BME PhD Preliminary Exam Announcement for Yuhyun Ji (Y. Kim, advisor)

Everyone is invited to attend the public presentation beginning at 3:00pm.

Title: Spectrally driven hyperspectral learning for hemodynamic imaging

Date: July 22, 2022

Time: 3:00pm EST

Location: Zoom*

https://purdue-edu.zoom.us/j/98106894285

Committee: Prof. Young Kim, Chair; Prof. Maria C. Dadarlat Makin; Prof. Stephen B. Hooser; Prof. Yunjie Tong

Abstract:

Hyperspectral imaging acquires and processes spatial and frequency data, offering rich physical and biological information for a variety of samples. However, due to the concurrent data acquisition in both spatial and frequency domains, conventional hyperspectral imaging systems have the intrinsic limitations of bulky instrumentation and slow data acquisition, often resulting in a tradeoff between spatial and spectral resolution. Here we introduce a learning-based snapshot hyperspectral imaging by hybridizing locally sampled hyperspectral data and a hyperspectral learning algorithm for hypercube recovery. Locally sampled hyperspectral data serve as prior information or physical constraints to incorporate domain-specific modeling into the algorithm. The trained hyperspectral learning algorithm can recover a hypercube from an RGB image without complete hyperspectral scanning of the entire area. We analyze vascular developmental models using learning-based snapshot hyperspectral imaging along with a conventional imaging system for demonstration and validation. Furthermore, hemodynamics of peripheral microcirculation in humans is assessed using a video mode of a smartphone camera with an unprecedentedly high temporal resolution, supported by functional near-infrared spectroscopy measurements of the brain and other peripheral sites. The key advantages of this hybrid approach include the hardware simplicity of using conventional cameras, high temporal resolution when a video is used, no tradeoff between spatial and spectral resolutions, and rich spectral information for a variety of machine learning methods.

______________________________________________________

*ji145@purdue.edu is inviting you to a scheduled Zoom meeting.

Topic: Yuhyun Ji - Ph.D. preliminary exam

Time: Jul 22, 2022 03:00 PM Indiana (East)

Meeting ID: 981 0689 4285

One tap mobile

+13017158592,,98106894285# US (Washington DC)

+13126266799,,98106894285# US (Chicago)

Dial by your location

        +1 301 715 8592 US (Washington DC)

        +1 312 626 6799 US (Chicago)

        +1 646 558 8656 US (New York)

        +1 253 215 8782 US (Tacoma)

        +1 346 248 7799 US (Houston)

        +1 669 900 6833 US (San Jose)

Meeting ID: 981 0689 4285

Find your local number: https://purdue-edu.zoom.us/u/adeRrHXCLQ

______________________________________________________