Rehabilitation Engineering Research Articles

Attention Induced Dual Convolutional-Capsule Network (AIDC-CN): A deep learning framework for motor imagery classification

In recent times, Electroencephalography (EEG)-based motor imagery (MI) decoding has garnered significant attention due to its extensive applicability in healthcare, including areas such as assistive robotics and rehabilitation engineering. Nevertheless, the decoding of EEG signals presents considerable challenges owing to their inherent complexity, non-stationary characteristics, and low signal-to-noise ratio. Notably, deep learning-based classifiers have emerged as a prominent focus for addressing the EEG signal decoding process. This study introduces a novel deep learning classifier named the Attention Induced Dual Convolutional-Capsule Network (AIDC-CN) with the specific aim of accurately categorizing various motor imagination class labels. To enhance the classifier’s performance, a dual feature extraction approach leveraging spectrogram and brain connectivity networks has been employed, diversifying the feature set in the classification task. The main highlights of the proposed AIDC-CN classifier includes the introduction of a dual convolution layer to handle the brain connectivity and spectrogram features, addition of a novel self-attention module (SAM) to accentuate the relevant parts of the convolved spectrogram features, introduction of a new cross-attention module (CAM) to refine the outputs obtained from the dual convolution layers and incorporation of a Gaussian Error Linear Unit (GELU) based dynamic routing algorithm to strengthen the coupling among the primary and secondary capsule layers. Performance analysis undertaken on four public data sets depict the superior performance of the proposed model with respect to the state-of-the-art techniques. The code for this model is available at https://github.com/RiteshSurChowdhury/AIDC-CN.

Perceptions and assessment of a novel robotic wheelchair transfer system

Objectives Wheelchair transfers risk injury to users and caregivers. Conventional transfer devices are injury-prone and time inefficient. The Powered Personal Transfer System (PPTS), utilizing a modified Electric Powered Wheelchair (EPW) and a hospital bed, provides a no-lift solution for bed-to-wheelchair transfers. Objective 1: Assess PPTS workload compared to existing methods. Objective 2: Evaluate PPTS EPW in daily mobility tasks. Objective 3: Perform Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) wheelchair standards testing for PPTS EPW stability and performance. Methods Fifteen professional and family caregivers, experienced in assisting EPW users, performed transfers between the bed and EPW using the PPTS. Subsequently, participants drove the PPTS EPW providing ratings on the ease of performing mobility tasks. Wheelchair testing was conducted following RESNA standards. Setting : Simulated bedroom in a laboratory setting. Results Participants reported low workload demands for employing the PPTS and indicated a preference for the PPTS over existing transfer devices/methods. Ease of performing everyday mobility tasks was not significantly different between the modified PPTS and the commercially available original manufacturer equipment EPW (p > 0.05). RESNA wheelchair standards testing confirmed that the PPTS EPW preserves functionality, stability and performance when compared to similar commercially available EPWs. Conclusion The PPTS demonstrated promise in offering a practical, low demanding, and safe solution for transfers. It has the potential to enhance user and caregiver safety by reducing the incidence of caregiver injuries associated with assisting in transfer tasks. In addition to its efficiency and ease of use, it is an advancement in assistive technology for wheelchair transfers.

Enhanced Hand Gesture Recognition with Surface Electromyogram and Machine Learning.

This study delves into decoding hand gestures using surface electromyography (EMG) signals collected via a precision Myo-armband sensor, leveraging machine learning algorithms. The research entails rigorous data preprocessing to extract features and labels from raw EMG data. Following partitioning into training and testing sets, four traditional machine learning models are scrutinized for their efficacy in classifying finger movements across seven distinct gestures. The analysis includes meticulous parameter optimization and five-fold cross-validation to evaluate model performance. Among the models assessed, the Random Forest emerges as the top performer, consistently delivering superior precision, recall, and F1-score values across gesture classes, with ROC-AUC scores surpassing 99%. These findings underscore the Random Forest model as the optimal classifier for our EMG dataset, promising significant advancements in healthcare rehabilitation engineering and enhancing human-computer interaction technologies.

