In this paper, we explore the use of deep learning (DL) in conjunction with photogrammetry for scanning amputated limbs. Combining these two technologies can expand the scope of prosthetic telemedicine by facilitating low-cost limb scanning using cell phones. Previous research identified image segmentation as one of the main limitations of using photogrammetry for limb scanning. Based on those limitations, this work sought to answer two main research questions: (1) Can a neural network be trained to identify and segment an amputated limb automatically? (2) Will segmenting 2D limb images using neural networks impact the accuracy of 3D models generated via photogrammetry? To answer the first question, transfer learning was applied to a neural network with the DeepLabv3 architecture. After training, the model was able to successfully identify and segment limb images with an IoU of 79.9\%. To answer the second question, the fine-tuned DL model was applied to a dataset of 22 scans comprising 6312 limb images, then 3D models were rendered utilizing Agisoft Metashape. The Mean Absolute Error (MAE) of models rendered from images segmented with DL was 0.57 mm ± 0.63 mm when compared to models rendered from ground truth images. These results are important because segmentation with DL makes photogrammetry for limb scanning feasible on a large clinical scale. Future work should focus on generalizing the segmentation model for different types of amputations and imaging conditions.

Additive manufacturing is one of the most promising emerging technologies for building prosthetic sockets. However, there is no reliable way to estimate the factor of safety and the lifetime of 3D printed prosthetic sockets. Here, we explore 360° 3D digital image correlation (DIC) and discover how this new tool can increase our understanding of prosthetic structural failures. We establish that this new technology can dramatically improve the prosthetic design cycle by identifying local strain concentrations and by highlighting limitations in current simulated models. Overall, 360° 3D DIC technology empowers prosthetic engineers to characterize the performance of new materials and create innovative designs that are both safe and affordable.

Abstract—Recent trends in the field of prosthetic technology are shifting towards all-digital approaches. These digital technologies have the potential to augment the current models of clinical healthcare and reach more amputees than currently possible. Unfortunately, most of the equipment needed to design and build digitally shaped prostheses is expensive or requires a high level of expertise. Objective: This paper developed several methods to enable the digital fabrication of prostheses using only low cost tools that do not require extensive specialized training. Methods: The authors built a cell phone application in Android Studio that enables automated collection of image data which can be rendered into accurate 3D-models using photogrammetry on a remote server. They then developed a new protocol to shape these residual limb models into functional prosthetic sockets using the freely available software Autodesk Meshmixer. Results: Finally, the authors ran a case study where they rectified a prosthetic socket for an amputee and compared this model to a socket built by a clinician. Conclusion: This case study showed that these new methods can successfully create accurate and functional prosthetic sockets. Significance: By leveraging ubiquitous low cost smartphone technology, the authors believe that amputees in underserved areas, who currently face large barriers both in cost and physical access to proper care, could soon be able to obtain affordable prosthetic limbs.

Digital healthcare technologies are transforming the face of prosthetic care. Millions of amputees around the world do not currently have access to any form of prosthetic healthcare. However, digital technologies provide a promising solution. Digital healthcare technologies have the potential to augment the range and efficiency of prosthetists so they can reach more patients. These technologies will enable affordable prostheses to be built on a scale larger than currently possible with today’s clinical practices. In this paper, we explore the social aspects of amputation as a global issue, describe current practices for designing and manufacturing prosthetic sockets, and examine shifting trends towards virtual care models. Importantly, we assess the technologies used in these virtual health workflows to understand their critical needs. Large technological gaps need to be overcome in order to enable the mass production and distribution of prostheses digitally. However, recent advances in computational methods and CAD/CAM technologies are bridging this gap faster than ever before. We foresee that these technologies will return mobility and economic opportunity to amputees on a global scale in the near future.