Advanced liver surgery training in collaborative VR environments
Not Available
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “medical training”
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.
Neutron Source Facility of the National Science Center “Kharkiv Institute of Physics and Technology” at Kharkiv, Ukraine
Argonne National Laboratory developed, designed, and supported the construction of a state-of-the-art Neutron Source Facility (NSF) at the Kharkov Institute of Physics and Technology (KIPT) in Kharkov Ukraine, under the U.S. DOE NNSA Russian Research Reactor Fuel Return (RRRFR) program. Ukraine approved the return of all highly enriched uranium in the country to Russia prior to the 2012 Nuclear Security Summit in return for the RRRFR program to fund the development, the design, and the construction of the NSF. The facility is designed to produce medical isotopes, train nuclear professionals, support the Ukrainian nuclear industry, and provide experimental capabilities for performing reactor physics, materials, and basic science research. The NSF was successfully started and operated in August 2021. The NSF is the first facility of this type in the world, and it will be used to understand the physics of driven systems for energy production and the disposal of spent nuclear fuels. The NSF consists of a subcritical assembly using low enriched uranium (LEU) fuel driven with an electron accelerator. The NSF target design utilizes tungsten or natural uranium for producing neutrons through photonuclear reactions using 100-MeV electrons. The accelerator power is 100 KW, which produces 3x10 14 neutrons per second from the uranium target. The subcritical assembly is designed to obtain the highest possible neutron flux intensity with an effective neutron multiplication factor of less than 0.98. Passive safety, reliability, and environmental considerations were included in the NSF design. The NSF utilization study shows that this neutron source has the capability of producing different medical isotopes. Several horizontal neutron channels are incorporated for performing applied and basic research. The NSF is configured to accommodate future design upgrades and new missions. The facility design was approved by the Ukraine Academy of Sciences before starting the NSF construction. The construction, the equipment installation, and the operation of the different systems of the NSF were completed and approved by the Ukrainian regulators. In July 2020, the State Nuclear Regulatory Inspectorate of Ukraine (SNRIU) issued a license for the physical startup of the NSF. The construction of facility was completed in early 2021.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Draft Prototype Microreactor Transportation Safety Program
Microreactors are compact reactors capable of producing less than 50 megawatts of electrical energy. Typically, these reactors are factory-fabricated and designed to be easily transportable by truck, rail, vessel, or air. Microreactor designs often assume that the unit can be transported containing either unirradiated or irradiated fuel. The interest in microreactors is driven by several factors, including the need to generate power on at remote locations, at military installations, at facilities such as data centers, and in areas recovering from natural disasters. The U.S. Department of Defense is actively pursuing the microreactor concept to meet the increasing energy demands of military operations that require portable and dense power sources. Commercial vendors are also exploring microreactor concepts. The report Microreactor Transportation Emergency Planning Challenges (Maheras et al. 2024) outlined the emergency planning challenges associated with the transportation of microreactors by road, rail, and by barge/ship. The successful commercial deployment and redeployment of microreactors will also require the development of microreactor transportation safety programs. The elements in these safety programs are not specific to microreactors; however, the transport of microreactors may pose unique challenges in these areas. This report builds on the report Microreactor Transportation Emergency Planning Challenges (Maheras et al. 2024) and develops the elements of a prototype microreactor transportation safety program that describes the elements that should be contained vendor-developed microreactor transportation safety programs, identifying the unique elements associated with microreactor transport. This will provide vendors and their transportation contractors a basis for their transportation planning and will accelerate the commercial deployment and redeployment of microreactors by identifying those issues unique to microreactor transport. The emphasis of this report is on highway transport of microreactors. This is based on a U.S. Nuclear Regulatory Commission transportation package approval strategy of crawl-walk-run, where transport by highway is evaluated first (Coles et al. 2021, 2024, Maheras et al. 2021), then other surface modes (rail and barge/ship), and finally air transport. Evaluation of maritime transport of microreactors was recently initiated (Rigato et al. 2024, Maheras et al. 2025). The report first discusses microreactors in general and microreactor transportation safety program planning assumptions. The report then provides a description of the transportation safety planning process and provides an extensive discussion of the elements of transportation safety programs. Specific elements examined included transportation roles and responsibilities, transportation planning, transportation mode and route selection, carrier selection, transportation packaging, advance notification of shipments, public information and communications, emergency response plans and procedures, inspections, security, safe parking, shipment tracking, weather and road conditions, medical preparedness, training and exercises, and program evaluation. The report then identifies the unique elements of a transportation safety program associated with microreactor transport. These unique elements were in the areas of: the unusual nature of microreactor designs, compensatory measures, increased radiation dose rates in the vicinity of microreactors, transportation package approval versus 10 CFR 50.59, and the use of a risk-informed transportation package approval process.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
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↗
Residents-as-Teachers Curriculum for Radiation Oncology: A Targeted Needs Assessment
Achieving competency as educators is increasingly recognized as a critical part of residents’ training in graduate medical education across specialties. In addition to teaching medical students, radiation oncology residents often play a vital role in peer and interprofessional education. We conducted a survey to identify the needs of radiation oncology residents for developing skills in teaching.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Sequential Inference of Hospitalization Electronic Health Records Using Probabilistic Models
In the dynamic hospital setting, decision support can be a valuable tool for improving patient outcomes. Data-driven inference of future outcomes is challenging in this dynamic setting, where long sequences such as laboratory tests and medications are updated frequently. This is due in part to heterogeneity of data types and mixed-sequence types contained in variable length sequences. In this work we design a probabilistic unsupervised model for multiple arbitrary-length sequences contained in hospitalization Electronic Health Record (EHR) data. The model uses a latent variable structure and captures complex relationships between medications, diagnoses, laboratory tests, neurological assessments, and medications. It can be trained on original data, without requiring any lossy transformations or time binning. Inference algorithms are derived that use partial data to infer properties of the complete sequences, including their length and presence of specific values. We train this model on data from subjects receiving medical care in the Kaiser Permanente Northern California integrated healthcare delivery system. The results are evaluated against held-out data for predicting the length of sequences and presence of Intensive Care Unit (ICU) in hospitalization bed sequences. Our method outperforms a baseline approach, showing that in these experiments the trained model captures information in the sequences that is informative of their future values.
