Enhancing Oncology-Specific Question Answering With Large Language Models Through Fine-Tuned Embeddings With Synthetic Data.

Purpose: The recent advancements of retrieval-augmented generation (RAG) and large language models (LLMs) have revolutionized the extraction of real-world evidence from unstructured electronic health records (EHRs) in oncology. This study aims to enhance RAG's effectiveness by implementing a retriever encoder specifically designed for oncology EHRs, with the goal of improving the precision and relevance of retrieved clinical notes for oncology-related queries.

Methods: Our model was pretrained with more than six million oncology notes from 209,135 patients at City of Hope.

Predicting survival of NSCLC patients treated with immune checkpoint inhibitors: Impact and timing of immune-related adverse events and prior tyrosine kinase inhibitor therapy.

Introduction: Immune checkpoint inhibitors (ICIs) produce a broad spectrum of immune-related adverse events (irAEs) affecting various organ systems. While ICIs are established as a therapeutic option in non-small cell lung cancer (NSCLC) treatment, most patients receiving ICI relapse. Additionally, the role of ICIs on survival in patients receiving prior targeted tyrosine kinase inhibitor (TKI) therapy has not been well-defined.

High-throughput segmentation of unmyelinated axons by deep learning.

Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats.

Automatic assessment of human gastric motility and emptying from dynamic 3D magnetic resonance imaging.

Background: Time-sequenced magnetic resonance imaging (MRI) of the stomach is an emerging technique for non-invasive assessment of gastric emptying and motility. However, an automated and systematic image processing pipeline for analyzing dynamic 3D (ie, 4D) gastric MRI data has not been established. This study uses an MRI protocol for imaging the stomach with high spatiotemporal resolution and provides a pipeline for assessing gastric emptying and motility.

Psychosocial impairment following mild blast-induced traumatic brain injury in rats.

Traumatic brain injury (TBI) is associated with increased risk for mental health disorders, impacting post-injury quality of life and societal reintegration. TBI is also associated with deficits in psychosocial processing, defined as the cognitive integration of social and emotional behaviors, however little is known about how these deficits manifest and their contributions to post-TBI mental health. In this pre-clinical investigation using rats, a single mild blast TBI (mbTBI) induced impairment of psychosocial processing in the absence of confounding physical polytrauma, post-injury motor deficits, affective abnormalities, or deficits in non-social behavior.

Acute effects of vagus nerve stimulation parameters on gastric motility assessed with magnetic resonance imaging.

Background: Vagus nerve stimulation (VNS) is an emerging bioelectronic therapy for regulating food intake and controlling gastric motility. However, the effects of different VNS parameters and polarity on postprandial gastric motility remain incompletely characterized.

Methods: In anesthetized rats (N = 3), we applied monophasic electrical stimuli to the left cervical vagus and recorded compound nerve action potential (CNAP) as a measure of nerve response.

Magnetic Resonance Imaging of the Rat Vocal Folds After Systemic Dehydration and Rehydration.

Objective Consuming less water (systemic dehydration) has long been thought to dehydrate the vocal folds. An , repeated measures study tested the assumption that systemic dehydration causes vocal fold dehydration. Proton density (PD)-weighted magnetic resonance imaging (MRI) of rat vocal folds was employed to investigate (a) whether varying magnitudes of systemic dehydration would dehydrate the vocal folds and (b) whether systemic rehydration would rehydrate the vocal folds.

Variational autoencoder: An unsupervised model for encoding and decoding fMRI activity in visual cortex.

Goal-driven and feedforward-only convolutional neural networks (CNN) have been shown to be able to predict and decode cortical responses to natural images or videos. Here, we explored an alternative deep neural network, variational auto-encoder (VAE), as a computational model of the visual cortex. We trained a VAE with a five-layer encoder and a five-layer decoder to learn visual representations from a diverse set of unlabeled images.

Gastric stimulation drives fast BOLD responses of neural origin.

Functional magnetic resonance imaging (fMRI) is commonly thought to be too slow to capture any neural dynamics faster than 0.1 Hz. However, recent findings demonstrate the feasibility of detecting fMRI activity at higher frequencies beyond 0.

Task-evoked functional connectivity does not explain functional connectivity differences between rest and task conditions.

During complex tasks, patterns of functional connectivity differ from those in the resting state. However, what accounts for such differences remains unclear. Brain activity during a task reflects an unknown mixture of spontaneous and task-evoked activities.

Vagal nerve stimulation triggers widespread responses and alters large-scale functional connectivity in the rat brain.

