Search

Despite the promising performance of convolutional neural networks (CNNs) in brain tumor diagnosis from magnetic resonance imaging (MRI), their integration into the clinical workflow has been limited. That is mainly due to the fact that the features contributing to a model's prediction are unclear to radiologists and hence, clinically irrelevant, i.e., lack of explainability. As the invaluable sources of radiologists' knowledge and expertise, radiology reports can be integrated with MRI in a contrastive learning (CL) framework, enabling learning from image-report associations, to improve CNN explainability. In this work, we train a multimodal CL architecture on 3D brain MRI scans and radiology reports to learn informative MRI representations. Furthermore, we integrate tumor location, salient to several brain tumor analysis tasks, into this framework to improve its generalizability. We then apply the learnt image representations to improve explainability and performance of genetic marker classification of pediatric Low-grade Glioma, the most prevalent brain tumor in children, as a downstream task. Our results indicate a Dice score of 31.1% between the model's attention maps and manual tumor segmentation (as an explainability measure) with test classification performance of 87.7%, significantly outperforming the baselines. These enhancements can build trust in our model among radiologists, facilitating its integration into clinical practices for more efficient tumor diagnosis.

Overcoming both modeling and computational challenges, we present, for the first time, the extended surface-brightness distribution model of a strongly-lensed source in a complex galaxy-cluster-scale system. We exploit the high-resolution Hubble Space Telescope (HST) imaging and extensive Multi Unit Spectroscopic Explorer spectroscopy to build an extended strong-lensing model, in a full multi-plane formalism, of SDSS J1029+2623, a lens cluster at $z = 0.588$ with three multiple images of a background quasar ($z = 2.1992$). Going beyond typical cluster strong-lensing modeling techniques, we include as observables both the positions of 26 pointlike multiple images from seven background sources, spanning a wide redshift range between 1.02 and 5.06, and the extended surface-brightness distribution of the strongly-lensed quasar host galaxy, over $\sim78000$ HST pixels. In addition, we model the light distribution of seven objects, angularly close to the strongly-lensed quasar host, over $\sim9300$ HST pixels. Our extended lens model reproduces well both the observed intensity and morphology of the quasar host galaxy in the HST F160W band (with a 0''.03 pixel scale). The reconstructed source shows a single, compact, and smooth surface-brightness distribution, for which we estimate an intrinsic magnitude of 23.3 $\pm$ 0.1 in the F160W band and a half-light radius of (2.39 $\pm$ 0.03) kpc. The increased number of observables enables the accurate determination of the total mass of line-of-sight halos lying angularly close to the extended arc. This work paves the way for a new generation of galaxy cluster strong-lens models, where additional, complementary lensing observables are directly incorporated as model constraints., Comment: 19 pages, 9 Figures, 2 Tables. Accepted for publication in ApJ

When an electron in a semiconductor gets excited to the conduction band the missing electron can be viewed as a positively charged particle, the hole. Due to the Coulomb interaction electrons and holes can form a hydrogen-like bound state called exciton. For cuprous oxide a Rydberg series up to high principle quantum numbers has been observed by Kazimierczuk et al. [Nature 514, 343 (2014)] with the extension of excitons up to the $\mu$m-range. In this region the correspondence principle should hold and quantum mechanics turn into classical dynamics. Due to the complex valence band structure of Cu$_2$O the classical dynamics deviates from a purely hydrogen-like behavior. The uppermost valence band in cuprous oxide splits into various bands resulting in a yellow and green exciton series. Since the system exhibits no spherical symmetry, the angular momentum is not conserved. Thus, the classical dynamics becomes non-integrable, resulting in the possibility of chaotic motion. Here we investigate the classical dynamics of the yellow and green exciton series in cuprous oxide for two-dimensional orbits in the symmetry planes as well as fully three-dimensional orbits. The analysis reveals substantial differences between the dynamics of the yellow and green exciton series. While it is mostly regular for the yellow series large regions in phase space with classical chaos do exist for the green exciton series., Comment: 10 pages, 10 figures, accepted for publication in Chaos

