An Automated Machine-Learning Approach for Road Pothole Detection Using Smartphone Sensor Data.

Road surface monitoring and maintenance are essential for driving comfort, transport safety and preserving infrastructure integrity. Traditional road condition monitoring is regularly conducted by specially designed instrumented vehicles, which requires time and money and is only able to cover a limited proportion of the road network. In light of the ubiquitous use of smartphones, this paper proposes an automatic pothole detection system utilizing the built-in vibration sensors and global positioning system receivers in smartphones. We collected road condition data in a city using dedicated vehicles and smartphones with a purpose-built mobile application designed for this study. A series of processing methods were applied to the collected data, and features from different frequency domains were extracted, along with various machine-learning classifiers. The results indicated that features from the time and frequency domains outperformed other features for identifying potholes. Among the classifiers tested, the Random Forest method exhibited the best classification performance for potholes, with a precision of 88.5% and recall of 75%. Finally, we validated the proposed method using datasets generated from different road types and examined its universality and robustness.

Modeling transient particle transport in transient indoor airflow by fast fluid dynamics with the Markov chain method.

It is crucial to accurately and efficiently predict transient particle transport in indoor environments to improve air distribution design and reduce health risks. For steady-state indoor airflow, fast fluid dynamics (FFD) + Markov chain model increased the calculation speed by around seven times compared to computational fluid dynamics (CFD) + Eulerian model and CFD + Lagrangian model, while achieving the same level of accuracy. However, the indoor airflow could be transient, if there were human behaviors involved like coughing or sneezing and air was supplied periodically. Therefore, this study developed an FFD + Markov chain model solver for predicting transient particle transport in transient indoor airflow. This investigation used two cases, transient particle transport in a ventilated two-zone chamber and a chamber with periodic air supplies, for validation. Case 1 had experimental data for validation and the results showed that the predicted particle concentration by FFD + Markov chain model matched well with the experimental data. Besides, it had similar accuracy as the CFD + Eulerian model. In the second case, the prediction by large eddy simulation (LES) was used for validating the FFD. The simulated particle concentrations by the Markov chain model and the Eulerian model were similar. The simulated particle concentrations by the Markov chain model and the Eulerian model were similar. The computational time of the FFD + Markov chain model was 7.8 times less than that of the CFD + Eulerian model.

Quantitative measurement of cancer metabolism using stimulated echo hyperpolarized carbon-13 MRS.

PURPOSE: Magnetic resonance spectroscopy of hyperpolarized substrates allows for the observation of label exchange catalyzed by enzymes providing a powerful tool to investigate tissue metabolism and potentially kinetics in vivo. However, the accuracy of current methods to calculate kinetic parameters has been limited by T1 relaxation effects, extracellular signal contributions, and reduced precision at lower signal-to-noise ratio. THEORY AND METHODS: To address these challenges, we investigated a new modeling technique using metabolic activity decomposition-stimulated echo acquisition mode. The metabolic activity decomposition-stimulated echo acquisition mode technique separates exchanging from nonexchanging metabolites providing twice the information as conventional techniques. RESULTS: This allowed for accurate measurements of rates of conversion and of multiple T1 values simultaneously using a single acquisition. CONCLUSION: The additional measurement of T1 values for the reaction metabolites provides further biological information about the cellular environment of the metabolites. The new technique was investigated through simulations and in vivo studies of transgenic mouse models of cancer demonstrating improved assessments of kinetic rate constants and new T1 relaxation value measurements for hyperpolarized (13) C-pyruvate, (13) C-lactate, and (13) C-alanine.

Evaluation of heterogeneous metabolic profile in an orthotopic human glioblastoma xenograft model using compressed sensing hyperpolarized 3D 13C magnetic resonance spectroscopic imaging.

