Accelerated MRI using intelligent protocolling and subject-specific denoising applied to Alzheimer's disease imaging.

Magnetic Resonance Imaging (MR Imaging) is routinely employed in diagnosing Alzheimer's Disease (AD), which accounts for up to 60-80% of dementia cases. However, it is time-consuming, and protocol optimization to accelerate MR Imaging requires local expertise since each pulse sequence involves multiple configurable parameters that need optimization for contrast, acquisition time, and signal-to-noise ratio (SNR). The lack of this expertise contributes to the highly inefficient utilization of MRI services diminishing their clinical value. In this work, we extend our previous effort and demonstrate accelerated MRI via intelligent protocolling of the modified brain screen protocol, referred to as the Gold Standard (GS) protocol. We leverage deep learning-based contrast-specific image-denoising to improve the image quality of data acquired using the accelerated protocol. Since the SNR of MR acquisitions depends on the volume of the object being imaged, we demonstrate subject-specific (SS) image-denoising. The accelerated protocol resulted in a 1.94 × gain in imaging throughput. This translated to a 72.51% increase in MR Value-defined in this work as the ratio of the sum of median object-masked local SNR values across all contrasts to the protocol's acquisition duration. We also computed PSNR, local SNR, MS-SSIM, and variance of the Laplacian values for image quality evaluation on 25 retrospective datasets. The minimum/maximum PSNR gains (measured in dB) were 1.18/11.68 and 1.04/13.15, from the baseline and SS image-denoising models, respectively. MS-SSIM gains were: 0.003/0.065 and 0.01/0.066; variance of the Laplacian (lower is better): 0.104/-0.135 and 0.13/-0.143. The GS protocol constitutes 44.44% of the comprehensive AD imaging protocol defined by the European Prevention of Alzheimer's Disease project. Therefore, we also demonstrate the potential for AD-imaging via automated volumetry of relevant brain anatomies. We performed statistical analysis on these volumetric measurements of the hippocampus and amygdala from the GS and accelerated protocols, and found that 27 locations were in excellent agreement. In conclusion, accelerated brain imaging with the potential for AD imaging was demonstrated, and image quality was recovered post-acquisition using DL-based image denoising models.

A Machine Learning Approach for Continuous Mining of Nonidentifiable Smartphone Data to Create a Novel Digital Biomarker Detecting Generalized Anxiety Disorder: Prospective Cohort Study.

BACKGROUND: Anxiety is one of the leading causes of mental health disability around the world. Currently, a majority of the population who experience anxiety go undiagnosed or untreated. New and innovative ways of diagnosing and monitoring anxiety have emerged using smartphone sensor-based monitoring as a metric for the management of anxiety. This is a novel study as it adds to the field of research through the use of nonidentifiable smartphone usage to help detect and monitor anxiety remotely and in a continuous and passive manner. OBJECTIVE: This study aims to evaluate the accuracy of a novel mental behavioral profiling metric derived from smartphone usage for the identification and tracking of generalized anxiety disorder (GAD). METHODS: Smartphone data and self-reported 7-item GAD anxiety assessments were collected from 229 participants using an Android operating system smartphone in an observational study over an average of 14 days (SD 29.8). A total of 34 features were mined to be constructed as a potential digital phenotyping marker from continuous smartphone usage data. We further analyzed the correlation of these digital behavioral markers against each item of the 7-item Generalized Anxiety Disorder Scale (GAD-7) and its influence on the predictions of machine learning algorithms. RESULTS: A total of 229 participants were recruited in this study who had completed the GAD-7 assessment and had at least one set of passive digital data collected within a 24-hour period. The mean GAD-7 score was 11.8 (SD 5.7). Regression modeling was tested against classification modeling and the highest prediction accuracy was achieved from a binary XGBoost classification model (precision of 73%-81%; recall of 68%-87%; F1-score of 71%-79%; accuracy of 76%; area under the curve of 80%). Nonparametric permutation testing with Pearson correlation results indicated that the proposed metric (Mental Health Similarity Score [MHSS]) had a colinear relationship between GAD-7 Items 1, 3 and 7. CONCLUSIONS: The proposed MHSS metric demonstrates the feasibility of using passively collected nonintrusive smartphone data and machine learning-based data mining techniques to track an individuals' daily anxiety levels with a 76% accuracy that directly relates to the GAD-7 scale.