A porous elastomer with a cavity array for three-dimensional plantar force sensing

Human gait is an important indicator for diagnosis of various movement-related disorders. Three-dimensional (3D) plantar force monitoring enables real-time recording of contact forces in both the normal and tangential directions in each step, providing useful clues for identification of irregular gait patterns or gait-related health issues. Most flexible sensors for gait monitoring focus on contact forces in the normal direction, being limited to detect forces in the tangential direction. Herein we have developed a porous elastomer with a cavity array (PECA) to measure 3D contact forces for gait analysis. The sensor consists of two fabric electrodes and a dielectric layer of porous Ecoflex elastomer containing a 5 × 5 cavity array, forming four parallel-plate capacitor units in a soft construction. Therefore, a 3D force in any arbitrary direction generates four unique capacitive electrical signals. Importantly, the PECA includes a well-designed combination of micrometer-scale pores and millimeter-sized cavities, dramatically improving the detection sensitivity and linear elasticity range. We have demonstrated high sensitivities of 0.41 N−1 and 0.23 N−1 in the normal and tangential directions, respectively. The flexible PECA-based sensors have been tested to sensitively distinguish various standing postures and different stride lengths for gait analysis, promising reliable translation into areas such as healthcare monitoring, sports training, and rehabilitation engineering.

Continuous reach-to-grasp motion recognition based on an extreme learning machine algorithm using sEMG signals.

Recognizing user intention in reach-to-grasp motions is a critical challenge in rehabilitation engineering. To address this, a Machine Learning (ML) algorithm based on the Extreme Learning Machine (ELM) was developed for identifying motor actions using surface Electromyography (sEMG) during continuous reach-to-grasp movements, involving multiple Degrees of Freedom(DoFs). This study explores feature extraction methods based on time domain and autoregressive models to evaluate ELM performance under different conditions. The experimental setup encompassed variations in neuron size, time windows, validation with each muscle, increase in the number of features, comparison with five conventional ML-based classifiers, inter-subjects variability, and temporal dynamic response. To evaluate the efficacy of the proposed ELM-based method, an openly available sEMG dataset containing data from 12 participants was used. Results highlight the method's performance, achieving Accuracy above 85%, F-score above 90%, Recall above 85%, Area Under the Curve of approximately 84% and compilation times (computational cost) of less than 1ms. These metrics significantly outperform standard methods (p < 0.05). Additionally, specific trends were found in increasing and decreasing performance in identifying specific tasks, as well as variations in the continuous transitions in the temporal dynamics response. Thus, the ELM-based method effectively identifies continuous reach-to-grasp motions through myoelectric data. These findings hold promise for practical applications. The method's success prompts future research into implementing it for more reliable and effective Human-Machine Interface (HMI) control. This can revolutionize real-time upper limb rehabilitation, enabling natural and complex Activities of Daily Living (ADLs) like object manipulation. The robust results encourages further research and innovative solutions to improve people's quality of life through more effective interventions.

A Protocol for Comprehensive Analysis of Gait in Individuals with Incomplete Spinal Cord Injury.

This is a protocol for comprehensive analysis of gait and affecting factors in individuals with incomplete paraplegia due to spinal cord injury (SCI). A SCI is a devastating event affecting both sensory and motor functions. Due to better care, the SCI population is changing, with a greater proportion retaining impaired ambulatory function. Optimizing ambulatory function after SCI remains challenging. To investigate factors influencing optimal ambulation, a multi-professional research project was grounded with expertise from clinical rehabilitation, neurophysiology, and biomechanical engineering from Karolinska Institutet, the Spinalis Unit at Aleris Rehab Station (Sweden's largest center for specialized neurorehabilitation), and the Promobilia MoveAbility Lab at KTH Royal Institute of Technology. Ambulatory adults with paraplegia will be consecutively invited to participate. Muscle strength, sensitivity, and spasticity will be assessed, and energy expenditure, 3D movements, and muscle function (EMG) during gait and submaximal contractions will be analyzed. Innovative computational modeling and data-driven analyses will be performed, including the identification of clusters of similar movement patterns among the heterogeneous population and analyses that study the link between complex sensorimotor function and movement performance. These results may help optimize ambulatory function for persons with SCI and decrease the risk of secondary conditions during gait with a life-long perspective.

