Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “vision”

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 1,423 records · Page 79

Astromaterial Curation and Research at NASA

Astromaterial sample return missions from other planetary bodies (e.g., the Moon, asteroids, the Sun) and astromaterial sample collection missions here on Earth (e.g., Antarctic Meteorites, Cosmic Dust) have been a vital part of NASA’s science vision since nearly its inception. Beginning with the Apollo missions to the Moon and extending to the recent successful sample collection by the OSIRIS-REx asteroid sample return mission, these astromaterials collections have been an invaluable resource to scientists and educators around the world. Sample studies continue to provide fundamental insight into how our solar system and its constituent bodies formed and evolved over the past 4.5 billion years. As evidence of their broad impact, there are over 19,141 samples on loan to 433 Principal Investigators in 24 countries [1]. As we plan for exploration missions through 2050, sample return missions will continue to play a vital role in NASA’s science vision. Returned samples truly are the gift that keeps on giving. Having the samples accessible on Earth allows new generations of scientists and new generations of instrumentation to pursue ever evolving scientific questions. For example, the Apollo samples were collected ~50 years ago, yet our views of how the Earth-Moon system formed, the role of volatiles in the early inner solar system, and even the positions of the gas giants in the outer solar system have changed dramatically as a result of Apollo sample analyses conducted very recently. Vital to the long-term viability of any sample return mission is the careful curation of the samples. Curatorial efforts need to begin early in the project lifecycle, not with the return of the samples, but at mission conception. The Astromaterials Acquisition and Curation Office at NASA Johnson Space Center is responsible for curating all of NASA’s current and future extraterrestrial samples. Looking at possible sample return missions over the next 35+ years [2], many samples would require curation efforts a step beyond current capabilities, e.g., cold or cryogenic curation, organically and biologically clean curation, curation of gases and ices, and curation of samples with extreme pressure, temperature, or redox requirements. During the lecture, we discuss the current curatorial efforts in JSC curation, as well as discoveries from the astromaterial research. [1] Zeigler, R. A. et al. (2017) Planetary Science Vision 2050 Workshop. [2] McCubbin F. M. et al. (2017) Planetary Science Vision 2050 Workshop.

astromaterial↗

IRIS: High-fidelity Perception Sensor Modeling for Closed-Loop Planetary Simulations

Perception plays a key role in autonomous and semi-autonomous planetary exploration vehicles. For instance, landers can use computer vision techniques for identifying safe landing locations, aerial vehicles use cameras as navigation sensors, and planetary rovers use them for localization and hazard detection. Engineering simulations of such systems requires the accurate modeling of perception and vision sensors for simulating autonomy scenarios. In addition, the modeling of sensors for landers, aerial and ground vehicles requires the ability to handle large and high-resolution terrains, the accurate modeling of illumination, hi-fidelity rendering via ray/path tracing and the inclusion of sensor characteristics. Vision sensor models strive to simulate sensor reality by using physics principles to model the interaction of light and objects. Furthermore, high frame rate performance is highly desirable for in-the-loop simulations involving vehicle dynamics and control software. In this paper we describe a new sensor modeling capability called Inter-planetary Rendering for Imaging and Sensors (IRIS) that meets these requirements for the real-time and high-fidelity simulation of vision sensors for planetary aerospace and robotics applications.

Elmquist, Asher↗

Exploration Systems Exterior Lighting Design Guidance

Humans are returning to the Moon — this time, to stay. NASA has selected a location that maximizes line-of-sight communication with Earth, solar visibility, and access to water ice: the Lunar South Pole (LSP). While the Sun is more consistently in the lunar sky at the poles, it never rises more than 7° above the horizon in the target landing regions. This harsh lighting environment--never experienced during the Apollo missions or in human spaceflight--presents an engineering challenge: Support and protect functional vision. The human vision system, which despite having a high-dynamic range, cannot see well into bright light and cannot adapt quickly from bright to dark or vice versa. The design of helmets, windows, and lighting solutions must work in a complementary fashion to achieve a system of lighting and functional vision support that enables crews to see into darkness while their eyes are light-adapted and see in bright light while still dark-adapted that protects their eyes from injury. This report brings together information and identifies gaps related to LSP Natural environment (topology, regolith, temperature, lighting, and so forth), NASA historical experience exploring the Moon, human vision capabilities and needs, exploration operations, simulation capabilities and needs (for design verification, training, mission planning, and so forth) and existing engineering, safety, medical and performance requirements related to support human exploration.