High resolution compressed sensing hyperpolarized (13)C magnetic resonance spectroscopic imaging was applied in orthotopic human glioblastoma xenografts for quantitative assessment of spatial variations in (13)C metabolic profiles and comparison with histopathology. A new compressed sensing sampling design with a factor of 3.72 acceleration was implemented to enable a factor of 4 increase in spatial resolution. Compressed sensing 3D (13)C magnetic resonance spectroscopic imaging data were acquired from a phantom and 10 tumor-bearing rats following injection of hyperpolarized [1-(13)C]-pyruvate using a 3T scanner. The (13)C metabolic profiles were compared with hematoxylin and eosin staining and carbonic anhydrase 9 staining. The high-resolution compressed sensing (13)C magnetic resonance spectroscopic imaging data enabled the differentiation of distinct (13)C metabolite patterns within abnormal tissues with high specificity in similar scan times compared to the fully sampled method. The results from pathology confirmed the different characteristics of (13)C metabolic profiles between viable, non-necrotic, nonhypoxic tumor, and necrotic, hypoxic tissue.

Combined parallel and partial fourier MR reconstruction for accelerated 8-channel hyperpolarized carbon-13 in vivo magnetic resonance Spectroscopic imaging (MRSI).

PURPOSE: To implement and evaluate combined parallel magnetic resonance imaging (MRI) and partial Fourier acquisition and reconstruction for rapid hyperpolarized carbon-13 ((13) C) spectroscopic imaging. Short acquisition times mitigate hyperpolarized signal losses that occur due to T1 decay, metabolism, and radiofrequency (RF) saturation. Human applications additionally require rapid imaging to permit breath-holding and to minimize the effects of physiologic motion. MATERIALS AND METHODS: Numerical simulations were employed to validate and characterize the reconstruction. In vivo MR spectroscopic images were obtained from a rat following injection of hyperpolarized (13) C pyruvate using an 8-channel array of carbon-tuned receive elements. RESULTS: For small spectroscopic matrix sizes, combined parallel imaging and partial Fourier undersampling resulted primarily in decreased spatial resolution, with relatively less visible spatial aliasing. Parallel reconstruction qualitatively restored lost image detail, although some pixel spectra had persistent numerical error. With this technique, a 30 × 10 × 16 matrix of 4800 3D MR spectroscopy imaging voxels from a whole rat with isotropic 8 mm(3) resolution was acquired within 11 seconds. CONCLUSION: Parallel MRI and partial Fourier acquisitions can provide the shorter imaging times and wider spatial coverage that will be necessary as hyperpolarized (13) C techniques move toward human clinical applications.

Fast dynamic 3D MR spectroscopic imaging with compressed sensing and multiband excitation pulses for hyperpolarized 13C studies.

Hyperpolarized 13C MR spectroscopic imaging can detect not only the uptake of the pre-polarized molecule but also its metabolic products in vivo, thus providing a powerful new method to study cellular metabolism. Imaging the dynamic perfusion and conversion of these metabolites provides additional tissue information but requires methods for efficient hyperpolarization usage and rapid acquisitions. In this work, we have developed a time-resolved 3D MR spectroscopic imaging method for acquiring hyperpolarized 13C data by combining compressed sensing methods for acceleration and multiband excitation pulses to efficiently use the magnetization. This method achieved a 2 sec temporal resolution with full volumetric coverage of a mouse, and metabolites were observed for up to 60 sec following injection of hyperpolarized [1-(13)C]-pyruvate. The compressed sensing acquisition used random phase encode gradient blips to create a novel random undersampling pattern tailored to dynamic MR spectroscopic imaging with sampling incoherency in four (time, frequency, and two spatial) dimensions. The reconstruction was also tailored to dynamic MR spectroscopic imaging by applying a temporal wavelet sparsifying transform to exploit the inherent temporal sparsity. Customized multiband excitation pulses were designed with a lower flip angle for the [1-(13)C]-pyruvate substrate given its higher concentration than its metabolic products ([1-(13)C]-lactate and [1-(13)C]-alanine), thus using less hyperpolarization per excitation. This approach has enabled the monitoring of perfusion and uptake of the pyruvate, and the conversion dynamics to lactate and alanine throughout a volume with high spatial and temporal resolution.

Imaging of blood flow using hyperpolarized [(13)C]urea in preclinical cancer models.

