Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning framework”

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 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Embedded FPGA developments in 130 nm and 28 nm CMOS for machine learning in particle detector readout

Embedded field programmable gate array (eFPGA) technology allows the implementation of reconfigurable logic within the design of an application-specific integrated circuit (ASIC). This approach offers the low power and efficiency of an ASIC along with the ease of FPGA configuration, particularly beneficial for the use case of machine learning in the data pipeline of next-generation collider experiments. An open-source framework called "FABulous" was used to design eFPGAs using 130 nm and 28 nm CMOS technology nodes, which were subsequently fabricated and verified through testing. The capability of an eFPGA to act as a front-end readout chip was assessed using simulation of high energy particles passing through a silicon pixel sensor. A machine learning-based classifier, designed for reduction of sensor data at the source, was synthesized and configured onto the eFPGA. A successful proof-of-concept was demonstrated through reproduction of the expected algorithm result on the eFPGA with perfect accuracy. Finally, further development of the eFPGA technology and its application to collider detector readout is discussed.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Physics-guided machine learning approaches to predict the ideal stability properties of fusion plasmas

One of the biggest challenges to achieve the goal of producing fusion energy in tokamak devices is the necessity of avoiding disruptions of the plasma current due to instabilities. The disruption event characterization and forecasting (DECAF) framework has been developed in this purpose, integrating physics models of many causal events that can lead to a disruption. Two different machine learning approaches are proposed to improve the ideal magnetohydrodynamic (MHD) no-wall limit component of the kinetic stability model included in DECAF. First, a random forest regressor (RFR), was adopted to reproduce the DCON computed change in plasma potential energy without wall effects for a large database of equilibria from the national spherical torus experiment (NSTX). This tree-based method provides an analysis of the importance of each input feature, giving an insight into the underlying physics phenomena. Secondly, a fully-connected neural network has been trained on sets of calculations with the DCON code, to get an improved closed form equation of the no-wall β limit as a function of the relevant plasma parameters indicated by the RFR. The neural network has been guided by physics theory of ideal MHD in its extension outside the domain of the NSTX experimental data. The estimated value has been incorporated into the DECAF kinetic stability model and tested against a set of experimentally stable and unstable discharges. Moreover, the neural network results were used to simulate a real-time stability assessment using only quantities available in real-time. Finally, the portability of the model was investigated, showing encouraging results by testing the NSTX-trained algorithm on the mega ampere spherical tokamak (MAST).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Predicting Si-Anode Calendar Life Using Machine Learning: Correlating Electrolyte Properties and Electrochemical Signals

This study evaluates novel electrolytes tailored for Si-containing anodes to promote calendar-life. Drawing inspiration from advancements in electrolytes for Li-metal cells, the work investigates correlations between predicted electrolyte properties and measured electrochemical performance using several machine-learning models. By leveraging machine learning and advanced modeling techniques, this study aims to establish predictive frameworks that accelerate calendar-aging experiments and inform rational electrolyte design for Si-containing cells. In the present study, fifteen different electrolytes are evaluated in a Si-containing cell using an accelerated calendar-life protocol. For each electrolyte considered, 87 properties (features) from the Advanced Electrolyte Model were produced to identify key property/performance relationships. In this study, the best performing electrolytes were generally those formulations that included non-coordinating fluoroether solvents, and the most predictive features for long-term calendar-life were features related to salt concentration and electrolyte viscosity as well as early capacity, ionic conductivity, and Coulombic efficiency measurements. The framework developed in this study correlating electrolyte properties to measured electrochemical performance is expected to accelerate electrolyte design for Si-containing anodes and ultimately enable high-energy-density, long-life Li-ion batteries.