Simulation↗

Building Energy Modeling Enhancements to Identify Least-Cost Pathways to Net-Zero Carbon Homes: Preprint

Residential grid-interactive efficient buildings (GEBs) can utilize high levels of energy efficiency and demand flexibility to deliver value to occupants, the grid, and society. However, without the ability to analyze, design, and optimize residential GEBs there is a risk that homes will not realize their full potential value as efficient and dynamic resources, which could ultimately lead to higher than necessary energy costs for U.S. households and lower realization of potential energy efficiency and demand flexibility benefits such as increased convenience/automation, thermal comfort, durability, indoor air quality, and resilience. In 2018, the National Renewable Energy Laboratory (NREL) Residential Modeling Team developed a vision for an open source Residential GEB Analytics Platform built within DOE's EnergyPlus and OpenStudio modeling environment that would enable the design and optimization of residential GEBs, including the identification of least-cost pathways to highly energy-efficient and energy-flexible homes (e.g., net zero carbon homes). We created a detailed workplan for the development of new and enhanced residential GEB component-level models for EnergyPlus and OpenStudio needed to progress toward the vision for the analytics platform while delivering near-term benefits to industry. This paper 1) presents the vision for the platform, summarizing the workplan for residential GEB modeling enhancements; 2) highlights significant advancements that have been achieved between 2018 and 2022, including stochastic residential occupancy modeling, flexible water heater modeling, detailed lithium-ion stationary battery modeling, and realistic residential HVAC modeling; and 3) outlines ongoing efforts and next steps toward the full vision for the platform.

building energy modeling↗

Central Plateau Cleanup at DOE's Hanford Site - 12504

The discussion of Hanford's Central Plateau includes significant work in and around the center of the Hanford Site - located about 7 miles from the Columbia River. The Central Plateau is the area to which operations will be shrunk in 2015 when River Corridor cleanup is complete. This work includes retrieval and disposal of buried waste from miles of trenches; the cleanup and closure of massive processing canyons; the clean-out and demolition to 'slab on grade' of the high-hazard Plutonium Finishing Plant; installation of key groundwater treatment facilities to contain and shrink plumes of contaminated groundwater; demolition of all other unneeded facilities; and the completion of decisions about remaining Central Plateau waste sites. A stated goal of EM has been to shrink the footprint of active cleanup to less than 10 square miles by 2020. By the end of FY2011, Hanford will have reduced the active footprint of cleanup by 64 percent exceeding the goal of 49 percent. By 2015, Hanford will reduce the active footprint of cleanup by more than 90 percent. The remaining footprint reduction will occur between 2015 and 2020. The Central Plateau is a 75-square-mile region near the center of the Hanford Site including the area designated in the Hanford Comprehensive Land Use Plan Environmental Impact Statement (DOE 1999) and Record of Decision (64 FR 61615) as the Industrial-Exclusive Area, a rectangular area of about 20 square miles in the center of the Central Plateau. The Industrial-Exclusive Area contains the 200 East and 200 West Areas that have been used primarily for Hanford's nuclear fuel processing and waste management and disposal activities. The Central Plateau also encompasses the 200 Area CERCLA National Priorities List site. The Central Plateau has a large physical inventory of chemical processing and support facilities, tank systems, liquid and solid waste disposal and storage facilities, utility systems, administrative facilities, and groundwater monitoring wells. As a companion to the Hanford Site Cleanup Completion Framework document, DOE issued its draft Central Plateau Cleanup Completion Strategy in September 2009 to provide an outline of DOE's vision for completion of cleanup activities across the Central Plateau. As major elements of the Hanford cleanup along the Columbia River Corridor near completion, DOE believed it appropriate to articulate the agency vision for the remainder of the cleanup mission. The Central Plateau Cleanup Completion Strategy and the Hanford Site Cleanup Completion Framework were provided to the regulatory community, the Tribal Nations, political leaders, the public, and Hanford stakeholders to promote dialogue on Hanford's future. The Central Plateau Cleanup Completion Strategy describes DOE's vision for completion of Central Plateau cleanup and outlines the decisions needed to achieve the vision. The Central Plateau strategy involves steps to: (1) contain and remediate contaminated groundwater, (2) implement a geographic cleanup approach that guides remedy selection from a plateau-wide perspective, (3) evaluate and deploy viable treatment methods for deep vadose contamination to provide long-term protection of the groundwater, and (4) conduct essential waste management operations in coordination with cleanup actions. The strategy will also help optimize Central Plateau readiness to use funding when it is available upon completion of River Corridor cleanup projects. One aspect of the Central Plateau strategy is to put in place the process to identify the final footprint for permanent waste management and containment of residual contamination within the 20-square-mile Industrial-Exclusive Area. The final footprint identified for permanent waste management and containment of residual contamination should be as small as practical and remain under federal ownership and control for as long as a potential hazard exists. Outside the final footprint, the remainder of the Central Plateau will be available for other uses consistent with the Hanford Comprehensive Land-Use Plan (DOE 1999), while maintained under federal ownership and control. (author)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Meningioma Causing Visual Impairment: Outcomes and Toxicity After Intensity Modulated Radiation Therapy