Innovative Prosthetic Hand Design: Integrating EMG Sensors and 3D Printing for Enhanced Usability

The development of affordable and user-friendly prosthetic hands presents a significant challenge within rehabilitation engineering, as traditional prosthetics often lack intuitive control and adaptability, adversely affecting user experience and daily functionality. This study proposes an innovative prosthetic hand that leverages advanced sensor technologies and 3D printing techniques to enhance usability and performance. Historically, prosthetic hands have been hindered by mechanical systems that do not facilitate effective user interaction, leading to frustration and limited functionality. By integrating electromyography (EMG) sensors, this research aims to bridge the gap between user needs and technological capabilities, enabling more responsive control based on natural muscle signals. The primary objectives include the utilization of advanced EMG sensors for intuitive control, the integration of real-time feedback mechanisms to enhance user interaction, and the design of a prosthetic hand that is both affordable and comfortable. Additionally, the study focuses on ensuring adaptability to accommodate diverse user requirements. Key features of the proposed design consist of EMG sensors for detecting muscle contractions, real-time feedback through LED displays, voltage sensors for battery monitoring, pressure sensors for adaptive grip strength, and the implementation of 3D printing for lightweight, customizable designs. Through this multifaceted approach, the study aims to significantly improve the quality of life for individuals requiring prosthetic support by delivering a solution that aligns with functional requirements while prioritizing user experience and accessibility. The findings are expected to pave the way for further innovations in prosthetic technology, ultimately making these devices more effective and accessible for users.

장애인 자가운전에 관한 체계적 문헌 고찰: 국내문헌을 중심으로

Objective: This study systematically analyzed and reviewed literature on self-driving for the disabled published in Korea over the past 10 years. Methods: We searched literature published between January 2014 and December 2023 in the Library of Congress, RISS, KISS, DBpia, and Google Scholar. The search terms “disabled” and “self-driving” were used, and a total of 469 documents were searched. Of these, 28 articles that met the selection criteria were analyzed. Results: Research published domestically on self-driving for the disabled was gradually decreasing. The most common type of published literature was academic journals. The first author who conducted literature research most often belonged to the Department of Occupational Therapy and the Department of Rehabilitation Science and Engineering, and the most common research area was the establishment of systems to promote and support self-driving for the disabled. The majority of research designs were experimental studies, but the overall level of research was confirmed to be low. Conclusion: Analyzing literature on self-driving for the disabled published domestically, we were able to understand the current status of research in our country. This study is significant as basic data that can be used as a reference when an advanced system that can support and guarantee self-driving for the disabled is introduced in Korea in the future.

Hybrid Soft-Rigid Active Prosthetics Laboratory Exercise for Hands-On Biomechanical and Biomedical Engineering Education.