Let $X$ be a smooth projective integral variety over a finitely generated field $k$ of characteristic $p>0$. We show that the finiteness of the exponent of the $p$-primary part of $\mathrm{Br}(X_{k^s})^{G_k}$ is equivalent to the Tate conjecture for divisors, generalizing D'Addezio's theorem for abelian varieties to arbitrary smooth projective varieties. In combination with the Leray spectral sequence for rigid cohomology derived from the Berthelot conjecture recently proved by Ertl-Vezzani, we show that the cokernel of $\mathrm{Br}_{\mathrm{nr}}(K(X)) \rightarrow \mathrm{Br}(X_{k^s})^{G_k}$ is of finite exponent. This completes the $p$-primary part of the generalization of Artin-Grothendieck's theorem on relations between Brauer groups and Tate-Shafarevich groups to higher relative dimensions., Comment: Added an appendix by Veronika Ertl. All comments are welcome

We use motivic methods to give a quick proof of Berthelot's conjecture stating that the push-forward map in rigid cohomology of the structural sheaf along a smooth and proper map has a canonical structure of overconvergent F-isocrystal on the base., Comment: 28 pages

Observed evolution of the total mass distribution with redshift is crucial to testing galaxy evolution theories. To measure the total mass distribution, strong gravitational lenses complement the resolved dynamical observations currently limited to $z \lesssim 0.5$. Here we present the lens models for a pilot sample of seven galaxy-scale lenses from the ASTRO3D Galaxy Evolution with Lenses (AGEL) survey. The AGEL lenses, modeled using HST/WFC3-F140W images with Gravitational Lens Efficient Explorer (GLEE) software, have deflector redshifts between $0.3 < z_{\rm defl} < 0.9$. Assuming a power-law density profile with slope $\gamma$, we measure the total density profile for the deflector galaxies via lens modeling. We also measure the stellar velocity dispersions ($\sigma_{\rm obs}$) for four lenses and obtain $\sigma_{\rm obs}$ from SDSS-BOSS for the remaining lenses to test our lens models by comparing observed and model-predicted velocity dispersions. For the seven AGEL lenses, we measure an average density profile slope of $-1.95 \pm 0.09$ and a $\gamma$--$z$ relation that does not evolve with redshift at $z<1$. Although our result is consistent with some observations and simulations, it differs from other studies at $z<1$ that suggest the $\gamma$--$z$ relation evolves with redshift. The apparent conflicts among observations and simulations may be due to a combination of 1) systematics in the lensing and dynamical modeling; 2) challenges in comparing observations with simulations; and 3) assuming a simple power-law for the total mass distribution. By providing more lenses at $z_{\rm defl} > 0.5$, the AGEL survey will provide stronger constraints on whether the mass profiles evolve with redshift as predicted by current theoretical models., Comment: Accepted for publication in the Astrophysical Journal (ApJ) 24 Pages, 8 Figures, 3 Tables

Parallel computing is very important to accelerate the performance of software systems. Additionally, considering that a recurring challenge is to process high data volumes continuously, stream processing emerged as a paradigm and software architectural style. Several software systems rely on stream processing to deliver scalable performance, whereas open-source frameworks provide coding abstraction and high-level parallel computing. Although stream processing's performance is being extensively studied, the measurement of fault tolerance--a key abstraction offered by stream processing frameworks--has still not been adequately measured with comprehensive testbeds. In this work, we extend the previous fault recovery measurements with an exploratory analysis of the configuration space, additional experimental measurements, and analysis of improvement opportunities. We focus on robust deployment setups inspired by requirements for near real-time analytics of a large cloud observability platform. The results indicate significant potential for improving fault recovery and performance. However, these improvements entail grappling with configuration complexities, particularly in identifying and selecting the configurations to be fine-tuned and determining the appropriate values for them. Therefore, new abstractions for transparent configuration tuning are also needed for large-scale industry setups. We believe that more software engineering efforts are needed to provide insights into potential abstractions and how to achieve them. The stream processing community and industry practitioners could also benefit from more interactions with the high-level parallel programming community, whose expertise and insights on making parallel programming more productive and efficient could be extended., Comment: Extended paper version. arXiv admin note: substantial text overlap with arXiv:2404.06203

