Synthesized 7T MPRAGE From 3T MPRAGE Using Generative Adversarial Network and Validation in Clinical Brain Imaging: A Feasibility Study.

BACKGROUND: Ultra-high field 7T MRI can provide excellent tissue contrast and anatomical details, but is often cost prohibitive, and is not widely accessible in clinical practice. PURPOSE: To generate synthetic 7T images from widely acquired 3T images with deep learning and to evaluate the feasibility of this approach for brain imaging. STUDY TYPE: Prospective. POPULATION: 33 healthy volunteers and 89 patients with brain diseases, divided into training, and evaluation datasets in the ratio 4:1. SEQUENCE AND FIELD STRENGTH: T1-weighted nonenhanced or contrast-enhanced magnetization-prepared rapid acquisition gradient-echo sequence at both 3T and 7T. ASSESSMENT: A generative adversarial network (SynGAN) was developed to produce synthetic 7T images from 3T images as input. SynGAN training and evaluation were performed separately for nonenhanced and contrast-enhanced paired acquisitions. Qualitative image quality of acquired 3T and 7T images and of synthesized 7T images was evaluated by three radiologists in terms of overall image quality, artifacts, sharpness, contrast, and visualization of vessel using 5-point Likert scales. STATISTICAL TESTS: Wilcoxon signed rank tests to compare synthetic 7T images with acquired 7T and 3T images and intraclass correlation coefficients to evaluate interobserver variability. P < 0.05 was considered significant. RESULTS: Of the 122 paired 3T and 7T MRI scans, 66 were acquired without contrast agent and 56 with contrast agent. The average time to generate synthetic images was ~11.4 msec per slice (2.95 sec per participant). The synthetic 7T images achieved significantly improved tissue contrast and sharpness in comparison to 3T images in both nonenhanced and contrast-enhanced subgroups. Meanwhile, there was no significant difference between acquired 7T and synthetic 7T images in terms of all the evaluation criteria for both nonenhanced and contrast-enhanced subgroups (P ≥ 0.180). DATA CONCLUSION: The deep learning model has potential to generate synthetic 7T images with similar image quality to acquired 7T images. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 1.

Clinically Informed Automated Assessment of Finger Tapping Videos in Parkinson's Disease.

The utilization of Artificial Intelligence (AI) for assessing motor performance in Parkinson's Disease (PD) offers substantial potential, particularly if the results can be integrated into clinical decision-making processes. However, the precise quantification of PD symptoms remains a persistent challenge. The current standard Unified Parkinson's Disease Rating Scale (UPDRS) and its variations serve as the primary clinical tools for evaluating motor symptoms in PD, but are time-intensive and prone to inter-rater variability. Recent work has applied data-driven machine learning techniques to analyze videos of PD patients performing motor tasks, such as finger tapping, a UPDRS task to assess bradykinesia. However, these methods often use abstract features that are not closely related to clinical experience. In this paper, we introduce a customized machine learning approach for the automated scoring of UPDRS bradykinesia using single-view RGB videos of finger tapping, based on the extraction of detailed features that rigorously conform to the established UPDRS guidelines. We applied the method to 75 videos from 50 PD patients collected in both a laboratory and a realistic clinic environment. The classification performance agreed well with expert assessors, and the features selected by the Decision Tree aligned with clinical knowledge. Our proposed framework was designed to remain relevant amid ongoing patient recruitment and technological progress. The proposed approach incorporates features that closely resonate with clinical reasoning and shows promise for clinical implementation in the foreseeable future.

PA-Tran: Learning to Estimate 3D Hand Pose with Partial Annotation.

