Nonlinear approach to difference imaging in diffuse optical tomography

Difference imaging from single measurements in diffuse optical tomography: a deep learning approach

SIGNIFICANCE

"Difference imaging," which reconstructs target optical properties using measurements with and without target information, is often used in diffuse optical tomography (DOT) in vivo imaging. However, taking additional reference measurements is time consuming, and mismatches between the target medium and the reference medium can cause inaccurate reconstruction.

AIM

We aim to streamline the data acquisition and mitigate the mismatch problems in DOT difference imaging using a deep learning-based approach to generate data from target measurements only.

APPROACH

We train an artificial neural network to output data for difference imaging from target measurements only. The model is trained and validated on simulation data and tested with simulations, phantom experiments, and clinical data from 56 patients with breast lesions.

RESULTS

The proposed method has comparable performance to the traditional approach using measurements without mismatch between the target side and the reference side, and it outperforms the traditional approach using measurements when there is a mismatch. It also improves the target-to-artifact ratio and lesion localization in patient data.

CONCLUSIONS

The proposed method can simplify the data acquisition procedure, mitigate mismatch problems, and improve reconstructed image quality in DOT difference imaging.

A Model-Based Iterative Learning Approach for Diffuse Optical Tomography

Diffuse optical tomography (DOT) utilises near-infrared light for imaging spatially distributed optical parameters, typically the absorption and scattering coefficients. The image reconstruction problem of DOT is an ill-posed inverse problem, due to the non-linear light propagation in tissues and limited boundary measurements. The ill-posedness means that the image reconstruction is sensitive to measurement and modelling errors. The Bayesian approach for the inverse problem of DOT offers the possibility of incorporating prior information about the unknowns, rendering the problem less ill-posed. It also allows marginalisation of modelling errors utilising the so-called Bayesian approximation error method. A more recent trend in image reconstruction techniques is the use of deep learning, which has shown promising results in various applications from image processing to tomographic reconstructions. In this work, we study the non-linear DOT inverse problem of estimating the (absolute) absorption and scattering coefficients utilising a 'model-based' learning approach, essentially intertwining learned components with the model equations of DOT. The proposed approach was validated with 2D simulations and 3D experimental data. We demonstrated improved absorption and scattering estimates for targets with a mix of smooth and sharp image features, implying that the proposed approach could learn image features that are difficult to model using standard Gaussian priors. Furthermore, it was shown that the approach can be utilised in compensating for modelling errors due to coarse discretisation enabling computationally efficient solutions. Overall, the approach provided improved computation times compared to a standard Gauss-Newton iteration.

Multitask Deep Learning Reconstruction and Localization of Lesions in Limited Angle Diffuse Optical Tomography

Diffuse optical tomography (DOT) leverages near-infrared light propagation through tissue to assess its optical properties and identify abnormalities. DOT image reconstruction is an ill-posed problem due to the highly scattered photons in the medium and the smaller number of measurements compared to the number of unknowns. Limited-angle DOT reduces probe complexity at the cost of increased reconstruction complexity. Reconstructions are thus commonly marred by artifacts and, as a result, it is difficult to obtain an accurate reconstruction of target objects, e.g., malignant lesions. Reconstruction does not always ensure good localization of small lesions. Furthermore, conventional optimization-based reconstruction methods are computationally expensive, rendering them too slow for real-time imaging applications. Our goal is to develop a fast and accurate image reconstruction method using deep learning, where multitask learning ensures accurate lesion localization in addition to improved reconstruction. We apply spatial-wise attention and a distance transform based loss function in a novel multitask learning formulation to improve localization and reconstruction compared to single-task optimized methods. Given the scarcity of real-world sensor-image pairs required for training supervised deep learning models, we leverage physics-based simulation to generate synthetic datasets and use a transfer learning module to align the sensor domain distribution between in silico and real-world data, while taking advantage of cross-domain learning. Applying our method, we find that we can reconstruct and localize lesions faithfully while allowing real-time reconstruction. We also demonstrate that the present algorithm can reconstruct multiple cancer lesions. The results demonstrate that multitask learning provides sharper and more accurate reconstruction.

An Automated Preprocessing Method for Diffuse Optical Tomography to Improve Breast Cancer Diagnosis

The ultrasound-guided diffuse optical tomography is a noninvasive imaging technique for breast cancer diagnosis and treatment monitoring. The technique uses a handheld probe capable of providing measurements of multiple wavelengths in a few seconds. These measurements are used to estimate optical absorptions of lesions and calculate the total hemoglobin concentration. Any measurement errors caused by low signal to noise ratio data and/or movements during data acquisition would reduce the accuracy of reconstructed total hemoglobin concentration. In this article, we introduce an automated preprocessing method that combines data collected from multiple sets of lesion measurements of 4 optical wavelengths to detect and correct outliers in the perturbation. Two new measures of correlation between each pair of wavelength measurements and a wavelength consistency index of all reconstructed absorption maps are introduced. For phantom and patients' data without evidence of measurement errors, the correlation coefficient between each pair of wavelength measurements was above 0.6. However, for patients with measurement errors, the correlation coefficient was much lower. After applying the correction method to 18 patients' data with measurement errors, the correlation has improved and the wavelength consistency index is in the same range as the cases without wavelength-dependent measurement errors. The results show an improvement in classification of malignant and benign lesions.