Algorithmic detection of facial palsy offers the potential to improve current practices, which usually involve labor-intensive and subjective assessments by clinicians. In this paper, we present a multimodal fusion-based deep learning model that utilizes an MLP mixer-based model to process unstructured data (i.e. RGB images or images with facial line segments) and a feed-forward neural network to process structured data (i.e. facial landmark coordinates, features of facial expressions, or handcrafted features) for detecting facial palsy. We then contribute to a study to analyze the effect of different data modalities and the benefits of a multimodal fusion-based approach using videos of 20 facial palsy patients and 20 healthy subjects. Our multimodal fusion model achieved 96.00 F1, which is significantly higher than the feed-forward neural network trained on handcrafted features alone (82.80 F1) and an MLP mixer-based model trained on raw RGB images (89.00 F1).

In this paper, we present how Bell's Palsy, a neurological disorder, can be detected just from a subject's eyes in a video. We notice that Bell's Palsy patients often struggle to blink their eyes on the affected side. As a result, we can observe a clear contrast between the blinking patterns of the two eyes. Although previous works did utilize images/videos to detect this disorder, none have explicitly focused on the eyes. Most of them require the entire face. One obvious advantage of having an eye-focused detection system is that subjects' anonymity is not at risk. Also, our AI decisions based on simple blinking patterns make them explainable and straightforward. Specifically, we develop a novel feature called blink similarity, which measures the similarity between the two blinking patterns. Our extensive experiments demonstrate that the proposed feature is quite robust, for it helps in Bell's Palsy detection even with very few labels. Our proposed eye-focused detection system is not only cheaper but also more convenient than several existing methods.

Abstract: "Tendon-transfer surgeries are performed for a variety of conditions such as stroke, palsies, trauma, and congenital defects. The surgery involves re-routing a tendon from a nonfunctioning muscle to a functioning muscle to partially restore lost function. However, a fundamental aspect of the current surgery, namely the suture that attaches the tendon(s) to the muscles, can lead to poor post-surgery function. For example, in the hand tendon-transfer surgery for high median-ulnar palsy, one muscle is sutured to all four finger flexor tendons. This couples finger movement, prevents the fingers from adapting to an object's shape while grasping, and leads to poor hand function overall. This project investigates the design and use of miniature passive differential mechanisms, such as pulleys and links, as implants to attach the muscles and tendons in place of the direct suture. Results from biomechanical simulations and human cadaver experiments show that the new surgical procedure results in significantly better hand function in terms of finger movement and reduced actuator-force requirement in grasping tasks. The long-term goal is to enable re-engineering the mechanics of movement and force transmission from within the body using robotic devices."

An exoskeleton suit has helped children with cerebral palsy to walk. Experts tested the device on seven children that are suffering from the disorder in a clinical trial. Each of them were having difficulty walking, with their knees starting to slope inwards. But a video of them walking in the exoskeleton suit showed noticeable improvements. It helped to improve knee extension for the children and made their walking more fluid while wearing the device.