SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force from Highly Sparse Ultrasound Images.

Ultrasound imaging or sonomyography has been found to be a robust modality for measuring muscle activity due to its ability to image deep-seated muscles directly while providing superior spatiotemporal specificity compared to surface electromyography-based techniques. Quantifying the morphological changes during muscle activity involves computationally expensive approaches for tracking muscle anatomical structures or extracting features from brightness-mode (B-mode) images and amplitude-mode (A-mode) signals. This paper uses an offline regression convolutional neural network (CNN) called SonoMyoNet to estimate continuous isometric force from sparse ultrasound scanlines. SonoMyoNet learns features from a few equispaced scanlines selected from B-mode images and utilizes the learned features to estimate continuous isometric force accurately. The performance of SonoMyoNet was evaluated by varying the number of scanlines to simulate the placement of multiple single-element ultrasound transducers in a wearable system. Results showed that SonoMyoNet could accurately predict isometric force with just four scanlines and is immune to speckle noise and shifts in the scanline location. Thus, the proposed network reduces the computational load involved in feature tracking algorithms and estimates muscle force from the global features of sparse ultrasound images.

A Sonomyography-Based Muscle Computer Interface for Individuals With Spinal Cord Injury.

Impairment of hand functions in individuals with spinal cord injury (SCI) severely disrupts activities of daily living. Recent advances have enabled rehabilitation assisted by robotic devices to augment the residual function of the muscles. Traditionally, electromyography-based muscle activity sensing interfaces have been utilized to sense volitional motor intent to drive robotic assistive devices. However, the dexterity and fidelity of control that can be achieved with electromyography-based control have been limited due to inherent limitations in signal quality. We have developed and tested a muscle-computer interface (MCI) utilizing sonomyography to provide control of a virtual cursor for individuals with motor-incomplete spinal cord injury. We demonstrate that individuals with SCI successfully gained control of a virtual cursor by utilizing contractions of muscles of the wrist joint. The sonomyography-based interface enabled control of the cursor at multiple graded levels demonstrating the ability to achieve accurate and stable endpoint control. Our sonomyography-based muscle-computer interface can enable dexterous control of upper-extremity assistive devices for individuals with motor-incomplete SCI.

Wearable Ultrasound System Using Low-Voltage Time Delay Spectrometry for Dynamic Tissue Imaging.

OBJECTIVE: Wearable ultrasound is emerging as a new paradigm of real-time imaging in freely moving humans and has wide applications from cardiovascular health monitoring to human gesture recognition. However, current wearable ultrasound devices have typically employed pulse-echo imaging which requires high excitation voltages and sampling rates, posing safety risks, and requiring specialized hardware. Our objective was to develop and evaluate a wearable ultrasound system based on time delay spectrometry (TDS) that utilizes low-voltage excitation and significantly simplified instrumentation. METHODS: We developed a TDS-based ultrasound system that utilizes continuous, frequency-modulated sweeps at low excitation voltages. By mixing the transmit and receive signals, the system digitizes the ultrasound signal at audio frequency (kHz) sampling rates. Wearable ultrasound transducers were developed, and the system was characterized in terms of imaging performance, acoustic output, thermal characteristics, and applications in musculoskeletal imaging. RESULTS: The prototype TDS system is capable of imaging up to 6 cm of depth with signal-to-noise ratio of up to 42 dB at a spatial resolution of 0.33 mm. Acoustic and thermal radiation measurements were within clinically safe limits for continuous ultrasound imaging. We demonstrated the ability to use a 4-channel wearable system for dynamic imaging of muscle activity. CONCLUSION: We developed a wearable ultrasound imaging system using TDS to mitigate challenges with pulse echo-based wearable ultrasound imaging systems. Our device is capable of high-resolution, dynamic imaging of deep-seated tissue structures and is safe for long-term use. SIGNIFICANCE: This work paves the way for low-voltage wearable ultrasound imaging devices with significantly reduced hardware complexity.

Classification Performance and Feature Space Characteristics in Individuals With Upper Limb Loss Using Sonomyography.

