Unsupervised deep learning model for correcting Nyquist ghosts of single-shot spatiotemporal encoding.

PURPOSE: To design an unsupervised deep learning (DL) model for correcting Nyquist ghosts of single-shot spatiotemporal encoding (SPEN) and evaluate the model for real MRI applications. METHODS: The proposed method consists of three main components: (1) an unsupervised network that combines Residual Encoder and Restricted Subspace Mapping (RERSM-net) and is trained to generate a phase-difference map based on the even and odd SPEN images; (2) a spin physical forward model to obtain the corrected image with the learned phase difference map; and (3) cycle-consistency loss that is explored for training the RERSM-net. RESULTS: The proposed RERSM-net could effectively generate smooth phase difference maps and correct Nyquist ghosts of single-shot SPEN. Both simulation and real in vivo MRI experiments demonstrated that our method outperforms the state-of-the-art SPEN Nyquist ghost correction method. Furthermore, the ablation experiments of generating phase-difference maps show the advantages of the proposed unsupervised model. CONCLUSION: The proposed method can effectively correct Nyquist ghosts for the single-shot SPEN sequence.

Unsupervised cycle-consistent network using restricted subspace field map for removing susceptibility artifacts in EPI.

PURPOSE: To design an unsupervised deep neural model for correcting susceptibility artifacts in single-shot Echo Planar Imaging (EPI) and evaluate the model for preclinical and clinical applications. METHODS: This work proposes an unsupervised cycle-consistent model based on the restricted subspace field map to take advantage of both the deep learning (DL) and the reverse polarity-gradient (RPG) method for single-shot EPI. The proposed model consists of three main components: (1) DLRPG neural network (DLRPG-net) to obtain field maps based on a pair of images acquired with reversed phase encoding; (2) spin physical model-based modules to obtain the corrected undistorted images based on the learned field map; and (3) cycle-consistency loss between the input images and back-calculated images from each cycle is explored for network training. In addition, the field maps generated by DLRPG-net belong to a restricted subspace, which is a span of predefined cubic splines to ensure the smoothness of the field maps and avoid blurring in the corrected images. This new method is trained and validated on both preclinical and clinical datasets for diffusion MRI. RESULTS: The proposed network could effectively generate smooth field maps and correct susceptibility artifacts in single-shot EPI. Simulated and in vivo preclinical/clinical experiments demonstrated that our method outperforms the state-of-the-art susceptibility artifact correction methods. Furthermore, the ablation experiments of the cycle-consistent network and the restricted subspace in generating field maps did show the advantages of DLRPG-net. CONCLUSION: The proposed method (DLRPG-net) can effectively correct susceptibility artifacts for preclinical and clinical single-shot EPI sequences.

Risk, Prognostic Factors and Nomograms for Bone Metastasis in Young Females with Breast Cancer: A Large Cohort Retrospective Study.

Purpose: To determine the incidence of bone metastasis (BM) in young female patients with breast cancer (BC) and develop 2 robust nomograms for BM in young female patients with BC. Methods: We searched and downloaded the data from young (age ≤40 years) female patients with bone cancer from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2015. Univariate and multivariate analyses were performed to screen the potential diagnostic variables and prognostic factors for BM. The diagnostic and prognostic nomograms were generated and evaluated by the area under the receiver operating characteristic (ROC) curve (AUC), calibration curves, and decision curve analysis (DCA). Results: A total of 13 347 young female patients with BC were identified; of these, 462 were initially diagnosed as having BM. The independent risk factors for BM in young female patients with BC were tumor size, BC subtype, American Joint Committee on Cancer (AJCC) T stage, AJCC N stage, age and marital status. The independent prognostic factors in these patients were tumor size, subtype, surgery performed, lung metastasis, liver metastasis and brain metastasis. The AUC values of the diagnostic nomogram were 0.803 (95% CI; 0.795-0.811) and 0.813 (95% CI; 0.800-0.825) in the training and validation cohorts, respectively. The time-dependent AUC values of prognostic nomogram were 0.850, 0.853, and 0.824 at 2, 3 and 4 years in the training cohort, and also >0.700 in the validation cohort. For both nomograms, the discrimination was higher than all independent variables. Calibration curve and decision curve analysis (DCA) indicated that both nomograms had favorable calibration and clinical utilization. Finally, a risk stratification system was generated and the 3 risk subgroups showed significantly distinct prognoses. Conclusions: A total of 2 nomograms were developed to assess the risk for and in prognosis of young female patients with BC with BM (BCBM).

Retrospective motion correction for preclinical/clinical magnetic resonance imaging based on a conditional generative adversarial network with entropy loss.

