Artificial intelligence-assisted diagnosis of ocular surface diseases.

With the rapid development of computer technology, the application of artificial intelligence (AI) in ophthalmology research has gained prominence in modern medicine. Artificial intelligence-related research in ophthalmology previously focused on the screening and diagnosis of fundus diseases, particularly diabetic retinopathy, age-related macular degeneration, and glaucoma. Since fundus images are relatively fixed, their standards are easy to unify. Artificial intelligence research related to ocular surface diseases has also increased. The main issue with research on ocular surface diseases is that the images involved are complex, with many modalities. Therefore, this review aims to summarize current artificial intelligence research and technologies used to diagnose ocular surface diseases such as pterygium, keratoconus, infectious keratitis, and dry eye to identify mature artificial intelligence models that are suitable for research of ocular surface diseases and potential algorithms that may be used in the future.

Robotic system for accurate percutaneous puncture guided by 3D-2D ultrasound.

PURPOSE: Ultrasound (US)-guided robotic systems can reduce the reliance on the experience and skills of surgeons and enable automatic and accurate percutaneous puncture. Two-dimensional (2D) and three-dimensional (3D) US guidance have various advantages and disadvantages. The planned puncture path in the US data directly affects the puncture quality and tissue injury risk. It is difficult to define the optimal path in 2D US images and achieve accurate and safe puncture under the guidance of 3D US volume. This study aims to propose a robotic system guided by 3D-2D US to realize accurate and safe percutaneous puncture. METHODS: We proposed a 3D-2D US-guided percutaneous puncture robotic system by integrating a 3D US scanning robotic system and a 2D US-guided puncture robotic system. The optimal spatial puncture path that targets the lesion and avoids other important tissues was determined in the 3D US volume reconstructed through robotic US scanning. Thereafter, the puncture robot was placed at the puncture site determined according to the planned path. The optimal path was mapped to the 2D US image taken at the puncture site. Finally, the 2D US image and puncture path were used to guide the robot in performing an accurate and safe percutaneous puncture. RESULTS: The proposed robotic system based on the guidance of 3D-2D US exhibits the advantages of both 3D US and 2D US to improve the accuracy of percutaneous puncture and reduce the risk of tissue injury. The experimental results of phantom puncture demonstrate that the mean puncture accuracy of the system is 1.09 ± 0.35 mm, and the puncture success rate with single needle insertion is 100%. CONCLUSION: A percutaneous puncture robotic system based on 3D-2D US guidance was proposed and tested successfully. The experimental results demonstrate the feasibility of the proposed system for achieving accurate and safe robotic percutaneous puncture.

Meibomian gland morphological changes in ocular herpes zoster patients based on AI analysis.

Varicella-zoster virus (VZV) infections result in a series of ophthalmic complications. Clinically, we also discover that the proportion of dry eye symptoms was significantly higher in patients with herpes zoster ophthalmicus (HZO) than in healthy individuals. Meibomian gland dysfunction (MGD) is one of the main reasons for dry eye. Therefore, we hypothesize that HZO may associate with MGD, affecting the morphology of meibomian gland (MG) because of immune response and inflammation. The purpose of this study is to retrospectively analyze the effect of HZO with craniofacial herpes zoster on dry eye and MG morphology based on an Artificial intelligence (AI) MG morphology analytic system. In this study, 26 patients were diagnosed as HZO based on a history of craniofacial herpes zoster accompanied by abnormal ocular signs. We found that the average height of all MGs of the upper eyelid and both eyelids were significantly lower in the research group than in the normal control group (p < 0.05 for all). The average width and tortuosity of all MGs for both upper and lower eyelids were not significantly different between the two groups. The MG density of the upper eyelid and both eyelids were significantly lower in the HZO group than in the normal control group (p = 0.020 and p = 0.022). Therefore, HZO may lead to dry eye, coupled with the morphological changes of MGs, mainly including a reduction in MG density and height. Moreover, it is important to control HZO early and timely, which could prevent potential long-term severe ocular surface injury.

Screening of Common Retinal Diseases Using Six-Category Models Based on EfficientNet.

