Regularized image reconstruction for ultrasound attenuation transmission tomography

The paper is focused on ultrasonic transmission tomography as a potential medical imaging modality, namely for breast cancer diagnosis. Ultrasound attenuation coefficient is one of the tissue parameters which are related to the pathological tissue state. A technique to reconstruct images of attenuation distribution is presented. Furthermore, an alternative to the commonly used filtered backprojection or algebraic reconstruction techniques is proposed. It is based on regularization of the image reconstruction problem which imposes smoothness in the resulting images while preserving edges. The approach is analyzed on synthetic data sets. The results show that it stabilizes the image restoration by compensating for main sources of estimation errors in this imaging modality.