Purpose: To evaluate ophthalmologic outcomes and toxicity of intensity modulated radiation therapy (IMRT) in patients with meningiomas causing visual deficits. Methods and Materials: A prospective observational study with formal ophthalmologic and clinical assessment of 30 consecutive cases of meningioma affecting vision treated with IMRT from 2007 to 2011. Prescriptions were 50.4 Gy to mean target dose in 28 daily fractions. The median follow-up time was 28 months. Twenty-six meningiomas affected the anterior visual pathway (including 3 optic nerve sheath meningiomas); 4 were posterior to the chiasm. Results: Vision improved objectively in 12 patients (40%). Improvements were in visual field (5/16 patients), color vision (4/9 patients), acuity (1/15 patients), extraocular movements (3/11 patients), ptosis (1/5 patients), and proptosis (2/6 patients). No predictors of clinical response were found. Two patients had minor reductions in tumor dimensions on magnetic resonance imaging, 1 patient had radiological progression, and the other patients were stable. One patient experienced grade 2 keratitis, 1 patient had a minor visual field loss, and 5 patients had grade 1 dry eye. Conclusion: IMRT is an effective method for treating meningiomas causing ophthalmologic deficits, and toxicity is minimal. Thorough ophthalmologic assessment is important because clinical responses often occur in the absence of radiological change.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

van der Waals Semiconductor Empowered Vertical Color Sensor

We report biomimetic artificial vision is receiving significant attention nowadays, particularly for the development of neuromorphic electronic devices, artificial intelligence, and microrobotics. Nevertheless, color recognition, the most critical vision function, is missed in the current research due to the difficulty of downscaling of the prevailing color sensing devices. Conventional color sensors typically adopt a lateral color sensing channel layout and consume a large amount of physical space, whereas compact designs suffer from an unsatisfactory color detection accuracy. In this work, we report a van der Waals semiconductor-empowered vertical color sensing structure with the emphasis on compact device profile and precise color recognition capability. More attractive, we endow color sensor hardware with the function of chromatic aberration correction, which can simplify the design of an optical lens system and, in turn, further downscales the artificial vision systems. Also, the dimension of a multiple pixel prototype device in our study confirms the scalability and practical potentials of our developed device architecture toward the above applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Managing the Performance/Error Tradeoff of Floating-point Intensive Applications