25 - ENERGY STORAGE↗
DOE OSTI2022

Direction-optimizing Label Propagation Framework for Structure Detection in Graphs: Design, Implementation, and Experimental Analysis

Label Propagation is not only a well-known machine learning algorithm for classification but also an effective method for discovering communities and connected components in networks. We propose a new Direction-optimizing Label Propagation Algorithm (DOLPA) framework that enhances the performance of the standard Label Propagation Algorithm (LPA), increases its scalability, and extends its versatility and application scope. As a central feature, the DOLPA framework relies on the use of frontiers and alternates between label push and label pull operations to attain high performance. It is formulated in such a way that the same basic algorithm can be used for finding communities or connected components in graphs by only changing the objective function used. Additionally, DOLPA has parameters for tuning the processing order of vertices in a graph to reduce the number of edges visited and improve the quality of solution obtained. We present the design and implementation of the enhanced algorithm as well as our shared-memory parallelization of it using OpenMP. We also present an extensive experimental evaluation of our implementations using the LFR benchmark and real-world networks drawn from various domains. Compared with an implementation of LPA for community detection available in a widely used network analysis software, we achieve at most five times the F-Score while maintaining similar runtime for graphs with overlapping communities. We also compare DOLPA against an implementation of the Louvain method for community detection using the same LFR-graphs and show that DOLPA achieves about three times the F-Score at just 10% of the runtime. For connected component decomposition, our algorithm achieves orders of magnitude speedups over the basic LP-based algorithm on large-diameter graphs, up to 13.2× speedup over the Shiloach-Vishkin algorithm, and up to 1.6× speedup over Afforest on an Intel Xeon processor using 40 threads.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Multivariate Machine Learning Models of Nanoscale Porosity from Ultrafast NMR Relaxometry

Abstract Nanoporous materials are of great interest in many applications, such as catalysis, separation, and energy storage. The performance of these materials is closely related to their pore sizes, which are inefficient to determine through the conventional measurement of gas adsorption isotherms. Nuclear magnetic resonance (NMR) relaxometry has emerged as a technique highly sensitive to porosity in such materials. Nonetheless, streamlined methods to estimate pore size from NMR relaxometry remain elusive. Previous attempts have been hindered by inverting a time domain signal to relaxation rate distribution, and dealing with resulting parameters that vary in number, location, and magnitude. Here we invoke well‐established machine learning techniques to directly correlate time domain signals to BET surface areas for a set of metal‐organic frameworks (MOFs) imbibed with solvent at varied concentrations. We employ this series of MOFs to establish a correlation between NMR signal and surface area via partial least squares (PLS), following screening with principal component analysis, and apply the PLS model to predict surface area of various nanoporous materials. This approach offers a high‐throughput, non‐destructive way to assess porosity in c.a. one minute. We anticipate this work will contribute to the development of new materials with optimized pore sizes for various applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Advances in solar forecasting: Computer vision with deep learning

Renewable energy forecasting is crucial for integrating variable energy sources into the grid. It allows power systems to address the intermittency of the energy supply at different spatiotemporal scales. To anticipate the future impact of cloud displacements on the energy generated by solar facilities, conventional modeling methods rely on numerical weather prediction or physical models, which have difficulties in assimilating cloud information and learning systematic biases. Augmenting computer vision with machine learning overcomes some of these limitations by fusing real-time cloud cover observations with surface measurements acquired from multiple sources. This Review summarizes recent progress in solar forecasting from multisensor Earth observations with a focus on deep learning, which provides the necessary theoretical framework to develop architectures capable of extracting relevant information from data generated by ground-level sky cameras, satellites, weather stations, and sensor networks. Overall, machine learning has the potential to significantly improve the accuracy and robustness of solar energy meteorology; however, more research is necessary to realize this potential and address its limitations.