Purpose: A six-category model of common retinal diseases is proposed to help primary medical institutions in the preliminary screening of the five common retinal diseases. Methods: A total of 2,400 fundus images of normal and five common retinal diseases were provided by a cooperative hospital. Two six-category deep learning models of common retinal diseases based on the EfficientNet-B4 and ResNet50 models were trained. The results from the six-category models in this study and the results from a five-category model in our previous study based on ResNet50 were compared. A total of 1,315 fundus images were used to test the models, the clinical diagnosis results and the diagnosis results of the two six-category models were compared. The main evaluation indicators were sensitivity, specificity, F1-score, area under the curve (AUC), 95% confidence interval, kappa and accuracy, and the receiver operator characteristic curves of the two six-category models were compared in the study. Results: The diagnostic accuracy rate of EfficientNet-B4 model was 95.59%, the kappa value was 94.61%, and there was high diagnostic consistency. The AUC of the normal diagnosis and the five retinal diseases were all above 0.95. The sensitivity, specificity, and F1-score for the diagnosis of normal fundus images were 100, 99.9, and 99.83%, respectively. The specificity and F1-score for RVO diagnosis were 95.68, 98.61, and 93.09%, respectively. The sensitivity, specificity, and F1-score for high myopia diagnosis were 96.1, 99.6, and 97.37%, respectively. The sensitivity, specificity, and F1-score for glaucoma diagnosis were 97.62, 99.07, and 94.62%, respectively. The sensitivity, specificity, and F1-score for DR diagnosis were 90.76, 99.16, and 93.3%, respectively. The sensitivity, specificity, and F1-score for MD diagnosis were 92.27, 98.5, and 91.51%, respectively. Conclusion: The EfficientNet-B4 model was used to design a six-category model of common retinal diseases. It can be used to diagnose the normal fundus and five common retinal diseases based on fundus images. It can help primary doctors in the screening for common retinal diseases, and give suitable suggestions and recommendations. Timely referral can improve the efficiency of diagnosis of eye diseases in rural areas and avoid delaying treatment.

Automatic and accurate needle detection in 2D ultrasound during robot-assisted needle insertion process.

PURPOSE: Robot-assisted needle insertion guided by 2D ultrasound (US) can effectively improve the accuracy and success rate of clinical puncture. To this end, automatic and accurate needle-tracking methods are important for monitoring puncture processes, avoiding the needle deviating from the intended path, and reducing the risk of injury to surrounding tissues. This work aims to develop a framework for automatic and accurate detection of an inserted needle in 2D US image during the insertion process. METHODS: We propose a novel convolutional neural network architecture comprising of a two-channel encoder and single-channel decoder for needle segmentation using needle motion information extracted from two adjacent US image frames. Based on the novel network, we further propose an automatic needle detection framework. According to the prediction result of the previous frame, a region of interest of the needle in the US image was extracted and fed into the proposed network to achieve finer and faster continuous needle localization. RESULTS: The performance of our method was evaluated based on 1000 pairs of US images extracted from robot-assisted needle insertions on freshly excised bovine and porcine tissues. The needle segmentation network achieved 99.7% accuracy, 86.2% precision, 89.1% recall, and an F1-score of 0.87. The needle detection framework successfully localized the needle with a mean tip error of 0.45 ± 0.33 mm and a mean orientation error of 0.42° ± 0.34° and achieved a total processing time of 50 ms per image. CONCLUSION: The proposed framework demonstrated the capability to realize robust, accurate, and real-time needle localization during robot-assisted needle insertion processes. It has a promising application in tracking the needle and ensuring the safety of robotic-assisted automatic puncture during challenging US-guided minimally invasive procedures.

Intelligent Segmentation of Intima-Media and Plaque Recognition in Carotid Artery Ultrasound Images.

Ultrasound imaging has been established as an effective method for measuring the thickness of the intima-media, the thickening of which, along with carotid plaque, is an indicator of cerebrovascular diseases. Here, a 2-D V-Net model that can automatically segment the intima-media in carotid artery ultrasound images is proposed. Moreover, a plaque recognition algorithm that automatically identifies plaque-affected areas is described. Performance tests to determine the average accuracy of the intima-media segmentation yielded the following results (expressed as lumen-intima boundary/media-adventitia boundary): intersection over union (IOU) of 0.752/0.813, pixel accuracy of 0.813/0.885 and Dice loss of 0.858/0.897. Finally, average IOU of 0.785, pixel accuracy of 0.825 and Dice loss of 0.866 were obtained for plaque recognition. These results satisfy the threshold for clinical application and indicate that the proposed model can assist doctors in making more efficient and accurate diagnoses.

Automatic ultrasound scanning robotic system with optical waveguide-based force measurement.