Multishot scan magnetic resonance imaging (MRI) acquisition is inherently sensitive to motion, and motion artifact reduction is essential for improving the image quality in MRI. This work proposes and validates a new end-to-end motion-correction method for the multishot sequence that incorporates a conditional generative adversarial network with minimum entropy (cGANME) of MR images. The cGANME contains an encoder-decoder generator to obtain motion-corrected images and a PatchGAN discriminator to classify the image as either real (motion-free) or fake (motion-corrected). The entropy of the images is set as one loss item in the cGAN's loss as the entropy increases monotonically with the motion artifacts. An ablation experiment of the different weights of entropy loss was performed to evaluate the function of entropy loss. The preclinical dataset was acquired with a fast spin echo pulse sequence on a 7.0-T scanner. After the simulation, we had 10,080/2880/1440 slices for training, testing, and validating, respectively. The clinical dataset was downloaded from the Human Connection Project website, and 11,300/3500/2000 slices were used for training, testing, and validating after simulation, respectively. Extensive experiments for different motion patterns, motion levels, and protocol parameters demonstrate that cGANME outperforms traditional and some state-of-the-art, deep learning-based methods. In addition, we tested cGANME on in vivo awake rats and mitigated the motion artifacts, indicating that the model has some generalizability.

Frequency Modulation Approach for High Power Density 100 Hz Piezoelectric Vibration Energy Harvester.

Piezoelectric vibration energy harvester (PVEH) is a promising device for sustainable power supply of wireless sensor nodes (WSNs). PVEH is resonant and generates power under constant frequency vibration excitation of mechanical equipment. However, it cannot output high power through off-resonance if it has frequency offset in manufacturing, assembly and use. To address this issue, this paper designs and optimizes a PVEH to harvest power specifically from grid transformer vibration at 100 Hz with high power density of 5.28 µWmm-3g-2. Some resonant frequency modulation methods of PVEH are discussed by theoretical analysis and experiment, such as load impedance, additional mass, glue filling, axial and transverse magnetic force frequency modulation. Finally, efficient energy harvesting of 6.1 V output in 0.0226 g acceleration is tested in grid transformer reactor field application. This research has practical value for the design and optimization process of tunable PVEH for a specific vibration source.

Robust water-fat separation based on deep learning model exploring multi-echo nature of mGRE.

PURPOSE: To design a new deep learning network for fast and accurate water-fat separation by exploring the correlations between multiple echoes in multi-echo gradient-recalled echo (mGRE) sequence and evaluate the generalization capabilities of the network for different echo times, field inhomogeneities, and imaging regions. METHODS: A new multi-echo bidirectional convolutional residual network (MEBCRN) was designed to separate water and fat images in a fast and accurate manner for the mGRE data. This new MEBCRN network contains 2 main modules, the first 1 is the feature extraction module, which learns the correlations between consecutive echoes, and the other one is the water-fat separation module that processes the feature information extracted from the feature extraction module. The multi-layer feature fusion (MLFF) mechanism and residual structure were adopted in the water-fat separation module to increase separation accuracy and robustness. Moreover, we trained the network using in vivo abdomen images and tested it on the abdomen, knee, and wrist images. RESULTS: The results showed that the proposed network could separate water and fat images accurately. The comparison of the proposed network and other deep learning methods shows the advantage in both quantitative metrics and robustness for different TEs, field inhomogeneities, and images acquired for various imaging regions. CONCLUSION: The proposed network could learn the correlations between consecutive echoes and separate water and fat images effectively. The deep learning method has certain generalization capabilities for TEs and field inhomogeneity. Although the network was trained only in vivo abdomen images, it could be applied for different imaging regions.

Risk factors, prognostic factors, and nomograms for bone metastasis in patients with newly diagnosed infiltrating duct carcinoma of the breast: a population-based study.

BACKGROUND: Breast cancer is the most common malignancy in women, and it is also the leading cause of death in female patients; the most common pathological type of BC is infiltrating duct carcinoma (IDC). Some nomograms have been developed to predict bone metastasis (BM) in patients with breast cancer. However, there are no studies on diagnostic and prognostic nomograms for BM in newly diagnosed IDC patients. METHODS: IDC patients with newly diagnosed BM from 2010 to 2016 in the Surveillance, Epidemiology and End Results (SEER) database were reviewed. Multivariate logistic regression analysis was used to identify risk factors for BM in patients with IDC. Univariate and multivariate Cox proportional hazards regression analysis were used to explore the prognostic factors of BM in patients with IDC. We then constructed nomograms to predict the risk and prognosis of BM for patients with IDC. The results were validated using bootstrap resampling and retrospective research on 113 IDC patients with BM from 2015 to 2018 at the Affiliated Hospital of Chengde Medical University. RESULTS: This study included 141,959 patients diagnosed with IDC in the SEER database, of whom 2383 cases were IDC patients with BM. The risk factors for BM in patients with IDC included sex, primary site, grade, T stage, N stage, liver metastasis, race, brain metastasis, breast cancer subtype, lung metastasis, insurance status, and marital status. The independent prognostic factors were brain metastases, race, grade, surgery, chemotherapy, age, liver metastases, breast cancer subtype, insurance status, and marital status. Through calibration, receiver operating characteristic curve and decision curve analyses, we found that the nomogram for predicting the prognosis of IDC patients with BM displayed great performance both internally and externally. CONCLUSION: These nomograms are expected to be a precise and personalized tool for predicting the risk and prognosis for BM in patients with IDC. This will help clinicians develop more rational and effective treatment strategies.