Nowadays, several software systems rely on stream processing architectures to deliver scalable performance and handle large volumes of data in near real-time. Stream processing frameworks facilitate scalable computing by distributing the application's execution across multiple machines. Despite performance being extensively studied, the measurement of fault tolerance-a key feature offered by stream processing frameworks-has still not been measured properly with updated and comprehensive testbeds. Moreover, the impact that fault recovery can have on performance is mostly ignored. This paper provides a comprehensive analysis of fault recovery performance, stability, and recovery time in a cloud-native environment with modern open-source frameworks, namely Flink, Kafka Streams, and Spark Structured Streaming. Our benchmarking analysis is inspired by chaos engineering to inject failures. Generally, our results indicate that much has changed compared to previous studies on fault recovery in distributed stream processing. In particular, the results indicate that Flink is the most stable and has one of the best fault recovery. Moreover, Kafka Streams shows performance instabilities after failures, which is due to its current rebalancing strategy that can be suboptimal in terms of load balancing. Spark Structured Streaming shows suitable fault recovery performance and stability, but with higher event latency. Our study intends to (i) help industry practitioners in choosing the most suitable stream processing framework for efficient and reliable executions of data-intensive applications; (ii) support researchers in applying and extending our research method as well as our benchmark; (iii) identify, prevent, and assist in solving potential issues in production deployments., Comment: Accepted for publication in the 18th ACM International Conference on Distributed and Event-Based Systems (DEBS'24), June 24-28, 2024, Villeurbanne, France, 12 pages

A bright ($m_{\rm F150W,AB}$=24 mag), $z=1.95$ supernova (SN) candidate was discovered in JWST/NIRCam imaging acquired on 2023 November 17. The SN is quintuply-imaged as a result of strong gravitational lensing by a foreground galaxy cluster, detected in three locations, and remarkably is the second lensed SN found in the same host galaxy. The previous lensed SN was called "Requiem", and therefore the new SN is named "Encore". This makes the MACS J0138.0$-$2155 cluster the first known system to produce more than one multiply-imaged SN. Moreover, both SN Requiem and SN Encore are Type Ia SNe (SNe Ia), making this the most distant case of a galaxy hosting two SNe Ia. Using parametric host fitting, we determine the probability of detecting two SNe Ia in this host galaxy over a $\sim10$ year window to be $\approx3\%$. These observations have the potential to yield a Hubble Constant ($H_0$) measurement with $\sim10\%$ precision, only the third lensed SN capable of such a result, using the three visible images of the SN. Both SN Requiem and SN Encore have a fourth image that is expected to appear within a few years of $\sim2030$, providing an unprecedented baseline for time-delay cosmography., Comment: Accepted, ApJL

Excitons, as bound states of electrons and holes, embody the solid state analogue of the hydrogen atom, whose quantum spectrum is explained within a classical framework by the Bohr-Sommerfeld atomic model. In a first hydrogenlike approximation the spectra of excitons are also well described by a Rydberg series, however, due to the surrounding crystal environment deviations from this series can be observed. A theoretical treatment of excitons in cuprous oxide needs to include the band structure of the crystal, leading to a prominent fine-structure splitting in the quantum spectra. This is achieved by introducing additional spin degrees of freedom into the system, making the existence and meaningfulness of classical exciton orbits in the physical system a non-trivial question. Recently, we have uncovered the contributions of periodic exciton orbits directly in the quantum mechanical recurrence spectra of cuprous oxide [J. Ertl et al., Phys. Rev. Lett. 129, 067401 (2022)] by application of a scaling technique and fixing the energy of the classical dynamics to a value corresponding to a principle quantum number $n=5$ in the hydrogenlike case. Here, we present a comprehensive derivation of the classical and semiclassical theory of excitons in cuprous oxide. In particular, we investigate the energy dependence of the exciton dynamics. Both the semiclassical and quantum mechanical recurrence spectra exhibit stronger deviations from the hydrogenlike behavior with decreasing energy, which is related to a growing influence of the spin-orbit coupling and thus a higher velocity of the secular motion of the exciton orbits. The excellent agreement between semiclassical and quantum mechanical exciton recurrence spectra demonstrates the validity of the classical and semiclassical approach to excitons in cuprous oxide., Comment: 16 pages, 10 figures, accepted for publication in Phys. Rev. B

The distribution of keys to a given number of buckets is a fundamental task in distributed data processing and storage. A simple, fast, and therefore popular approach is to map the hash values of keys to buckets based on the remainder after dividing by the number of buckets. Unfortunately, these mappings are not stable when the number of buckets changes, which can lead to severe spikes in system resource utilization, such as network or database requests. Consistent hash algorithms can minimize remappings, but are either significantly slower than the modulo-based approach, require floating-point arithmetic, or are based on a family of hash functions rarely available in standard libraries. This paper introduces JumpBackHash, which uses only integer arithmetic and a standard pseudorandom generator. Due to its speed and simple implementation, it can safely replace the modulo-based approach to improve assignment and system stability. A production-ready Java implementation of JumpBackHash has been released as part of the Hash4j open source library., Comment: 16 pages, 3 figures