PURPOSE: To demonstrate dynamic imaging of a diffusible perfusion tracer, hyperpolarized [(13)C]urea, for regional measurement of blood flow in preclinical cancer models. MATERIALS AND METHODS: A pulse sequence using balanced steady state free precession (bSSFP) was developed, with progressively increasing flip angles for efficient sampling of the hyperpolarized magnetization. This allowed temporal and volumetric imaging of the [(13)C]urea signal. Regional signal dynamics were quantified for kidneys and liver, and estimates of relative blood flows were derived from the data. Detailed perfusion simulations were performed to validate the methodology. RESULTS: Significant differences were observed in the signal patterns between normal and cancerous murine hepatic tissues. In particular, a 19% reduction in mean blood flow was observed in tumors, with 26% elevation in the tumor rim. The blood flow maps were also compared with metabolic imaging results with hyperpolarized [1-(13)C]pyruvate. CONCLUSION: Regional assessment of perfusion is possible by imaging of hyperpolarized [(13)C]urea, which is significant for the imaging of cancer.

3D compressed sensing for highly accelerated hyperpolarized (13)C MRSI with in vivo applications to transgenic mouse models of cancer.

High polarization of nuclear spins in liquid state through hyperpolarized technology utilizing dynamic nuclear polarization has enabled the direct monitoring of (13)C metabolites in vivo at a high signal-to-noise ratio. Acquisition time limitations due to T(1) decay of the hyperpolarized signal require accelerated imaging methods, such as compressed sensing, for optimal speed and spatial coverage. In this paper, the design and testing of a new echo-planar (13)C three-dimensional magnetic resonance spectroscopic imaging (MRSI) compressed sensing sequence is presented. The sequence provides up to a factor of 7.53 in acceleration with minimal reconstruction artifacts. The key to the design is employing x and y gradient blips during a fly-back readout to pseudorandomly undersample k(f)-k(x)-k(y) space. The design was validated in simulations and phantom experiments where the limits of undersampling and the effects of noise on the compressed sensing nonlinear reconstruction were tested. Finally, this new pulse sequence was applied in vivo in preclinical studies involving transgenic prostate cancer and transgenic liver cancer murine models to obtain much higher spatial and temporal resolution than possible with conventional echo-planar spectroscopic imaging methods.

Investigation of tumor hyperpolarized [1-13C]-pyruvate dynamics using time-resolved multiband RF excitation echo-planar MRSI.

Hyperpolarized [1-(13)C]-pyruvate is an exciting new agent for the in vivo study of cellular metabolism and a potential cancer biomarker. The nature of the hyperpolarized signal poses unique challenges because of its short duration and the loss of magnetization with every excitation. In this study, we applied a novel and efficient time-resolved MR spectroscopic imaging (MRSI) method to investigate in a prostate cancer model the localized temporal dynamics of the uptake of [1-(13)C]-pyruvate and its conversion to metabolic products, specifically [1-(13)C]-lactate. This hyperpolarized (13)C method used multiband excitation pulses for efficient use of the magnetization. This study demonstrated that regions of tumor were differentially characterized from normal tissue by the lactate dynamics, where tumors showed later lactate detection and longer lactate duration that was statistically significant (P < 0.001). Compared to late-pathologic-stage tumors, early- to intermediate-stage tumors demonstrated significantly (P < 0.01) lower lactate total signal-to-noise ratio (SNR), with similar temporal dynamic parameters. Hyperpolarized pyruvate dynamics provided uptake, perfusion, and vascularization information on tumors and normal tissue. Large, heterogeneous tumors demonstrated spatially variable uptake of pyruvate and metabolic conversion that was consistent with cellularity and necrosis identified by histology. The results of this study demonstrated the potential of this new hyperpolarized MR dynamic method for improved cancer detection and characterization.

Discovery of the Environmental Factors Affecting Urban Dwellers' Mental Health: A Data-Driven Approach.

Mental health is the foundation of health and happiness as well as the basis for an individual's meaningful life. The environmental and social health of a city can measure the mental state of people living in a certain areas, and exploring urban dwellers' mental states is an important factor in understanding and better managing cities. New dynamic and granular urban data provide us with a way to determine the environmental factors that affect the mental states of urban dwellers. The characteristics of the maximal information coefficient can identify the linear and nonlinear relationships so that we can fully identify the physical and social environmental factors that affect urban dwellers' mental states and further test these relationships through linear and nonlinear modeling. Taking the Greater London as an example, we used data from the London Datastore to discover the environmental factors that had the highest correlation with urban mental health from 2015 to 2017 and to prove that they had a high nonlinear correlation through neural network modeling. This paper aimed to use a data-driven approach to find environmental factors that had not yet received enough attention and to provide a starting point for research by establishing hypotheses for further exploration of the impact of environmental factors on mental health.