Objective: Sonomyography, or ultrasound-based sensing of muscle deformation, is an emerging modality for upper limb prosthesis control. Although prior studies have shown that individuals with upper limb loss can achieve successful motion classification with sonomyography, it is important to better understand the time-course over which proficiency develops. In this study, we characterized user performance during their initial and subsequent exposures to sonomyography. Method: Ultrasound images corresponding to a series of hand gestures were collected from individuals with transradial limb loss under three scenarios: during their initial exposure to sonomyography (Experiment 1), during a subsequent exposure to sonomyography where they were provided biofeedback as part of a training protocol (Experiment 2), and during testing sessions held on different days (Experiment 3). User performance was characterized by offline classification accuracy, as well as metrics describing the consistency and separability of the sonomyography signal patterns in feature space. Results: Classification accuracy was high during initial exposure to sonomyography (96.2 ± 5.9%) and did not systematically change with the provision of biofeedback or on different days. Despite this stable classification performance, some of the feature space metrics changed. Conclusions: User performance was strong upon their initial exposure to sonomyography and did not improve with subsequent exposure. Clinical Impact: Prosthetists may be able to quickly assess if a patient will be successful with sonomyography without submitting them to an extensive training protocol, leading to earlier socket fabrication and delivery.

Sparsity Analysis of a Sonomyographic Muscle-Computer Interface.

OBJECTIVE: Sonomyography has been shown to be a promising method for decoding volitional motor intent from analysis of ultrasound images of the forearm musculature. The objectives of this paper are to determine the optimal location for ultrasound transducer placement on the anterior forearm for imaging maximum muscle deformations during different hand motions, and to investigate the effect of using a sparse set of ultrasound scanlines for motion classification for ultrasound-based muscle-computer interfaces (MCIs). METHODS: The optimal placement of the ultrasound transducer along the forearm was identified using freehand three-dimensional reconstructions of the muscle thickness during rest and motion completion. Based on the ultrasound images acquired from the optimally placed transducer, classification accuracy with equally spaced scanlines across the cross-sectional field of view was determined. Furthermore, the unique contribution of each scanline to class discrimination using Fisher criterion (FC) and mutual information (MI) with respect to motion discriminability was determined. RESULTS: Experiments with five able-bodied subjects show that the maximum muscle deformation occurred between 40%-50% of the forearm length for multiple degrees-of-freedom. The average classification accuracy was 94% ± 6% with the entire 128-scanline image and 94% ± 5% with four equally spaced scanlines. However, no significant improvement in classification accuracy was observed with optimal scanline selection using FC and MI. CONCLUSION: For an optimally placed transducer, a small subset of ultrasound scanlines can be used instead of a full imaging array without sacrificing performance in terms of classification accuracy for multiple degrees-of-freedom. SIGNIFICANCE: The selection of a small subset of transducer elements can enable the reduction of computation, and simplification of the instrumentation and power consumption of wearable sonomyographic MCIs, particularly for rehabilitation and gesture recognition applications.

Sonomyography Combined with Vibrotactile Feedback Enables Precise Target Acquisition Without Visual Feedback.

Upper limb prosthesis users currently lack haptic feedback from their terminal devices, which significantly limits their ability to meaningfully interact with their environment. Users therefore rely heavily on visual feedback when using terminal devices. Previously, it has been shown that force-related feedback from an end-effector or virtual environment can help the user minimize errors and improve performance. Currently, myoelectric control systems enable the user to control the velocity of terminal devices. We have developed a novel control method using ultrasound sensing, called sonomyography, that enables position control based on mechanical deformation of muscles. In this paper, we investigated whether the proprioceptive feedback from muscle deformation combined with vibrotactile haptic feedback can minimize the need for visual feedback. Able bodied subjects used sonomyography to control a virtual cursor, and performed a target acquisition task. The effect of visual and haptic feedback on performance of a target acquisition task was systematically tested. We found that subjects made large errors when they tried to reacquire a target without visual feedback, but in the presence of real-time haptic feedback, the precision of the target position improved, and were similar to when visual feedback was used for target acquisition. This result has implications for improving the performance of prosthetic control systems.

Two chair test: a substitute of 6 min walk test appear cardiopulmonary reserve specific.

