Breast cancer patients undergoing neoadjuvant chemotherapy (NAC) require precise and accurate evaluation of treatment response. Residual cancer burden (RCB) estimation is a critical prognostic tool used in breast cancer outcomes assessment. In this pioneering study, we introduce the OptiScan probe, an innovative machine-learning-based optical biosensor, to assess residual cancer burden in patients undergoing NAC. The study enrolled 32 patients (mean age: 61.8 years), with comprehensive data collected pre- and post-each NAC cycle. Using the Modified Diffusion Equation (MDE) algorithm and advanced regression analysis, we meticulously calculated the optical properties and generated functional images of both healthy and affected breast tissues. Leveraging these insights, a robust machine learning model was developed, harnessing optical parameter values and breast cancer imaging features to predict RCB values. The predictive model showcased exceptional performance, achieving an impressive accuracy of 96.875% and 96.88% sensitivity in predicting RCB based on optical property alterations. These findings underscore the potency of the OptiScan probe as a pivotal tool for assessing breast cancer response post-NAC. This innovative approach holds promise as a noninvasive and accurate method for monitoring patient responses, contributing to improved treatment decisions and patient outcomes. By combining the power of machine learning with cutting-edge optical imaging, this study marks a significant stride toward personalized and effective breast cancer management.
Diffuse Optical Breast Scanner (DOB-Scan) probe utilizes a linear charge-coupled device (CCD) array as the detector, measuring back-scattered light intensity above the breast tissue to create cross-sectional concentration images for different constituents. The response received at each pixel of the sensor is determined by optical properties of the scattering medium, source-detector distance, integration time of CCD array, and intensity of the light source. However, the performance of the probe is limited by the inherent electronic properties of CCD array, which cause saturation at high response region and high noise level at low response region. In this paper, an algorithm to enhance the dynamic range of the CCD array is presented. The objective is to maximize the dynamic range of the CCD array without any data loss while minimizing the noise-to-signal ratio where the response of the CCD array is relatively low. The desired output can be achieved by capturing multiple sets of data with different integration time and light intensity settings, ensuring the best CCD performance in each pixel range of interest. The profile of CCD array’s linearity and optical power measurement of the light source allow different sets of data to be translated into the same scale and joined accordingly into one. A series of phantom studies are conducted and confirm the feasibility of the probe’s dynamic range intensification.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.