Deep Network Regularization for Phase-based Magnetic Resonance Electrical Properties Tomography with Stein's Unbiased Risk Estimator.

Magnetic resonance imaging (MRI) can extract the tissue conductivity values from in vivo data using the so-called phase-based magnetic resonance electrical properties tomography (MR-EPT). However, this procedure suffers from noise amplification caused by the use of the Laplacian operator. To counter this issue, we propose a novel preprocessing denoiser for magnetic resonance transceive phase images, operating in an unsupervised manner. Inspired by the deep image prior approach, we apply the random initialization of a convolutional neural network, which enforces an implicit regularization. Additionally, we introduce Stein's unbiased risk estimator, which is the unbiased estimator of the mean square error for optimizing the network without the need for label images. This modification not only tackles the overfitting problem inherent in the deep image prior approach but also operates within a purely unsupervised framework. In addition, instead of using phase images, we use real and imaginary images, which aligns with the theoretical model of the risk estimator. Our generative model needs neither the preparation of training datasets nor prior training procedure, and it maintains adaptability across various resolutions and signal-to-noise ratio levels. In testing. our method significantly diminished residual error remaining in phase maps, quantitatively as well as qualitatively, for both phantom and simulated brain data. Furthermore, it outperformed other denoising methods in reducing noise amplification and boundary error. When applied to healthy volunteer and patient data, the proposed method revealed reduced error in the reconstructed conductivity maps, with conductivity values aligning well with established literature values. To the best of our knowledge, this is the first blind approach using a purely unsupervised denoising framework that can implement a 2D phase-based MR-EPT reconstruction algorithm. The source code is available at https://github.com/Yonsei-MILab/Implicit-Regularization-forMREPT-with-SURE.

Problem Solving MRI to Reduce False-Positive Biopsy Related to Breast US: Conductivity vs. DWI vs. Abbreviated Contrast-Enhanced MRI.

BACKGROUND: While breast ultrasound (US) is a useful tool for diagnosing breast masses, it can entail false-positive biopsy results because of some overlapping features between benign and malignant breast masses and subjective interpretation. PURPOSE: To evaluate the performance of conductivity imaging for reducing false-positive biopsy results related to breast US, as compared to diffusion-weighted imaging (DWI) and abbreviated MRI consisting of one pre- and one post-contrast T1-weighted imaging. STUDY TYPE: Prospective. SUBJECTS: Seventy-nine women (median age, 44 years) with 86 Breast Imaging Reporting and Data System (BI-RADS) category 4 masses as detected by breast US. FIELD STRENGTH/SEQUENCE: 3-T, T2-weighted turbo spin echo sequence, DWI, and abbreviated contrast-enhanced MRI (T1-weighted gradient echo sequence). ASSESSMENT: US-guided biopsy (reference standard) was obtained on the same day as MRI. The maximum and mean conductivity parameters from whole and single regions of interest (ROIs) were measured. Apparent diffusion coefficient (ADC) values were obtained from an area with the lowest signal within a lesion on the ADC map. The performance of conductivity, ADC, and abbreviated MRI for reducing false-positive biopsies was evaluated using the following criteria: lowest conductivity and highest ADC values among malignant breast lesions and BI-RADS categories 2 or 3 on abbreviated MRI. STATISTICAL TESTS: One conductivity parameter with the maximum area under the curve (AUC) from receiver operating characteristics was selected. A P-value <0.05 was considered statistically significant. RESULTS: US-guided biopsy revealed 65 benign lesions and 21 malignant lesions. The mean conductivity parameter of the single ROI method was selected (AUC = 0.74). Considering conductivity (≤0.10 S/m), ADC (≥1.60 × 10-3 mm2 /sec), and BI-RADS categories 2 or 3 reduced false-positive biopsies by 23% (15 of 65), 38% (25 of 65), and 43% (28 of 65), respectively, without missing malignant lesions. DATA CONCLUSION: Conductivity imaging may show lower performance than DWI and abbreviated MRI in reducing unnecessary biopsies. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

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.

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.

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.

Study on the association of ultrasonographic thickness and electromyographic activity of masseter muscle in young females with different vertical craniofacial morphology.

PURPOSE: To study the relationship between ultrasonographic thickness and EMG activity of the masseter muscle in subjects with different vertical craniofacial morphology. METHODS: Thirty female students were separated into two groups (14 cases with high-angle, 16 cases with low-angle) based on SN-MP angle, FH-MP angle, and FHI. The thickness of the masseter muscle under relaxed conditions and during maximal clenching was assessed by ultrasonography. EMG activity of the masseter muscle under relaxed conditions and during maximal clenching was recorded with bipolar surface electrodes.All measurements were analyzed with SPSS 11.0 software package. Differences between groups were tested for statistical significance using Student's t test. The relationship between masseter muscle thickness and its EMG activity was estimated by Pearson's correlation coefficient. RESULTS: The thickness of the masseter muscle in the low-angle individuals was significantly greater than that in the high-angle individuals under relaxed conditions (P=0.009) and during maximal clenching (P=0.000). Although there was no significant difference in resting EMG activity between the two groups, the EMG activity of masseter muscle in the low-angle individuals was also significantly higher than that in the high-angle individuals during maximal clenching(P=0.022). Relaxed thickness of masseter muscle was significantly correlated with its mean maximum EMG activity in the low-angle group (r=0.61, P=0.003) and moderately correlated with that in the high-angle group (r=0.38, P=0.023). Similar correlation was found between contracted thickness of masseter muscle and the mean maximum EMG activity, being significantly correlated in the low-angle group (r=0.73, P=0.002) and moderately correlated in the high-angle group(r=0.53, P=0.006). CONCLUSIONS: The present findings support the concept that subjects with different vertical craniofacial morphology have different form and function of masseter muscle. The ultrasonographic thickness and EMG activity of masseter muscle in the low-angle individuals are both greater than those in the high-angle individuals.