arXiv subjects

Christina Lee

Publications and source records attributed to Christina Lee.

8 recordsLinked to original sources

arXiv2026

Prediction of Rectal Cancer Regrowth from Longitudinal Endoscopy

Clinical trial studies indicate benefit of watch-and-wait (WW) surveillance for patients with rectal cancer showing a complete or near clinical response (CR) directly after treatment (restaging). However, there are no objectively accurate methods to early detect local tumor regrowth (LR) in patients undergoing WW from follow-up exams. Hence, we developed Temporal Rectal Endoscopy Cross-attention (TREX), a longitudinal deep learning approach that combines pairs of images acquired at restaging and follow-up to distinguish CR from LR. TREX uses pretrained Swin Transformers in a siamese setting to extract features from longitudinal images and dual cross-attention to combine the features without spatial co-registration between image pairs. TREX and Swin-based baselines were trained under two settings: (a) detecting LR or CR at the last available follow-up and (b) early detection of LR at 3--6, 6--12, and 12--24 months before clinical confirmation. TREX achieved the highest accuracy in detecting LR with a high sensitivity of 97% $\pm$ 6% and a balanced accuracy of 90% $\pm$ 3%, and outperformed all baselines in early detection at both 3--6 (74% $\pm$ 1%) and 6--12 months (62% $\pm$ 4%) prior to clinical detection. Clinical validation via a surgeon survey showed that TREX matched attending-level overall accuracy (TREX: 86.21% vs.\ Clinicians: 87.84% $\pm$ 1.28%). Finally, we explored TREX's ability to predict treatment response by combining pre-treatment (pre-TNT) and restaging endoscopies, achieving a balanced accuracy of 73% $\pm$ 12%. These results show that longitudinal deep learning analysis of endoscopy may improve surveillance and enable earlier identification of rectal cancer regrowth.

cs.CV↗

arXiv2026

Radial Dependency of ICME-associated Particle Acceleration Processes: Statistical Multipoint Observations from 2016-2023

During the propagation of interplanetary coronal mass ejections (ICMEs), evolution of the ICME-driven shock along with interactions with other solar wind structures, planetary bodies, and general changes to their morphology can alter particle acceleration efficiency and transport effects at their associated shocks. While the underlying mechanisms for these processes have been studied, the connection between the radial evolution of the ICME-driven shock during propagation and resulting gradual Solar Energetic Particle (SEP)and Energetic Storm Particle (ESP) intensities, composition, and acceleration has yet to be fully understood. The current distributed array of spacecraft at varying heliocentric distances provides a welcome opportunity to statistically analyze the radial dependency of particle populations and acceleration mechanisms present at ICME-driven shocks. We compile a database of 39 multipoint ICME events from 2016-2023, which are observed in situ by at least two of the following spacecraft: Parker Solar Probe (PSP), Solar Orbiter, ACE, Wind, and STEREO-A. Using the magnetic field, plasma, and ion compositional data provided by these spacecraft, we derive both local shock and ESP spectral shape parameters. By comparing the changes in these parameters at different stages of ICME propagation, we analyze the connection between the evolution of the local shock conditions and the spectral shape. We find evidence to suggest a consistent increase in shock acceleration efficiency with heliocentric distance while the parent ICME is within 0.7 au, followed by a reduction in shock efficiency at further distances.

physics.space-ph↗

arXiv2026

All-organic self-separating three-dimensionally nanoarchitected electrochemical energy storage devices

This work realizes a three-dimensionally (3D) nanoarchitected, all organic, "self-separating" lithium-ion electrochemical energy storage (EES) device that is cycled as a solid-state full cell. The device is enabled by a monolithic carbon anode with a co-continuous pore network, derived from the structure direction of resols by an ultra-large molar mass block copolymer (BCP), poly(styrene-block-2-dimethylaminoethyl methacrylate) (SA). Electropolymerization of a single-phase conductive and redox-active material, poly((2,3-dihydrothieno[3,4-b][1,4]dioxin-2-yl)methyl 9,10-dioxo-9,10-dihydroanthracene-2-carboxylate) (PAQEDOT), into the pore space provides the cathode of the cell. The device is electronically contacted to the relevant electrode network enabled by the co-continuous nature of each electrode. Electrochemical processing via cycling against external lithium in an electrolyte generates a solid electrolyte interphase (SEI) as a separator and lithiates the cell electrodes, after which the EES device is cycled in the solid state. While the full cell does not demonstrate high cyclability, the best full cell demonstrates a discharge capacity of 267 milliamp hours per gram (mAh/g). This work marks, to the best of knowledge of the authors, the first example of an all-organic materials derived 3D nanoarchitected EES device, as well as the first design of "self-separating" cell fabrication. Furthermore, generalization of the design to another co-continuous carbon form factor is demonstrated.

cond-mat.mtrl-sci↗

arXiv2025

Dual Cross-Attention Siamese Transformer for Rectal Tumor Regrowth Assessment in Watch-and-Wait Endoscopy

