Development of a novel MR-conditional microwave needle for MR-guided interventional microwave ablation at 1.5T.

PURPOSE: To develop an MR-conditional microwave needle that generates a spherical ablation zone and clear MRI visibility for MR-guided microwave ablation. METHODS: An MR-conditional microwave needle consisting of zirconia tip and TA18 titanium alloy tube was investigated. The numerical model was created to optimize the needle's geometry and analyze its performance. A geometrically optimized needle was produced using non-magnetic materials based on the electromagnetics simulation results. The needle's mechanical properties were tested per the Chinese pharmaceutical industry standard YY0899-2013. The MRI visibility performance and ablation characteristics of the needle was tested both in vitro (phantom) and in vivo (rabbit) at 1.5T. The RF-induced heating was evaluated in ex vivo porcine liver. RESULTS: The needle's mechanical properties met the specified requirements. The needle susceptibility artifact was clearly visible both in vitro and in vivo. The needle artifact diameter (A) was small in in vivo (Ashaft: 4.96 ± 0.18 mm for T1W-FLASH, 3.13 ± 0.05 mm for T2-weighted fast spin-echo (T2W-FSE); Atip: 2.31 ± 0.09 mm for T1W-FLASH, 2.29 ± 0.08 mm for T2W-FSE; tip location error [TLE]: -0.94 ± 0.07 mm for T1W-FLASH, -1.10 ± 0.09 mm for T2W-FSE). Ablation zones generated by the needle were nearly spherical with an elliptical aspect ratio ranging from 0.79 to 0.90 at 30 W, 50 W for 3, 5, 10 min duration ex vivo ablations and 0.86 at 30 W for 10 min duration in vivo ablations. CONCLUSION: The designed MR-conditional microwave needle offers excellent mechanical properties, reliable MRI visibility, insignificant RF-induced heating, and a sufficiently spherical ablation zone. Further clinical development of MR-guided microwave ablation appears warranted.

A novel method for highly linear gradient coil design based on stream function.

BACKGROUND: Magnetoencephalography (MEG) and magnetic resonance imaging (MRI) are non-invasive imaging techniques that offer effective means for disease diagnosis. A more straightforward and optimized method is presented for designing gradient coils which are pivotal parts of the above imaging systems. PURPOSE: A novel design method based on stream function combining an optimization algorithm is proposed to obtain highly linear gradient coil. METHODS: Two-dimensional Fourier expansion of the current field on the surface where the coil is located and the equipotential line of the expansion term superposition according to the number of turns of the coil are used to represent the coil shape. Particle swarm optimization is utilized to optimize the coil shape while linearity and field uniformity are used as parameters to evaluate the coil performance. Through this method, the main parameters such as input current distribution region, coil turns, desired magnetic field strength, expansion order and iteration times can be combined in a given solution space to optimize coil design. RESULTS: Simulation results show that the maximum linearity spatial deviation of the designed bi-planar x-gradient coil compared with that of target field method is reduced from 14% to 0.54%, and that of the bi-planar z-gradient coil is reduced from 8.98% to 0.52%. Similarly, that of the cylindrical x-gradient coil is reduced from 2% to 0.1%, and that of the cylindrical z-gradient coil is reduced from 0.87% to 0.45%. The similar results are found in the index of inhomogeneity error. Moreover, it has also been verified experimentally that the result of measured magnetic field is consist with simulated result. CONCLUSIONS: The proposed method provides a straightforward way that simplifies the design process and improves the linearity of designed gradient coil, which could be beneficial to realize better magnetic field in engineering applications.

CSA: A Channel-Separated Attention Module for Enhancing MRI Reconstruction.