BACKGROUND: A simple and efficient exercise test possible in a small space is welcome to supplement 6 min walk test (6MWT) that demands a 100 feet corridor to perform. METHODS: The proposed two chair test (2CT) makes a person to sit and move five times between two chairs placed face to face at 5 feet apart and note the changes in pulse-rate (PR) and arterial oxygen saturation (SpO2) at every 10 s for 2 min after that. Comparison of the post-exercise measurements (PR and SpO2) with a repeat performance in same patients was done for reproducibility and doing the same after 6MWT and 2CT in another set of patients was meant for for acceptability. The statistical analysis was made on moment to moment change, mean maximal difference and mean cumulative difference for the measurements using p value, z-score, r value and principal component analysis (PCA). FINDINGS: A total of 40 and 60 volunteers were included for testing reproducibility and acceptability. On both the sets, the difference in most of comparisons between the measured variable (PR and SpO2) showed the p values remaining insignificant (>0.05), and z-score being <1 SD of the corresponding other and the correlation coefficients (r) remaining excellent (>0.9). Furthermore, the PCA shows complete overlapping. The post-exercise changes did not corelate the walking distance in 6MWT. INTERPRETATION: The proposed 2CT demands small space and appears reproducible and comparable with 6MWT in terms of its post-exercise impact on PR and SpO2. This novel test also appears more of cardiopulmonary reserve specific.

Evaluation of the Role of Proprioception During Proportional Position Control Using Sonomyography: Applications in Prosthetic Control.

Prosthetics need to incorporate the users sense of proprioception into the control paradigm to provide intuitive control, and reduce training times and prosthetic rejection rates. In the absence of functional tasks with a prosthetic, virtual cursor control tasks have been used to train users to control multiple degrees of freedom. In this study, A proportional position signal was derived from the cross-sectional ultrasound images of the users forearm. We designed a virtual cursor control task with one degree of freedom to measure the users ability to repeatably and accurately acquire different levels of muscle flexion, using only their sense of proprioception. The experiment involved a target acquisition task, where the cursors height corresponded to the extent of muscle flexion. Users were asked to acquire targets on a screen. Visual feedback was disabled at certain times during the experiment, to isolate the effect of proprioception. We found that as visual feedback was taken away from the subjects, position error increased but their stability error did not change significantly. This indicates that users are not perfect at using only their proprioceptive sense to reacquire a level of muscle flexion, in the absence of haptic or visual feedback. However, they are adept at retaining an acquired flexion level without drifting. These results could help to quantify the role of proprioception in target acquisition tasks, in the absence of haptic or visual feedback.

Proprioceptive Sonomyographic Control: A novel method for intuitive and proportional control of multiple degrees-of-freedom for individuals with upper extremity limb loss.

Technological advances in multi-articulated prosthetic hands have outpaced the development of methods to intuitively control these devices. In fact, prosthetic users often cite "difficulty of use" as a key contributing factor for abandoning their prostheses. To overcome the limitations of the currently pervasive myoelectric control strategies, namely unintuitive proportional control of multiple degrees-of-freedom, we propose a novel approach: proprioceptive sonomyographic control. Unlike myoelectric control strategies which measure electrical activation of muscles and use the extracted signals to determine the velocity of an end-effector; our sonomyography-based strategy measures mechanical muscle deformation directly with ultrasound and uses the extracted signals to proportionally control the position of an end-effector. Therefore, our sonomyography-based control is congruent with a prosthetic user's innate proprioception of muscle deformation in the residual limb. In this work, we evaluated proprioceptive sonomyographic control with 5 prosthetic users and 5 able-bodied participants in a virtual target achievement and holding task for 5 different hand motions. We observed that with limited training, the performance of prosthetic users was comparable to that of able-bodied participants and thus conclude that proprioceptive sonomyographic control is a robust and intuitive prosthetic control strategy.

Healthcare costs among adults with type 2 diabetes initiating saxagliptin or linagliptin: a US-based claims analysis.