14 SOLAR ENERGY↗
DOE OSTI2025

Autonomous organic synthesis for redox flow batteries via flexible batch Bayesian optimization

Traditional trial-and-error methods for materials discovery are inefficient to meet the urgent demands posed by the rapid progression of climate change. This urgency has driven the increasing interest in integrating robotics and machine learning into materials research to accelerate experimental learning. However, idealized decision-making frameworks to achieve maximum sampling efficiency are not always compatible with high-throughput experimental workflows inside a laboratory. For multi-step chemical processes, differences in hardware capacities can complicate the digital framework by introducing constraints on the maximum number of samples in each step of the experiment, hence causing varying batch sizes in variable selection within the same batch. Therefore, designing flexible sampling algorithms is necessary to accommodate the multi-step synthesis with practical constraints unique to each high-throughput workflow. In this work, we designed and employed three strategies on a high-throughput robotic platform to optimize the sulfonation reaction of redox-active molecules used in flow batteries. Our strategies adapt to the multi-step experimental workflow, where their formulation and heating steps are separate, causing varying batch size requirements. By strategically sampling using clustering and mixed-variable batch Bayesian optimization, we were able to iteratively identify optimal conditions that maximize the yields. Our work presents a flexible approach that allows tailoring the machine learning decision-making to suit the practical constraints in individual high-throughput experimental platforms, followed by performing resource-efficient yield optimization using available open-source Python libraries.

Tamura, Clara [Univ. of Washington, Seattle, WA (U↗
DOE OSTI2018

Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics

Machine learning has been effective at detecting patterns and predicting the response of systems that behave free of natural laws. Examples include learning crowd dynamics, recommender systems and autonomous mobility. There also have been applications to the search for new materials that draw upon big-data classification problems. Though, when it comes to physical systems governed by conservation laws, the role of machine learning has been more limited. Here, we present our recent work in exploring the role of machine learning methods in discovering, or aiding, the search for physics. Specifically, we focus on using machine learning algorithms to represent high-dimensional free energy surfaces with the goal of identifying precipitate morphologies in alloy systems. Traditionally, this problem has been approached by combining phase field models, which impose first-order dynamics, with elasticity, to traverse a free energy landscape in search of minima. Equilibrium precipitate morphologies occur at these minima. Here, we exploit the machine learning methods to represent high-dimensional data, combined with surrogate optimization, sensitivity analysis and multifidelity modeling as an alternate framework to explore phenomena controlled by energy extremization. This combination of data-driven methods offers an alternative to the imposition of first-order dynamics via phase field methods, and represents one aspect of applying machine learning to materials physics.

42 ENGINEERING↗
DOE OSTI2025

Stable Machine‐Learning Parameterization of Subgrid Processes in a Comprehensive Atmospheric Model Learned From Embedded Convection‐Permitting Simulations

Modern climate projections often suffer from inadequate spatial and temporal resolution due to computational limitations, resulting in inaccurate representations of sub-grid processes. A promising technique to address this is the multiscale modeling framework (MMF), which embeds a kilometer-resolution cloud-resolving model (CRM) within each atmospheric column of a host climate model to replace traditional convection and cloud parameterizations. Machine learning offers a unique opportunity to make MMF more accessible by emulating the embedded CRM and reducing its substantial computational cost. Although many studies have demonstrated proof-of-concept success of achieving stable hybrid simulations, it remains a challenge to achieve near operational-level success with real geography and comprehensive variable emulation that includes, for example, explicit cloud condensate coupling. In this study, we present a stable hybrid model capable of integrating for at least 5 years with near operational-level complexity, including coarse-grid geography, seasonality, explicit cloud condensate and wind predictions, and land coupling. Our model demonstrates skillful online performance, achieving a 5-year zonal mean tropospheric temperature bias within 2 K, water vapor bias within 1 g/kg, and a precipitation root mean square error of 0.96 mm/day. Key factors contributing to our online performance include an expressive U-Net architecture and physical thermodynamic constraints for microphysics. With microphysical constraints mitigating unrealistic cloud formation, our work is the first to demonstrate realistic multi-year cloud condensate climatology under the MMF framework. Despite these advances, online diagnostics reveal persistent biases in certain regions, highlighting the need for innovative strategies to further optimize online performance.