Modern embedded systems are becoming more reliant on real-valued arithmetic as they employ mathematically complex vision algorithms and sensor signal processing. Double-precision floating point is the most commonly used precision in computer vision algorithm implementations. A single-precision floating point can provide a performance boost due to less memory transfers, less cache occupancy, and relatively faster mathematical operations on some architectures. However, adopting it can result in loss of accuracy. Identifying which parts of the program can run in single-precision floating point with low impact on error is a manual and tedious process. In this paper, we propose an automatic approach to identify parts of the program that have a low impact on error using shadow-value analysis. Our approach provides the user with a performance/error tradeoff, using which the user can decide how much accuracy can be sacrificed in return for performance improvement. We illustrate the impact of the approach using a well known implementation of Apriltag detection used in robotics vision. In conclusion, we demonstrate that an average 1.3x speedup can be achieved with no impact on tag detection, and a 1.7x speedup with only 4% false negatives.

97 MATHEMATICS AND COMPUTING↗

Intelligent Process Visualization through Nuclear Operation Process Modeling, Reasoning, and Object Detection from Field Videos (Final Report)

This report is a deliverable for the “Final Report” task of DOE NEET Project 19-16790, "Context-Aware Safety Information Display for Nuclear Field Workers." This project's overall goal is to test the hypothesis that integrating computer vision and process reasoning methods will enable proactive visualization of the safe operation and maintenance processes of Nuclear Power Plants (NPP) for field workers. Augmented Reality (AR) glasses adopting such proactive safety information visualization techniques can significantly increase personnel safety and reduce the NPP’s operating costs. The current practice of monitoring NPPs requires workers to switch between digital models, data, and physical workspaces in identifying relevant but potentially occluded objects and in assessing the risks of operation and maintenance processes. On the other hand, frequently changed field conditions require field workers to report to supervisors for real-time guidance. Such guidance is essential to ensure that changing conditions will not invalidate or endanger the work order and other ongoing processes that may jeopardize NPP operations. Additionally, incorrect recognition of equipment objects can result in communication errors and safety problems. AR techniques can assist engineers in viewing the physical workspaces with objects labeled with detailed operation procedures and safety reminders during field operations. The project team developed an “Intelligent Context-Aware Safety Information Display” (ICAD) for supporting Nuclear Power Plant (NPP) field workers in achieving safe and efficient execution of a series of operational tasks in uncertain and changing workspaces of an NPP. Before designing the ICAD-AR prototype, the project team synthesized NPP operational knowledge models through literature review studies, surveys, interviews with domain experts, and knowledge modeling. The project team conducted an extensive study of the operational procedures of various NPPs, and digital technologies that can support the safe and efficient execution of those procedures in different NPP operational contexts. This literature review helped the project team conduct surveys and interviews with nuclear engineers and field workers to identify three categories of information. The NPP knowledge modeling efforts reveal that the three categories of information identified have different levels of importance in a typical procedure of carrying out a series of tasks to achieve a specific NPP operation goal (e.g., shutdown, mode changes). These three categories of information include 1) Workspace dynamics – the changing spatial arrangements of workspaces, tools, protection equipment, and supporting materials, 2) Workflow prognostics – the dynamic dependencies between different parts of an NPP that functionally support and influence each other in terms of safety and efficiency, and 3) Hazards – objects and spaces that contain hazardous materials or physical conditions that can pose risks to workers or mechanical systems. The project team has profiled the importance levels of these categories of information into a knowledge model. This knowledge model specifies what types of information are more critical for a given task in a given workspace so that computers can automatically identify critical objects and sensors in a scene for delivering context-ware safety information to field workers through AR devices. Significant research development of this project results in technical research outcomes and a prototyping system that illustrates the technical feasibility of establishing an ICAD-AR system supporting the proactive safety information display for nuclear field workers. This final report summarizes the project team’s technological achievements in the past three years. Overall, the project team completed the development and integration of five techniques into a prototype ICAD Augmented Reality (ICAD-AR) system and demonstrated the developed system’s real-time execution in a mechanical room. The project team completed the analysis of using this prototype in other types of workspaces based on 3D image data and digital design models collected from two additional workspaces (a water treatment plant and a flow loop training facility). The integrated techniques include 1) Natural Language Processing (NLP) algorithms supporting the generation and updates of nuclear fieldwork process models based on text analysis of work packages and operation manuals; 2) sensor log analysis for predicting control actions in given sensor reading contexts; 3) computer vision algorithms for automatic localization and navigation of workers; 4) object detection algorithms for identifying task-related objects and correlated sensors for safety checking; 5) AR technique as a platform for supporting the integration. The testing results of these five techniques have shown that 1) the sensor log analysis model can predict the next control action with an accuracy of 0.883; 2) the trained natural language processing model can extract more than 80% of the critical information from paper-based procedures (PBPs); 3) the navigation algorithm with the integration of Visual Inertial Odometry (VIO) and Non-Recursive Bayesian Filter methods make operator’s trajectory estimation resilient to drift error; 4) the computer vision algorithm can detect task-specific and safety-critical objects with an average accuracy of 95.3%. The project team used work procedures collected from a flow loop training facility and two datasets collected from two mechanical rooms simulating the workspaces of NPPs to demonstrate the technical capabilities of the developed ICAD-AR prototype. The demonstration validated the technical feasibility of establishing the ICAD-AR system for nuclear field workers and identified the challenges in 1) automatic text analysis of work packages; 2) use of limited samples of sensor logs for predicting the proper timings of control actions; 3) reliably tracking workers and their task progress in mechanical rooms with many similar objects.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Demonstration and Evaluation of the Human-Technology Integration Guidance for Plant Modernization