This paper tackles a novel and challenging problem-3D hand pose estimation (HPE) from a single RGB image using partial annotation. Most HPE methods ignore the fact that the keypoints could be partially visible (e.g., under occlusions). In contrast, we propose a deep-learning framework, PA-Tran, that jointly estimates the keypoints status and 3D hand pose from a single RGB image with two dependent branches. The regression branch consists of a Transformer encoder which is trained to predict a set of target keypoints, given an input set of status, position, and visual features embedding from a convolutional neural network (CNN); the classification branch adopts a CNN for estimating the keypoints status. One key idea of PA-Tran is a selective mask training (SMT) objective that uses a binary encoding scheme to represent the status of the keypoints as observed or unobserved during training. In addition, by explicitly encoding the label status (observed/unobserved), the proposed PA-Tran can efficiently handle the condition when only partial annotation is available. Investigating the annotation percentage ranging from 50-100%, we show that training with partial annotation is more efficient (e.g., achieving the best 6.0 PA-MPJPE when using about 85% annotations). Moreover, we provide two new datasets. APDM-Hand, is for synthetic hands with APDM sensor accessories, which is designed for a specific hand task. PD-APDM-Hand, is a real hand dataset collected from Parkinson's Disease (PD) patients with partial annotation. The proposed PA-Tran can achieve higher estimation accuracy when evaluated on both proposed datasets and a more general hand dataset.

Does Extended PET Acquisition in PET/MRI Rectal Cancer Staging Improve Results?

OBJECTIVE: The purpose of this study was to determine if extended PET acquisition times in the pelvis during PET/MRI increase detection rates of potentially metastatic lymph nodes in patients with rectal cancer. MATERIALS AND METHODS: Our study was approved by the institutional review board of the University of California, San Francisco. Twenty-two patients with biopsy-proven rectal cancer underwent imaging via simultaneous 3-T time-of-flight PET/MRI, with seven undergoing two separate PET/MRI examinations, for a total of 29 studies. Each examination included both a whole-body PET/MRI and a dedicated pelvic PET/MRI with both 3- and 15-minute PET acquisitions for the pelvis. Three radiologists interpreted each examination with PET only, MRI only, then combined PET and MRI examinations, using all available images. Additionally, the 3- and 15-minute PET acquisitions of the pelvis were reviewed separately by a single radiologist. RESULTS: A total of 94 lymph nodes were identified as abnormal on PET, all with MRI anatomic correlates. Of these, 37 (39.4%) were seen only on the dedicated 15-minute acquisition. Fifty-seven (60.6%) nodes measured 5 mm or less, including 29 (30.9%) seen only on the 15-minute acquisition. Thirty-one (33.0%) nodes measured 5.1-10 mm, including eight (25.8%) seen only on the 15-minute acquisition. Of the 17 subjects imaged for initial staging, 11 (64.7%) were upstaged as a result of the increased PET acquisition time (10 from N1 to N2 and one from N0 to N1). CONCLUSION: Longer PET acquisition times during PET/MRI for rectal cancer increases the number of FDG-avid lymph nodes detected without increasing scan time.

Predicting fruit fly's sensing rate with insect flight simulations.

Without sensory feedback, flies cannot fly. Exactly how various feedback controls work in insects is a complex puzzle to solve. What do insects measure to stabilize their flight? How often and how fast must insects adjust their wings to remain stable? To gain insights into algorithms used by insects to control their dynamic instability, we develop a simulation tool to study free flight. To stabilize flight, we construct a control algorithm that modulates wing motion based on discrete measurements of the body-pitch orientation. Our simulations give theoretical bounds on both the sensing rate and the delay time between sensing and actuation. Interpreting our findings together with experimental results on fruit flies' reaction time and sensory motor reflexes, we conjecture that fruit flies sense their kinematic states every wing beat to stabilize their flight. We further propose a candidate for such a control involving the fly's haltere and first basalar motor neuron. Although we focus on fruit flies as a case study, the framework for our simulation and discrete control algorithms is applicable to studies of both natural and man-made fliers.

Novel Tactile Sensor Technology and Smart Tactile Sensing Systems: A Review.

During the last decades, smart tactile sensing systems based on different sensing techniques have been developed due to their high potential in industry and biomedical engineering. However, smart tactile sensing technologies and systems are still in their infancy, as many technological and system issues remain unresolved and require strong interdisciplinary efforts to address them. This paper provides an overview of smart tactile sensing systems, with a focus on signal processing technologies used to interpret the measured information from tactile sensors and/or sensors for other sensory modalities. The tactile sensing transduction and principles, fabrication and structures are also discussed with their merits and demerits. Finally, the challenges that tactile sensing technology needs to overcome are highlighted.

Novel Flexible Wearable Sensor Materials and Signal Processing for Vital Sign and Human Activity Monitoring.