A data driven methodology for social science research with left-behind children as a case study.

For decades, traditional correlation analysis and regression models have been used in social science research. However, the development of machine learning algorithms makes it possible to apply machine learning techniques for social science research and social issues, which may outperform standard regression methods in some cases. Under the circumstances, this article proposes a methodological workflow for data analysis by machine learning techniques that have the possibility to be widely applied in social issues. Specifically, the workflow tries to uncover the natural mechanisms behind the social issues through a data-driven perspective from feature selection to model building. The advantage of data-driven techniques in feature selection is that the workflow can be built without so much restriction of related knowledge and theory in social science. The advantage of using machine learning techniques in modelling is to uncover non-linear and complex relationships behind social issues. The main purpose of our methodological workflow is to find important fields relevant to the target and provide appropriate predictions. However, to explain the result still needs theory and knowledge from social science. In this paper, we trained a methodological workflow with left-behind children as the social issue case, and all steps and full results are included.

Hyperpolarized [2-13C]-fructose: a hemiketal DNP substrate for in vivo metabolic imaging.

Hyperpolarized (13)C labeled molecular probes have been used to investigate metabolic pathways of interest as well as facilitate in vivo spectroscopic imaging by taking advantage of the dramatic signal enhancement provided by DNP. Due to the limited lifetime of the hyperpolarized nucleus, with signal decay dependent on T(1) relaxation, carboxylate carbons have been the primary targets for development of hyperpolarized metabolic probes. The use of these carbon nuclei makes it difficult to investigate upstream glycolytic processes, which have been related to both cancer metabolism as well as other metabolic abnormalities, such as fatty liver disease and diabetes. Glucose carbons have very short T(1)s (<1 s) and therefore cannot be used as an in vivo hyperpolarized metabolic probe of glycolysis. However, the pentose analogue fructose can also enter glycolysis through its phosphorylation by hexokinase and yield complementary information. The C(2) of fructose is a hemiketal that has a relatively longer relaxation time (approximately 16 s at 37 degrees C) and high solution state polarization (approximately 12%). Hyperpolarized [2-(13)C]-fructose was also injected into a transgenic model of prostate cancer (TRAMP) and demonstrated difference in uptake and metabolism in regions of tumor relative to surrounding tissue. Thus, this study demonstrates the first hyperpolarization of a carbohydrate carbon with a sufficient T(1) and solution state polarization for ex vivo spectroscopy and in vivo spectroscopic imaging studies.

Compressed sensing for resolution enhancement of hyperpolarized 13C flyback 3D-MRSI.

High polarization of nuclear spins in liquid state through dynamic nuclear polarization has enabled the direct monitoring of 13C metabolites in vivo at very high signal-to-noise, allowing for rapid assessment of tissue metabolism. The abundant SNR afforded by this hyperpolarization technique makes high-resolution 13C 3D-MRSI feasible. However, the number of phase encodes that can be fit into the short acquisition time for hyperpolarized imaging limits spatial coverage and resolution. To take advantage of the high SNR available from hyperpolarization, we have applied compressed sensing to achieve a factor of 2 enhancement in spatial resolution without increasing acquisition time or decreasing coverage. In this paper, the design and testing of compressed sensing suited for a flyback 13C 3D-MRSI sequence are presented. The key to this design was the undersampling of spectral k-space using a novel blipped scheme, thus taking advantage of the considerable sparsity in typical hyperpolarized 13C spectra. Phantom tests validated the accuracy of the compressed sensing approach and initial mouse experiments demonstrated in vivo feasibility.

Rapid sequential injections of hyperpolarized [1-¹³C]pyruvate in vivo using a sub-kelvin, multi-sample DNP polarizer.

