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

<div>Diffuse optical tomography (DOT) leverages near-infrared light propagation through tissue to assess its optical properties and identify abnormalities. </div><div>DOT image reconstruction from limited-angle data acquisition is severely ill-posed due to the highly scattered photons in the medium and the relatively small number of collected projections. Reconstructions are thus commonly marred by artifacts and, as a result, it is difficult to obtain accurate reconstruction of target objects, e.g., malignant lesions.</div><div>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.</div><div>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.</div><div>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.</div><div>Given the scarcity of real-world sensor-image pairs required for training supervised deep learning models,</div><div>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.</div><div>Both quantitative and qualitative results on phantom and real data indicate the superiority of our multitask method in the reconstruction and localization of lesions in tissue compared to state-of-the-art methods.</div><div>The results demonstrate that multitask learning provides sharper and more accurate reconstruction.</div>