STIR-Net: Deep Spatial-Temporal Image Restoration Net for Radiation Reduction in CT Perfusion

Abstract

Computed Tomography Perfusion (CTP) imaging is a cost-effective and fast approach to provide diagnostic images for acute stroke treatment. Its cine scanning mode allows the visualization of anatomic brain structures and blood flow; however, it requires contrast agent injection and continuous CT scanning over an extended time. In fact, the accumulative radiation dose to patients will increase health risks such as skin irritation, hair loss, cataract formation, and even cancer. Solutions for reducing radiation exposure include reducing the tube current and/or shortening the X-ray radiation exposure time. However, images scanned at lower tube currents are usually accompanied by higher levels of noise and artifacts. On the other hand, shorter X-ray radiation exposure time with longer scanning intervals will lead to image information that is insufficient to capture the blood flow dynamics between frames. Thus, it is critical for us to seek a solution that can preserve the image quality when the tube current and the temporal frequency are both low. We propose STIR-Net in this paper, an end-to-end spatial-temporal convolutional neural network structure, which exploits multi-directional automatic feature extraction and image reconstruction schema to recover high-quality CT slices effectively. With the inputs of low-dose and low-resolution patches at different cross-sections of the spatio-temporal data, STIR-Net blends the features from both spatial and temporal domains to reconstruct high-quality CT volumes. In this study, we finalize extensive experiments to appraise the image restoration performance at different levels of tube current and spatial and temporal resolution scales.The results demonstrate the capability of our STIR-Net to restore high-quality scans at as low as 11% of absorbed radiation dose of the current imaging protocol, yielding an average of 10% improvement for perfusion maps compared to the patch-based log likelihood method.

Keywords: CT perfusion image; brain hemodynamics; deep learning; image restoration; radiation reduction.

Figure 1

(Top) A kernel regulation block (KR-block) with a massive of convolution computations (128 × 7 × 7) comprises two 1 × 1 convolution components for computation reduction and one 3 × 3 convolution module for regularizing the features extracted by the preceding large size kernels. The number of dark-gray blocks indicates the quantity of kernels in the current convolutional layers, and the size of dark-gray blocks represents the size of kernels and the density of convolution. The color arrows represent the quantity of feature-map outputs. (Bottom) SRDN is consisted of feature extraction, shrinking, regulation and mapping, expanding, and image reconstruction. Four KR-blocks are embedded in the proposed SRDN.

Figure 2

STIR-Net Architecture. STIR-Net takes low-dose inputs from three cross-sections: XY, XT, and YT. Each cross-section go through one SRDN, and the outputs of SRDNs meet in a conjoint layer, which calculates the mean of the three output volumes form SRDNs to provide the final results of STIR-Net.

Figure 3

Visual comparison of CBF for three test patients: #18, #19, and #21, when reducing the tube current to 40 mAs with a down-sample ratio of two (two times low spatial and two time low temporal resolutions). The notation for each column is: GT, Ground truth image; LR, Low-Resolution input; MS-EPLL, MS-EPLL restoration result; STAR-Spat, STAR reconstruction result (spatial only); STAR-Temp, STAR reconstruction result (temporal only); STAR-Conj, STAR reconstruction result (spatial + temporal); STIR-Spat, STIR-Net reconstruction result (spatial only); STIR-Temp, STIR-Net reconstruction result (temporal only); STIR-Conj, STIR-Net reconstruction result (spatial + temporal). All figures are displayed by using the same colormap and the color range for each patient is shown in the colorbar on the rightmost of each row. We use white arrows to compare the details in the region of interests.

Figure 4

Visual comparison of CBV for three test patients: #18, #19, and #21, when reducing the tube current to 40 mAs with a down-sample ratio of two (two times low spatial and two time low temporal resolutions). The notation for each column is: GT, Ground truth image; LR, Low-Resolution input; MS-EPLL, MS-EPLL restoration result; STAR-Spat, STAR reconstruction result (spatial only); STAR-Temp, STAR reconstruction result (temporal only); STAR-Conj, STAR reconstruction result (spatial + temporal); STIR-Spat, STIR-Net reconstruction result (spatial only); STIR-Temp, STIR-Net reconstruction result (temporal only); STIR-Conj, STIR-Net reconstruction result (spatial + temporal). All figures are displayed by using the same colormap and the color range for each patient is shown in the colorbar on the rightmost of each row. We use white arrows to compare the details in the region of interests.

Figure 5

Visual comparison of CBF for three test patients: #18, #19, and #21, when reducing the tube current to 40 mAs with a down-sample ratio of three (three times low spatial and two time low temporal resolutions). The notation for each column is: GT, Ground truth image; LR, Low-Resolution input; MS-EPLL, MS-EPLL restoration result; STAR-Spat, STAR reconstruction result (spatial only); STAR-Temp, STAR reconstruction result (temporal only); STAR-Conj, STAR reconstruction result (spatial + temporal); STIR-Spat, STIR-Net reconstruction result (spatial only); STIR-Temp, STIR-Net reconstruction result (temporal only); STIR-Conj, STIR-Net reconstruction result (spatial + temporal). All figures are displayed by using the same colormap and the color range for each patient is shown in the colorbar on the rightmost of each row. We use white arrows to compare the details in the region of interests.

Figure 6

Visual comparison of CBV for three test patients: #18, #19, and #21, when reducing the tube current to 40 mAs with a down-sample ratio of three (three times low spatial and two time low temporal resolutions). The notation for each column is: GT, Ground truth image; LR, Low-Resolution input; MS-EPLL, MS-EPLL restoration result; STAR-Spat, STAR reconstruction result (spatial only); STAR-Temp, STAR reconstruction result (temporal only); STAR-Conj, STAR reconstruction result (spatial + temporal); STIR-Spat, STIR-Net reconstruction result (spatial only); STIR-Temp, STIR-Net reconstruction result (temporal only); STIR-Conj, STIR-Net reconstruction result (spatial + temporal). All figures are displayed by using the same colormap and the color range for each patient is shown in the colorbar on the rightmost of each row. We use white arrows to compare the details in the region of interests.