Preliminary Assessment of a Postural Synergy-Based Exoskeleton for Post-Stroke Upper Limb Rehabilitation.

Upper limb exoskeletons have drawn significant attention in neurorehabilitation because of the anthropomorphic mechanical structure analogous to human anatomy. Whereas, the training movements are typically unorganized because most exoskeletons ignore the natural movement characteristic of human upper limbs, particularly inter-joint postural synergy. This paper introduces a newly developed exoskeleton (Armule) for upper limb rehabilitation with a postural synergy design concept, which can reproduce activities of daily living (ADL) motion with the characteristics of human natural movements. The semitransparent active control strategy with the interactive force guidance and visual feedback ensured the active participation of users. Eight participants with hemiplegia due to a first-ever, unilateral stroke were recruited and included. They participated in exoskeleton therapy sessions for 4 weeks, with passive/active training under trajectories and postures with the characteristics of human natural movements. The primary outcome was the Fugl-Meyer Assessment for Upper Extremities (FMA-UE). The secondary outcomes were the Action Research Arm Test(ARAT), modified Barthel Index (mBI), and metric measured with the exoskeleton After the 4-weeks intervention, all subjects showed significant improvements in the following clinical measures: the FMA-UE (difference, 11.50 points, p = 0.002), the ARAT (difference, 7.75 points ), and the mBI (difference, 17.50 points, p = 0.003 ) score. Besides, all subjects showed significant improvements in kinematic and interaction force metrics measured with the exoskeleton. These preliminary results demonstrate that the Armule exoskeleton could improve individuals' motor control and ADL function after stroke, which might be associated with kinematic and interaction force optimization and postural synergy modification during functional tasks.

Modality alignment contrastive learning for severity assessment of COVID-19 from lung ultrasound and clinical information.

The outbreak of COVID-19 around the world has caused great pressure to the health care system, and many efforts have been devoted to artificial intelligence (AI)-based analysis of CT and chest X-ray images to help alleviate the shortage of radiologists and improve the diagnosis efficiency. However, only a few works focus on AI-based lung ultrasound (LUS) analysis in spite of its significant role in COVID-19. In this work, we aim to propose a novel method for severity assessment of COVID-19 patients from LUS and clinical information. Great challenges exist regarding the heterogeneous data, multi-modality information, and highly nonlinear mapping. To overcome these challenges, we first propose a dual-level supervised multiple instance learning module (DSA-MIL) to effectively combine the zone-level representations into patient-level representations. Then a novel modality alignment contrastive learning module (MA-CLR) is presented to combine representations of the two modalities, LUS and clinical information, by matching the two spaces while keeping the discriminative features. To train the nonlinear mapping, a staged representation transfer (SRT) strategy is introduced to maximumly leverage the semantic and discriminative information from the training data. We trained the model with LUS data of 233 patients, and validated it with 80 patients. Our method can effectively combine the two modalities and achieve accuracy of 75.0% for 4-level patient severity assessment, and 87.5% for the binary severe/non-severe identification. Besides, our method also provides interpretation of the severity assessment by grading each of the lung zone (with accuracy of 85.28%) and identifying the pathological patterns of each lung zone. Our method has a great potential in real clinical practice for COVID-19 patients, especially for pregnant women and children, in aspects of progress monitoring, prognosis stratification, and patient management.