This article presents an overview of the current state of research and application of haptic (primarily kinesthetic) feedback and force-based teleoperation in the context of surgical robotics. Telerobotic surgery provides an approach for transferring the sensorimotor skills of a surgeon through a robotic platform to perform surgical intervention inside a patient’s body. Integration of advanced sensing and haptic technologies in telerobotic surgery can help to enhance the sensory awareness and motor accuracy of the surgeon, thereby leading to improved surgical procedures and outcomes for patients. The primary mode of sensory feedback has been through 3-D visual observation using stereo endoscopes. However, until recently, the sense of touch, i.e., haptics, has been missing in the commercial telesurgery robots approved for use in the operating room despite over two decades of research and development in the field of haptics for teleoperated systems (“telehaptics”). Research has shown that high-fidelity force feedback can enhance the performance of telesurgery and potential outcomes by enabling the surgeon to have a more natural feel of interaction between surgical tools and tissue as normally experienced during open surgery. Interaction forces, such as those generated during palpation of tissue, insertion of a needle, unintentional (and potentially unsafe) exertion of force by a tool, suture breakage, needle slippage, or tool interaction, are replaced by indirect (virtual) sensations, termed visual haptics, which provides an alternative to sensory compensation. Although there is a significant amount of literature supporting this benefit, there are still several important technical challenges in introducing haptics in telesurgery, including instrumentation, fidelity (transparency), stability, and modalities for force reflection, e.g., direct or indirect. This article examines these challenges and discusses recent work on haptics-based teleoperated surgical robotic systems.

This work is motivated by the recent advances in Deep Neural Networks (DNNs) and their widespread applications in human-machine interfaces. DNNs have been recently used for detecting the intended hand gesture through the processing of surface electromyogram (sEMG) signals. Objective: Although DNNs have shown superior accuracy compared to conventional methods when large amounts of data are available for training, their performance substantially decreases when data are limited. Collecting large datasets for training may be feasible in research laboratories, but it is not a practical approach for real-life applications. The main objective of this work is to design a modern DNN-based gesture detection model that relies on minimal training data while providing high accuracy. Methods: We propose the novel Few-Shot learning- Hand Gesture Recognition (FS-HGR) architecture. Few-shot learning is a variant of domain adaptation with the goal of inferring the required output based on just one or a few training observations. The proposed FS-HGR generalizes after seeing very few observations from each class by combining temporal convolutions with attention mechanisms. This allows the meta-learner to aggregate contextual information from experience and to pinpoint specific pieces of information within its available set of inputs. Data Source & Summary of Results: The performance of FS-HGR was tested on the second and fifth Ninapro databases, referred to as the DB2 and DB5, respectively. The DB2 consists of 50 gestures (rest included) from 40 healthy subjects. The Ninapro DB5 contains data from 10 healthy participants performing a total of 53 different gestures (rest included). The proposed approach for the Ninapro DB2 led to 85.94% classification accuracy on new repetitions with few-shot observation (5-way 5-shot), 81.29% accuracy on new subjects with few-shot observation (5-way 5-shot), and 73.36% accuracy on new gestures with few-shot observation (5-way 5-shot). Moreover, the proposed approach for the Ninapro DB5 led to 64.65% classification accuracy on new subjects with few-shot observation (5-way 5-shot).

While conventional bilateral Single-Master/Single-Slave (SM/SS) teleoperation systems have received considerable attention during the past several decades, multilateral teleoperation is only recently being studied. Unlike an SM/SS system, which consists of one master-slave set, multilateral teleoperation frameworks involve a minimum of three agents in order to remotely perform a task. This paper presents an overview of multilateral teleoperation systems and classifies the existing state-of-the-art architecture based on topologies, applications, and closed-loop stability analysis. For each category, the review discusses control strategies used for various architectures as well as control challenges (e.g., closed-loop instability as a result of a delay in the communication network) for each methodology.