The significance of nuclear power in its role producing carbon-free electricity to the U.S. cannot be overstated. However, with changes in the energy market coupled with changes in incentives given to certain resources like solar and wind, the operating and maintenance costs for these sources have seen a significant reduction, which has consequently negatively impacted the economic viability of the existing U.S. nuclear power plant fleet. Digital instrumentation and control (I&C) and control room modernization is a major critical work domain to reduce operating and maintenance costs. Existing nuclear power plants are commonly configured with mostly legacy analog I&C as well as isolated pockets of digital I&C (a plant process computer, digital recorders, etc.). One challenge with this analog I&C is that replacement parts are becoming prohibitively more expensive and difficult to obtain. Moreover, a significant challenge with the existing analog I&C is that the way in which plants are currently operated and maintained is no longer competitive with other electricity generating sources, like natural gas, where advanced digital I&C technologies are commonplace. This gap between the waynuclear power plants are operated compared to other electricity generating sources significantly challenges the economic viability of the nuclear industry. Indeed, digital I&C systems can fundamentally change the way the plant is operated (i.e., the concept of operation). The introduction of digital I&C technologies offers a wealth of benefits to the nuclear industry. However, it is important to emphasize that, to realize these benefits, a careful understanding of how to integrate technology in a collaborative way that leverages the capabilities of people and technologies is necessary. Human-technology integration applies human factors engineering methods and tools to ensure the safe and reliable use of these technologies while ensuring that the inherent features of the technologies that provide economic value are not missed. The scope of this work documents the demonstration of the recently developed human and technology integration methodology, as applied to developing a new vision and concept of operations for a major U.S. nuclear power plant fleet. This report focuses on the methodological aspects of developing a vision and concept of operations. This report shares the tools, activities, and lessons learned during a modernization currently underway for industry as a whole to consider when planning any significant digital modification and developing a new vision and concept of operations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Enterprise: Exploration of Concepts, Perspectives and Implications for Systems Engineering