The development of hyperpolarized technology utilizing dynamic nuclear polarization (DNP) has enabled the rapid measurement of (13)C metabolism in vivo with very high SNR. However, with traditional DNP equipment, consecutive injections of a hyperpolarized compound in an animal have been subject to a practical minimum time between injections governed by the polarization build-up time, which is on the order of an hour for [1-(13)C]pyruvate. This has precluded the monitoring of metabolic changes occurring on a faster time scale. In this study, we demonstrated the ability to acquire in vivo dynamic magnetic resonance spectroscopy (MRS) and 3D magnetic resonance spectroscopic imaging (MRSI) data in normal rats with a 5 min interval between injections of hyperpolarized [1-(13)C]pyruvate using a prototype, sub-Kelvin dynamic nuclear polarizer with the capability to simultaneously polarize up to 4 samples and dissolve them in rapid succession. There were minimal perturbations in the hyperpolarized spectra as a result of the multiple injections, suggesting that such an approach would not confound the investigation of metabolism occurring on this time scale. As an initial demonstration of the application of this technology and approach for monitoring rapid changes in metabolism as a result of a physiological intervention, we investigated the pharmacodynamics of the anti-cancer agent dichloroacetate (DCA), collecting hyperpolarized data before administration of DCA, 1 min after administration, and 6 min after administration. Dramatic increases in (13)C-bicarbonate were detected just 1 min (as well as 6 min) after DCA administration.

Use of hyperpolarized [1-13C]pyruvate and [2-13C]pyruvate to probe the effects of the anticancer agent dichloroacetate on mitochondrial metabolism in vivo in the normal rat.

Development of hyperpolarized technology utilizing dynamic nuclear polarization has enabled the measurement of (13)C metabolism in vivo at very high signal-to-noise ratio (SNR). In vivo mitochondrial metabolism can, in principle, be monitored with pyruvate, which is catalyzed to acetyl-CoA via pyruvate dehydrogenase (PDH). The purpose of this work was to determine whether the compound sodium dichloroacetate (DCA) could aid the study of mitochondrial metabolism with hyperpolarized pyruvate. DCA stimulates PDH by inhibiting its inhibitor, pyruvate dehydrogenase kinase. In this work, hyperpolarized [1-(13)C]pyruvate and [2-(13)C]pyruvate were used to probe mitochondrial metabolism in normal rats. Increased conversion to bicarbonate (+181±69%, P=.025) was measured when [1-(13)C]pyruvate was injected after DCA administration, and increased glutamate (+74±23%, P=.004), acetoacetate (+504±281%, P=.009) and acetylcarnitine (+377±157%, P=.003) were detected when [2-(13)C]pyruvate was used.

Investigating tumor perfusion and metabolism using multiple hyperpolarized (13)C compounds: HP001, pyruvate and urea.

The metabolically inactive hyperpolarized agents HP001 (bis-1,1-(hydroxymethyl)-[1-(13)C]cyclopropane-d(8)) and urea enable a new type of perfusion magnetic resonance imaging based on a direct signal source that is background-free. The addition of perfusion information to metabolic information obtained by spectroscopic imaging of hyperpolarized [1-(13)C]pyruvate would be of great value in exploring the relationship between perfusion and metabolism in cancer. In preclinical normal murine and cancer model studies, we performed both dynamic multislice imaging of the specialized hyperpolarized perfusion compound HP001 (T(1)=95 s ex vivo, 32 s in vivo at 3 T) using a pulse sequence with balanced steady-state free precession and ramped flip angle over time for efficient utilization of the hyperpolarized magnetization and three-dimensional echo-planar spectroscopic imaging of urea copolarized with [1-(13)C]pyruvate, with compressed sensing for resolution enhancement. For the dynamic data, peak signal maps and blood flow maps derived from perfusion modeling were generated. The spatial heterogeneity of perfusion was increased 2.9-fold in tumor tissues (P=.05), and slower washout was observed in the dynamic data. The results of separate dynamic HP001 imaging and copolarized pyruvate/urea imaging were compared. A strong and significant correlation (R=0.73, P=.02) detected between the urea and HP001 data confirmed the value of copolarizing urea with pyruvate for simultaneous assessment of perfusion and metabolism.

Multi-band frequency encoding method for metabolic imaging with hyperpolarized [1-(13)C]pyruvate.

