Despite significant strides in diagnosis and treatment, breast cancer remains a formidable health concern, underscoring the ongoing necessity for research. A study employing the polarized Monte Carlo approach has been conducted to investigate and pinpoint breast cancer. Utilizing the Mueller matrix derived from Monte Carlo simulations offers several advantages for diagnostic purposes, including enhanced contrast and the revelation of obscured details. This investigation focuses specifically on scenarios where malignancy is intertwined with normal breast tissue.In addition to its binary classification distinguishing between normal and abnormal conditions, the study presents an additional benefit: pinpointing the center of malignancy in nine specific spatial positions relative to the point of illumination. This offers a means to locate the tumor, even if it is not precisely within the directly illuminated area. The integration of deep learning techniques into a system enables automation and facilitates real-time diagnosis. This research aims to demonstrate the simultaneous detection of both the presence and location of the tumor through Convolutional Neural Network (CNN) implementation on depolarized index images derived from polarized Monte Carlo simulations. The CNN model achieves a classification accuracy of 96%, highlighting its superior performance.
In the medical field, the 'optical biopsy' is considered the primary diagnostic application of light. Tissue abnormalities, such as cancerous growth, introduce changes in the target tissue's optical properties. The Polarized Monte Carlo (PMC) simulation applied to specific tissue models acts as a tool for observing these changes and helps monitor them in conjunction with experiments. In this work, we have performed PMC simulations on two-layered skin tissue models and compared the Mueller matrix parameters for normal and skin cancer conditions. These simulations are expected to help design diagnostic instruments for anomalies such as melanoma in situ.
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.