Hu, Zeyuan [NVIDIA Corporation, Santa Clara, CA (U↗
DOE OSTI2026

Leveraging machine learning to enhance aerosol classification using Single-Particle Mass Spectrometry

Advancing automated classification of atmospheric aerosols from Single-Particle Mass Spectrometry (SPMS) data remains challenging due to overlapping ion signatures, compositional diversity, and limited labeled data. This study evaluates supervised and semi-supervised learning frameworks to enhance aerosol identification by jointly leveraging labeled and unlabeled spectra. Four models were compared: a supervised Support Vector Machine (SVM), a self-training SVM, a stacked autoencoder classifier, and a stacked autoencoder trained using a temporal-ensembling Mean Teacher approach. All models achieved high and stable accuracies (90.0 %–91.1 %), surpassing previous results on the same dataset (87 %) and matching the performance of state-of-the-art deep learning methods. Despite small global metric differences (≤ 1 %), semi-supervised variants yielded up to 5 %–10 % improvements for compositionally rare particle types – such as soot (0.77 % of spectra, F1-score: 0.93–0.97) and hazelnut pollen (0.98 % of spectra, F1-score: 0.97–1.00) – equating to roughly ∼ 187 additional correctly classified spectra. These gains are scientifically significant, as such rare particles exert disproportionate influence on radiative absorption and ice nucleation processes; their improved detection reduces modeled uncertainties in aerosol absorption optical depth and mixed-phase cloud ice nucleation rates. The models' residual misclassifications (≈ 9 %) largely arise from true spectral overlap among chemically adjacent species (e.g., Na- vs. K-feldspar, coated vs. uncoated feldspars), reflecting physical compositional continuity rather than algorithmic error. Collectively, these findings demonstrate that leveraging unlabeled data to learn robust spectral representations and refine classification enhances both fidelity and interpretability, bridging data-driven analysis with aerosol–climate process understanding.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Multi‐Decadal Dynamics of Wetland Methane Emissions Revealed by Knowledge‐Guided Machine Learning

Measurement of methane fluxes (FCH 4 ) from natural systems, such as wetlands, has lagged far behind carbon dioxide fluxes. Short and fragmented wetland FCH 4 data limit our ability to assess its long-term dynamics and potential climate feedbacks. Extrapolating short-term FCH 4 records to recent decades remains challenging for both process-based models and data-driven machine learning (ML) approaches. Here, we develop a knowledge-guided ML framework that integrates eddy covariance (EC) FCH 4 observations, field warming experiments, and biogeochemical knowledge to reconstruct the long-term FCH 4 budgets and trends. Focusing on the 11 longest EC monitoring sites in the AmeriFlux network, we found considerable variability in multi-decadal trends of wetland FCH 4 , with increases up to 14% per decade from 2000 to 2024. We also found that the strength of these increasing trends declines from high to low latitudes, highlighting the vulnerability of northern wetlands. This work presents novel and robust reconstructions of long-term wetland FCH 4 , offering critical benchmark datasets for bottom-up ecosystem models and advancing fundamental understanding of wetland biogeochemistry.

AmeriFlux site↗
DOE OSTI2021

Development of Digital Twin Predictive Model for PWR Components: Updates on Multi Times Series Temperature Prediction Using Recurrent Neural Network, DMW Fatigue Tests, System Level Thermal-Mechanical-Stress Analysis