Vagus nerve stimulation (VNS) is a therapy for epilepsy and depression. However, its efficacy varies and its mechanism remains unclear. Prior studies have used functional magnetic resonance imaging (fMRI) to map brain activations with VNS in human brains, but have reported inconsistent findings.

Chronic cuffing of cervical vagus nerve inhibits efferent fiber integrity in rat model.

Objective: Numerous studies of vagal nerve stimulation (VNS) have been published showing it to be a potential treatment for chronic inflammation and other related diseases and disorders. Studies in recent years have shown that electrical stimulation of the vagal efferent fibers can artificially modulate cytokine levels and reduce systematic inflammation. Most VNS research in the treatment of inflammation have been acute studies on rodent subjects.

Musical Imagery Involves Wernicke's Area in Bilateral and Anti-Correlated Network Interactions in Musicians.

Musical imagery is the human experience of imagining music without actually hearing it. The neural basis of this mental ability is unclear, especially for musicians capable of engaging in accurate and vivid musical imagery. Here, we created a visualization of an 8-minute symphony as a silent movie and used it as real-time cue for musicians to continuously imagine the music for repeated and synchronized sessions during functional magnetic resonance imaging (fMRI).

Proton density-weighted laryngeal magnetic resonance imaging in systemically dehydrated rats.

Objectives/hypothesis: Dehydrated vocal folds are inefficient sound generators. Although systemic dehydration of the body is believed to induce vocal fold dehydration, this causative relationship has not been demonstrated in vivo. Here we investigate the feasibility of using in vivo proton density (PD)-weighted magnetic resonance imaging (MRI) to demonstrate hydration changes in vocal fold tissue following systemic dehydration in rats.

Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision.

Convolutional neural network (CNN) driven by image recognition has been shown to be able to explain cortical responses to static pictures at ventral-stream areas. Here, we further showed that such CNN could reliably predict and decode functional magnetic resonance imaging data from humans watching natural movies, despite its lack of any mechanism to account for temporal dynamics or feedback processing. Using separate data, encoding and decoding models were developed and evaluated for describing the bi-directional relationships between the CNN and the brain.

Contrast-Enhanced Magnetic Resonance Imaging of Gastric Emptying and Motility in Rats.

The assessment of gastric emptying and motility in humans and animals typically requires radioactive imaging or invasive measurements. Here, we developed a robust strategy to image and characterize gastric emptying and motility in rats based on contrast-enhanced magnetic resonance imaging (MRI) and computer-assisted image processing. The animals were trained to naturally consume a gadolinium-labeled dietgel while bypassing any need for oral gavage.

Spontaneous activity in the visual cortex is organized by visual streams.

Large-scale functional networks have been extensively studied using resting state functional magnetic resonance imaging (fMRI). However, the pattern, organization, and function of fine-scale network activity remain largely unknown. Here, we characterized the spontaneously emerging visual cortical activity by applying independent component (IC) analysis to resting state fMRI signals exclusively within the visual cortex.

Mapping white-matter functional organization at rest and during naturalistic visual perception.

Despite the wide applications of functional magnetic resonance imaging (fMRI) to mapping brain activation and connectivity in cortical gray matter, it has rarely been utilized to study white-matter functions. In this study, we investigated the spatiotemporal characteristics of fMRI data within the white matter acquired from humans both in the resting state and while watching a naturalistic movie. By using independent component analysis and hierarchical clustering, resting-state fMRI data in the white matter were de-noised and decomposed into spatially independent components, which were further assembled into hierarchically organized axonal fiber bundles.

Influences of High-Level Features, Gaze, and Scene Transitions on the Reliability of BOLD Responses to Natural Movie Stimuli.

Complex, sustained, dynamic, and naturalistic visual stimulation can evoke distributed brain activities that are highly reproducible within and across individuals. However, the precise origins of such reproducible responses remain incompletely understood. Here, we employed concurrent functional magnetic resonance imaging (fMRI) and eye tracking to investigate the experimental and behavioral factors that influence fMRI activity and its intra- and inter-subject reproducibility during repeated movie stimuli.

Fabry-Perot based metal-dielectric multilayered filters and metamaterials.

The traditional three-layered metal-dielectric-metal Fabry-Perot filter is developed as a new metal-dielectric multilayered band-pass filter. Our design method allows metal and dielectric films to be alternatively arranged to achieve a narrow and high transmission peak and the peak height remains unchanged for any number of metal films arranged in the multilayer. Furthermore, the equivalent refractive index of a subwavelength metal-dielectric multilayer could be negative real at the passband of the filter and such metamaterial exhibits stronger figure of merit than a previous result.