DOT-AE-GAN: a hybrid autoencoder-GAN model for enhanced ultrasound-guided diffuse optical tomography reconstruction.

Significance: Diffuse optical tomography (DOT) is a noninvasive functional imaging technique; however, the reconstruction of high-quality images from DOT data is a challenging task because of the ill-posed nature of the inverse problem. We introduce a hybrid machine learning model that combines the strengths of autoencoders (AEs) and generative adversarial networks (GANs) for robust DOT reconstruction. Aim: We leveraged a hybrid machine learning model for robust ultrasound-guided DOT reconstruction. Approach: A hybrid model, DOT-AE-GAN, that combines the strengths of AEs and GANs to enhance the robustness of DOT reconstruction is introduced. The proposed model utilizes an AE to efficiently encode the DOT measurement to reconstruction and decode back to measurement, modeling the inverse and forward process of reconstruction. In parallel, a GAN framework is incorporated to enhance the robustness of the reconstruction for irregularly shaped lesions, utilizing adversarial training. Results: The DOT-AE-GAN model is first trained and validated using simulations, demonstrating reconstruction accuracy in absorption coefficients and lateral dimensions of the targets. The DOT-AE-GAN is then fine-tuned with phantom data and compared with the AE model, showing the improvement over the AE model in the reconstructed target lateral dimension while keeping similar accuracy in absorption coefficient. The DOT-AE-GAN is validated with patient data, revealing that the DOT-AE-GAN-reconstructed breast lesion lateral dimensions follow size measurements of co-registered ultrasound significantly better than the optimization-based reconstruction algorithm and AE model with improved absorption contrast between malignant and benign lesions. Conclusions: Our results demonstrate that the DOT-AE-GAN model has great potential in ultrasound-guided DOT reconstruction.