This paper introduces a hands-on laboratory exercise focused on assembling and testing a hybrid soft-rigid active finger prosthetic for biomechanical and biomedical engineering (BME) education. This hands-on laboratory activity focuses on the design of a myoelectric finger prosthesis, integrating mechanical, electrical, sensor (i.e., inertial measurement units (IMUs), electromyography (EMG)), pneumatics, and embedded software concepts. We expose students to a hybrid soft-rigid robotic system, offering a flexible, modifiable lab activity that can be tailored to instructors' needs and curriculum requirements. All necessary files are made available in an open-access format for implementation. Off-the-shelf components are all purchasable through global vendors (e.g., DigiKey Electronics, McMaster-Carr, Amazon), costing approximately USD 100 per kit, largely with reusable elements. We piloted this lab with 40 undergraduate engineering students in a neural and rehabilitation engineering upper year elective course, receiving excellent positive feedback. Rooted in real-world applications, the lab is an engaging pedagogical platform, as students are eager to learn about systems with tangible impacts. Extensions to the lab, such as follow-up clinical (e.g., prosthetist) and/or technical (e.g., user-device interface design) discussion, are a natural means to deepen and promote interdisciplinary hands-on learning experiences. In conclusion, the lab session provides an engaging journey through the lifecycle of the prosthetic finger research and design process, spanning conceptualization and creation to the final assembly and testing phases.

The International Functional Electrical Stimulation Society (IFESS): Highlights from the IFESS conference at Rehabweek 2023.

The annual conference of the International Functional Electrical Stimulation Society (IFESS) was held in conjunction with the 7th RehabWeek Congress, from September 24 to 28, 2023 at the Resorts World Convention Centre on Sentosa Island, in Singapore. The Congress was a joint meeting of the International Consortium on Rehabilitation Technology (ICRT) together with 10 other societies in the field of assistive technology and rehabilitation engineering. The conference features comprehensive blend of technical and clinical context of FES, a sustained value the society has offered over many years. The cross- and inter- disciplinary approach of medicine, engineering, and science practiced in the FES community had enabled vibrant interaction, creation, and development of impactful and novel contributions to the field of FES, translating FES directly into highly relevant and sustainable solutions for the users.

Rehabilitation Engineering: A Narrative Review on Recent Advances in Mobility Aids in India.

Mobility has been characterized as the capacity to move across an environment safely, pleasantly, elegantly, and autonomously. India's current population is 1.4 billion, out of which 2.3%, i.e., 32 million people, are suffering from some kind of disability. With the rise in the geriatric population, the incidence of non-communicable and communicable diseases also rises and presents the risk of disorders that may progress to disability. People often neglect their disability and learn to live with it, even when most of them can use rehabilitation programs in conjunction with various mobility aids. Affordable access to adequate healthcare and assistive devices is limited, contributing to the challenges faced by disabled adults. Despite the potential for many disabled individuals to engage in productive work, their employment rates remain significantly lower. Mobility aids can provide significant benefits to individuals affected by a range of medical conditions, including arthritis, cerebral palsy, developmental disabilities, diabetic ulcers and wounds, fractures or broken bones, injuries, and walking impairments resulting from brain injury or stroke. Each person is different and may require help in a certain way for their disability, so choosing the most appropriate aid is crucial for the individual's well-being. Commonly used mobility aids are canes, walking sticks, walkers, and wheelchairs, with prostheses being used less commonly. With the advent of techniques such as state-of-the-art 3D printing and challenging surgeries, various Indian tech companies, along with non-governmental organizations (NGOs), have brought about many significant changes in the world of prosthesis by making it better, affordable, and accessible.

The influence of biomedical engineering in India

This comprehensive analysis delves into various crucial facets of biomedical engineering, covering cutting-edge technologies, creative methodologies, and ethical dilemmas. Quality Management Systems (QMS) play a pivotal role in maintaining precision, safety, and efficacy in lab experiments and biomedical product development, ensuring adherence to strict quality standards through guidelines like Good Laboratory Practice (GLP) and Good Manufacturing Practice (GMP). Advancements in medical imaging, from X-ray CT to molecular imaging, are revolutionizing disease diagnosis and treatment across multiple medical fields. Biomaterials and tissue engineering hold immense potential in regenerative medicine, addressing challenges like immune rejection and implant wear to meet diverse healthcare needs. Biomechanics and rehabilitation engineering merge biomechanical principles with assistive technologies to empower individuals with disabilities and improve their daily autonomy. Biomedical sensors, devices, and nanotechnology are driving personalized healthcare solutions, enhancing disease management through wearable and implantable technologies. Regulatory policies in India underscore the importance of strict regulations for medical devices and therapeutics to ensure safety and efficacy. Overall, this review highlights the transformative impact of biomedical engineering on healthcare advancements and societal well-being through responsible innovation and ethical practices.