PURPOSE: The three-dimensional (3D) ultrasound (US) imaging realized by continuous scanning of a region is of great value for medical diagnosis and robot-assisted needle insertion. During scanning, the contact force and posture between the probe and skin of the patient are crucial factors that determine the quality of US imaging. We propose a robotic system for automatic scanning of curved surfaces with a stable contact force and vertical contact posture (the probe is parallel to the normal of the surface at the contact point). METHODS: A 6-DOF robotic arm is used to hold and drive a two-dimensional (2D) US probe to complete automatic scanning. Further, a path-planning strategy is proposed to generate the scan path covering the selected area automatically. We also developed a novel force-measuring device based on optical waveguides to measure the distributed contact force and contact posture. Based on the measured force and posture, the robotic arm automatically adjusts the position and orientation of the probe and maintains a stable contact force and vertical contact posture at each scan point. RESULTS: The novel force-measuring device is easy to fabricate, integrates with the probe and has the capacity of measuring the force distributed on the contact surface and estimating the contact posture. The experimental results of automatic scanning of a US phantom and parts of the human body demonstrate that the proposed system performs well in automatically scanning curved surfaces, maintaining a stable contact force and vertical contact posture and producing a good quality 3D US volume. CONCLUSION: An automatic US scanning robotic system with an optical waveguide-based force-measuring device was developed and tested successfully. Experimental results demonstrated the feasibility of the proposed system to scan the human body.

A cable-driven distal end-effector mechanism for single-port robotic surgery.

PURPOSE: The development of surgery is to be minimally invasive and collaborative with robot systems, which has caught increasing attention in recent years. However, the narrow access routes and confined working spaces in vivo usually make distal end-effectors of surgical systems not easy to operate. To overcome this problem, a novel cable-driven distal end-effector mechanism designed for single-port robotic surgery was proposed. METHODS: A cable-driven joint structure and the corresponding methods of threading cables were proposed which can maintain the length and even the tension force of cables constant during operation. Based on the proposed joint structure, the cable-driven distal end-effector mechanism consists of a parallelogram mechanism and a snake mechanism. The parallelogram mechanism is used to enlarge its reachable workspace through establishing the triangulation of operation. The snake mechanism is used to achieve the expected pose through providing sufficient bending degrees of freedom. All of the degrees of freedom can be decoupled at the expense of a slightly more tedious process of threading cables. RESULTS: The primary prototype and its miniature assembled and threaded manually performed as expected regardless of bend, translation and their combination. But the inadequate tension force of cables and assembly errors affect the load capacity and accuracy, which need to be improved by automatic assembly. CONCLUSION: A cable-driven distal end-effector mechanism composed of a parallelogram mechanism, and a snake mechanism used for single-port robotic surgery was proposed. The mechanism adopts a novel cable-driven joint structure and corresponding methods of threading cables to keep the length and even the tension force of cables constant during surgery.

Diabetes mellitus as a risk factor for retinal vein occlusion: A meta-analysis.

Retinal vein occlusion (RVO) is the second most common etiology for vision loss. There is contrasting evidence on the association between diabetes mellitus (DM) and the risk of RVO. We performed a meta-analysis of published articles before October 31, 2019, to estimate a pooled odds ratio for the association between DM and RVO, including central and branch RVO by a fixed or random effects model. We identified 37 publications from 38 studies (1 publication was from 2 studies), published between 1985 and 2019. In total, 148,654 cases and 23,768,820 controls were included in this meta-analysis. The results of pooled analysis for all 37 publications (or 38 studies) showed a significant association between DM and the risk of RVO (OR = 1.68, 95% CI: 1.43-1.99). Subgroup analysis indicated that DM was significantly associated with CRVO (OR = 1.98, 95% CI: 1.29-3.03, I = 67.9%), but not significantly associated with BRVO (OR = 1.22, 95% CI: 0.95-1.56, I = 64.1%). In conclusion, the result of present meta-analysis suggested that DM is a risk factor for RVO. More well-designed studies on the relationship between RVO and DM should be undertaken in the future.

Association between MDM2 rs2279744, MDM2 rs937283, and p21 rs1801270 polymorphisms and retinoblastoma susceptibility.

Retinoblastoma (Rb) is the most common intra-ocular malignancy in children. The association of rs2279744, and rs937283 in MDM2 gene, and p21 rs1801270 polymorphism and RB development have been demonstrated. To provide a comprehensive assessment of and to clarify associations between the 3 SNPs (MDM2 rs2279744, MDM2 rs937283, and p21 rs1801270) and the risk of RB, we performed a meta-analysis of all the eligible case-control studies. We searched English databases include PubMed, Embase, Google Scholar, and Cochrane Library, using an upper date limit of January 1, 2018. The association between MDM2 rs2279744, MDM2 rs937283, and p21 rs1801270 polymorphisms and the risk of RB were estimated by calculating a pooled OR and 95% CI under a homozygote comparison, heterozygote comparison, dominant model, and recessive model. The statistical power analysis was performed using G*Power. Our meta-analysis showed a significant association between RB susceptibility and MDM2 rs2279744 recessive model (OR = 1.427, 95%CI: 1.107-1.840, P = .006, I = 0%). Moreover, a significant link was observed between RB risk and MDM2 rs937283 homozygote comparison (OR = 0.471, 95%CI: 0.259-0.858, P = .014, I = 0%) and recessive model (OR = 0.587, 95%CI: 0.410-0.840, P = .004, I = 0%). However, no significant relationship between the p21 rs1801270 polymorphism and RB susceptibility was detected in any of the 4 models (P > .05). In conclusion, we found that significant association between the MDM2 rs2279744 polymorphism and increased RB risk, while MDM2 rs937283 polymorphism was associated with significantly decreased RB risk. However, as to the P21 rs1801270 polymorphism, a statistically significant association was not identified for RB.

