the two applications. Section III describes the SYCL programming model in more details, and shows the SYCL implementation of a kernel function in the Particle Filter application as an example. In Section IV, we evaluate the performance of the applications on the CPUs and GPUs. Section V concludes the report.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Medical Imaging Equipment Energy Efficiency [Slides]

The slide deck is being prepared for healthcare sector stakeholders as a resource on the energy use of Medical Imaging Equipment (MIE) which will provide an overview of existing work, review existing literature on MIE energy use and identify energy efficiency opportunities.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2001

Normal and abnormal tissue identification system and method for medical images such as digital mammograms

A system and method for analyzing a medical image to determine whether an abnormality is present, for example, in digital mammograms, includes the application of a wavelet expansion to a raw image to obtain subspace images of varying resolution. At least one subspace image is selected that has a resolution commensurate with a desired predetermined detection resolution range. A functional form of a probability distribution function is determined for each selected subspace image, and an optimal statistical normal image region test is determined for each selected subspace image. A threshold level for the probability distribution function is established from the optimal statistical normal image region test for each selected subspace image. A region size comprising at least one sector is defined, and an output image is created that includes a combination of all regions for each selected subspace image. Each region has a first value when the region intensity level is above the threshold and a second value when the region intensity level is below the threshold. This permits the localization of a potential abnormality within the image.

Heine, John J.↗
DOE OSTI2023

Medical Imaging Equipment Energy Efficiency

The fact sheet is being prepared for stakeholders of Better Building Alliance's (BBA) Healthcare sector as a resource on the energy use of medical imaging equipment. This is a concise version of earlier published slide deck - NREL/PR-5500-83743.

ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION↗
NASA NTRS1993

Advanced data visualization and sensor fusion: Conversion of techniques from medical imaging to Earth science

Hughes Aircraft Company and the University of Chicago propose to transfer existing medical imaging registration algorithms to the area of multi-sensor data fusion. The University of Chicago's algorithms have been successfully demonstrated to provide pixel by pixel comparison capability for medical sensors with different characteristics. The research will attempt to fuse GOES (Geostationary Operational Environmental Satellite), AVHRR (Advanced Very High Resolution Radiometer), and SSM/I (Special Sensor Microwave Imager) sensor data which will benefit a wide range of researchers. The algorithms will utilize data visualization and algorithm development tools created by Hughes in its EOSDIS (Earth Observation SystemData/Information System) prototyping. This will maximize the work on the fusion algorithms since support software (e.g. input/output routines) will already exist. The research will produce a portable software library with documentation for use by other researchers.

Savage, Richard C.↗
NASA NTRS1992

Advanced data visualization and sensor fusion: Conversion of techniques from medical imaging to Earth science

Hughes Aircraft Company and the University of Chicago propose to transfer existing medical imaging registration algorithms to the area of multi-sensor data fusion. The University of Chicago's algorithms have been successfully demonstrated to provide pixel by pixel comparison capability for medical sensors with different characteristics. The research will attempt to fuse GOES, AVHRR, and SSM/I sensor data which will benefit a wide range of researchers. The algorithms will utilize data visualization and algorithm development tools created by Hughes in its EOSDIS prototyping. This will maximize the work on the fusion algorithms since support software (e.g. input/output routines) will already exist. The research will produce a portable software library with documentation for use by other researchers.

Savage, Richard C.↗
NASA NTRS1994

Neural networks: Application to medical imaging

The research mission is the development of computer assisted diagnostic (CAD) methods for improved diagnosis of medical images including digital x-ray sensors and tomographic imaging modalities. The CAD algorithms include advanced methods for adaptive nonlinear filters for image noise suppression, hybrid wavelet methods for feature segmentation and enhancement, and high convergence neural networks for feature detection and VLSI implementation of neural networks for real time analysis. Other missions include (1) implementation of CAD methods on hospital based picture archiving computer systems (PACS) and information networks for central and remote diagnosis and (2) collaboration with defense and medical industry, NASA, and federal laboratories in the area of dual use technology conversion from defense or aerospace to medicine.

Clarke, Laurence P.↗