Deep Learning for Enhanced Prosthetic Control: Real-Time Motor Intent Decoding for Simultaneous Control of Artificial Limbs.

The development of advanced prosthetic devices that can be seamlessly used during an individual's daily life remains a significant challenge in the field of rehabilitation engineering. This study compares the performance of deep learning architectures to shallow networks in decoding motor intent for prosthetic control using electromyography (EMG) signals. Four neural network architectures, including a feedforward neural network with one hidden layer, a feedforward neural network with multiple hidden layers, a temporal convolutional network, and a convolutional neural network with squeeze-and-excitation operations were evaluated in real-time, human-in-the-loop experiments with able-bodied participants and an individual with an amputation. Our results demonstrate that deep learning architectures outperform shallow networks in decoding motor intent, with representation learning effectively extracting underlying motor control information from EMG signals. Furthermore, the observed performance improvements by using deep neural networks were consistent across both able-bodied and amputee participants. By employing deep neural networks instead of a shallow network, more reliable and precise control of a prosthesis can be achieved, which has the potential to significantly enhance prosthetic functionality and improve the quality of life for individuals with amputations.

Bioelectronics for electrical stimulation: materials, devices and biomedical applications.

Bioelectronics is a hot research topic, yet an important tool, as it facilitates the creation of advanced medical devices that interact with biological systems to effectively diagnose, monitor and treat a broad spectrum of health conditions. Electrical stimulation (ES) is a pivotal technique in bioelectronics, offering a precise, non-pharmacological means to modulate and control biological processes across molecular, cellular, tissue, and organ levels. This method holds the potential to restore or enhance physiological functions compromised by diseases or injuries by integrating sophisticated electrical signals, device interfaces, and designs tailored to specific biological mechanisms. This review explains the mechanisms by which ES influences cellular behaviors, introduces the essential stimulation principles, discusses the performance requirements for optimal ES systems, and highlights the representative applications. From this review, we can realize the potential of ES based bioelectronics in therapy, regenerative medicine and rehabilitation engineering technologies, ranging from tissue engineering to neurological technologies, and the modulation of cardiovascular and cognitive functions. This review underscores the versatility of ES in various biomedical contexts and emphasizes the need to adapt to complex biological and clinical landscapes it addresses.

Maximizing stroke recovery with advanced technologies: A comprehensive assessment of robot-assisted, EMG-Controlled robotics, virtual reality, and mirror therapy interventions

Inconvenience caused by stroke brings physical disability found in many people which restricts their daily life activities. Globally, it was predicted that the prevalence of stroke will rise to 21.9 % by 2030. To improve the sensory and motor recovery of the stroke survivors, they required high attention for their controllability and adaptability. About 80 % of stroke victims have upper-limb motor deficits which affects their daily living activities. Due to technological advancement in rehabilitation engineering with new interventions, traditional physical therapy for stroke patients now translates into new rehabilitation strategies which help in fast recovery of motor tasks with intention motions. Electromyography (EMG) based stroke rehabilitation now being developed for enhancement and assessment of motion control in clinical settings. The integration of EMG-based intervention provides the feasibility to use the concept of myoelectric control with therapeutic settings. In this paper, the use of EMG-based robot aided therapy has been discussed and highlights the contribution of interventions for stroke rehabilitation. Furthermore, discussion also emphasis on virtual reality and mirror therapy and their latest interventions and approaches carried out by different investigators for the evaluations and assessment of stroke rehabilitation in lieu of considerations for improved functional motor task. The most widely used functional outcome measures for conducting clinical assessment of stroke patients in randomized control trials (RCTs) are Fugl-meyer assessment-upper extremity (FMA-UE), a score range from 0 to 66points, Fugl-meyer assessment for lower extremity (FMA-LE) has a score from 0 to 34 points, the Action Research Arm Test (ARAT), a scale from 0 to 57 points, the Functional independence measure (FIM) has a scale of 18–126 points, Modified Ashworth Scale (MAS), a scale from 0 to 5 points and Box and block test (BBT). Furthermore, in most of the RCTs the statistical significance was set at p < 0.05 (95 % confidence interval). Moreover, future directions suggested that for real time autonomous detection of motion intentions, the EMG-based machine learning must be involved with robots, virtual reality and mirror therapy-based interventions to achieve 95 % accuracy that could leads to the development of intelligent rehabilitation interventions for stroke survivors.