Increasing evidence supports watch-and-wait (WW) surveillance for patients with rectal cancer who show clinical complete response (cCR) at restaging following total neoadjuvant treatment (TNT). However, accurate methods to early detect local regrowth (LR) from follow-up endoscopy images during WW are essential to manage care and prevent distant metastases. Hence, we developed a Siamese Swin Transformer with Dual Cross-Attention (SSDCA) to combine longitudinal endoscopic images at restaging and follow-up and distinguish cCR from LR. SSDCA leverages pretrained Swin Transformers to extract domain agnostic features and enhance robustness to imaging variations. Dual cross attention is implemented to emphasize features from the paired scans without requiring any spatial alignment to predict response. SSDCA as well as Swin-based baselines were trained using image pairs from 135 patients and evaluated on a held-out set of image pairs from 62 patients. SSDCA produced the best balanced accuracy (81.76% $\pm$ 0.04), sensitivity (90.07% $\pm$ 0.08), and specificity (72.86% $\pm$ 0.05). Robustness analysis showed stable performance irrespective of artifacts including blood, stool, telangiectasia, and poor image quality. UMAP clustering of extracted features showed maximal inter-cluster separation (1.45 $\pm$ 0.18) and minimal intra-cluster dispersion (1.07 $\pm$ 0.19) with SSDCA, confirming discriminative representation learning. Code and weights available at: https://github.com/Jotanator/SSDCA

cs.CV↗

arXiv2022

PennyLane: Automatic differentiation of hybrid quantum-classical computations

PennyLane is a Python 3 software framework for differentiable programming of quantum computers. The library provides a unified architecture for near-term quantum computing devices, supporting both qubit and continuous-variable paradigms. PennyLane's core feature is the ability to compute gradients of variational quantum circuits in a way that is compatible with classical techniques such as backpropagation. PennyLane thus extends the automatic differentiation algorithms common in optimization and machine learning to include quantum and hybrid computations. A plugin system makes the framework compatible with any gate-based quantum simulator or hardware. We provide plugins for hardware providers including the Xanadu Cloud, Amazon Braket, and IBM Quantum, allowing PennyLane optimizations to be run on publicly accessible quantum devices. On the classical front, PennyLane interfaces with accelerated machine learning libraries such as TensorFlow, PyTorch, JAX, and Autograd. PennyLane can be used for the optimization of variational quantum eigensolvers, quantum approximate optimization, quantum machine learning models, and many other applications.

quant-ph↗

arXiv2022

Quantum computing with differentiable quantum transforms

We present a framework for differentiable quantum transforms. Such transforms are metaprograms capable of manipulating quantum programs in a way that preserves their differentiability. We highlight their potential with a set of relevant examples across quantum computing (gradient computation, circuit compilation, and error mitigation), and implement them using the transform framework of PennyLane, a software library for differentiable quantum programming. In this framework, the transforms themselves are differentiable and can be parametrized and optimized, which opens up the possibility of improved quantum resource requirements across a spectrum of tasks.

quant-ph↗

arXiv2021

Large-Scale Intelligent Microservices

Deploying Machine Learning (ML) algorithms within databases is a challenge due to the varied computational footprints of modern ML algorithms and the myriad of database technologies each with its own restrictive syntax. We introduce an Apache Spark-based micro-service orchestration framework that extends database operations to include web service primitives. Our system can orchestrate web services across hundreds of machines and takes full advantage of cluster, thread, and asynchronous parallelism. Using this framework, we provide large scale clients for intelligent services such as speech, vision, search, anomaly detection, and text analysis. This allows users to integrate ready-to-use intelligence into any datastore with an Apache Spark connector. To eliminate the majority of overhead from network communication, we also introduce a low-latency containerized version of our architecture. Finally, we demonstrate that the services we investigate are competitive on a variety of benchmarks, and present two applications of this framework to create intelligent search engines, and real-time auto race analytics systems.

cs.AI↗

arXiv2011

Peer Effects and Stability in Matching Markets

Many-to-one matching markets exist in numerous different forms, such as college admissions, matching medical interns to hospitals for residencies, assigning housing to college students, and the classic firms and workers market. In all these markets, externalities such as complementarities and peer effects severely complicate the preference ordering of each agent. Further, research has shown that externalities lead to serious problems for market stability and for developing efficient algorithms to find stable matchings. In this paper we make the observation that peer effects are often the result of underlying social connections, and we explore a formulation of the many-to-one matching market where peer effects are derived from an underlying social network. The key feature of our model is that it captures peer effects and complementarities using utility functions, rather than traditional preference ordering. With this model and considering a weaker notion of stability, namely two-sided exchange stability, we prove that stable matchings always exist and characterize the set of stable matchings in terms of social welfare. We also give distributed algorithms that are guaranteed to converge to a two-sided exchange stable matching. To assess the competitive ratio of these algorithms and to more generally characterize the efficiency of matching markets with externalities, we provide general bounds on how far the welfare of the worst-case stable matching can be from the welfare of the optimal matching, and find that the structure of the social network (e.g. how well clustered the network is) plays a large role.

cs.SI↗