Advances in flexible electronic materials and smart textile, along with broad availability of smart phones, cloud and wireless systems have empowered the wearable technologies for significant impact on future of digital and personalized healthcare as well as consumer electronics. However, challenges related to lack of accuracy, reliability, high power consumption, rigid or bulky form factor and difficulty in interpretation of data have limited their wide-scale application in these potential areas. As an important solution to these challenges, we present latest advances in novel flexible electronic materials and sensors that enable comfortable and conformable body interaction and potential for invisible integration within daily apparel. Advances in novel flexible materials and sensors are described for wearable monitoring of human vital signs including, body temperature, respiratory rate and heart rate, muscle movements and activity. We then present advances in signal processing focusing on motion and noise artifact removal, data mining and aspects of sensor fusion relevant to future clinical applications of wearable technology.

A delayed functional observer/predictor with bounded-error for depth of hypnosis monitoring.

With the motivation of providing safety for a patient under anesthesia, this paper suggests conditions for evaluating the correctness of an available user interface for systems under shared control based on observability and predictability requirements. Situation awareness is necessary for the user to make correct decisions about the inputs. In this article, we develop a technique to investigate the conditions under which an anesthetists can attain situation awareness about a limited but important aspect of anesthesia, namely depth of hypnosis (DOH). Furthermore, we consider that, in practice, to attain situation awareness, the estimation of the task states does not necessarily need to be precise but can be bounded within certain margins. Hence, attaining situation awareness about DOH is modeled as a bounded-error delayed functional observation/prediction. Unless such an observer/predictor exists for a system with a given user-interface, the safety of the operation may be compromised. The suggested technique proves that, in order to provide safety for the patient under anesthesia, it is necessary for the anesthetist to have access to the predictive information from a clinical decision support system.

Identification of Mechanism-Based Inactivation in P450-Catalyzed Cyclopropanation Facilitates Engineering of Improved Enzymes.

Following the recent discovery that heme proteins can catalyze the cyclopropanation of styrenyl olefins with high efficiency and selectivity, interest in developing new enzymes for a variety of non-natural carbene transfer reactions has burgeoned. The fact that diazo compounds and other carbene precursors are known mechanism-based inhibitors of P450s, however, led us to investigate if they also interfere with this new enzyme function. We present evidence for two inactivation pathways that are operative during cytochrome P450-catalyzed cyclopropanation. Using a combination of UV-vis, mass spectrometry, and proteomic analyses, we show that the heme cofactor and several nucleophilic side chains undergo covalent modification by ethyl diazoacetate (EDA). Substitution of two of the affected residues with less-nucleophilic amino acids led to a more than twofold improvement in cyclopropanation performance (total TTN). Elucidating the inactivation pathways of heme protein-based carbene transfer catalysts should aid in the optimization of this new biocatalytic function.

Appearance and Frequency of Gas Interface Artifacts Involving Small Bowel on Rapid-Voltage-Switching Dual-Energy CT Iodine-Density Images.

OBJECTIVE: The purpose of this study is to describe the appearance and frequency of gas interface artifacts in the jejunum that may mimic severe bowel disease on iodine-density images generated from rapid-voltage-switching dual-energy CT (DECT) scans. MATERIALS AND METHODS: Two readers retrospectively reviewed 108 consecutive abdominal rapid-voltage-switching DECT scans to record the presence of image artifacts in jejunal segments with different degrees of gaseous luminal filling, classified as full, partial, or absent. Readers viewed iodine-density images and corresponding 140-kVp and 65-keV virtual monochromatic images and classified the jejunal artifacts on iodine-density images as pseudostratified appearance of the bowel wall, pseudopneumatosis, pseudohyperenhancement, or pseudohypoenhancement. We correlated the presence of the artifacts with clinical features suggesting bowel disease. RESULTS: Image artifacts were found in 91 of 108 scans (84.3%), appeared in 148 of 265 jejunal segments (55.8%), and included each type except for pseudohypoenhancement. Artifacts occurred exclusively when gas was present in the bowel lumen and were seen in 59 of 59 (100%) fully gas-distended segments, 89 of 98 (90.8%) partially gas-distended segments, and none of 108 gas-absent segments (p < 0.0001). In fully and partially gas-distended jejunal segments (n = 157), 148 (94.3%) segments had two or more artifacts. None of the patients was found to have clinical bowel-related injury on follow-up of medical records. CONCLUSION: Pseudostratified appearance, pseudopneumatosis, and pseudohyperenhancement, but not pseudohypoenhancement, artifacts are common in gas-filled jejunal segments on iodine-density images generated from rapid-voltage-switching DECT scans and are not seen in the corresponding 140-kVp or 65-keV images. Knowledge of the appearance of such iodine-density image artifacts will avoid potential examination interpretation pitfalls.

