Harmonic field extension for QSM with reduced spatial coverage using physics-informed generative adversarial network.

Quantitative susceptibility mapping (QSM) is frequently employed in investigating brain iron related to brain development and diseases within deep gray matter (DGM). Nonetheless, the acquisition of whole-brain QSM data is time-intensive. An alternative approach, focusing the QSM specifically on areas of interest such as the DGM by reducing the field-of-view (FOV), can significantly decrease scan times. However, severe susceptibility value underestimations have been reported during QSM reconstruction with a limited FOV, largely attributable to artifacts from incorrect background field removal in the boundary region. This presents a considerable barrier to the clinical use of QSM with small spatial coverages using conventional methods alone. To mitigate the propagation of these errors, we proposed a harmonic field extension method based on a physics-informed generative adversarial network. Both quantitative and qualitative results demonstrate that our method outperforms conventional methods and delivers results comparable to those obtained with full FOV. Furthermore, we demonstrate the versatility of our method by applying it to data acquired prospectively with limited FOV and to data from patients with Parkinson's disease. The method has shown significant improvements in local field results, with QSM outcomes. In a clear illustration of its feasibility and effectiveness in real clinical environments, our proposed method addresses the prevalent issue of susceptibility underestimation in QSM with small spatial coverage.

Data-driven electrical conductivity brain imaging using 3 T MRI.

Magnetic resonance electrical properties tomography (MR-EPT) is a non-invasive measurement technique that derives the electrical properties (EPs, e.g., conductivity or permittivity) of tissues in the radiofrequency range (64 MHz for 1.5 T and 128 MHz for 3 T MR systems). Clinical studies have shown the potential of tissue conductivity as a biomarker. To date, model-based conductivity reconstructions rely on numerical assumptions and approximations, leading to inaccuracies in the reconstructed maps. To address such limitations, we propose an artificial neural network (ANN)-based non-linear conductivity estimator trained on simulated data for conductivity brain imaging. Network training was performed on 201 synthesized T2-weighted spin-echo (SE) data obtained from the finite-difference time-domain (FDTD) electromagnetic (EM) simulation. The dataset was composed of an approximated T2-w SE magnitude and transceive phase information. The proposed method was tested three in-silico and in-vivo on two volunteers and three patients' data. For comparison purposes, various conventional phase-based EPT reconstruction methods were used that ignore B 1 + magnitude information, such as Savitzky-Golay kernel combined with Gaussian filter (S-G Kernel), phase-based convection-reaction EPT (cr-EPT), magnitude-weighted polynomial-fitting phase-based EPT (Poly-Fit), and integral-based phase-based EPT (Integral-based). From the in-silico experiments, quantitative analysis showed that the proposed method provides more accurate and improved quality (e.g., high structural preservation) conductivity maps compared to conventional reconstruction methods. Representatively, in the healthy brain in-silico phantom experiment, the proposed method yielded mean conductivity values of 1.97 ± 0.20 S/m for CSF, 0.33 ± 0.04 S/m for WM, and 0.52 ± 0.08 S/m for GM, which were closer to the ground-truth conductivity (2.00, 0.30, 0.50 S/m) than the integral-based method (2.56 ± 2.31, 0.39 ± 0.12, 0.68 ± 0.33 S/m). In-vivo ANN-based conductivity reconstructions were also of improved quality compared to conventional reconstructions and demonstrated network generalizability and robustness to in-vivo data and pathologies. The reported in-vivo brain conductivity values were in agreement with literatures. In addition, the proposed method was observed for various SNR levels (SNR levels = 10, 20, 40, and 58) and repeatability conditions (the eight acquisitions with the number of signal averages = 1). The preliminary investigations on brain tumor patient datasets suggest that the network trained on simulated dataset can generalize to unforeseen in-vivo pathologies, thus demonstrating its potential for clinical applications.

A single stage knowledge distillation network for brain tumor segmentation on limited MR image modalities.

BACKGROUND AND OBJECTIVE: Precisely segmenting brain tumors using multimodal Magnetic Resonance Imaging (MRI) is an essential task for early diagnosis, disease monitoring, and surgical planning. Unfortunately, the complete four image modalities utilized in the well-known BraTS benchmark dataset: T1, T2, Fluid-Attenuated Inversion Recovery (FLAIR), and T1 Contrast-Enhanced (T1CE) are not regularly acquired in clinical practice due to the high cost and long acquisition time. Rather, it is common to utilize limited image modalities for brain tumor segmentation. METHODS: In this paper, we propose a single stage learning of knowledge distillation algorithm that derives information from the missing modalities for better segmentation of brain tumors. Unlike the previous works that adopted a two-stage framework to distill the knowledge from a pre-trained network into a student network, where the latter network is trained on limited image modality, we train both models simultaneously using a single-stage knowledge distillation algorithm. We transfer the information by reducing the redundancy from a teacher network trained on full image modalities to the student network using Barlow Twins loss on a latent-space level. To distill the knowledge on the pixel level, we further employ a deep supervision idea that trains the backbone networks of both teacher and student paths using Cross-Entropy loss. RESULTS: We demonstrate that the proposed single-stage knowledge distillation approach enables improving the performance of the student network in each tumor category with overall dice scores of 91.11% for Tumor Core, 89.70% for Enhancing Tumor, and 92.20% for Whole Tumor in the case of only using the FLAIR and T1CE images, outperforming the state-of-the-art segmentation methods. CONCLUSIONS: The outcomes of this work prove the feasibility of exploiting the knowledge distillation in segmenting brain tumors using limited image modalities and hence make it closer to clinical practices.