TECHNOLOGY AS A CATALYST FOR SUPPORTING AGING WITH DISABILITY

Abstract Individuals aging with long-term disabilities may need support to perform and participate in everyday activities associated with well-being and quality of life. Technology solutions have potential to effectively promote autonomy and aging-in-place for this population. This symposium will highlight technology research and development efforts from the Rehabilitation Engineering Research Center on Technologies to Support Aging-in-Place for People with Long-Term Disabilities (RERC TechSAge). TechSAge is dedicated to understanding the needs of, and developing supportive technologies for people aging with long-term vision, hearing, and mobility disabilities. Mumma et al. will present insights from interviews of adults aging with vision loss due to glaucoma and macular degeneration regarding their challenges and response strategies for everyday activities. Lee et al. will discuss findings from interview data exploring how wisdom is manifested from the lived experiences of individuals aging with disability (i.e., hearing, vision, and mobility). Mitzner et al. will describe characteristics of the participant sample from a clinical trial examining the effect of a Tele Tai Chi intervention on physical activity and social connectedness for adults aging with long-term mobility disabilities. Sanford et al. will present the findings from three TechSAge pilot projects focused on the use of technology to support in-home rehabilitation for individuals aging with long-term upper extremity disabilities: DigiHand, KeyStroke, and 3DP for AT. Together these studies illustrate the needs and coping strategies of older adults with disabilities and the potential of technology to support those needs. This is a collaborative symposium between the Lifelong Disabilities and Technology and Aging Interest Groups.

Selective chronic recording in small nerve fascicles of sciatic nerve with carbon nanotube yarns in rats

Objective. The primary challenge faced in the field of neural rehabilitation engineering is the limited advancement in nerve interface technology, which currently fails to match the mechanical properties of small-diameter nerve fascicles. Novel developments are necessary to enable long-term, chronic recording from a multitude of small fascicles, allowing for the recovery of motor intent and sensory signals. Approach. In this study, we analyze the chronic recording capabilities of carbon nanotube yarn electrodes in the peripheral somatic nervous system. The electrodes were surgically implanted in the sciatic nerve’s three individual fascicles in rats, enabling the recording of neural activity during gait. Signal-to-noise ratio (SNR) and information theory were employed to analyze the data, demonstrating the superior recording capabilities of the electrodes. Flat interface nerve electrode and thin-film longitudinal intrafascicular electrode electrodes were used as a references to assess the results from SNR and information theory analysis. Main results. The electrodes exhibited the ability to record chronic signals with SNRs reaching as high as 15 dB, providing 12 bits of information for the sciatic nerve, a significant improvement over previous methods. Furthermore, the study revealed that the SNR and information content of the neural signals remained consistent over a period of 12 weeks across three different fascicles, indicating the stability of the interface. The signals recorded from these electrodes were also analyzed for selectivity using information theory metrics, which showed an information sharing of approximately 1.4 bits across the fascicles. Significance. The ability to safely and reliably record from multiple fascicles of different nerves simultaneously over extended periods of time holds substantial implications for the field of neural and rehabilitation engineering. This advancement addresses the limitation of current nerve interface technologies and opens up new possibilities for enhancing neural rehabilitation and control.