OBJECTIVE: To compare healthcare costs of adults with type 2 diabetes (T2D) after initiation of saxagliptin or linagliptin, two antidiabetic medications in the dipeptidyl peptidase-4 inhibitor medication class. METHODS: Patients with T2D who were at least 18 years old and initiated saxagliptin or linagliptin (index date) between 1 June 2011 and 30 June 2014 were identified in the MarketScan Commercial and Medicare Supplemental Databases. All-cause healthcare costs and diabetes-related costs (T2D diagnosis on a medical claim and/or an antidiabetic medication claim) were measured in the 1 year follow-up period. Saxagliptin and linagliptin initiators were matched using propensity score methods. Cost ratios (CRs) and predicted costs were estimated from generalized linear models and recycled predictions. RESULTS: There were 34,560 saxagliptin initiators and 18,175 linagliptin initiators identified (mean ages 57 and 59; 55% and 56% male, respectively). Before matching, saxagliptin initiators had significantly lower all-cause total healthcare costs than linagliptin initiators (mean = $15,335 [SD $28,923] vs. mean = $20,069 [SD $48,541], p < .001) and significantly lower diabetes-related total healthcare costs (mean = $6109 [SD $13,851] vs. mean = $7393 [SD $26,041], p < .001). In matched analyses (n = 16,069 per cohort), saxagliptin initiators had lower all-cause follow-up costs than linagliptin initiators (CR = 0.953, 95% CI = 0.932-0.974, p < .001; predicted costs = $17,211 vs. $18,068). There was no significant difference in diabetes-related total costs after matching; however, diabetes-related medical costs were significantly lower for saxagliptin initiators (CR = 0.959, 95% CI = 0.927-0.993, p = 0.017; predicted costs = $3989 vs. $4159). CONCLUSIONS: Adult patients with T2D initiating treatment with saxagliptin had lower total all-cause healthcare costs and diabetes-related medical costs over 1 year compared with patients initiating treatment with linagliptin.

An Eye Toward Improving: A new training approach in ophthalmic anesthesia provides qualitative and quantitative feedback.

In ophthalmic anesthesia administration prior to surgeries for problems such as cataracts or glaucoma, the training of new doctors, as in other surgical specialties, is based on a model in which a student trains on a patient under the expert supervision of an experienced doctor. However, the traditional apprenticeship approach is problematic in eye surgery because ocular structures could potentially be damaged by those administering ophthalmic anesthesia for the first time. Apart from the obvious risk to patients, there is also the inability to quantify the performance of a trainee. One solution to these problems might be found in the development of a manikin-based ophthalmic anesthesia training system that can emulate the human ocular anatomy while providing real-time quantitative and qualitative feedback to the trainee during training.

A Multi-Electrode Electric Field Based Sensing System For Ophthalmic Anesthesia Training.

Local anesthesia administration prior to ophthalmic surgery involves inserting a syringe needle into a confined intraorbital space at the proper position, angle and depth. During this procedure ocular structures must remain unhurt and systemic complications must be avoided while achieving quick akinesia and analgesia. Animal cadavers do not emulate human anatomy accurately and human subject based training entails risk to the patient. Therefore, a training system that closely replicates the human ocular and orbital anatomy and provides the trainee with real-time feedback on the safety and effectiveness of the block administered would help reduce risks involved with real life procedures. This paper presents an anatomically accurate, rapid-prototyped manikin based training system for ophthalmic anesthetic blocks. The depth of penetration of the needle, the proximity of the needle to extraocular muscles and the touch of the needle to the muscles or optic nerve is detected by a multi-electrode electric field/capacitive sensing system. The eye structure of the manikin does not have any electrical connections to it, rendering it replaceable, thus, enabling the emulation of anatomical variations due to pathologies of the eye. A virtual instrument measures and computes the position of the needle and displays it to the trainee through an intuitive GUI with a 3D display of the orbital anatomy. The proposed capacitive sensing scheme has been validated by tests performed on a prototype system, thus demonstrating its usefulness for practical training purposes.

An efficient capacitive sensing scheme for an ophthalmic regional anesthesia training system.

Ophthalmic regional blocks are critical preoperative procedures involving the insertion of a syringe needle into the orbital cavity at such a position and angle that akinesia and analgesia is achieved without damage or harm to the eye and its associated musculature. A training system that accurately represents the orbital anatomical features and provides qualitative feedback on the performed anesthetic technique, can be of immense help in reducing risks involved in regional block administration. In this paper, a training system that employs a special but simple capacitive sensing scheme has been developed. A rapid prototyped eye-model has been used to ensure anatomical accuracy. Capacitive transmitter electrodes placed on the orbital wall along the length of the extraocular muscles are excited with a special excitation sequence and the displacement current at the needle of the syringe is measured using simple electronic unit and a Data Acquisition System, enabling the developed Virtual Instrument to detect the depth of penetration and proximity of the syringe needle to the ocular muscles. Additionally, the system detects needle touch of the muscles accurately. The proposed electrode array system and excitation schemes have been validated on a prototype system thus demonstrating its usefulness for practical training purposes.