97 MATHEMATICS AND COMPUTING↗
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↗
Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization
Concept normalization, the task of linking phrases in text to concepts in an ontology, is useful for many downstream tasks including relation extraction, information retrieval, etc. We present a generate-and-rank concept normalization system based on our participation in the 2019 National NLP Clinical Challenges Shared Task Track 3 Concept Normalization. The shared task provided 13 609 concept mentions drawn from 100 discharge summaries. We first design a sieve-based system that uses Lucene indices over the training data, Unified Medical Language System (UMLS) preferred terms, and UMLS synonyms to generate a list of possible concepts for each mention. We then design a listwise classifier based on the BERT (Bidirectional Encoder Representations from Transformers) neural network to rank the candidate concepts, integrating UMLS semantic types through a regularizer. Our generate-and-rank system was third of 33 in the competition, outperforming the candidate generator alone (81.66% vs 79.44%) and the previous state of the art (76.35%). During postevaluation, the model’s accuracy was increased to 83.56% via improvements to how training data are generated from UMLS and incorporation of our UMLS semantic type regularizer. Analysis of the model shows that prioritizing UMLS preferred terms yields better performance, that the UMLS semantic type regularizer results in qualitatively better concept predictions, and that the model performs well even on concepts not seen during training. Our generate-and-rank framework for UMLS concept normalization integrates key UMLS features like preferred terms and semantic types with a neural network–based ranking model to accurately link phrases in text to UMLS concepts.
96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
This software offers methods and functions for training calibrated out-of-distribution detectors for medical image classification tasks. It includes functionalities for training, synthesizing data augmentations, calibration, and out-of-distribution detection. Developed using PyTorch, this software is compatible with standard neural network architectures used for imaging data. Additionally, it provides capabilities to compute evaluation metrics for assessing the performance and quality of the detectors.
Narayanaswamy, VivekSivaraman↗
Los Alamos National Laboratory Release of Cesium-137 Corrective Action Plan
This Corrective Action Plan (CAP) was developed by a team chartered by John Sarrao, Deputy Director for Science, Technology, and Engineering (DDSTE), to review and respond to the findings of the Joint National Nuclear Security Administration/Triad National Security (NNSA/Triad) Investigation Team (JIT) Joint Investigation Report for the “Sealed Source Recovery at the University of Washington Harborview Training and Research Facility Results in Release of Cesium-137 on May 2, 2019,” dated March 30, 2020. On May 2, 2019, International Isotopes, Inc. (INIS), a subcontractor to Triad National Security, LLC, inadvertently breached a sealed cesium-137 source at the University of Washington (UW), Harborview Medical Center Research and Training (HRT) building in downtown Seattle while attempting to recover the source for the National Nuclear Security Administration (NNSA) Off-Site Source Recovery Program (OSRP). The source breach resulted in contamination of personnel and the HRT building, as well as a release of radioactive material to the environment
07 ISOTOPE AND RADIATION SOURCES↗
Training calibration-based counterfactual explainers for deep learning models in medical image analysis
The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model’s predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Position-Enhanced Gradient Attack (PEGA) on Medical Language Models
Federated Learning (FL) enables collaborative training of language models on sensitive clinical notes without sharing the data. However, this paradigm is vulnerable to gradient inversion attacks that can reconstruct private data from shared gradients. We find that state-of-the-art attacks are less effective in the medical domain, failing to overcome the unique challenges posed by its specialized vocabulary and unstructured format. To address this, we introduce the Position-Enhanced Gradient Attack (PEGA), a novel attack that makes gradients position-aware by optimizing token and position embeddings simultaneously. PEGA employs two key innovations: a periodic sorting of positional embeddings to resolve token order ambiguity and a late-stage embedding replacement strategy to correct hard-to-recover critical tokens. To evaluate the leakage of sensitive data more directly, we also propose the Unified PHI-Recall (UPHI), a new metric measuring the recovery of Protected Health Information. Experiments on the MIMIC-III dataset show that PEGA significantly outperforms leading attacks like TAG and LAMP, particularly in its ability to reconstruct identifiable patient information, exposing a more severe and nuanced privacy risk in federated medical NLP.
