Neural Architecture Search for compressed sensing Magnetic Resonance image reconstruction

Spatial-frequency parallel subsampling for distributed compressive sensing in ultrasonic imaging inspection

To address the problem of the high hardware requirements and insufficient data storage capacity in current ultrasonic imaging testing, a novel approach is developed using a programmable device, which combines spatial-frequency parallel subsampling with the distributed compressive sensing simultaneous orthogonal matching pursuit (DCS-SOMP) algorithm to achieve fast and high-quality ultrasonic imaging inspection with a small amount of subsampled data. The spatial sparse measurement method was employed to achieve spatial subsampling and minimize the count of signals. Additionally, frequency subsampling was utilized to significantly reduce the data volume of time-domain signals while ensuring signal quality by truncating the primary testing frequency components. The subsampled data was then reconstructed using distributed compressive sensing (DCS) for multi-channel data reconstruction. The experiment of ultrasonic scanning imaging was conducted on a carbon steel specimen containing six transverse through-holes with a diameter of Ф1.5 mm at different depths. The ultrasonic signals were acquired using the spatial-frequency parallel subsampling method, and subsequently reconstructed using the DCS-SOMP algorithm. The results show that the proposed method achieves comparable image quality to that obtained with complete data, using only 1/8 of the complete data, while accurately locating and quantifying defects.

LENAS: Learning-Based Neural Architecture Search and Ensemble for 3-D Radiotherapy Dose Prediction

Radiation therapy treatment planning requires balancing the delivery of the target dose while sparing normal tissues, making it a complex process. To streamline the planning process and enhance its quality, there is a growing demand for knowledge-based planning (KBP). Ensemble learning has shown impressive power in various deep learning tasks, and it has great potential to improve the performance of KBP. However, the effectiveness of ensemble learning heavily depends on the diversity and individual accuracy of the base learners. Moreover, the complexity of model ensembles is a major concern, as it requires maintaining multiple models during inference, leading to increased computational cost and storage overhead. In this study, we propose a novel learning-based ensemble approach named LENAS, which integrates neural architecture search with knowledge distillation for 3-D radiotherapy dose prediction. Our approach starts by exhaustively searching each block from an enormous architecture space to identify multiple architectures that exhibit promising performance and significant diversity. To mitigate the complexity introduced by the model ensemble, we adopt the teacher-student paradigm, leveraging the diverse outputs from multiple learned networks as supervisory signals to guide the training of the student network. Furthermore, to preserve high-level semantic information, we design a hybrid loss to optimize the student network, enabling it to recover the knowledge embedded within the teacher networks. The proposed method has been evaluated on two public datasets: 1) OpenKBP and 2) AIMIS. Extensive experimental results demonstrate the effectiveness of our method and its superior performance to the state-of-the-art methods. Code: github.com/hust-linyi/LENAS.

Hierarchical neural architecture search with adaptive global-local feature learning for Magnetic Resonance Image reconstruction

Neural architecture search (NAS) has been introduced into the design of deep neural network architectures for Magnetic Resonance Imaging (MRI) reconstruction since NAS-based methods can acquire the complex network architecture automatically without professional designing experience and improve the model's generalization ability. However, current NAS-based MRI reconstruction methods suffer from a lack of efficient operators in the search space, which leads to challenges in effectively recovering high-frequency details. This limitation is primarily due to the prevalent use of convolution operators in the current search space, which struggle to capture both global and local features of MR images simultaneously, resulting in insufficient information utilization. To address this issue, a generative adversarial network (GAN) based model is proposed to reconstruct the MR image from under-sampled K-space data. Firstly, parameterized global and local feature learning modules at multiple scales are added into the search space to improve the capability of recovering high-frequency details. Secondly, to mitigate the increased search time caused by the augmented search space, a hierarchical NAS is designed to learn the global-local feature learning modules that enable the reconstruction network to learn global and local information of MR images at different scales adaptively. Thirdly, to reduce the number of network parameters and computational complexity, the standard operations in global-local feature learning modules are replaced with lightweight operations. Finally, experiments on several publicly available brain MRI image datasets evaluate the performance of the proposed method. Compared to the state-of-the-art MRI reconstruction methods, the proposed method yields better reconstruction results in terms of peak signal-to-noise ratio and structural similarity at a lower computational cost. Additionally, our reconstruction results are validated through a brain tumor classification task, affirming the practicability of the proposed method. Our code is available at https://github.com/wwHwo/HNASMRI.