A syringe injection rate detector employing a dual Hall-effect sensor configuration.

Injection of fluids in the body using needle syringes is a standard clinical practice. The rate of injection can have various pathological effects on the body such as the pain perceived or in case of anesthesia, the amount of akinesia attained. Hence, a training system with a modified syringe employing a simple measurement scheme where a trainee can observe and practice the rate of injection prior to administering on actual human subjects, can be of great value towards reduction of complications in real life situations. In this paper, we develop a system for measurement of syringe injection rate with two Hall-effect sensors. Ring magnets attached to the body of the syringe along with the dual Hall-effect sensor configuration help in determining the position of the piston with respect to the syringe body. The two Hall-sensors are arranged in a differential configuration such that a linear relationship is obtained between the volume of liquid in the syringe (in ml) and the Hall-effect sensor output voltages. A prototype developed validated the measurement scheme. The rate of injection was displayed in real-time with a LabVIEW based Virtual Instrument. The error was within acceptable limits illustrating its efficacy for practical training purposes.

Electroglottographic parameterization of the effects of gender, vowel and phonatory registers on vocal fold vibratory patterns: an Indian perspective.

In-depth study on laryngeal biomechanics and vocal fold vibratory patterns reveal that a single vibratory cycle can be divided into two major phases, the closed and open phase, which is subdivided into opening and closing phases. Studies reveal that the relative time course of abduction and adduction, which in turn is dependent on the relative relaxing and tensing of the vocal fold cover and body, to be the determining factor in production of a particular vocal register like the modal (or chest), falsetto, glottal fry registers. Studies further point out Electroglottography to be particularly suitable for the study of vocal vibratory patterns during register changes. However, to date, there has been limited study on quantitative parameterization of EGG wave form in vocal fry register. Moreover, contradictory findings abound in literature regarding effects of gender and vowel types on vocal vibratory patterns, especially during phonation at different registers. The present study endeavors to find out the effects of vowel and gender differences on the vocal fold vibratory patterns in different registers and how these would be reflected in standard EGG parameters of Contact Quotient (CQ) and Contact Index (CI), taking into consideration the Indian sociolinguistic context. Electroglottographic recordings of 10 young adults (5 males and 5 females) were taken while the subjects phonated the three vowels /a/,/i/,/u/ each in two vocal registers, modal and vocal fry. Obtained raw EGG were further normalized using the Derived EGG algorithm and theCQ and CI values were derived. Obtained data were subject to statistical analysis using the 3-way ANOVA with gender, vowel and vocal register as the three variables. Post-hoc Dunnett C multiple comparison analysis were also performed. Results reveal that CQ values are significantly higher in vocal fry than modal phonation for both males and females, indicating a relatively hyperconstricted vocal system during vocal fry. The males have significantly greater CQ values than females both at modal and vocal fry phonations which indicate that the males are predisposed to greater vocal fold constriction. Females demonstrated no significant increase in CI values in vocal fry state; and in some cases actually decrease in the CI values which suggest an inherently distinct vocal fold physiological adjustment from that in males. No vowel effects were found in any conditions. Perturbation values (CQP and CIP) are significantly more in vocal fry register than in modal register, and the increase was more in case of females than males. The findings give strong evidence to certain hypotheses in literature regarding effects of vowel, gender and phonatory register on vocal fold vibratory patterns.

Extrahepatic biliary cystadenoma: an unusual cause of recurrent cholangitis.

Extrahepatic biliary cystadenoma is a rare benign lesion with malignant potential. Fewer than 100 cases have been reported in the literature. The most common clinical presentation is obstructive jaundice. Frank cholangitis is extremely rare. The authors report a case of extrahepatic biliary cystadenoma in a 55-year-old woman who presented with recurrent episodes of cholangitis.