Distributed stream processing frameworks help building scalable and reliable applications that perform transformations and aggregations on continuous data streams. This paper introduces ShuffleBench, a novel benchmark to evaluate the performance of modern stream processing frameworks. In contrast to other benchmarks, it focuses on use cases where stream processing frameworks are mainly employed for shuffling (i.e., re-distributing) data records to perform state-local aggregations, while the actual aggregation logic is considered as black-box software components. ShuffleBench is inspired by requirements for near real-time analytics of a large cloud observability platform and takes up benchmarking metrics and methods for latency, throughput, and scalability established in the performance engineering research community. Although inspired by a real-world observability use case, it is highly configurable to allow domain-independent evaluations. ShuffleBench comes as a ready-to-use open-source software utilizing existing Kubernetes tooling and providing implementations for four state-of-the-art frameworks. Therefore, we expect ShuffleBench to be a valuable contribution to both industrial practitioners building stream processing applications and researchers working on new stream processing approaches. We complement this paper with an experimental performance evaluation that employs ShuffleBench with various configurations on Flink, Hazelcast, Kafka Streams, and Spark in a cloud-native environment. Our results show that Flink achieves the highest throughput while Hazelcast processes data streams with the lowest latency., Comment: accepted for publication in Proceedings of the 15th ACM/SPEC International Conference on Performance Engineering (ICPE '24), May 7--11, 2024, London, United Kingdom, 12 pages

This work introduces ExaLogLog, a new data structure for approximate distinct counting, which has the same practical properties as the popular HyperLogLog algorithm. It is commutative, idempotent, mergeable, reducible, has a constant-time insert operation, and supports distinct counts up to the exa-scale. At the same time, as theoretically derived and experimentally verified, it requires 43% less space to achieve the same estimation error., Comment: 10 pages. arXiv admin note: text overlap with arXiv:2308.16862

Pediatric Low-Grade Neuroepithelial Tumors (PLGNT) are the most common pediatric cancer type, accounting for 40% of brain tumors in children, and identifying PLGNT molecular subtype is crucial for treatment planning. However, the gold standard to determine the PLGNT subtype is biopsy, which can be impractical or dangerous for patients. This research improves the performance of Convolutional Neural Networks (CNNs) in classifying PLGNT subtypes through MRI scans by introducing a loss function that specifically improves the model's Area Under the Receiver Operating Characteristic (ROC) Curve (AUROC), offering a non-invasive diagnostic alternative. In this study, a retrospective dataset of 339 children with PLGNT (143 BRAF fusion, 71 with BRAF V600E mutation, and 125 non-BRAF) was curated. We employed a CNN model with Monte Carlo random data splitting. The baseline model was trained using binary cross entropy (BCE), and achieved an AUROC of 86.11% for differentiating BRAF fusion and BRAF V600E mutations, which was improved to 87.71% using our proposed AUROC loss function (p-value 0.045). With multiclass classification, the AUROC improved from 74.42% to 76. 59% (p-value 0.0016).

We study the image of the Hodge-Tate logarithm map (in any cohomological degree), defined by Heuer, in the case of smooth Stein varieties. Heuer, motivated by the computations for the affine space of any dimension, raised the question whether this image is always equal to the group of closed differential forms. We show that it indeed always contains such forms but the quotient can be non-trivial: it contains a slightly mysterious $Z_p$-module that maps, via the Bloch-Kato exponential map, to integral classes in the pro-\'etale cohomology. This quotient is already non-trivial for open unit discs of dimension strictly greater than $1$., Comment: Final version; to appear in IMRN

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it requires only one annotated frame per action. However, it often suffers from poor performance due to the lack of precise boundary annotations. To address this issue, we propose a visual analysis method that aligns similar actions and then propagates a few user-provided annotations (e.g. , boundaries, category labels) to similar actions via the generated alignments. Our method models the alignment between actions as a heaviest path problem and the annotation propagation as a quadratic optimization problem. As the automatically generated alignments may not accurately match the associated actions and could produce inaccurate localization results, we develop a storyline visualization to explain the localization results of actions and their alignments. This visualization facilitates users in correcting wrong localization results and misalignments. The corrections are then used to improve the localization results of other actions. The effectiveness of our method in improving localization performance is demonstrated through quantitative evaluation and a case study.

