CaltechAUTHORS
  A Caltech Library Service

Early-stage tumor detection using photoacoustic microscopy: a pattern recognition approach

Yeh, Chenghung and Wang, Liang and Liang, Jinyang and Zhou, Yong and Hu, Song and Sohn, Rebecca E. and Arbeit, Jeffrey M. and Wang, Lihong V. (2017) Early-stage tumor detection using photoacoustic microscopy: a pattern recognition approach. In: Photons Plus Ultrasound: Imaging and Sensing 2017. Proceedings of SPIE. No.10064. Society of Photo-Optical Instrumentation Engineers , Bellingham, WA, Art. No. 100644N. ISBN 9781510605695. http://resolver.caltech.edu/CaltechAUTHORS:20180905-110718457

[img] PDF - Published Version
See Usage Policy.

1107Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180905-110718457

Abstract

We report photoacoustic microscopy (PAM) of arteriovenous (AV) shunts in early stage tumors in vivo, and develop a pattern recognition framework for computerized tumor detection. Here, using a high-resolution photoacoustic microscope, we implement a new blood oxygenation (sO_2)-based disease marker induced by the AV shunt effect in tumor angiogenesis. We discovered a striking biological phenomenon: There can be two dramatically different sO_2 values in bloodstreams flowing side-by-side in a single vessel. By tracing abnormal sO_2 values in the blood vessels, we can identify a tumor region at an early stage. To further automate tumor detection based on our findings, we adopt widely used pattern recognition methods and develop an efficient computerized classification framework. The test result shows over 80% averaged detection accuracy with false positive contributing 18.52% of error test samples on a 50 PAM image dataset.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1117/12.2253529DOIArticle
ORCID:
AuthorORCID
Wang, Lihong V.0000-0001-9783-4383
Additional Information:© 2017 Society of Photo-Optical Instrumentation Engineers. The authors appreciate the close reading of the manuscript by Prof. James Ballard. We also thank Cheng Ma, Pengfei Hai, and Hsun-Chia Hsu for helpful discussions. This work was sponsored by National Institutes of Health Grants DP1 EB016986 (NIH Director’s Pioneer Award), R01 CA186567 (NIH Director’s Transformative Research Award), and R01 CA159959.
Funders:
Funding AgencyGrant Number
NIHDP1 EB016986
NIHR01 CA186567
NIHR01 CA159959
Subject Keywords:photoacoustic microscopy, optical-resolution, oxygen saturation, tumor, cancer, arteriovenous shunt, pattern recognition, machine learning
Record Number:CaltechAUTHORS:20180905-110718457
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180905-110718457
Official Citation:Chenghung Yeh, Chenghung Yeh, Liang Wang, Liang Wang, Jinyang Liang, Jinyang Liang, Yong Zhou, Yong Zhou, Song Hu, Song Hu, Rebecca E. Sohn, Rebecca E. Sohn, Jeffrey M. Arbeit, Jeffrey M. Arbeit, Lihong V. Wang, Lihong V. Wang, } "Early-stage tumor detection using photoacoustic microscopy: a pattern recognition approach", Proc. SPIE 10064, Photons Plus Ultrasound: Imaging and Sensing 2017, 100644N (3 March 2017); doi: 10.1117/12.2253529; https://doi.org/10.1117/12.2253529
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:89389
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 Sep 2018 20:33
Last Modified:05 Sep 2018 20:33

Repository Staff Only: item control page