CT Findings for Detecting the Presence of Gangrenous Ischemia in Cholecystitis.

OBJECTIVE: The objective of our study was to evaluate the diagnostic accuracy of CT in differentiating gangrenous cholecystitis from uncomplicated cholecystitis and healthy gallbladders. MATERIALS AND METHODS: We performed a retrospective review of 308 patients with histologically proven gangrenous cholecystitis who underwent preoperative CT 1 month before gallbladder removal over a 4-year period. Two readers who were blinded to the histologic diagnosis independently recorded CT features of and overall likelihood of gangrenous cholecystitis on a 5-point scale (1, definitely absent; 5, definitely present). Ratings were dichotomized such that a diagnosis was considered present at a rating of 4 or 5 and considered absent at lower ratings. Interobserver variability for individual CT findings was also assessed. RESULTS: Patients had gangrenous cholecystitis (n = 28), acute cholecystitis (n = 98), chronic cholecystitis (n = 118), or healthy gallbladders (n = 64). Multivariate analysis showed that CT findings of gallbladder distention greater than 4.0 cm (odds ratio [OR], 9.63; p < 0.01), mural striation (OR, 11.39; p < 0.01), and decreased mural enhancement (OR, 3.55; p < 0.05) independently predicted gangrenous cholecystitis. Using these CT features, the diagnosis of gangrenous cholecystitis was made with a specificity of 93.9% and 89.6% for readers 1 and 2, respectively, and accuracy of 90.9% and 87.0%, respectively. Good agreement was seen between the two readers with respect to gallbladder distention greater than 4.0 cm (κ = 0.77) and decreased mural enhancement (κ = 0.64). CONCLUSION: A markedly distended gallbladder associated with decreased wall enhancement is highly specific for gangrenous cholecystitis.

A serine-substituted P450 catalyzes highly efficient carbene transfer to olefins in vivo.

Whole-cell catalysts for non-natural chemical reactions will open new routes to sustainable production of chemicals. We designed a cytochrome 'P411' with unique serine-heme ligation that catalyzes efficient and selective olefin cyclopropanation in intact Escherichia coli cells. The mutation C400S in cytochrome P450(BM3) gives a signature ferrous CO Soret peak at 411 nm, abolishes monooxygenation activity, raises the resting-state Fe(III)-to-Fe(II) reduction potential and substantially improves NAD(P)H-driven activity.

Transient respiratory motion artifact during arterial phase MRI with gadoxetate disodium: risk factor analyses.

OBJECTIVE: The purpose of this article is to identify risk factors for arterial phase respiratory motion artifact in gadoxetate disodium-enhanced liver MRI. MATERIALS AND METHODS: We retrospectively identified 220 consecutive patients who underwent 357 MRI examinations, including 68 patients who underwent multiple MRI examinations, with gadoxetate disodium between 2010 and 2013. The arterial phase timing was determined by a fluoroscopic-triggering method. T1-weighted unenhanced and contrast-enhanced images were reviewed to record respiratory motion artifact, which was graded on a 5-point scale. Arterial phase transient severe motion was considered to be present if the motion score was 4 or greater on the arterial phase images and if the motion scores were 2 or less on unenhanced and other contrast-enhanced images. Patient characteristics and risk factors (e.g., age, sex, weight, body mass index, medical and radiologic history, allergy to MRI and iodinated contrast agents, estimated glomerular filtration rate, Child-Pugh class, and findings on current MRI examinations) were recorded. We included a history of transient severe motion on prior MRI as a predictor variable. We performed univariable and multivariable analysis using the generalized estimated equations to adjust for clustering. RESULTS: The incidence of transient severe motion was 12.9% (46/357). On univariable analysis, a history of transient severe motion (odds ratio [OR] = 3.31; p = 0.04) on prior MRI and allergy to iodinated contrast agent (OR = 3.03; p = 0.01) statistically significantly increased the incidence of transient severe motion for a given MRI examination. These associations were not seen on multivariable analysis (adjusted OR = 2.38 and p = 0.23 for a history of transient severe motion; adjusted OR = 1.93 and p = 0.23 for allergy to CT contrast agent). CONCLUSION: The occurrence of transient severe motion during arterial phase MRI with gadoxetate disodium is 12.9% and is poorly predicted on the basis of risk factors.

