Breast Cancer Detection With Low-Dimensional Ordered Orthogonal Projection in Terahertz Imaging
Chavez, Tanny, Nagma Vohra, Jingxian Wu, Keith Bailey, and Magda El-Shenawee. “Breast Cancer Detection with Low-dimension Ordered Orthogonal Projection in Terahertz Imaging.” IEEE Transactions on Terahertz Science and Technology (2019).
Abstract
This article proposes a new dimension reduction algorithm based on low-dimensional ordered orthogonal projection, which is used for cancer detection with terahertz (THz) images of freshly excised human breast cancer tissues. A THz image can be represented by a data cube with each pixel containing a high-dimensional spectrum vector covering several THz frequencies, where each frequency represents a different dimension in the vector. The proposed algorithm projects the high-dimensional spectrum vector of each pixel within the THz image into a low-dimensional subspace that contains the majority of the unique features embedded in the image. The low-dimensional subspace is constructed by sequentially identifying its orthonormal basis vectors, such that each newly chosen basis vector represents the most unique information not contained by existing basis vectors. A multivariate Gaussian mixture model is used to represent the statistical distributions of the low-dimensional feature vectors obtained from the proposed dimension reduction algorithm. The model parameters are iteratively learned by using unsupervised learning methods, such as Markov chain Monte Carlo or expectation maximization, and the results are used to classify the various regions within a tumor sample. Experiment results demonstrate that the proposed method achieves apparent performance improvement in human breast cancer tissue over existing approaches such as one-dimensional Markov chain Monte Carlo. The results confirm that the dimension reduction algorithm presented in this article is a promising technique for breast cancer detection with THz images, and the classification results present a good correlation with respect to the histopathology results of the analyzed samples.
“The reflection measurements were taken by using a TPSSpectra 3000 pulsed THz imaging and spectroscopy system. The diagram of the system is shown in Fig. 2(a). The system uses a Ti:Sapphire laser that produces an 800-nm pulse to excite the THz emitter and the THz receiver. Upon excitation, the THz emitter generates a time-domain THz pulse, as shown in Fig. 2(b). The Fourier transform of the pulse, as shown in Fig. 2(c), demonstrates a power spectrum of pulse ranging from 0.1 to 4 THz. This emitted pulse is made incident on the sample through a set of mirrors, and the reflected pulse from the sample is directed toward the THz receiver [8]. In the reflection mode measurements, both the THz emitter and the detector are offset 30◦ with respect to the normal direction on the sample. To obtain the THz-reflected signal at each pixel on the tissue to produce an image, the scanning stage was set to move in increments of 200-μm step size using a stepper motor”