A Decoding Method Using Riemannian Local Linear Feature Construction for a Lower-Limb Motor Imagery Brain–Computer Interface System

Recently, motor imagery brain–computer interfaces (BCIs) have been developed for use in motor function assistance and rehabilitation engineering. In particular, lower-limb motor imagery BCI systems are receiving increasing attention in the field of motor rehabilitation, because these systems could accurately and rapidly identify a patient’s lower-limb movement intention, which could improve the practicability of the motor rehabilitation. In this study, a novel lower-limb BCI system combining visual stimulation, auditory stimulation, functional electrical stimulation, and proprioceptive stimulation was designed to assist patients in lower-limb rehabilitation training. In addition, the Riemannian local linear feature construction (RLLFC) algorithm is proposed to improve the performance of decoding by using unsupervised basis learning and representation weight calculation in the motor imagery BCI system. Three in-house experiment were performed to demonstrate the effectiveness of the proposed system in comparison with other state-of-the-art methods. The experimental results indicate that the proposed system can learn low-dimensional features and correctly characterize the relationship between the testing trial and its k-nearest neighbors.

Design and Fabrication of Robotic arm for Multiple Degrees of Freedom Control

This paper details the design, construction, and evaluation of a highly flexible, high-precision robotic arm primarily used in prosthetic and rehabilitation engineering applications. The robotic arm was designed using 3D printing and SolidWorks and features a modular design that simplifies the manufacturing process and improves scalability. The arm has three degrees of freedom and is realized by a well-designed circuit program integrating ESP32 and STM32 microcontrollers. The structural integrity and functionality of the arm were verified through finite element analysis and kinematic simulation. The study also presents a novel path-planning algorithm for the robot arm, which is based on linear position and Gaussian velocity models and is effective in generating smooth, continuous, and physically constrained paths. This work provides an open-source solution that offers a cost-effective and robust platform for diverse robotics applications.

Skeletal muscle extracellular matrix structure under applied deformation observed using second harmonic generation microscopy

The mechanical and structural properties of passive skeletal muscle are important for musculoskeletal models in impact biomechanics, rehabilitation engineering and surgical simulation. Passive properties of skeletal muscle depend strongly on the architecture of the extracellular matrix (ECM), but the structure of ECM and its realignment under applied deformation remain poorly understood. We apply second harmonic generation (SHG) microscopy to study muscle ECM in intact muscle samples both under deformation and in the undeformed state. A method for regional relocation was developed, so that the same ECM segment could be viewed before and after applying deformations. Skeletal muscle ECM was viewed at multiple scales and in three states: undeformed, under compression and under tension. Results show that second harmonic generation microscopy provides substantial detail of skeletal muscle ECM over a wide range of length scales, especially the perimysium structure. We present images of individual portions of skeletal muscle ECM both undeformed and subjected to tensile/compressive deformation. We also present data showing the response of the perimysium to a partial thickness cut applied to a section under tensile deformation. Statement of significanceSecond Harmonic Generation (SHG) microscopy is an imaging technique which takes advantage of a non-linear and coherent frequency doubling optical effect that is present in a small number of biological molecules, primarily collagen Type I, II and myosin. Collagen I is the most abundant collagen type in skeletal muscle, making SHG a promising option for visualisation of the skeletal muscle extracellular matrix (ECM). SHG microscopy does not require fixing or staining. This short communication presents the application of SHG microscopy to skeletal muscle ECM to improve our understanding of how collagen fibres reorganise under applied tensile and compression, including microscopic observations of collagen fibre reorganisation for intact samples by using a method to re-identify specific regions in repeated deformation tests.