The Malone Center for Engineering in Healthcare (MCEH) recently awarded grants through the center’s Seed Grant Program. The new grants support engineering innovations that aim to:

  • Introduce next generation assistive robots for children with autism spectrum disorder
  • Develop artificial-intelligence based tools to evaluate therapies for vascular anomalies
  • Advance shared-control strategies for skills assessment in robotic surgery

With the funding for this round of projects, the center will have awarded a total of 16 Seed Grants since the program’s inception in 2018. To learn about the past projects, visit the Malone Seed Grant page.

The Malone Center will fund the following three projects:

In-Home Robot-Mediated Social Play for Children with ASD
Research Team: Chien-Ming Huang (Computer Science); Any Keefer (Center for Autism and Related Disorders, Kennedy Krieger Institute); Chung Hyuk Park (Biomedical Engineering, George Washington University)

For children with autism spectrum disorder (ASD), early intensive behavioral interventions have proven effective in enhancing social and communicative behaviors impaired by the disorder. Previous research has shown that short sessions with robots can help children with ASD improve social skills. However, most prior research on robot-mediated intervention consists of controlled laboratory studies spanning short periods of time; but the longitudinal effects of robot-mediated intervention are unclear without large-scale, long-term field studies.

To advance the science of robot-mediated intervention for children with ASD, this seed project aims to develop and pilot test a robot-mediated social play system to be used in long-term, in-home deployments. This seed effort will allow the research team to build the engineering infrastructure and collect the preliminary data necessary to win external funding for investigating the longitudinal effects of in-home robot-mediated intervention for children with ASD.

Fully Automated Segmentation Algorithm for Low Flow Vascular Malformations
Research Team: Craig Jones (MCEH); Clifford Weiss (Radiology and Biomedical Engineering); Adham Khalil (Radiology)

 Low-Flow Vascular Malformations (LFVMs) are the most common vascular anomalies seen in patients. To date, there are no standardized clinical or radiologic methods published to objectively determine treatment outcomes after LFVM therapy. Therefore, quantifying the local and global changes occurring in LFVMs remains a challenging but essential task both for clinicians and researchers developing and assessing new therapies.

Researchers from the Malone Center and the world-renowned Johns Hopkins Vascular Anomalies Center will develop a fully automated MRI-based 3D neural network segmentation algorithm that allows for fast, reproducible, and quantitative assessment of treatment outcomes for LFVMs. The results of this project will provide a novel technical structure and clinical understanding for researchers to run large-scale diagnostic and therapeutic trials to improve the standard of care provided for patients with LFVMs.

Skill-Based Control Arbitration for Robot-Assisted Minimally Invasive Surgery
Research Team: Jeremy Brown (Mechanical Engineering); Axel Krieger (Mechanical Engineering); Gina Adrales (Division of Minimally Invasive Surgery)

Robot-assisted minimally invasive surgery (RAMIS) is quickly becoming the prescribed method of treatment for many surgical procedures. Yet there is no widely agreed upon skill assessment for RAMIS training, meaning trainees may be at various locations on the learning curve when performing actual procedures.

To better assess robotics surgery skills, the research team will focus on devising a shared control platform for a wide range of RAMIS procedures. In a shared-control system, both the robot and the surgeon directly manipulate the surgical tool. The  specific goals of  the project are to(1) develop a data-driven approach for real-time RAMIS skill assessment, and (2) to develop a shared-control framework which utilizes the real-time skill assessment to intelligently blend control between the surgeon and an autonomous controller.

The work has the potential to lay the foundation for the next generation of human-centered shared control surgical robots.