Asking questions during class time is one form of participation not commonly employed by members of underrepresented groups in large enrollment college classrooms, even though the form of participation is highly conducive to student learning. To encourage students to ask questions, many instructors initiate open question periods in their lectures with verbal solicitations (i.e., "Questions?"). Although several university centers for teaching and learning, such as at UC Berkeley, and instructor reflections suggest that the scripts of question solicitations impact the frequency of questions returned by students, no literature exists to support this claim. This quasi-experimental scholarship of teaching and learning (SoTL) study conducted with the Students-as-Partners model, observes the effect of a new solicitation script integrated into an introductory physics lectures to improve question participation from students. While the new solicitation script did not change the total number of questions asked by students in comparison to previous scripts, the number of questions asked by people who likely have gender identities traditionally underrepresented in physics (i.e. all but cis-men) increased significantly.

Simple and low-cost biosensing solutions are suitable for point-of-care applications aiming to overcome the gap between scientific concepts and technological production. To compete with sensitivity and selectivity of golden standards, such as liquid chromatography, the functionalization of biosensors is continuously optimized to enhance the signal and improve their performance, often leading to complex chemical assay development. In this research, the efforts are made on optimizing the methodology for electrochemical reduction of graphene oxide to produce thin film-modified gold electrodes. Under the employed specific conditions, 20 cycles of cyclic voltammetry (CV) are shown to be optimal for superior electrical activation of graphene oxide into electrochemically reduced graphene oxide (ERGO). This platform is further used to develop a matrix metalloproteinase 2 (MMP-2) biosensor, where specific anti-MMP2 aptamers are utilized as a biorecognition element. MMP-2 is a protein which is typically overexpressed in tumor tissues, with important roles in tumor invasion, metastasis as well as in tumor angiogenesis. Based on impedimetric measurements, we were able to detect as low as 3.32 pg/mL of MMP-2 in PBS with a dynamic range of 10 pg/mL - 10 ng/mL. Besides high specificity, ERGO-based aptasensor showed a potential of reuse due to demonstrated successful signal restoration after experimental detection of MMP-2.

Medical image analysis has significantly benefited from advancements in deep learning, particularly in the application of Generative Adversarial Networks (GANs) for generating realistic and diverse images that can augment training datasets. However, the effectiveness of such approaches is often limited by the amount of available data in clinical settings. Additionally, the common GAN-based approach is to generate entire image volumes, rather than solely the region of interest (ROI). Research on deep learning-based brain tumor classification using MRI has shown that it is easier to classify the tumor ROIs compared to the entire image volumes. In this work, we present a novel framework that uses vector-quantization GAN and a transformer incorporating masked token modeling to generate high-resolution and diverse 3D brain tumor ROIs that can be directly used as augmented data for the classification of brain tumor ROI. We apply our method to two imbalanced datasets where we augment the minority class: (1) the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019 dataset to generate new low-grade glioma (LGG) ROIs to balance with high-grade glioma (HGG) class; (2) the internal pediatric LGG (pLGG) dataset tumor ROIs with BRAF V600E Mutation genetic marker to balance with BRAF Fusion genetic marker class. We show that the proposed method outperforms various baseline models in both qualitative and quantitative measurements. The generated data was used to balance the data in the brain tumor types classification task. Using the augmented data, our approach surpasses baseline models by 6.4% in AUC on the BraTS 2019 dataset and 4.3% in AUC on our internal pLGG dataset. The results indicate the generated tumor ROIs can effectively address the imbalanced data problem. Our proposed method has the potential to facilitate an accurate diagnosis of rare brain tumors using MRI scans., Comment: Preprint, In Submission

Since its invention HyperLogLog has become the standard algorithm for approximate distinct counting. Due to its space efficiency and suitability for distributed systems, it is widely used and also implemented in numerous databases. This work presents UltraLogLog, which shares the same practical properties as HyperLogLog. It is commutative, idempotent, mergeable, and has a fast guaranteed constant-time insert operation. At the same time, it requires 28% less space to encode the same amount of distinct count information, which can be extracted using the maximum likelihood method. Alternatively, a simpler and faster estimator is proposed, which still achieves a space reduction of 24%, but at an estimation speed comparable to that of HyperLogLog. In a non-distributed setting where martingale estimation can be used, UltraLogLog is able to reduce space by 17%. Moreover, its smaller entropy and its 8-bit registers lead to better compaction when using standard compression algorithms. All this is verified by experimental results that are in perfect agreement with the theoretical analysis which also outlines potential for even more space-efficient data structures. A production-ready Java implementation of UltraLogLog has been released as part of the open-source Hash4j library., Comment: 25 pages, extended version, accepted at VLDB 2024