The purpose of this paper is to explore the concept of ‘enterprise’ in the context of Systems Engineering (SE). The term ‘enterprise’ has been used extensively to generally describe large complex entities that have an extensive scope of operations. However, a deeper examination of ‘enterprise’ significance for SE can provide insights as our challenges continue with increasingly complex, uncertain, ambiguous, and integrated entities struggling to thrive in the future. The paper explores three central topics. First, the concept of enterprise is introduced as a central aspect of the future focus for SE, as recognized in the INCOSE SE Vision 2035. Second, a more detailed examination of the enterprise concept is developed in relationship to SE. The thrust of this examination is to understand the nature and role of ‘enterprise’ across a broad spectrum of literature and knowledge, ultimately providing a more informed perspective of enterprise for SE. As part of this exploration, a bibliometric analysis of the term ‘enterprise’ is performed. This exploration extracts key themes (clusters) in the ‘enterprise’ literature. Third, challenges for further development and inculcation of ‘enterprise’ within the SE discipline and support for realization of the SE 2035 Vision are suggested. These challenges point out the need to ‘think differently’ about ‘enterprise’ within the SE context. ‘Enterprise’ is proposed as a central, albeit different, perspective for the SE discipline. Finally, the paper closes with a first–generation perspective for ‘enterprise’ in pursuit of the SE Vision 2035.

42 ENGINEERING↗

Foundations and Frontiers in Visual Analytics

This introduction and future vision section for this special issue of the Journal of Information Visualization hopes to set the stage for an emerging worldwide effort to advance the state of the science of visual analytics. We present some of the driving needs followed by some foundational principals and methods for advancing this science through partnerships among national laboratories, academia, industry, and the international science community. We will present a selection of the many success stories the science, engineering, and industrial communities have of taking core science research to end users in the field during these early years. Next, we will present some thoughts on the future vision. Finally, we will introduce the 8 papers in this special issue, each one addressing part of that vision.

97 MATHEMATICS AND COMPUTING↗

A sample holder for simultaneous Raman and neutron vibrational spectroscopy

We have built a sample holder (called a center stick or sample stick) for performing simultaneous Raman and neutron vibrational spectroscopy on samples of material at the VISION neutron vibrational spectrometer of the Spallation Neutron Source at Oak Ridge National Laboratory. This equipment holds material samples in the neutron beam within the cryogenic environment of the VISION spectrometer, allowing for samples to be studied at temperatures as low as 5 K. It also provides the capability for gas to be loaded to or evacuated from the sample while it is loaded at VISION. The optical components for directing and filtering light are located within the cryogenic volume, in physical proximity to the sample. We describe the construction of this sample holder and discuss our first measurements of simultaneous Raman and neutron vibrational spectra. Here, the samples that we report on were of 4-nitrophenol at a temperature of 20 K and of cryogenic hydrogen of a number of different orthohydrogen fractions.

4-nitrophenol↗

Ultrafast processing of pixel detector data with machine learning frameworks

Modern photon science performed at high repetition rate free-electron laser (FEL) facilities and beyond relies on 2D pixel detectors operating at increasing frequencies (towards 100 kHz at LCLS-II) and producing rapidly increasing amounts of data (towards TB/s). This data must be rapidly stored for offline analysis and summarized in real time for online feedback to the scientists. While at LCLS all raw data has been stored, at LCLS-II this would lead to a prohibitive cost; instead, enabling real time processing of pixel detector data (dark, gain, common mode, background, charge summing, subpixel position, photon counting, data summarization) allows reducing the size and cost of online processing, offline processing and storage by orders of magnitude while preserving full photon information. This could be achieved by taking advantage of the compressibility of sparse data typical for LCLS-II applications. Faced with a similar big data challenge a decade ago, computer vision stimulated revolutionary advances in machine learning hardware and software. We investigated if these developments are useful in the field of data processing for high speed pixel detectors and found that typical deep learning models and autoencoder architectures failed to yield useful noise reduction while preserving full photon information, presumably because of the very different statistics and feature sets in computer vision and radiation imaging. However, the raw performance of modern frameworks like Tensorflow inspired us to redesign in Tensorflow mathematically equivalent versions of the state-of-the-art, “classical” algorithms used at LCLS. The novel Tensorflow models resulted in elegant, compact and hardware agnostic code, gaining 1 to 2 orders of magnitude faster processing on an inexpensive consumer GPU, reducing by 3 orders of magnitude the projected cost of online analysis and compression without photon loss at LCLS-II. The novel Tensorflow models also enabled ongoing development of a pipelined hardware system expected to yield an additional 3 to 4 orders of magnitude speedup, necessary for meeting the data acquisition and storage requirements at LCLS-II, potentially enabling acquiring every single FEL pulse at full speed. Computer vision a decade ago was dominated by hand-crafted filters; their structure inspired the deep learning revolution resulting in modern deep convolutional networks; similarly, our novel Tensorflow filters provide inspiration for designing future deep learning models for ultrafast and efficient processing and classification of pixel detector images at FEL facilities.