A Machine Learning Approach for Detecting Digital Behavioral Patterns of Depression Using Nonintrusive Smartphone Data (Complementary Path to Patient Health Questionnaire-9 Assessment): Prospective Observational Study.

BACKGROUND: Depression is a major global cause of morbidity, an economic burden, and the greatest health challenge leading to chronic disability. Mobile monitoring of mental conditions has long been a sought-after metric to overcome the problems associated with the screening, diagnosis, and monitoring of depression and its heterogeneous presentation. The widespread availability of smartphones has made it possible to use their data to generate digital behavioral models that can be used for both clinical and remote screening and monitoring purposes. This study is novel as it adds to the field by conducting a trial using private and nonintrusive sensors that can help detect and monitor depression in a continuous, passive manner. OBJECTIVE: This study demonstrates a novel mental behavioral profiling metric (the Mental Health Similarity Score), derived from analyzing passively monitored, private, and nonintrusive smartphone use data, to identify and track depressive behavior and its progression. METHODS: Smartphone data sets and self-reported Patient Health Questionnaire-9 (PHQ-9) depression assessments were collected from 558 smartphone users on the Android operating system in an observational study over an average of 10.7 (SD 23.7) days. We quantified 37 digital behavioral markers from the passive smartphone data set and explored the relationship between the digital behavioral markers and depression using correlation coefficients and random forest models. We leveraged 4 supervised machine learning classification algorithms to predict depression and its severity using PHQ-9 scores as the ground truth. We also quantified an additional 3 digital markers from gyroscope sensors and explored their feasibility in improving the model's accuracy in detecting depression. RESULTS: The PHQ-9 2-class model (none vs severe) achieved the following metrics: precision of 85% to 89%, recall of 85% to 89%, F1 of 87%, and accuracy of 87%. The PHQ-9 3-class model (none vs mild vs severe) achieved the following metrics: precision of 74% to 86%, recall of 76% to 83%, F1 of 75% to 84%, and accuracy of 78%. A significant positive Pearson correlation was found between PHQ-9 questions 2, 6, and 9 within the severely depressed users and the mental behavioral profiling metric (r=0.73). The PHQ-9 question-specific model achieved the following metrics: precision of 76% to 80%, recall of 75% to 81%, F1 of 78% to 89%, and accuracy of 78%. When a gyroscope sensor was added as a feature, the Pearson correlation among questions 2, 6, and 9 decreased from 0.73 to 0.46. The PHQ-9 2-class model+gyro features achieved the following metrics: precision of 74% to 78%, recall of 67% to 83%, F1 of 72% to 78%, and accuracy of 76%. CONCLUSIONS: Our results demonstrate that the Mental Health Similarity Score can be used to identify and track depressive behavior and its progression with high accuracy.

Automated identification of cephalometric landmarks: Part 2-Might it be better than human?