The long-term operation (LTO) of nuclear power plant (NPP) beyond their original design life of 40 years, can lead to more material damage associated with cyclic fatigue under thermal-mechanical loading cycles and associated long-term exposure of reactor material to the deleterious reactor-coolant environments. However, under this LTO condition the reactor components can still safely operate but may require more frequent Nondestructive Evaluation (NDE) of reactor components. Frequent NDE requirement may lead to frequent shutdown of the NPP. This in turn can lead to power outage and additional NDE-inspection-cost related economic loss. The economic loss can be minimized by reducing uncertainty in life estimation of safety-critical pressure boundary components and by implementing more digital approach such as by using upcoming digital-twin (DT) technology for predicting the structural states (e.g., time and location dependent inside/outside thickness temperature, stress, strain, plastic deformation, etc.) and associated fatigue life of a component in real time. Towards this goal Argonne National Laboratory (ANL) with the sponsorship of DOE Light Water Reactor Sustainability (LWRS) program is working on the development of a DT framework that can be used for real time environmental fatigue prediction of reactor components. The DT framework is based on limited experiment-data, Artificial-intelligence (AI) – Machine-Learning (ML) - Deep-Learning (DL) based techniques and Multiphysics-computational-mechanics such as finite element (FE) based modeling tools. Towards this overall goal, following are some of the major contributions made during the FY21: 1) Multiple 82/182 dissimilar metal weld (DMW) specimens (both solid-weld and joint-weld representing the actual reactor multi-metal nozzles) were fatigue tested. The resulting fatigue lives were compared to the NUREG-6909 based best-fit and design fatigue curves. Additionally, the results of 52/152 DMW fatigue specimens (which were recently tested at Republic of Korea under the sponsorship of International Nuclear Energy Research Initiative - INERI program) were compared to the NUREG-6909 based best-fit and design fatigue curves. From the comparison of 82/182 and 52/152 DMW test data with NUREG-6909 best-fit curve, most of the reported test data fall way away from the NUREG-6909 suggested best-fit or mean curve. The NUREG-6909 suggested best-fit curve is the best-fit curve of austenitic stainless steel and due to lack of enough data on Nickel-based welds, this is currently being used for predicting the life of Nickel-alloy-based welded components. However, the above observation may require higher scaling factor (e.g., ASME suggested factor of 20 on cycles rather than the current NUREG-6909 suggested factor of 12 on cycles) for scaling the austenitic-stainless-steel best-fit-curve for estimating the design or safe-life of a welded component. Accordingly, for example, if a DMW component experience a strain amplitude of 0.6% the PWR-water life of the component would be 52 cycles instead of 85 cycles. However, more DMW tests are required to further ascertain the above-mentioned observations. 2) A system level CAD and finite element model were developed which consists of reactor pressure vessel (RPV), part of steam generator (SG), part of pressurizer (PRZ), hot leg (HL), and surge line (SL). This is with detailed nozzle geometry and thermal-mechanical material properties of different metals to simulate realistic thermal-mechanical stress under connected system global thermal-mechanical boundary conditions. 3) Different system level heat transfer analyses were performed with estimation of relevant heat transfer coefficients. The resulting data were used in subsequent system level thermal-mechanical stress analysis and for generating spatial-temporal training and validation data for a system level digital-twin based temperature predictor. Transient heat transfer analyses were performed considering thermal boundary condition under design-basis (DB) loading and EDF (Électricité de France) data-based grid-load-following (EDF-GLF) loading cycles. 4) System level thermal-mechanical stress analysis was performed for identifying damage-prone hotspots and for future extension of the model for cyclic state prediction. From the system-level model simulation under DB loading cycle it is found that HL and the SL nozzle that connect to the HL can experience significant stress and strain and could be one of the weakest links in the overall reactor coolant system (RCS). 5) An AI/ML based DT model was developed for multi-time-series temperature prediction at any inside/outside thickness locations of PWR pressure boundary components. This is by using Recurrent-neural-network (RNN) and keras machine learning libraries. The RNN model was validated against two laboratory test-based data sets with one obtained through ANL’s in-air fatigue test system and other through PWR-water test loop. The experimentally validated DT model further validated against FE model results to predict thermal scarification related spatialtemporal temperatures at random locations of a component. The well validated DT model was then used for demonstrating spatial-temporal temperature prediction under 100+ years of reactor operation subjected to combined DB, EDF-GLF and randomized grid-load-following (RANDOMGLF) loading Cycles. The expert-elicitation DT model framework was developed assuming field/input/process measurements can be available from a few existing plant sensors and can readily be used by the NPP operators. The above temperature prediction model will feed to the next-step stress analysis model based on which the life of a component can be predicted in realtime, which is one of our future works.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2021

Rotor blade imbalance fault detection for variable-speed marine current turbines via generator power signal analysis