Low yield of chemical shift MRI for characterization of adrenal lesions with high attenuation density on unenhanced CT.

PURPOSE: To investigate the threshold unenhanced CT density of adrenal nodules at which further evaluation with chemical shift MRI is unlikely to be definitive and therefore not helpful in further characterizing some indeterminate adrenal lesions. METHODS: Retrospective evaluation of 44 adrenal lesions imaged with unenhanced CT and chemical shift MRI and followed for at least 1 year. Qualitative and quantitative assessment of signal loss on chemical shift MRI was performed. Adenomas were diagnosed if the lesion measured equal or less than 10 HU on unenhanced CT; on MRI a SI index greater than 16.5% or adrenal:spleen chemical shift ratio less than 0.71 was considered diagnostic of adenoma. RESULTS: 31.8% (14/44), 47.7% (21/44), and 20.5% (9/44) of the adrenal lesions had an unenhanced CT attenuation density ≤10, 10-30, and >30 HU. Adrenal lesions with an unenhanced CT density 10-30 and >30 HU had a 76.2% (16/21) and a 33.3% (3/9) chance of being categorized as an adenoma using MRI SI index, respectively. CONCLUSIONS: Adrenal lesions with unenhanced attenuation CT density >30 HU had a 66.6% of remaining indeterminate even after evaluation with chemical shift MRI. ADVANCES IN KNOWLEDGE: Chemical shift MRI is reasonable for evaluating adrenal lesions with an unenhanced CT attenuation density less than 30 HU. The likelihood of chemical shift MRI detecting signal loss in lesions CT density greater than 30 HU, however, is low.

Expanding the enzyme universe: accessing non-natural reactions by mechanism-guided directed evolution.

High selectivity and exquisite control over the outcome of reactions entice chemists to use biocatalysts in organic synthesis. However, many useful reactions are not accessible because they are not in nature's known repertoire. In this Review, we outline an evolutionary approach to engineering enzymes to catalyze reactions not found in nature. We begin with examples of how nature has discovered new catalytic functions and how such evolutionary progression has been recapitulated in the laboratory starting from extant enzymes. We then examine non-native enzyme activities that have been exploited for chemical synthesis, with an emphasis on reactions that do not have natural counterparts. Non-natural activities can be improved by directed evolution, thus mimicking the process used by nature to create new catalysts. Finally, we describe the discovery of non-native catalytic functions that may provide future opportunities for the expansion of the enzyme universe.

Enantioselective imidation of sulfides via enzyme-catalyzed intermolecular nitrogen-atom transfer.

Engineering enzymes with novel reaction modes promises to expand the applications of biocatalysis in chemical synthesis and will enhance our understanding of how enzymes acquire new functions. The insertion of nitrogen-containing functional groups into unactivated C-H bonds is not catalyzed by known enzymes but was recently demonstrated using engineered variants of cytochrome P450BM3 (CYP102A1) from Bacillus megaterium. Here, we extend this novel P450-catalyzed reaction to include intermolecular insertion of nitrogen into thioethers to form sulfimides. An examination of the reactivity of different P450BM3 variants toward a range of substrates demonstrates that electronic properties of the substrates are important in this novel enzyme-catalyzed reaction. Moreover, amino acid substitutions have a large effect on the rate and stereoselectivity of sulfimidation, demonstrating that the protein plays a key role in determining reactivity and selectivity. These results provide a stepping stone for engineering more complex nitrogen-atom-transfer reactions in P450 enzymes and developing a more comprehensive biocatalytic repertoire.