47 OTHER INSTRUMENTATION↗

Image transformers for classifying acute lymphoblastic leukemia

Cancer is the leading cause of death by disease in American children. Each year, nearly 16,000 children in the United States and over 300,000 children globally are diagnosed with cancer. Leukemia is a form of blood cancer that originates in the bone marrow and accounts for one-third of pediatric cancers. This disease occurs when the bone marrow contains 20% or more immature white blood cell blasts. Acute lymphoblastic leukemia is the most prevalent leukemia type found in children, with half of all annual cases in the U.S. diagnosed for subjects under 20 years of age. To diagnose acute lymphoblastic leukemia, pathologists often conduct a morphological bone marrow assessment. This assessment determines whether the immature white blood cell blasts in bone marrow display the correct morphological characteristics, such as size and appearance of nuclei. Pathologists also use immunophenotyping via multi-channel flow cytometry to test whether certain antigens are present on the surface of blast cells; the antigens are used to identify the cell lineage of acute lymphoblastic leukemia. These manual processes require well-trained personnel and medical professionals, thus being costly in time and expenses. Computerized decision support via machine learning can accelerate the diagnosis process and reduce the cost. Training a reliable classification model to distinguish between mature and immature white blood cells is essential to the decision support system. Here, we adopted the Vision Transformer model to classify white blood cells. The Vision Transformer achieved superb classification performance compared to state-of-the-art convolutional neural networks while requiring less computational resources for training. Additionally, the latent self-attention architecture provided attention maps for a given image, providing clues as to which portion(s) of the image were significant in decision-making. We applied the Vision Transformer model and a convolutional neural network model to an acute lymphoblastic leukemia classification dataset of 12,528 samples and achieved accuracies of 88.4% and 86.2%.

Cho, Priscilla↗

Fast-MICP for frameless image-guided surgery

Purpose: In image-guided surgery (IGS) systems, image-to-physical registration is critical for reliable anatomical information mapping and spatial guidance. Conventional stereotactic frame-based or fiducial-based approaches provide accurate registration but are not patient-friendly. This study proposes a frameless cranial IGS system that uses computer vision techniques to replace the frame or fiducials with the natural features of the patient. Methods: To perform a cranial surgery with the proposed system, the facial surface of the patient is first reconstructed by stereo vision. Accuracy is ensured by capturing parallel-line patterns projected from a calibrated LCD projector. Meanwhile, another facial surface is reconstructed from preoperative computed tomography (CT) images of the patient. The proposed iterative closest point (ICP)-based algorithm [fast marker-added ICP (Fast-MICP)] is then used to register the two facial data sets, which transfers the anatomical information from the CT images to the physical space. Results: Experimental results reveal that the Fast-MICP algorithm reduces the computational cost of marker-added ICP (J.-D. Lee et al., ''A coarse-to-fine surface registration algorithm for frameless brain surgery,'' in Proceedings of International Conference of the IEEE Engineering in Medicine and Biology Society, 2007, pp. 836-839) to 10% and achieves comparable registration accuracy, which is under 3 mm target registration error (TRE). Moreover, two types of optical-based spatial digitizing devices can be integrated for further surgical navigation. Anatomical information or image-guided surgical landmarks can be projected onto the patient to obtain an immersive augmented reality environment. Conclusion: The proposed frameless IGS system with stereo vision obtains TRE of less than 3 mm. The proposed Fast-MICP registration algorithm reduces registration time by 90% without compromising accuracy.