Marine hydrokinetic (MHK) turbines extract renewable energy from oceanic environments. However, due to the harsh conditions that these turbines operate in, system performance naturally degrades over time. Thus, ensuring efficient condition-based maintenance is imperative towards guaranteeing reliable operation and reduced costs for marine hydrokinetic power. This work proposes a novel framework aimed at identifying and classifying the severity of rotor blade pitch imbalance faults experienced by marine current turbines (MCTs). In the framework, a Continuous Morlet Wavelet Transform (CMWT) is first utilized to acquire the wavelet coefficients encompassed within the 1P frequency range of the turbine's rotor shaft. From these coefficients, several statistical indices are tabulated into a six-dimensional feature space. Next, Principle Component Analysis (PCA) is employed on the resulting feature space for dimensionality reduction, and then the application of a K-Nearest Neighbor (KNN) machine learning algorithm is utilized for fault detection and severity classification. The effectiveness of the proposed framework is validated using a high-fidelity MCT numerical simulation platform, where results demonstrate that the presence of a pitch imbalance fault can be accurately detected 100% of the time and correctly classified based upon severity more than 97% of the time.

42 ENGINEERING↗
DOE OSTI2024

A General Materials Data Science Framework for Quantitative 2D Analysis of Particle Growth from Image Sequences

Abstract Phase transformations are a challenging problem in materials science, which lead to changes in properties and may impact performance of material systems in various applications. We introduce a general framework for the analysis of particle growth kinetics by utilizing concepts from machine learning and graph theory. As a model system, we use image sequences of atomic force microscopy showing the crystallization of an amorphous fluoroelastomer film. To identify crystalline particles in an amorphous matrix and track the temporal evolution of the particle dispersion, we have developed quantitative methods of 2D analysis. 700 image sequences were analyzed using a neural network architecture, achieving 0.97 pixel-wise classification accuracy as a measure of the correctly classified pixels. The growth kinetics of isolated and impinged particles were tracked throughout time using these image sequences. The relationship between image sequences and spatiotemporal graph representations was explored to identify the proximity of crystallites from each other. The framework enables the analysis of all image sequences without the requirement of sampling for specific particles or timesteps for various materials systems.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Robust Real-Time Modeling of Distribution Systems with Data-Driven Grid-Wise Observability (Final Technical Report)

The overall objective of this project is to leverage existing and emerging sensor measurements to develop data-driven observability enhancement algorithms as well as robust state estimation and parameter identification techniques to enable real-time grid-wise monitoring and modeling of loads and distributed energy resources (DERs). The project resulted in a holistic framework with the following key components: 1) data-driven and machine learning-based grid-edge visibility enhancement, 2) robust branch-current-based state estimation (BCSE), and 3) robust real-time steady-state and dynamic-state modeling of loads and DERs. The research outcomes have provided utility companies better network visibility, higher-fidelity load/DER models, and more accurate assessment of DERs’ impacts, thus, facilitating the integration of renewable energy sources. The synergistic collaborative project among Iowa State University (ISU), Argonne National Laboratory (ANL), Electric Power Research Center (EPRC), SIEMENS Industry, Alliant Energy, Cedar Falls Utilities (CFU), and Maquoketa Valley Electric Cooperative (MVEC) to leverage the team’s extensive expertise and experience in power distribution systems, state estimation, online modeling and identification, and DER integrations. The proposed frameworks have been verified with industry adopted software and attempted integrated with existing tool wherever possible

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A Predictive Prescription Framework for Stochastic Unit Commitment Using Boosting Ensemble Learning Algorithms

To take unit commitment (UC) decisions under uncertain load, most existing stochastic optimization (SO) frameworks adopt a generic representation of uncertainty. While load levels that materialize on a particular day are influenced by various covariates (such as the day of the week or temperature), SO frameworks typically disregard such side observations, wasting actionable information that could significantly enhance decision quality. Here, this article proposes a contextual SO (CSO) framework for UC under uncertain load, which can effectively exploit covariate observations in conjunction with a class of machine learning (ML) algorithms to improve the out-of-sample performance of UC decisions. It shows how three ML algorithms, adaptive boosting, gradient boosted trees, and extreme gradient boosting, can be used to this end, constituting the first application of these algorithms in any CSO framework. Using real-world data harvested from the New York ISO grid, we measure the out-of-sample performance of the framework in terms of total operation cost, shed load values, locational marginal prices, and total payments by the loads, against several benchmark methods proposed in the literature. The article has an online companion (Yurdakul et al.), wherein we present additional results and lay out further mathematical formulations used in this work.