Mutually communicated model based on multi-parametric MRI for automated segmentation and classification of prostate cancer.

BACKGROUND: Multiparametric magnetic resonance imaging (mp-MRI) is introduced and established as a noninvasive alternative for prostate cancer (PCa) detection and characterization. PURPOSE: To develop and evaluate a mutually communicated deep learning segmentation and classification network (MC-DSCN) based on mp-MRI for prostate segmentation and PCa diagnosis. METHODS: The proposed MC-DSCN can transfer mutual information between segmentation and classification components and facilitate each other in a bootstrapping way. For classification task, the MC-DSCN can transfer the masks produced by the coarse segmentation component to the classification component to exclude irrelevant regions and facilitate classification. For segmentation task, this model can transfer the high-quality localization information learned by the classification component to the fine segmentation component to mitigate the impact of inaccurate localization on segmentation results. Consecutive MRI exams of patients were retrospectively collected from two medical centers (referred to as center A and B). Two experienced radiologists segmented the prostate regions, and the ground truth of the classification refers to the prostate biopsy results. MC-DSCN was designed, trained, and validated using different combinations of distinct MRI sequences as input (e.g., T2-weighted and apparent diffusion coefficient) and the effect of different architectures on the network's performance was tested and discussed. Data from center A were used for training, validation, and internal testing, while another center's data were used for external testing. The statistical analysis is performed to evaluate the performance of the MC-DSCN. The DeLong test and paired t-test were used to assess the performance of classification and segmentation, respectively. RESULTS: In total, 134 patients were included. The proposed MC-DSCN outperforms the networks that were designed solely for segmentation or classification. Regarding the segmentation task, the classification localization information helped to improve the IOU in center A: from 84.5% to 87.8% (p < 0.01) and in center B: from 83.8% to 87.1% (p < 0.01), while the area under curve (AUC) of PCa classification was improved in center A: from 0.946 to 0.991 (p < 0.02) and in center B: from 0.926 to 0.955 (p < 0.01) as a result of the additional information provided by the prostate segmentation. CONCLUSION: The proposed architecture could effectively transfer mutual information between segmentation and classification components and facilitate each other in a bootstrapping way, thus outperforming the networks designed to perform only one task.

Percutaneous pedicle screw fixation combined with transforaminal endoscopic spinal canal decompression for the treatment of thoracolumbar burst fracture with severe neurologic deficit: A case report.

RATIONALE: The most common fractures of the spine are associated with the thoracolumbar junction (T10-L2). And burst fractures make up 15% of all traumatic thoracolumbar fractures, which are often accompanied by neurological deficits and require open surgeries. Common surgeries include either anterior, posterior or a combination of these approaches. Here, we report the first attempt to treat thoracolumbar burst fracture (TLBF) with severe neurologic deficits by percutaneous pedicle screw fixation (PPSF) and transforaminal endoscopic spinal canal decompression (TESCD). PATIENT CONCERNS: A 46-year-old Chinese woman suffered from severe lower back pain with grade 0 muscle strength of lower limbs, without any sensory function below the injury level, with an inability to urinate or defecate after a motor vehicle accident. Imaging studies confirmed that she had Magerl type A 3.2 L1 burst fracture. DIAGNOSES: Burst fracture at L1. INTERVENTIONS: The patient underwent PPSF at the level of T12 to L2, but her neurological function did not fully recover after the operation. One week after the injury, we performed TESCD on her. OUTCOMES: There was an immediate improvement in her neurological function in just 1 day after 2-stage operation. During the 6-month follow-up period, her neurological functions gradually recovered, and she was able to defecate and urinate. At the last follow-up visit, her spinal cord function was assessed to be at Frankel grade D. LESSONS: PPSF plus TESCD can achieve complete spinal cord decompression, promote neurological recovery, and is therefore an effective method for the treating lumbar burst fractures with severe neurologic deficits.

A new automatic baseline correction method based on iterative method.

A new automatic baseline correction method for Nuclear Magnetic Resonance (NMR) spectra is presented. It is based on an improved baseline recognition method and a new iterative baseline modeling method. The presented baseline recognition method takes advantages of three baseline recognition algorithms in order to recognize all signals in spectra. While in the iterative baseline modeling method, besides the well-recognized baseline points in signal-free regions, the 'quasi-baseline points' in the signal-crowded regions are also identified and then utilized to improve robustness by preventing the negative regions. The experimental results on both simulated data and real metabolomics spectra with over-crowded peaks show the efficiency of this automatic method.