Channel attention mechanisms have been proven to effectively enhance network performance in various visual tasks, including the Magnetic Resonance Imaging (MRI) reconstruction task. Channel attention mechanisms typically involve channel dimensionality reduction and cross-channel interaction operations to achieve complexity reduction and generate more effective weights of channels. However, the operations may negatively impact MRI reconstruction performance since it was found that there is no discernible correlation between adjacent channels and the low information value in some feature maps. Therefore, we proposed the Channel-Separated Attention (CSA) module tailored for MRI reconstruction networks. Each layer of the CSA module avoids compressing channels, thereby allowing for lossless information transmission. Additionally, we employed the Hadamard product to realize that each channel's importance weight was generated solely based on itself, avoiding cross-channel interaction and reducing the computational complexity. We replaced the original channel attention module with the CSA module in an advanced MRI reconstruction network and noticed that CSA module achieved superior reconstruction performance with fewer parameters. Furthermore, we conducted comparative experiments with state-of-the-art channel attention modules on an identical network backbone, CSA module achieved competitive reconstruction outcomes with only approximately 1.036% parameters of the Squeeze-and-Excitation (SE) module. Overall, the CSA module makes an optimal trade-off between complexity and reconstruction quality to efficiently and effectively enhance MRI reconstruction. The code is available at https://github.com/smd1997/CSA-Net.

Linear fine-tuning: a linear transformation based transfer strategy for deep MRI reconstruction.

Introduction: Fine-tuning (FT) is a generally adopted transfer learning method for deep learning-based magnetic resonance imaging (MRI) reconstruction. In this approach, the reconstruction model is initialized with pre-trained weights derived from a source domain with ample data and subsequently updated with limited data from the target domain. However, the direct full-weight update strategy can pose the risk of "catastrophic forgetting" and overfitting, hindering its effectiveness. The goal of this study is to develop a zero-weight update transfer strategy to preserve pre-trained generic knowledge and reduce overfitting. Methods: Based on the commonality between the source and target domains, we assume a linear transformation relationship of the optimal model weights from the source domain to the target domain. Accordingly, we propose a novel transfer strategy, linear fine-tuning (LFT), which introduces scaling and shifting (SS) factors into the pre-trained model. In contrast to FT, LFT only updates SS factors in the transfer phase, while the pre-trained weights remain fixed. Results: To evaluate the proposed LFT, we designed three different transfer scenarios and conducted a comparative analysis of FT, LFT, and other methods at various sampling rates and data volumes. In the transfer scenario between different contrasts, LFT outperforms typical transfer strategies at various sampling rates and considerably reduces artifacts on reconstructed images. In transfer scenarios between different slice directions or anatomical structures, LFT surpasses the FT method, particularly when the target domain contains a decreasing number of training images, with a maximum improvement of up to 2.06 dB (5.89%) in peak signal-to-noise ratio. Discussion: The LFT strategy shows great potential to address the issues of "catastrophic forgetting" and overfitting in transfer scenarios for MRI reconstruction, while reducing the reliance on the amount of data in the target domain. Linear fine-tuning is expected to shorten the development cycle of reconstruction models for adapting complicated clinical scenarios, thereby enhancing the clinical applicability of deep MRI reconstruction.

A hybrid convolutional neural network for super-resolution reconstruction of MR images.

PURPOSE: Spatial resolution is an important parameter for magnetic resonance imaging (MRI). High-resolution MR images provide detailed information and benefit subsequent image analysis. However, higher resolution MR images come at the expense of longer scanning time and lower signal-to-noise ratios (SNRs). Using algorithms to improve image resolution can mitigate these limitations. Recently, some convolutional neural network (CNN)-based super-resolution (SR) algorithms have flourished on MR image reconstruction. However, most algorithms usually adopt deeper network structures to improve the performance. METHODS: In this study, we propose a novel hybrid network (named HybridNet) to improve the quality of SR images by increasing the width of the network. Specifically, the proposed hybrid block combines a multipath structure and variant dense blocks to extract abundant features from low-resolution images. Furthermore, we fully exploit the hierarchical features from different hybrid blocks to reconstruct high-quality images. RESULTS: All SR algorithms are evaluated using three MR image datasets and the proposed HybridNet outperformed the comparative methods with peak a signal-to-noise ratio (PSNR) of 42.12 ± 0.92 dB, 38.60 ± 2.46 dB, 35.17 ± 2.96 dB and a structural similarity index (SSIM) of 0.9949 ± 0.0015, 0.9892 ± 0.0034, 0.9740 ± 0.0064, respectively. Besides, our proposed network can reconstruct high-quality images on an unseen MR dataset with PSNR of 33.27 ± 1.56 and SSIM of 0.9581 ± 0.0068. CONCLUSIONS: The results demonstrate that HybridNet can reconstruct high-quality SR images from degraded MR images and has good generalization ability. It also can be leveraged to assist the task of image analysis or processing.