Semi-automated machine learning approach to segment and register tissue oxygenation maps onto clinical images of wounds

Edwin Robledo Jr.; Richard Schutzman; Ruogu Fang; Cristianne Fernandez; Rebecca Kwasinski; Kevin Leiva; Francisco Perez-Clavijo; Anuradha Godavarty

doi:10.1117/12.2510065

4 March 2019 Semi-automated machine learning approach to segment and register tissue oxygenation maps onto clinical images of wounds

Edwin Robledo Jr., Richard Schutzman, Ruogu Fang, Cristianne Fernandez, Rebecca Kwasinski, Kevin Leiva, Francisco Perez-Clavijo, Anuradha Godavarty

Author Affiliations +

Proceedings Volume 10873, Optical Biopsy XVII: Toward Real-Time Spectroscopic Imaging and Diagnosis; 1087305 (2019) https://doi.org/10.1117/12.2510065
Event: SPIE BiOS, 2019, San Francisco, California, United States

Abstract

Near-infrared (NIR) spectroscopic imaging of wounds has been performed by past researchers to obtain tissue oxygenation at discrete point locations. We had developed a near-infrared optical scanner (NIROS) that performs noncontact NIR spectroscopic (NIRS) imaging to provide 2D tissue oxygenation maps of the entire wounds. Regions of changed oxygenation have to be demarcated and registered with respect to visual white light images of the wound. Herein, a semi-automatic image segmentation and co-registration approach using machine learning has been developed to differentiate regions of changed tissue oxygenation. A registration technique was applied using a transformation matrix approach using specific markers across the white light image and the NIR images (or tissue oxygenation maps). This allowed for physiological changes observed from hemodynamic changes to be observed in the RGB white light image as well. Semi-automated segmentation techniques employing graph cuts algorithms was implemented to demarcate the 2D tissue oxygenation maps depicting regions of increased or decreased oxygenation and further coregistered onto the white light images. The developed registration technique was validated via phantom studies (both flat and curved phantoms) and in-vivo studies on controls, demonstrating an accuracy >97%. The technique was further implemented on wounds (here, diabetic foot ulcers) across weeks of treatment. Regions of decreased oxygenation were demarcated, and its area estimated and co-registered in comparison to the clinically demarcated wound area. Future work involves the development of automated machine learning approaches of image analysis for clinicians to obtain real-time co-registered clinical and subclinical assessments of the wound.

Conference Presentation

Citation Download Citation

Edwin Robledo Jr., Richard Schutzman, Ruogu Fang, Cristianne Fernandez, Rebecca Kwasinski, Kevin Leiva, Francisco Perez-Clavijo, and Anuradha Godavarty "Semi-automated machine learning approach to segment and register tissue oxygenation maps onto clinical images of wounds", Proc. SPIE 10873, Optical Biopsy XVII: Toward Real-Time Spectroscopic Imaging and Diagnosis, 1087305 (4 March 2019); https://doi.org/10.1117/12.2510065

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available