Classification of EEG signals using a multiple kernel learning support vector machine.

In this study, a multiple kernel learning support vector machine algorithm is proposed for the identification of EEG signals including mental and cognitive tasks, which is a key component in EEG-based brain computer interface (BCI) systems. The presented BCI approach included three stages: (1) a pre-processing step was performed to improve the general signal quality of the EEG; (2) the features were chosen, including wavelet packet entropy and Granger causality, respectively; (3) a multiple kernel learning support vector machine (MKL-SVM) based on a gradient descent optimization algorithm was investigated to classify EEG signals, in which the kernel was defined as a linear combination of polynomial kernels and radial basis function kernels. Experimental results showed that the proposed method provided better classification performance compared with the SVM based on a single kernel. For mental tasks, the average accuracies for 2-class, 3-class, 4-class, and 5-class classifications were 99.20%, 81.25%, 76.76%, and 75.25% respectively. Comparing stroke patients with healthy controls using the proposed algorithm, we achieved the average classification accuracies of 89.24% and 80.33% for 0-back and 1-back tasks respectively. Our results indicate that the proposed approach is promising for implementing human-computer interaction (HCI), especially for mental task classification and identifying suitable brain impairment candidates.

Improved cyclopropanation activity of histidine-ligated cytochrome†P450 enables the enantioselective formal synthesis of levomilnacipran.

Engineering enzymes capable of modes of activation unprecedented in nature will increase the range of industrially important molecules that can be synthesized through biocatalysis. However, low activity for a new function is often a limitation in adopting enzymes for preparative-scale synthesis, reaction with demanding substrates, or when a natural substrate is also present. By mutating the proximal ligand and other key active-site residues of the cytochrome P450 enzyme from Bacillus megaterium (P450-BM3), a highly active His-ligated variant of P450-BM3 that can be employed for the enantioselective synthesis of the levomilnacipran core was engineered. This enzyme, BM3-Hstar, catalyzes the cyclopropanation of N,N-diethyl-2-phenylacrylamide with an estimated initial rate of over 1000 turnovers per minute and can be used under aerobic conditions. Cyclopropanation activity is highly dependent on the electronic properties of the P450 proximal ligand, which can be used to tune this non-natural enzyme activity.

Self-supervised anatomical continuity enhancement network for 7T SWI synthesis from 3T SWI.

Synthesizing 7T Susceptibility Weighted Imaging (SWI) from 3T SWI could offer significant clinical benefits by combining the high sensitivity of 7T SWI for neurological disorders with the widespread availability of 3T SWI in diagnostic routines. Although methods exist for synthesizing 7T Magnetic Resonance Imaging (MRI), they primarily focus on traditional MRI modalities like T1-weighted imaging, rather than SWI. SWI poses unique challenges, including limited data availability and the invisibility of certain tissues in individual 3T SWI slices. To address these challenges, we propose a Self-supervised Anatomical Continuity Enhancement (SACE) network to synthesize 7T SWI from 3T SWI using plentiful 3T SWI data and limited 3T-7T paired data. The SACE employs two specifically designed pretext tasks to utilize low-level representations from abundant 3T SWI data for assisting 7T SWI synthesis in a downstream task with limited paired data. One pretext task emphasizes input-specific morphology by balancing the elimination of redundant patterns with the preservation of essential morphology, preventing the blurring of synthetic 7T SWI images. The other task improves the synthesis of tissues that are invisible in a single 3T SWI slice by aligning adjacent slices with the current slice and predicting their difference fields. The downstream task innovatively combines clinical knowledge with brain substructure diagrams to selectively enhance clinically relevant features. When evaluated on a dataset comprising 97 cases (5495 slices), the proposed method achieved a Peak Signal-to-Noise Ratio (PSNR) of 23.05 dB and a Structural Similarity Index (SSIM) of 0.688. Due to the absence of specific methods for 7T SWI, our method was compared with existing enhancement techniques for general 7T MRI synthesis, outperforming these techniques in the context of 7T SWI synthesis. Clinical evaluations have shown that our synthetic 7T SWI is clinically effective, demonstrating its potential as a clinical tool.