Technical note: Multi-receiver combination method for phase-based electrical property tomography of the breast.

BACKGROUND: Phase-based electrical property tomography (EPT) is a technique that allows conductivity reconstruction with only phase of the B1 field under the assumption that the magnitude of the B1 fields are homogeneous. The more this assumption is violated, the less accurate the reconstructed conductivity. Thus, a method that ensures homogeneity of | B 1 - | $| {{\rm{B}}_1^ - } |$ field is important for breast image using multi-receiver coil. PURPOSE: To develop a method for multi-receiver combination for phase-based EPT usable for breast EPT imaging in the clinic. METHODS: Theory of the proposed method is presented. To validate the proposed method, the phantom and in-vivo experiments were conducted. Conductivity images were reconstructed using the transceive phase of the combined image and results were compared with another combination method. RESULTS: The proposed method's conductivity results were more stable than those of the previous method when | B 1 + | $| {{\rm{B}}_1^ + } |$ was not homogeneous and when the homogeneous contrast region was small. The phantom and in-vivo results indicate that the proposed method produces improved conductivity images than the previous method. The proposed combination method also increased the conductivity contrast between benign and cancerous tissues. CONCLUSION: The proposed method produced more stable multi-receiver combination for phase-based EPT of the breast in a clinical environment.

Detection of Cerebral Microbleeds in MR Images Using a Single-Stage Triplanar Ensemble Detection Network (TPE-Det).

BACKGROUND: Cerebral microbleeds (CMBs) are microscopic brain hemorrhages with implications for various diseases. Automated detection of CMBs is a challenging task due to their wide distribution throughout the brain, small size, and visual similarity to their mimics. For this reason, most of the previously proposed methods have been accomplished through two distinct stages, which may lead to difficulties in integrating them into clinical workflows. PURPOSE: To develop a clinically feasible end-to-end CMBs detection network with a single-stage structure utilizing 3D information. This study proposes triplanar ensemble detection network (TPE-Det), ensembling 2D convolutional neural networks (CNNs) based detection networks on axial, sagittal, and coronal planes. STUDY TYPE: Retrospective. SUBJECTS: Two datasets (DS1 and DS2) were used: 1) 116 patients with 367 CMBs and 12 patients without CMBs for training, validation, and testing (70.39 ± 9.30 years, 68 women, 60 men, DS1); 2) 58 subjects with 148 microbleeds and 21 subjects without CMBs only for testing (76.13 ± 7.89 years, 47 women, 32 men, DS2). FIELD STRENGTH/SEQUENCE: A 3 T field strength and 3D GRE sequence scan for SWI reconstructions. ASSESSMENT: The sensitivity, FPavg (false-positive per subject), and precision measures were computed and analyzed with statistical analysis. STATISTICAL TESTS: A paired t-test was performed to investigate the improvement of detection performance by the suggested ensembling technique in this study. A P value < 0.05 was considered significant. RESULTS: The proposed TPE-Det detected CMBs on the DS1 testing set with a sensitivity of 96.05% and an FPavg of 0.88, presenting statistically significant improvement. Even when the testing on DS2 was performed without retraining, the proposed model provided a sensitivity of 85.03% and an FPavg of 0.55. The precision was significantly higher than the other models. DATA CONCLUSION: The ensembling of multidimensional networks significantly improves precision, suggesting that this new approach could increase the benefits of detecting lesions in the clinic. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 2.

Improving phase-based conductivity reconstruction by means of deep learning-based denoising of B1+ phase data for 3T MRI.

PURPOSE: To denoise B1+ phase using a deep learning method for phase-based in vivo electrical conductivity reconstruction in a 3T MR system. METHODS: For B1+ phase deep-learning denoising, a convolutional neural network (U-net) was chosen. Training was performed on data sets from 10 healthy volunteers. Input data were the real and imaginary components of single averaged spin-echo data (SNR = 45), which was used to approximate the B1+ phase. For label data, multiple signal-averaged spin-echo data (SNR = 128) were used. Testing was performed on in silico and in vivo data. Reconstructed conductivity maps were derived using phase-based conductivity reconstructions. Additionally, we investigated the usability of the network to various SNR levels, imaging contrasts, and anatomical sites (ie, T1 , T2 , and proton density-weighted brain images and proton density-weighted breast images. In addition, conductivity reconstructions from deep learning-based denoised data were compared with conventional image filters, which were used for data denoising in electrical properties tomography (ie, the Gaussian filtering and the Savitzky-Golay filtering). RESULTS: The proposed deep learning-based denoising approach showed improvement for B1+ phase for both in silico and in vivo experiments with reduced quantitative error measures compared with other methods. Subsequently, this resulted in an improvement of reconstructed conductivity maps from the denoised B1+ phase with deep learning. CONCLUSION: The results suggest that the proposed approach can be used as an alternative preprocessing method to denoise B1+ maps for phase-based conductivity reconstruction without relying on image filters or signal averaging.