Xu, Nuo [University of Minnesota]↗
SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation
This paper presents a novel approach to addressing the long-sequence problem in high-resolution medical images for Vision Transformers (ViTs). Using smaller patches as tokens can enhance ViT performance, but quadratically increases computation and memory requirements. Therefore, the common practice for applying ViTs to high-resolution images is either to: (a) employ complex sub-quadratic attention schemes or (b) use large to medium-sized patches and rely on additional mechanisms within the model to capture the spatial hierarchy of details. We propose Symmetrical Hierarchical Forest (SHF), a lightweight approach that adaptively patches the input image to increase token information density and encode hierarchical spatial structures into the input embedding. We then apply a reverse depatching scheme to the output embeddings of the transformer encoder, eliminating the need for convolution-based decoders. Unlike previous methods that modify attention mechanisms or use a complex hierarchy of interacting models, SHF can be retrofitted to any ViT model to allow it to learn the hierarchical structure of details in high-resolution images without requiring architectural changes. Experimental results demonstrate significant gains in computational efficiency and performance: on the PAIP WSI dataset, we achieved a 3∼32×speedup or a 2.95%∼7.03% increase in accuracy (measured by Dice score) at a 64K2 resolution with the same computational budget, compared to state-of-the-art production models. On the 3D medical datasets BTCV and KiTS, training was 6×faster, with accuracy gains of 6.93% and 5.9%, respectively, compared to models without SHF.
Zhang, Enzhi [Hokkaido University, Japan]↗
Radiation Oncology Resident Quality by National Resident Matching Program Metrics From 2007 to 2018
To quantify how the quality of US medical students accepted to radiation oncology (RO) training programs, as defined by National Resident Matching Program (NRMP) metrics, has changed over time.
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization
Objective: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. Methods: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. Results: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. Conclusions: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.
Zhou, Doudou↗
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↗
Unsupervised probabilistic models for sequential Electronic Health Records
We develop an unsupervised probabilistic model for heterogeneous Electronic Health Record (EHR) data. Utilizing a mixture model formulation, our approach directly models sequences of arbitrary length, such as medications and laboratory results. This allows for subgrouping and incorporation of the dynamics underlying heterogeneous data types. The model consists of a layered set of latent variables that encode underlying structure in the data. These variables represent subject subgroups at the top layer, and unobserved states for sequences in the second layer. We train this model on episodic data from subjects receiving medical care in the Kaiser Permanente Northern California integrated healthcare delivery system. The resulting properties of the trained model generate novel insight from these complex and multifaceted data. In addition, we show how the model can be used to analyze sequences that contribute to assessment of mortality likelihood.
59 BASIC BIOLOGICAL SCIENCES↗
DNA Methylation Patterns of Chronic Explosive Breaching in U.S. Military Warfighters
Background: Injuries from exposure to explosions rose dramatically during the Iraq and Afghanistan wars, which motivated investigation of blast-related neurotrauma. We have undertaken human studies involving military “breachers” —exposed to controlled, low-level blast during a 3-days explosive breaching course. Methods: We screened epigenetic profiles in peripheral blood samples from 59 subjects (in two separate U.S. Military training sessions) using Infinium MethylationEPIC BeadChips. Participants had varying numbers of exposures to blast over their military careers (empirically defined as high ≥ 40, and conversely, low < 39 breaching exposures). Daily self-reported physiological symptoms were recorded. Tinnitus, memory problems, headaches, and sleep disturbances are most frequently reported. Results: We identified 14 significantly differentially methylated regions (DMRs) within genes associated with cumulative blast exposure in participants with high relative to low cumulative blast exposure. Notably, NTSR1 and SPON1 were significantly differentially methylated in high relative to low blast exposed groups, suggesting that sleep dysregulation may be altered in response to chronic cumulative blast exposure. In comparing lifetime blast exposure at baseline (prior to exposure in current training), and top associated symptoms, we identified significant DMRs associated with tinnitus, sleep difficulties, and headache. Notably, we identified KCNN3, SOD3, MUC4, GALR1, and WDR45B, which are implicated in auditory function, as differentially methylated associated with self-reported tinnitus. These findings suggest neurobiological mechanisms behind auditory injuries in our military warfighters and are particularly relevant given tinnitus is not only a primary disability among veterans, but has also been demonstrated in active duty medical records for populations exposed to blast in training. Additionally, we found that differentially methylated regions associated with the genes CCDC68 and COMT track with sleep difficulties, and those within FMOD and TNXB track with pain and headache. Conclusion: Sleep disturbances, as well as tinnitus and chronic pain, are widely reported in U.S. military service members and veterans. As we have previously demonstrated, DNA methylation encapsulates lifetime exposure to blast. The current data support previous findings and recapitulate transcriptional regulatory alterations in genes involved in sleep, auditory function, and pain. These data uncovered novel epigenetic and transcriptional regulatory mechanism underlying the etiological basis of these symptoms.
60 APPLIED LIFE SCIENCES↗