OBJECTIVES: To compare detection patterns of 80 cephalometric landmarks identified by an automated identification system (AI) based on a recently proposed deep-learning method, the You-Only-Look-Once version 3 (YOLOv3), with those identified by human examiners. MATERIALS AND METHODS: The YOLOv3 algorithm was implemented with custom modifications and trained on 1028 cephalograms. A total of 80 landmarks comprising two vertical reference points and 46 hard tissue and 32 soft tissue landmarks were identified. On the 283 test images, the same 80 landmarks were identified by AI and human examiners twice. Statistical analyses were conducted to detect whether any significant differences between AI and human examiners existed. Influence of image factors on those differences was also investigated. RESULTS: Upon repeated trials, AI always detected identical positions on each landmark, while the human intraexaminer variability of repeated manual detections demonstrated a detection error of 0.97 ± 1.03 mm. The mean detection error between AI and human was 1.46 ± 2.97 mm. The mean difference between human examiners was 1.50 ± 1.48 mm. In general, comparisons in the detection errors between AI and human examiners were less than 0.9 mm, which did not seem to be clinically significant. CONCLUSIONS: AI showed as accurate an identification of cephalometric landmarks as did human examiners. AI might be a viable option for repeatedly identifying multiple cephalometric landmarks.

Automated identification of cephalometric landmarks: Part 1-Comparisons between the latest deep-learning methods YOLOV3 and SSD.

OBJECTIVE: To compare the accuracy and computational efficiency of two of the latest deep-learning algorithms for automatic identification of cephalometric landmarks. MATERIALS AND METHODS: A total of 1028 cephalometric radiographic images were selected as learning data that trained You-Only-Look-Once version 3 (YOLOv3) and Single Shot Multibox Detector (SSD) methods. The number of target labeling was 80 landmarks. After the deep-learning process, the algorithms were tested using a new test data set composed of 283 images. Accuracy was determined by measuring the point-to-point error and success detection rate and was visualized by drawing scattergrams. The computational time of both algorithms was also recorded. RESULTS: The YOLOv3 algorithm outperformed SSD in accuracy for 38 of 80 landmarks. The other 42 of 80 landmarks did not show a statistically significant difference between YOLOv3 and SSD. Error plots of YOLOv3 showed not only a smaller error range but also a more isotropic tendency. The mean computational time spent per image was 0.05 seconds and 2.89 seconds for YOLOv3 and SSD, respectively. YOLOv3 showed approximately 5% higher accuracy compared with the top benchmarks in the literature. CONCLUSIONS: Between the two latest deep-learning methods applied, YOLOv3 seemed to be more promising as a fully automated cephalometric landmark identification system for use in clinical practice.

Steer-PROP: a GRASE-PROPELLER sequence with interecho steering gradient pulses.

PURPOSE: This study demonstrates a novel PROPELLER (periodically rotated overlapping parallel lines with enhanced reconstruction) pulse sequence, termed Steer-PROP, based on gradient and spin echo (GRASE), to reduce the imaging times and address phase errors inherent to GRASE. The study also illustrates the feasibility of using Steer-PROP as an alternative to single-shot echo planar imaging (SS-EPI) to produce distortion-free diffusion images in all imaging planes. METHODS: Steer-PROP uses a series of blip gradient pulses to produce N (N = 3-5) adjacent k-space blades in each repetition time, where N is the number of gradient echoes in a GRASE sequence. This sampling strategy enables a phase correction algorithm to systematically address the GRASE phase errors as well as the motion-induced phase inconsistency. Steer-PROP was evaluated on phantoms and healthy human subjects at both 1.5T and 3.0T for T2 - and diffusion-weighted imaging. RESULTS: Steer-PROP produced similar image quality as conventional PROPELLER based on fast spin echo (FSE), while taking only a fraction (e.g., 1/3) of the scan time. The robustness against motion in Steer-PROP was comparable to that of FSE-based PROPELLER. Using Steer-PROP, high quality and distortion-free diffusion images were obtained from human subjects in all imaging planes, demonstrating a considerable advantage over SS-EPI. CONCLUSION: The proposed Steer-PROP sequence can substantially reduce the scan times compared with FSE-based PROPELLER while achieving adequate image quality. The novel k-space sampling strategy in Steer-PROP not only enables an integrated phase correction method that addresses various sources of phase errors, but also minimizes the echo spacing compared with alternative sampling strategies. Steer-PROP can also be a viable alternative to SS-EPI to decrease image distortion in all imaging planes. Magn Reson Med 79:2533-2541, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Anomalous diffusion measured by a twice-refocused spin echo pulse sequence: analysis using fractional order calculus.

