Tissue Segmentation using Optical Photothermal Mid-infrared Spectroscopic Imaging and Machine Learning
Description:
Vibrational spectroscopy enables biochemical identification in tissue sections. Biomedical samples such as cancerous tissue are chemically heterogeneous, and bulk spectroscopy is often inadequate to ascertain the disease state in these samples. Mid-infrared spectroscopic imaging (MIRSI) is a class of technologies that combines the molecular specificity of vibrational spectroscopy with the spatial detail provided by microscopy. Traditionally, MIRSI has been performed using Fourier transform infrared (FT-IR) imaging instrumentation. The combination of machine learning and MIRSI has facilitated the identification of tissue sub-type and cancer grades in a label-free and quantitative manner. Innovations in Quantum Cascade Lasers (QCLs) have revolutionized MIRSI, and new techniques such as optical photothermal IR imaging have emerged recently. These technologies are more flexible, provide higher resolution, and have essential advantages over FT-IR. We will present a comparative analysis of these MIRSI technologies in the context of biomedical imaging and discuss the benefits of each technology.
Ovarian cancer is one of the deadliest cancers among women in the U.S., with over 22,000 women diagnosed with the disease every year. Early diagnosis of the disease is essential for improving survival. To automate the process of disease diagnosis, we perform MIRSI imaging followed by machine learning. However, this requires data of higher quality and resolution. We use the super-resolution capabilities of O-PTIR to analyze ovarian tissue and perform tissue subtype segmentation. Bone disorders such as osteosclerosis have spectroscopic signatures identified using MIRSI. We present imaging data and results of high-resolution MIRSI of bone samples. We also present the first study that uses polarization MIRSI to spectroscopically identify thin collagen fibers (≈1µm diameter) and their orientations, which is critical for accurate grading of human bone marrow fibrosis.
Speaker: Rohith Reddy - University of Houston
Dr. Rohith Reddy is an Asst. Prof. at the Univ. of Houston. He received his Ph.D. from the Univ. of Illinois at Urbana Champaign and a B.Tech from Indian Institute of Technology (IIT) Madras. He completed a post-doctoral fellowship with Dr. Gary Tearney at Harvard Medical School. His research focuses on mid-infrared spectroscopic imaging and optical coherence tomography for biomedical applications. Rohith has won the Federation of Analytical Chemistry and Spectroscopy Societies (FACSS) student poster award in 2007, 2009 and 2011, the Bioengineering Student Award (2010), Graduate Student Achievement Award (2009) at the University of Illinois, Society of Applied Spectroscopy Graduate Student award (2011), Coblentz Student Award (2011), William G. Fateley Student Award (2011), FACSS Innovation award (2012, 2016), Tomas Hirschfeld Award (2012) and the prestigious Applied Spectroscopy William F. Meggers’ Award (2014) for outstanding work in spectroscopy.
Co-Authors
Tissue Segmentation using Optical Photothermal Mid-infrared Spectroscopic Imaging and Machine Learning
Category
2023 Call for Invited Abstracts
Description
Session Number: AW05-04
Session Type: Award Abstract
Session Date: Monday 3/20/2023
Session Time: 8:30 AM - 11:50 AM
Room Number: 124
Track: Bioanalytics & Life Sciences
Category: Bioanalytical, Molecular Spectroscopy, Vibrational Spectroscopy
Register for Pittcon 2023