Strongly lensed systems with peculiar configurations allow us to probe the local properties of the deflecting lens mass while simultaneously testing general profile assumptions. The quasar HE0230$-$2130 is lensed by two galaxies at similar redshifts ($\Delta z \sim 0.003$) into four observed images. Using modeled quasar positions from fitting the brightness of the quasar images in ground-based imaging data from the Magellan telescope, we find that lens-mass models where each of these two galaxies is parametrized with a singular power-law (PL) profile predict five quasar images. To interpret the quad configuration of the system, we tested 12 different profile assumptions with the aim of obtaining lens-mass models that correctly predict only four observed images. We tested the effects of adopting: cored profiles for the lensing galaxies; external shear; and additional profiles to represent a dark matter clump. We find that half of our model classes can produce the correct image multiplicity. By comparing the Bayesian evidence of different model parametrizations, we favor two model classes: (i) one that incorporates two singular PL profiles for the lensing galaxies and a cored isothermal sphere in the region of the previously predicted fifth image (rNIS profile), and (ii) one with a bigger lensing galaxy parametrized by a singular PL profile and the smaller galaxy by a cored PL profile with external shear. We estimated the mass of the rNIS clump for each candidate model of our final Markov chain Monte Carlo sample, and find that only 2\% are in the range of $10^6 M_{\odot} \leq M_{\rm rNIS}\leq 10^9 M_{\odot}$, which is the predicted mass range of dark matter subhalos in cold dark matter simulations, or the mass of dark-matter-dominated and low-surface-brightness galaxies. We therefore favor the models with a cored mass distribution for the lens galaxy close to the predicted fifth image., Comment: 22 pages, 13 figures, 7 tables; accepted by A&A

We developed a new approach comprised of different visualizations for the comparative spatio-temporal analysis of displacement processes in porous media. We aim to analyze and compare ensemble datasets from experiments to gain insight into the influence of different parameters on fluid flow. To capture the displacement of a defending fluid by an invading fluid, we first condense an input image series to a single time map. From this map, we generate a spatio-temporal flow graph covering the whole process. This graph is further simplified to only reflect topological changes in the movement of the invading fluid. Our interactive tools allow the visual analysis of these processes by visualizing the graph structure and the context of the experimental setup, as well as by providing charts for multiple metrics. We apply our approach to analyze and compare ensemble datasets jointly with domain experts, where we vary either fluid properties or the solid structure of the porous medium. We finally report the generated insights from the domain experts and discuss our contribution's advantages, generality, and limitations.

Strong gravitational lensing is a powerful tool to provide constraints on galaxy mass distributions and cosmological parameters, such as the Hubble constant, $H_0$. Nevertheless, inference of such parameters from images of lensing systems is not trivial as parameter degeneracies can limit the precision in the measured lens mass and cosmological results. External information on the mass of the lens, in the form of kinematic measurements, is needed to ensure a precise and unbiased inference. Traditionally, such kinematic information has been included in the inference after the image modeling, using spherical Jeans approximations to match the measured velocity dispersion integrated within an aperture. However, as spatially resolved kinematic measurements become available via IFU data, more sophisticated dynamical modeling is necessary. Such kinematic modeling is expensive, and constitutes a computational bottleneck which we aim to overcome with our Stellar Kinematics Neural Network (SKiNN). SKiNN emulates axisymmetric modeling using a neural network, quickly synthesizing from a given mass model a kinematic map which can be compared to the observations to evaluate a likelihood. With a joint lensing plus kinematic framework, this likelihood constrains the mass model at the same time as the imaging data. We show that SKiNN's emulation of a kinematic map is accurate to considerably better precision than can be measured (better than $1\%$ in almost all cases). Using SKiNN speeds up the likelihood evaluation by a factor of $\sim 200$. This speedup makes dynamical modeling economical, and enables lens modelers to make effective use of modern data quality in the JWST era., Comment: (13 pages, 9 figures, submitted to Astronomy & Astrophysics)