Real-Time Monitoring of High-Intensity Focused Ultrasound Thermal Therapy Using the Manifold Learning Method

High-intensity focused ultrasound (HIFU) induces thermal lesions by increasing the tissue temperature in a tight focal region. The main ultrasound imaging techniques currently used to monitor HIFU treatment are standard pulse-echo B-mode ultrasound imaging, ultrasound temperature estimation and elastography-based methods. The present study was carried out on ex vivo animal tissue samples, in which backscattered radiofrequency (RF) signals were acquired in real time at time instances before, during and after HIFU treatment. The manifold learning algorithm, a non-linear dimensionality reduction method, was applied to RF signals which construct B-mode images to detect the HIFU-induced changes among the image frames obtained during HIFU treatment. In this approach, the embedded non-linear information in the region of interest of sequential images is represented in a 2-D manifold with the Isomap algorithm, and each image is depicted as a point on the reconstructed manifold. Four distinct regions are chosen in the manifold corresponding to the four phases of HIFU treatment (before HIFU treatment, during HIFU treatment, immediately after HIFU treatment and 10-min after HIFU treatment). It was found that disorganization of the points is achieved by increasing the acoustic power, and if the thermal lesion has been formed, the regions of points related to pre- and post-HIFU significantly differ. Moreover, the manifold embedding was repeated on 2-D moving windows in RF data envelopes related to pre- and post-HIFU exposure data frames. It was concluded that if mean values of the points related to pre- and post-exposure frames in the reconstructed manifold are estimated, and if the Euclidean distance between these two mean values is calculated and the sliding window is moved and this procedure is repeated for the whole image, a new image based on the Euclidean distance can be formed in which the HIFU thermal lesion is detectable.     

Mining the structural knowledge of high-dimensional medical data using isomap

The paper describes an application of a new, non-linear dimensionality reduction method, named Isomap, for mining the structural knowledge from high-dimensional medical data. The algorithm was evaluated on two publicly available medical datasets: the pathological dataset of breast cancer (241 malignant samples) and the gene expression dataset from the lung (186 tumours). It was found by Isomap that the approximate intrinsic dimensionalities of these two datasets were as low as three. The spatial structures of both datasets were presented in low-dimensional space. Isomap, as a general tool for dimensionality reduction analysis, is helpful in revealing the nonlinear structural knowledge of high-dimensional medical data.