PURPOSE: To theoretically develop and experimentally validate a formulism based on a fractional order calculus (FC) diffusion model to characterize anomalous diffusion in brain tissues measured with a twice-refocused spin-echo (TRSE) pulse sequence. MATERIALS AND METHODS: The FC diffusion model is the fractional order generalization of the Bloch-Torrey equation. Using this model, an analytical expression was derived to describe the diffusion-induced signal attenuation in a TRSE pulse sequence. To experimentally validate this expression, a set of diffusion-weighted (DW) images was acquired at 3 Tesla from healthy human brains using a TRSE sequence with twelve b-values ranging from 0 to 2600 s/mm(2). For comparison, DW images were also acquired using a Stejskal-Tanner diffusion gradient in a single-shot spin-echo echo planar sequence. For both datasets, a Levenberg-Marquardt fitting algorithm was used to extract three parameters: diffusion coefficient D, fractional order derivative in space ß, and a spatial parameter µ (in units of µm). Using adjusted R-squared values and standard deviations, D, ß, and µ values and the goodness-of-fit in three specific regions of interest (ROIs) in white matter, gray matter, and cerebrospinal fluid, respectively, were evaluated for each of the two datasets. In addition, spatially resolved parametric maps were assessed qualitatively. RESULTS: The analytical expression for the TRSE sequence, derived from the FC diffusion model, accurately characterized the diffusion-induced signal loss in brain tissues at high b-values. In the selected ROIs, the goodness-of-fit and standard deviations for the TRSE dataset were comparable with the results obtained from the Stejskal-Tanner dataset, demonstrating the robustness of the FC model across multiple data acquisition strategies. Qualitatively, the D, ß, and µ maps from the TRSE dataset exhibited fewer artifacts, reflecting the improved immunity to eddy currents. CONCLUSION: The diffusion-induced signal attenuation in a TRSE pulse sequence can be described by an FC diffusion model at high b-values. This model performs equally well for data acquired from the human brain tissues with a TRSE pulse sequence or a conventional Stejskal-Tanner sequence.

Diffusion tensor imaging study of white matter fiber tracts in pediatric bipolar disorder and attention-deficit/hyperactivity disorder.

BACKGROUND: To investigate microstructure of white matter fiber tracts in pediatric bipolar disorder (PBD) and attention-deficit/hyperactivity disorder (ADHD). METHODS: A diffusion tensor imaging (DTI) study was conducted at 3 Tesla on age- and IQ-matched children and adolescents with PBD (n = 13), ADHD (n = 13), and healthy control subjects (HC) (n = 15). Three DTI parameters, fractional anisotropy (FA), apparent diffusion coefficient (ADC), and regional fiber coherence index (r-FCI), were examined in eight fiber tracts: anterior corona radiata (ACR), anterior limb of the internal capsule (ALIC), superior region of the internal capsule (SRI), posterior limb of the internal capsule (PLIC), superior longitudinal fasciculus (SLF), inferior longitudinal fasciculus (ILF), cingulum (CG), and splenium (SP). RESULTS: Significantly lower FA was observed in ACR in both PBD and ADHD relative to HC. In addition, FA and r-FCI values were significantly lower in ADHD relative to PBD and HC in both the ALIC and the SRI. Further, ADC was significantly greater in ADHD relative to both the PBD and HC in ACR, ALIC, PLIC, SRI, CG, ILF, and SLF. CONCLUSIONS: Decreased FA in ACR implies an impaired fiber density or reduced myelination in both PBD and ADHD in this prefrontal tract. These abnormalities, together with the reduced fiber coherence, extended to corticobulbar tracts in ADHD. Increased ADC across multiple white matter tracts in ADHD indicates extensive cellular abnormalities with less diffusion restriction in ADHD relative to PBD.