Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications

Abstract

Significance: Deep learning (DL) models are being increasingly developed to map sensor data to the image domain directly. However, DL methodologies are data-driven and require large and diverse data sets to provide robust and accurate image formation performances. For research modalities such as 2D/3D diffuse optical imaging, the lack of large publicly available data sets and the wide variety of instrumentation designs, data types, and applications leads to unique challenges in obtaining well-controlled data sets for training and validation. Meanwhile, great efforts over the last four decades have focused on developing accurate and computationally efficient light propagation models that are flexible enough to simulate a wide variety of experimental conditions.Aim: Recent developments in Monte Carlo (MC)-based modeling offer the unique advantage of simulating accurately light propagation spatially, temporally, and over an extensive range of optical parameters, including minimally to highly scattering tissue within a computationally efficient platform. Herein, we demonstrate how such MC platforms, namely "Monte Carlo eXtreme" and "Mesh-based Monte Carlo," can be leveraged to generate large and representative data sets for training the DL model efficiently. Approach:We propose data generator pipeline strategies using these platforms and demonstrate their potential in fluorescence optical topography, fluorescence optical tomography, and singlepixel diffuse optical tomography. These applications represent a large variety in instrumentation design, sample properties, and contrast function.Results: DL models trained using the MC-based in silico datasets, validated further with experimental data not used during training, show accurate and promising results. Conclusion:Overall, these MC-based data generation pipelines are expected to support the development of DL models for rapid, robust, and user-friendly image formation in a wide variety of applications.

Unrolled-DOT: an interpretable deep network for diffuse optical tomography

“…Deep learning has also been applied for generating data in DOT applications. 47 Recently, Zou et al 42 used an autoencoder to learn the forward model and inverse problem of FD-DOT. While their training data included experimental data, it was limited to only 30 unique configurations.…”

“…has applied deep learning and DOT to clinical applications, improving the accuracy of breast tumor imaging. Deep learning has also been applied for generating data in DOT applications 47 . Recently, Zou et al 42 .…”

Periodic-net: an end-to-end data driven framework for diffuse optical imaging of breast cancer from noisy boundary data

“… 18 , 19 Well-controlled data sets for training and validation are among the most important topics in the neural network, but the lack of large, publicly available data sets leads to unique challenges. The development of a data generation pipeline 20 based on Monte Carlo modeling has shown to be a useful method for rapid, robust, and user-friendly image formation in a wide variety of applications. Three-layer deep neural network is proposed in Ref.…”

scatterBrains: an open database of human head models and companion optode locations for realistic Monte Carlo photon simulations

“…24,30,32,[42][43][44] This is driven in part by difficulties in manually placing optodes and potentially limits the works' investigative scope. Recently, both Nizam et al 45 and Bürmen et al 46 have acknowledged the need in the field for open reference datasets, as well as user-friendly multiple optode placement, for both machine learning training and validation of custom MC software. Both groups have provided datasets based on slab geometries with embedded absorbing targets of various shapes meant for training tomographic reconstruction algorithms.…”