Novel miniature transendoscopic telerobotic system for endoscopic submucosal dissection (with videos).

BACKGROUND AND AIMS: The lack of tissue traction and instrument dexterity to allow for adequate visualization and effective dissection were the main issues in performing endoscopic submucosal dissection (ESD). Robot-assisted systems may provide advantages. In this study we developed a novel transendoscopic telerobotic system and evaluated its performance in ESD. METHODS: A miniature dual-arm robotic endoscopic assistant for minimally invasive surgery (DREAMS) was developed. The DREAMS system contained the current smallest robotic ESD instruments and was compatible with the commercially available dual-channel endoscope. After the system was established, a prospective randomized controlled study was conducted to validate the performance of the DREAMS-assisted ESD in terms of efficacy, safety, and workload by comparing it with the conventional technique. RESULTS: Two robotic instruments can achieve safe collaboration and provide sufficient visualization and efficient dissection during ESD. Forty ESDs in the stomach and esophagus of 8 pigs were completed by DREAMS-assisted ESD or conventional ESD. Submucosal dissection time was comparable between the 2 techniques, but DREAMS-assisted ESD demonstrated a significantly lower muscular injury rate (15% vs 50%, P = .018) and workload scores (22.30 vs 32.45, P < .001). In the subgroup analysis of esophageal ESD, DREAMS-assisted ESD showed significantly improved submucosal dissection time (6.45 vs 16.37 minutes, P = .002), muscular injury rate (25% vs 87.5%, P = .041), and workload (21.13 vs 40.63, P = .001). CONCLUSIONS: We developed a novel transendoscopic telerobotic system, named DREAMS. The safety profile and technical feasibility of ESD were significantly improved with the assistance of the DREAMS system, especially in the narrower esophageal lumen.

Federated Semi-Supervised Learning for Medical Image Segmentation via Pseudo-Label Denoising.

Distributed big data and digital healthcare technologies have great potential to promote medical services, but challenges arise when it comes to learning predictive model from diverse and complex e-health datasets. Federated Learning (FL), as a collaborative machine learning technique, aims to address the challenges by learning a joint predictive model across multi-site clients, especially for distributed medical institutions or hospitals. However, most existing FL methods assume that clients possess fully labeled data for training, which is often not the case in e-health datasets due to high labeling costs or expertise requirement. Therefore, this work proposes a novel and feasible approach to learn a Federated Semi-Supervised Learning (FSSL) model from distributed medical image domains, where a federated pseudo-labeling strategy for unlabeled clients is developed based on the embedded knowledge learned from labeled clients. This greatly mitigates the annotation deficiency at unlabeled clients and leads to a cost-effective and efficient medical image analysis tool. We demonstrated the effectiveness of our method by achieving significant improvements compared to the state-of-the-art in both fundus image and prostate MRI segmentation tasks, resulting in the highest Dice scores of 89.23% and 91.95% respectively even with only a few labeled clients participating in model training. This reveals the superiority of our method for practical deployment, ultimately facilitating the wider use of FL in healthcare and leading to better patient outcomes.

Mapping Drug-Induced Neuropathy through In-Situ Motor Protein Tracking and Machine Learning.

Chemotherapy can induce toxicity in the central and peripheral nervous systems and result in chronic adverse reactions that impede continuous treatment and reduce patient quality of life. There is a current lack of research to predict, identify, and offset drug-induced neurotoxicity. Rapid and accurate assessment of potential neuropathy is crucial for cost-effective diagnosis and treatment. Here we report dynamic near-infrared upconversion imaging that allows intraneuronal transport to be traced in real time with millisecond resolution, but without photobleaching or blinking. Drug-induced neurotoxicity can be screened prior to phenotyping, on the basis of subtle abnormalities of kinetic characteristics in intraneuronal transport. Moreover, we demonstrate that combining the upconverting nanoplatform with machine learning offers a powerful tool for mapping chemotherapy-induced peripheral neuropathy and assessing drug-induced neurotoxicity.

Fully organic compliant dry electrodes self-adhesive to skin for long-term motion-robust epidermal biopotential monitoring.

Wearable dry electrodes are needed for long-term biopotential recordings but are limited by their imperfect compliance with the skin, especially during body movements and sweat secretions, resulting in high interfacial impedance and motion artifacts. Herein, we report an intrinsically conductive polymer dry electrode with excellent self-adhesiveness, stretchability, and conductivity. It shows much lower skin-contact impedance and noise in static and dynamic measurement than the current dry electrodes and standard gel electrodes, enabling to acquire high-quality electrocardiogram (ECG), electromyogram (EMG) and electroencephalogram (EEG) signals in various conditions such as dry and wet skin and during body movement. Hence, this dry electrode can be used for long-term healthcare monitoring in complex daily conditions. We further investigated the capabilities of this electrode in a clinical setting and realized its ability to detect the arrhythmia features of atrial fibrillation accurately, and quantify muscle activity during deep tendon reflex testing and contraction against resistance.