A new method was developed for simultaneous spatial localization and spectral separation of multiple compounds based on a single echo, by designing the acquisition to place individual compounds in separate frequency encoding bands. This method was specially designed for rapid and robust metabolic imaging of hyperpolarized (13)C substrates and their metabolic products, and was investigated in phantom studies and studies in normal mice and transgenic models of prostate cancer to provide rapid metabolic imaging of hyperpolarized [1-(13)C]pyruvate and its metabolic products [1-(13)C]lactate and [1-(13)C]alanine at spatial resolutions up to 3mm in-plane. Elevated pyruvate and lactate signals in the vicinity of prostatic tissues were observed in transgenic tumor mice. The multi-band frequency encoding technique enabled rapid metabolic imaging of hyperpolarized (13)C compounds with important advantages over prior approaches, including less complicated acquisition and reconstruction methods.

13C-pyruvate imaging reveals alterations in glycolysis that precede c-Myc-induced tumor formation and regression.

Tumor cells have an altered metabolic phenotype characterized by increased glycolysis and diminished oxidative phosphorylation. Despite the suspected importance of glycolysis in tumorigenesis, the temporal relationship between oncogene signaling, in vivo tumor formation, and glycolytic pathway activity is poorly understood. Moreover, how glycolytic pathways are altered as tumors regress remains unknown. Here, we use a switchable model of Myc-driven liver cancer, along with hyperpolarized (13)C-pyruvate magnetic resonance spectroscopic imaging (MRSI) to visualize glycolysis in de novo tumor formation and regression. LDHA abundance and activity in tumors is tightly correlated to in vivo pyruvate conversion to lactate and is rapidly inhibited as tumors begin to regress, as are numerous glycolysis pathway genes. Conversion of pyruvate to alanine predominates in precancerous tissues prior to observable morphologic or histological changes. These results demonstrate that metabolic changes precede tumor formation and regression and are directly linked to the activity of a single oncogene.

In vivo measurement of normal rat intracellular pyruvate and lactate levels after injection of hyperpolarized [1-(13)C]alanine.

Hyperpolarized technology utilizing dynamic nuclear polarization has enabled rapid and high-sensitivity measurements of (13)C metabolism in vivo. The most commonly used in vivo agent for hyperpolarized (13)C metabolic imaging thus far has been [1-(13)C]pyruvate. In preclinical studies, not only is its uptake detected, but also its intracellular enzymatic conversion to metabolic products including [1-(13)C]lactate and [1-(13)C]alanine. However, the ratio of (13)C-lactate/(13)C-pyruvate measured in this data does not accurately reflect cellular values since much of the [1-(13)C]pyruvate is extracellular depending on timing, vascular properties, and extracellular space and monocarboxylate transporter activity. In order to measure the relative levels of intracellular pyruvate and lactate, in this project we hyperpolarized [1-(13)C]alanine and monitored the in vivo conversion to [1-(13)C]pyruvate and then the subsequent conversion to [1-(13)C]lactate. The intracellular lactate-to-pyruvate ratio of normal rat tissue measured with hyperpolarized [1-(13)C]alanine was 4.89±0.61 (mean±S.E.) as opposed to a ratio of 0.41±0.03 when hyperpolarized [1-(13)C]pyruvate was injected.

Multi-channel metabolic imaging, with SENSE reconstruction, of hyperpolarized [1-(13)C] pyruvate in a live rat at 3.0 tesla on a clinical MR scanner.

We report metabolic images of (13)C, following injection of a bolus of hyperpolarized [1-(13)C] pyruvate in a live rat. The data were acquired on a clinical scanner, using custom coils for volume transmission and array reception. Proton blocking of all carbon resonators enabled proton anatomic imaging with the system body coil, to allow for registration of anatomic and metabolic images, for which good correlation was achieved, with some anatomic features (kidney and heart) clearly visible in a carbon image, without reference to the corresponding proton image. Parallel imaging with sensitivity encoding was used to increase the spatial resolution in the SI direction of the rat. The signal to noise ratio in was in some instances unexpectedly high in the parallel images; variability of the polarization among different trials, plus partial volume effects, are noted as a possible cause of this.