Research on rainy day traffic sign recognition algorithm based on PMRNet

The recognition of traffic signs is of great significance to intelligent driving and traffic systems. Most current traffic sign recognition algorithms do not consider the impact of rainy weather. The rain marks will obscure the recognition target in the image, which will lead to the performance degradation of the algorithm, a problem that has yet to be solved. In order to improve the accuracy of traffic sign recognition in rainy weather, we propose a rainy traffic sign recognition algorithm. The algorithm in this paper includes two modules. First, we propose an image deraining algorithm based on the Progressive multi-scale residual network (PMRNet), which uses a multi-scale residual structure to extract features of different scales, so as to improve the utilization rate of the algorithm for information, combined with the Convolutional long-short term memory (ConvLSTM) network to enhance the algorithm's ability to extract rain mark features. Second, we use the CoT-YOLOv5 algorithm to recognize traffic signs on the recovered images. In this paper, in order to improve the performance of YOLOv5 (You-Only-Look-Once, YOLO), the 3 × 3 convolution in the feature extraction module is replaced by the Contextual Transformer (CoT) module to make up for the lack of global modeling capability of Convolutional Neural Network (CNN), thus improving the recognition accuracy. The experimental results show that the deraining algorithm based on PMRNet can effectively remove rain marks, and the evaluation indicators Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) are better than the other representative algorithms. The mean Average Precision (mAP) of the CoT-YOLOv5 algorithm on the TT100k datasets reaches 92.1%, which is 5% higher than the original YOLOv5.

M3NAS: Multi-Scale and Multi-Level Memory-Efficient Neural Architecture Search for Low-Dose CT Denoising

Lowering the radiation dose in computed tomography (CT) can greatly reduce the potential risk to public health. However, the reconstructed images from dose-reduced CT or low-dose CT (LDCT) suffer from severe noise which compromises the subsequent diagnosis and analysis. Recently, convolutional neural networks have achieved promising results in removing noise from LDCT images. The network architectures that are used are either handcrafted or built on top of conventional networks such as ResNet and U-Net. Recent advances in neural network architecture search (NAS) have shown that the network architecture has a dramatic effect on the model performance. This indicates that current network architectures for LDCT may be suboptimal. Therefore, in this paper, we make the first attempt to apply NAS to LDCT and propose a multi-scale and multi-level memory-efficient NAS for LDCT denoising, termed M3NAS. On the one hand, the proposed M3NAS fuses features extracted by different scale cells to capture multi-scale image structural details. On the other hand, the proposed M3NAS can search a hybrid cell- and network-level structure for better performance. In addition, M3NAS can effectively reduce the number of model parameters and increase the speed of inference. Extensive experimental results on two different datasets demonstrate that the proposed M3NAS can achieve better performance and fewer parameters than several state-of-the-art methods. In addition, we also validate the effectiveness of the multi-scale and multi-level architecture for LDCT denoising, and present further analysis for different configurations of super-net.

Real-time MRI motion estimation through an unsupervised k-space-driven deformable registration network (KS-RegNet)

Purpose. Real-time three-dimensional (3D) magnetic resonance (MR) imaging is challenging because of slow MR signal acquisition, leading to highly under-sampled k-space data. Here, we proposed a deep learning-based, k-space-driven deformable registration network (KS-RegNet) for real-time 3D MR imaging. By incorporating prior information, KS-RegNet performs a deformable image registration between a fully-sampled prior image and on-board images acquired from highly-under-sampled k-space data, to generate high-quality on-board images for real-time motion tracking. Methods. KS-RegNet is an end-to-end, unsupervised network consisting of an input data generation block, a subsequent U-Net core block, and following operations to compute data fidelity and regularization losses. The input data involved a fully-sampled, complex-valued prior image, and the k-space data of an on-board, real-time MR image (MRI). From the k-space data, under-sampled real-time MRI was reconstructed by the data generation block to input into the U-Net core. In addition, to train the U-Net core to learn the under-sampling artifacts, the k-space data of the prior image was intentionally under-sampled using the same readout trajectory as the real-time MRI, and reconstructed to serve an additional input. The U-Net core predicted a deformation vector field that deforms the prior MRI to on-board real-time MRI. To avoid adverse effects of quantifying image similarity on the artifacts-ridden images, the data fidelity loss of deformation was evaluated directly in k-space. Results. Compared with Elastix and other deep learning network architectures, KS-RegNet demonstrated better and more stable performance. The average (±s.d.) DICE coefficients of KS-RegNet on a cardiac dataset for the 5- , 9- , and 13-spoke k-space acquisitions were 0.884 ± 0.025, 0.889 ± 0.024, and 0.894 ± 0.022, respectively; and the corresponding average (±s.d.) center-of-mass errors (COMEs) were 1.21 ± 1.09, 1.29 ± 1.22, and 1.01 ± 0.86 mm, respectively. KS-RegNet also provided the best performance on an abdominal dataset. Conclusion. KS-RegNet allows real-time MRI generation with sub-second latency. It enables potential real-time MR-guided soft tissue tracking, tumor localization, and radiotherapy plan adaptation.