Abstract
Is it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range of clinical applications, such as intraoperative breast-conserving surgery margin assessment. However, translating tissue optical properties to clinical pathology information is still a cumbersome problem due to, amongst other things, inter- and intrapatient variability, calibration, and ultimately the nonlinear behavior of light in turbid media. These challenges limit the ability of standard statistical methods to generate a simple model of pathology, requiring more advanced algorithms. We present a data-driven, nonlinear model of breast cancer pathology for real-time margin assessment of resected samples using optical properties derived from spatial frequency domain imaging data. A series of deep neural network models are employed to obtain sets of latent embeddings that relate optical data signatures to the underlying tissue pathology in a tractable manner. These self-explanatory models can translate absorption and scattering properties measured from pathology, while also being able to synthesize new data. The method was tested on a total of 70 resected breast tissue samples containing 137 regions of interest, achieving rapid optical property modeling with errors only limited by current semi-empirical models, allowing for mass sample synthesis and providing a systematic understanding of dataset properties, paving the way for deep automated margin assessment algorithms using structured light imaging or, in principle, any other optical imaging technique seeking modeling. Code is available.
Highlights
I N the past two decades, breast-conserving surgery (BCS) has become the most common procedure in the treatment of early invasive breast cancer, with clinical results similar to [1] or better [2] than those achieved via full mastectomy
Analysis of histopathological slides was performed by an expert pathologist, who delineated regions of interest (ROIs) on the hematoxylin and eosin (H&E) images associated with distinct tissue subtypes
These ROIs were conservatively co-registered with wide-field-of-view Spatial frequency domain imaging (SFDI) data
Summary
I N the past two decades, breast-conserving surgery (BCS) has become the most common procedure in the treatment of early invasive breast cancer, with clinical results similar to [1] or better [2] than those achieved via full mastectomy. This first model must be capable of reproducing textural information with sufficient fidelity, which will be measured in terms of a reconstruction loss that compares the input patches r ∈ Rnx×ny×nch , with the reconstructed output r ∈ Rnx×ny×nch at the other side of the bottleneck, L(r, r), where nx and ny are the width and height in pixels, respectively, and nch is the number of input channels (nch = nλnfx , with nλ number of wavelengths and nfx number of spatial frequencies per wavelength) This network is a skip-connection convolutional variational autoencoder with an auxiliary discriminator; it is composed of encoder qθ(z|r) and decoder pφ(r|z). This is done via an additional neural network, namely a multi-layer perceptron with skip connections, which allows the translation of keywords z into known pathology classes y
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