An original design of remote robot-assisted intubation system.

The success rate of pre-hospital endotracheal intubation (ETI) by paramedics is lower than physicians. We aimed to establish a remote robot-assisted intubation system (RRAIS) and expected it to improve success rate of pre-hospital ETI. To test the robot's feasibility, 20 pigs were intubated by direct laryngoscope or the robot system. Intubation time, success rate, airway complications were recorded during the experiment. The animal experiment showed that participants achieved a higher success rate in absolute numbers by the robot system. In summary, we have successfully developed a remote robot-assisted intubation system. It is promising for RRAIS to improve the success rate of pre-hospital ETI and change the current rescue model.

A novel optimal coordinated control strategy for the updated robot system for single port surgery.

BACKGROUND: Research into robotic systems for single port surgery (SPS) has become widespread around the world in recent years. A new robot arm system for SPS was developed, but its positioning platform and other hardware components were not efficient. Special features of the developed surgical robot system make good teleoperation with safety and efficiency difficult. METHODS: A robot arm is combined and used as new positioning platform, and the remote center motion is realized by a new method using active motion control. A new mapping strategy based on kinematics computation and a novel optimal coordinated control strategy based on real-time approaching to a defined anthropopathic criterion configuration that is referred to the customary ease state of human arms and especially the configuration of boxers' habitual preparation posture are developed. RESULTS: The hardware components, control architecture, control system, and mapping strategy of the robotic system has been updated. A novel optimal coordinated control strategy is proposed and tested. CONCLUSIONS: The new robot system can be more dexterous, intelligent, convenient and safer for preoperative positioning and intraoperative adjustment. The mapping strategy can achieve good following and representation for the slave manipulator arms. And the proposed novel control strategy can enable them to complete tasks with higher maneuverability, lower possibility of self-interference and singularity free while teleoperating.

Efficacy of fibrin glue versus sutures for attaching conjunctival autografts in pterygium surgery: a systematic review with meta-analysis and trial sequential analysis of evidence.

Previous meta-analyses have been conducted to compare the efficacy of fibrin glue (FG) versus sutures in pterygium surgery; however, additional clinical trials have since been published. Therefore, we conducted an updated meta-analysis to further explore the association between FG application in pterygium surgery, and the recurrence rate, complication rate, and surgical duration. An electronic literature search for eligible studies published before July 29, 2016 was conducted across multiple databases. Odds ratios (ORs), standardized mean difference (SMD), and 95% confidence intervals (CI) were calculated. Publication bias of the included articles was evaluated by funnel plots. Differences in recurrence rate and complication rate between the FG and suture groups were evaluated in terms of OR with 95% CI, and SMD with 95% CI were used to estimate the difference in surgical duration. Trial sequential analysis (TSA) was used to determine whether the currently available evidence was sufficient and conclusive. Twenty-four studies were included in this study. The pooled ORs for recurrence rate and complication rate were 0.35 and 1.121, respectively. The pooled SMD for surgical duration was -4.142. The TSA results indicated that evidence of the effect was sufficient in the recurrence group and surgical duration group. Although there was no difference in complication rate between FG and sutures, the apparent advantages of FG over sutures are shorter surgical duration and greater reduction in the recurrence rate of pterygium.

Ubiquitous Robotic Technology for Smart Manufacturing System.

As the manufacturing tasks become more individualized and more flexible, the machines in smart factory are required to do variable tasks collaboratively without reprogramming. This paper for the first time discusses the similarity between smart manufacturing systems and the ubiquitous robotic systems and makes an effort on deploying ubiquitous robotic technology to the smart factory. Specifically, a component based framework is proposed in order to enable the communication and cooperation of the heterogeneous robotic devices. Further, compared to the service robotic domain, the smart manufacturing systems are often in larger size. So a hierarchical planning method was implemented to improve the planning efficiency. A test bed of smart factory is developed. It demonstrates that the proposed framework is suitable for industrial domain, and the hierarchical planning method is able to solve large problems intractable with flat methods.