42 ENGINEERING↗
DOE OSTI2019

Deep learning and radiomics: the utility of Google TensorFlow™ Inception in classifying clear cell renal cell carcinoma and oncocytoma on multiphasic CT

Purpose: Currently, all solid enhancing renal masses without microscopic fat are considered malignant until proven otherwise and there is substantial overlap in the imaging findings of benign and malignant renal masses, particularly between clear cell RCC (ccRCC) and benign oncocytoma (ONC). Radiomics has attracted increased attention for its utility in pre-operative work-up on routine clinical images. Radiomics based approaches have converted medical images into mineable data and identified prognostic imaging signatures that machine learning algorithms can use to construct predictive models by learning the decision boundaries of the underlying data distribution. The TensorFlow™ framework from Google is a state-of-the-art open-source software library that can be used for training deep learning neural networks for performing machine learning tasks. The purpose of this study was to investigate the diagnostic value and feasibility of a deep learning-based renal lesion classifier using open-source Google TensorFlow™ Inception in differentiating ccRCC from ONC on routine four-phase MDCT in patients with pathologically confirmed renal masses. Methods: With institutional review board approval for this 1996 Health Insurance Portability and Accountability Act compliant retrospective study and a waiver of informed consent, we queried our institution’s pathology, clinical, and radiology databases for histologically proven cases of ccRCC and ONC obtained between January 2000 and January 2016 scanned with a an intravenous contrast-enhanced four-phase renal mass protocol (unenhanced (UN), corticomedullary (CM), nephrographic (NP), and excretory (EX) phases). To extract features to be used for the machine learning model, the entire renal mass was contoured in the axial plane in each of the four phases, resulting in a 3D volume of interest (VOI) representative of the entire renal mass. We investigated thirteen different approaches to convert the acquired VOI data into a set of images that adequately represented each tumor which was used to train the final layer of the neural network model. Training was performed over 4000 iterations. In each iteration, 90% of the data were designated as training data and the remaining 10% served as validation data and a leave-one-out cross-validation scheme was implemented. Accuracy, sensitivity, specificity, positive (PPV) and negative predictive (NPV) values, and CIs were calculated for the classification of the thirteen processing modes. Results: We analyzed 179 consecutive patients with 179 lesions (128 ccRCC and 51 ONC). The ccRCC cohort had a mean size of 3.8 cm (range 0.8–14.6 cm) and the ONC cohort had a mean lesion size of 3.9 cm (range 1.0–13.1 cm). The highest specificity and PPV (52.9% and 80.3%, respectively) were achieved in the EX phase when we analyzed the single mid-slice of the tumor in the axial, coronal and sagittal plane, and when we increased the number of mid-slices of the tumor to three, with an accuracy of 75.4%, which also increased the sensitivity to 88.3% and the PPV to 79.6%. Using the entire tumor volume also showed that classification performance was best in the EX phase with an accuracy of 74.4%, a sensitivity of 85.8% and a PPV of 80.1%. When the entire tumor volume, plus mid-slices from all phases and all planes presented as tiled images, were submitted to the final layer of the neural network we achieved a PPV of 82.5%. Conclusions: The best classification result was obtained in the EX phase among the thirteen classification methods tested. Our proof of concept study is the first step towards understanding the utility of machine learning in the differentiation of ccRCC from ONC on routine CT images. We hope this could lead to future investigation into the development of a multivariate machine learning model which may augment our ability to accurately predict renal lesion histology on imaging.

62 RADIOLOGY AND NUCLEAR MEDICINE↗