The newly discovered Coronavirus Disease 2019 (COVID-19) has been globally spreading and causing hundreds of thousands of deaths around the world as of its first emergence in late 2019. The rapid outbreak of this disease has overwhelmed health care infrastructures and arises the need to allocate medical equipment and resources more efficiently. The early diagnosis of this disease will lead to the rapid separation of COVID-19 and non-COVID cases, which will be helpful for health care authorities to optimize resource allocation plans and early prevention of the disease. In this regard, a growing number of studies are investigating the capability of deep learning for early diagnosis of COVID-19. Computed tomography (CT) scans have shown distinctive features and higher sensitivity compared to other diagnostic tests, in particular the current gold standard, i.e., the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Current deep learning-based algorithms are mainly developed based on Convolutional Neural Networks (CNNs) to identify COVID-19 pneumonia cases. CNNs, however, require extensive data augmentation and large datasets to identify detailed spatial relations between image instances. Furthermore, existing algorithms utilizing CT scans, either extend slice-level predictions to patient-level ones using a simple thresholding mechanism or rely on a sophisticated infection segmentation to identify the disease. In this paper, we propose a two-stage fully automated CT-based framework for identification of COVID-19 positive cases referred to as the “COVID-FACT”. COVID-FACT utilizes Capsule Networks, as its main building blocks and is, therefore, capable of capturing spatial information. In particular, to make the proposed COVID-FACT independent from sophisticated segmentations of the area of infection, slices demonstrating infection are detected at the first stage and the second stage is responsible for classifying patients into COVID and non-COVID cases. COVID-FACT detects slices with infection, and identifies positive COVID-19 cases using an in-house CT scan dataset, containing COVID-19, community acquired pneumonia, and normal cases. Based on our experiments, COVID-FACT achieves an accuracy of 90.82%, a sensitivity of 94.55%, a specificity of 86.04%, and an Area Under the Curve (AUC) of 0.98, while depending on far less supervision and annotation, in comparison to its counterparts.

Blind source separation (BSS) algorithms, such as the gradient convolution kernel compensation (gCKC), can efciently and accurately decompose high-density surface electromyography (HD-sEMG) signals into the constituent motor unit (MU) action potential trains. Once the separation matrix is blindly estimated on a signal interval, it is also possible to apply the same matrix to subsequent signal segments. Nonetheless, the trained separation matrices are sub-optimal in noisy conditions and require that incoming data undergo computationally expensive whitening. One unexplored alternative is to instead use the paired HD-sEMG signal and BSS output to train a model to predict MU activations within a supervised learning framework. A gated recurrent unit (GRU) network was trained to decompose both simulated and experimental unwhitened HD-sEMG signal using the output of the gCKC algorithm. The results on the experimental data were validated by comparison with the decomposition of concurrently recorded intramuscular EMG signals. The GRU network outperformed gCKC at low signal-to-noise ratios, proving superior performance in generalising to new data. Using 12 seconds of experimental data per recording, the GRU performed similarly to gCKC, at rates of agreement of 92.5% (84.5% - 97.5%) and 94.9% (88.8% - 100.0%) respectively for GRU and gCKC against matched intramuscular sources.

The unprecedented shock caused by the COVID-19 pandemic has severely influenced the delivery of regular healthcare services. Most non-urgent medical activities, including elective surgeries, have been paused to mitigate the risk of infection and to dedicate medical resources to managing the pandemic. In this regard, not only surgeries are substantially influenced, but also pre- and post-operative assessment of patients and training for surgical procedures have been significantly impacted due to the pandemic. Many countries are planning a phased reopening, which includes the resumption of some surgical procedures. However, it is not clear how the reopening safe-practice guidelines will impact the quality of healthcare delivery. This perspective article evaluates the use of robotics and AI in 1) robotics-assisted surgery, 2) tele-examination of patients for pre- and post-surgery, and 3) tele-training for surgical procedures. Surgeons interact with a large number of staff and patients on a daily basis. Thus, the risk of infection transmission between them raises concerns. In addition, pre- and post-operative assessment also raises concerns about increasing the risk of disease transmission, in particular, since many patients may have other underlying conditions, which can increase their chances of mortality due to the virus. The pandemic has also limited the time and access that trainee surgeons have for training in the OR and/or in the presence of an expert. In this article, we describe existing challenges and possible solutions and suggest future research directions that may be relevant for robotics and AI in addressing the three tasks mentioned above.