In IEEE transactions on ultrasonics, ferroelectrics, and frequency control
Deep learning is heavily being borrowed to solve problems in medical imaging applications and Siamese neural networks are the front-runners of motion tracking. In this paper, we propose to upgrade one such Siamese architecture-based neural network for robust and accurate landmark tracking in ultrasound images to improve the quality of image-guided radiation therapy. Although several researchers have improved the Siamese architecture-based networks with sophisticated detection modules and by incorporating transfer learning, the inherent assumption of constant position model and missing motion model remain unaddressed limitations. In our proposed model, we overcome these limitations by introducing two modules into the original architecture. We employ reference template update to resolve the constant position model and a Linear Kalman Filter (LKF) to address the missing motion model. Moreover, we demonstrate that the proposed architecture provides promising results without transfer learning. The proposed model was submitted to an open challenge organized by MICCAI and was evaluated exhaustively on the Liver Ultrasound Tracking (CLUST) 2D data set. Experimental results proved that the proposed model tracked the landmarks with promising accuracy. Furthermore, we also induced synthetic occlusions to perform a qualitative analysis of the proposed approach. The evaluations were performed on the training set of the CLUST 2D data set. The proposed method outperformed the original Siamese architecture by a significant margin.
Bharadwaj Skanda, Prasad Sumukha, Almekkawy Mohamed