skip to main content

Search for: All records

Creators/Authors contains: "Kim, S."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Augmented Reality (AR) is increasingly used in medical applications for visualizing medical information. In this paper, we present an AR-assisted surgical guidance system that aims to improve the accuracy of catheter placement in ventriculostomy, a common neurosurgical procedure. We build upon previous work on neurosurgical AR, which has focused on enabling the surgeon to visualize a patient’s ventricular anatomy, to additionally integrate surgical tool tracking and contextual guidance. Specifically, using accurate tracking of optical markers via an external multi-camera OptiTrack system, we enable Microsoft HoloLens 2-based visualizations of ventricular anatomy, catheter placement, and the information on how far the cathetermore »tip is from its target. We describe the system we developed, present initial hologram registration results, and comment on the next steps that will prepare our system for clinical evaluations.« less
    Free, publicly-accessible full text available March 12, 2023
  2. Free, publicly-accessible full text available March 1, 2023
  3. Free, publicly-accessible full text available January 1, 2023
  4. Much research in healthcare robotics explores ex- tending rehabilitative interventions to the home. However, for adults, little guidance exists on how to translate human-delivered, clinic-based interventions into robot-delivered, home-based ones to support longitudinal interaction. This is particularly problematic for neurorehabilitation, where adults with cognitive impairments require unique styles of interaction to avoid frustration or overstimulation. In this paper, we address this gap by exploring the design of robot-delivered neurorehabilitation interventions for people with mild cognitive impairment (PwMCI). Through a multi-year collaboration with clinical neuropsychologists and PwMCI, we developed robot prototypes which deliver cognitive training at home. We used these prototypesmore »as design probes to understand how participants envision long-term deployment of the intervention, and how it can be contextualized to the lives of PwMCI. We report our findings and specify design patterns and considerations for translating neurorehabilitation interventions to robots. This work will serve as a basis for future endeavors to translate cognitive training and other clinical interventions onto a robot, support longitudinal engagement with home-deployed robots, and ultimately extend the accessibility of longitudinal health interventions for people with cognitive impairments.« less
    Free, publicly-accessible full text available January 1, 2023
  5. Free, publicly-accessible full text available January 15, 2023
  6. This study aimed to provide a review of the current status of the biomimetic adhesives that have the potential for clinical application. Biomimetic materials emulate compounds and properties with a biological origin. They have grown to be more relevant in medical fields due to biocompatibility, low toxicity, and a less damaging impact on the environment. Bonding living tissues has proved to be difficult due to the adverse immune reactions to foreign materials and the wet environment of the damaged area. There is a need for biomimetic adhesives due to the shortcomings of synthetic adhesives and metal tools required for woundmore »closure. Despite differences in developmental approaches and organismal properties, the biomimetic adhesives developed have the potential to be used in wet environments with enough strength to help bond the tissues together without any supporting materials.« less
    Free, publicly-accessible full text available October 1, 2022
  7. Free, publicly-accessible full text available October 1, 2022
  8. Cyberbullying is a prevalent concern within social computing research that has led to the development of several supervised machine learning (ML) algorithms for automated risk detection. A critical aspect of ML algorithm development is how to establish ground truth that is representative of the phenomenon of interest in the real world. Often, ground truth is determined by third-party annotators (i.e., “outsiders”) who are removed from the situational context of the interaction; therefore, they cannot fully understand the perspective of the individuals involved (i.e., “insiders”). To understand the extent of this problem, we compare “outsider” versus “insider” perspectives when annotating 2,000more »posts from an online peer-support platform. We interpolate this analysis to a corpus containing over 2.3 million posts on bullying and related topics, and reveal significant gaps in ML models that use third-party annotators to detect bullying incidents. Our results indicate that models based on the insiders’ perspectives yield a significantly higher recall in identifying bullying posts and are able to capture a range of explicit and implicit references and linguistic framings, including person-specific impressions of the incidents. Our study highlights the importance of incorporating the victim’s point of view in establishing effective tools for cyberbullying risk detection. As such, we advocate for the adoption of human-centered and value-sensitive approaches for algorithm development that bridge insider-outsider perspective gaps in a way that empowers the most vulnerable.« less
  9. Free, publicly-accessible full text available January 1, 2023
  10. We study image segmentation from an information-theoretic perspective, proposing a novel adversarial method that performs unsupervised segmentation by partitioning images into maximally independent sets. More specifically, we group image pixels into foreground and background, with the goal of minimizing predictability of one set from the other. An easily computed loss drives a greedy search process to maximize inpainting error over these partitions. Our method does not involve training deep networks, is computationally cheap, class-agnostic, and even applicable in isolation to a single unlabeled image. Experiments demonstrate that it achieves a new state-of-the-art in unsupervised segmentation quality, while being substantially fastermore »and more general than competing approaches.« less