60 APPLIED LIFE SCIENCES↗

WE-D-BRE-03: Late Toxicity Following Photon Or Proton Radiotherapy in Patients with Brain Tumors

Purpose: To identify indicators of Late Grade 3 (LG3) toxicity, late vision and hearing changes in patients treated for primary brain tumors with photon (XRT) or proton radiotherapy (PRT). Methods: We retrospectively reviewed 102 patients who received brain XRT or PRT to doses of 54 or 59.6 Gy in daily fractions of 1.8–2 Gy. Of the 80 patients (34 XRT, 39 PRT and 7 both modalities) reviewed for indicators of LG3 toxicity, 25 developed LG3 toxicity 90 to 500 days after radiotherapy completion. 55 patients had less than LG3 toxicity > 500 days after treatment. In that time, late vision and hearing changes were seen in 44 of 75 and 25 of 78 patients, respectively. The correlation between late toxicity and prescription dose, planning target volume (PTV) size, and doses to the brainstem, brain, optic chiasm, optic nerves, eyes and cochlea was evaluated. A two-tailed Fisher's exact test and Wilcoxon rank sum test were used for the statistical analysis for XRT, PRT and all patients combined. Results: Exceeding the 54 Gy-5% dose-volume brainstem constraint, but not the optic structure constraints, was significantly correlated (p < 0.05) with late vision changes in all three groups. Exceeding maximum and mean cochlear doses of 45 and 30 Gy, respectively, was a significant indicator of hearing changes (p < 0.05) in PRT patients and all patients combined. In a sub-group of 52 patients in whom the brain was contoured, the absolute brain volume receiving ≤ 50 Gy and > 60 Gy was significantly larger in patients with LG3 toxicity for all patients combined (p < 0.05). Prescription dose, brainstem dose and PTV volume were not correlated to LG3 toxicity. Conclusion: Our results indicate the importance of minimizing the brain volume irradiated, and brainstem and cochlea doses to reduce the risk of late toxicities following brain radiotherapy.

60 APPLIED LIFE SCIENCES↗

Using computer-extracted image features for modeling of error-making patterns in detection of mammographic masses among radiology residents

Purpose: Mammography is the most widely accepted and utilized screening modality for early breast cancer detection. Providing high quality mammography education to radiology trainees is essential, since excellent interpretation skills are needed to ensure the highest benefit of screening mammography for patients. The authors have previously proposed a computer-aided education system based on trainee models. Those models relate human-assessed image characteristics to trainee error. In this study, the authors propose to build trainee models that utilize features automatically extracted from images using computer vision algorithms to predict likelihood of missing each mass by the trainee. This computer vision-based approach to trainee modeling will allow for automatically searching large databases of mammograms in order to identify challenging cases for each trainee. Methods: The authors’ algorithm for predicting the likelihood of missing a mass consists of three steps. First, a mammogram is segmented into air, pectoral muscle, fatty tissue, dense tissue, and mass using automated segmentation algorithms. Second, 43 features are extracted using computer vision algorithms for each abnormality identified by experts. Third, error-making models (classifiers) are applied to predict the likelihood of trainees missing the abnormality based on the extracted features. The models are developed individually for each trainee using his/her previous reading data. The authors evaluated the predictive performance of the proposed algorithm using data from a reader study in which 10 subjects (7 residents and 3 novices) and 3 experts read 100 mammographic cases. Receiver operating characteristic (ROC) methodology was applied for the evaluation. Results: The average area under the ROC curve (AUC) of the error-making models for the task of predicting which masses will be detected and which will be missed was 0.607 (95% CI,0.564-0.650). This value was statistically significantly different from 0.5 (p < 0.0001). For the 7 residents only, the AUC performance of the models was 0.590 (95% CI,0.537-0.642) and was also significantly higher than 0.5 (p = 0.0009). Therefore, generally the authors’ models were able to predict which masses were detected and which were missed better than chance. Conclusions: The authors proposed an algorithm that was able to predict which masses will be detected and which will be missed by each individual trainee. This confirms existence of error-making patterns in the detection of masses among radiology trainees. Furthermore, the proposed methodology will allow for the optimized selection of difficult cases for the trainees in an automatic and efficient manner.

60 APPLIED LIFE SCIENCES↗