Photoactivation of Solid-State Fluorescence through Controllable Intermolecular [2+2] Photodimerization.

Intermolecular [2+2] photodimerization provides a distinctive approach to construct photoresponsive fluorescent materials in a manner of switching on solid-state fluorescence. Herein, we report efficient photoactivation of bright solid-state fluorescence based on controllable intermolecular [2+2] photodimerization reaction of benzo[b]thiophene 1,1-dioxide (BTO) derivatives, which provides a simple and effective way to construct smart photoresponsive solid-state fluorescent materials. Rational choice of substituents in BTO molecular skeleton enables them to efficiently undergo photodimerization through regulating molecular stacking in crystal, and also leads to photoactivation of solid-state fluorescence due to the generation of brightly fluorescent photodimers. This intermolecular photodimerization reaction also offers an effective method to synthesize photostable AIEgens with purely through-space conjugation.

Drusen-aware model for age-related macular degeneration recognition.

INTRODUCTION: The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age-related changes by using drusen masks for spatial feature supervision. METHODS: A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre-processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver-operating characteristic (AUC). Fivefold cross-validation was performed, and the results compared with four other methods. RESULTS: Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01). CONCLUSION: The proposed drusen-aware model outperformed baseline and other vessel feature-based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five-category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real-life clinical setting.

Multi-user upper limb rehabilitation training system integrating social interaction.

COVID-19 causes persistent symptoms such as weakness and myasthenia in most patients. Due to the cross-infection of COVID-19, the traditional face-to-face rehabilitation services are risky for the elderly. To ensure that the elderly in urgent need of rehabilitation services receive training while minimizing the disturbance of the COVID-19 pandemic on their social activities. We have improved the existing virtual upper limb training system, and added a social factor to the system. Seniors with upper limb rehabilitation needs can use the system to compete or collaborate with others for training. In addition, a set of natural and scientific exclusive gestures have been designed under the direction of following the doctor's advice. The experiment is conducted jointly with the chief physicians of the geriatrics department in the authoritative class-A hospitals of Class III. Our experiment, which lasted for two months, showed that the virtual training system with social factors added had the best rehabilitation effect and enhanced the initiative of patients. The system has value for popularization during the COVID-19 epidemic.

Quantitative influence and performance analysis of virtual reality laparoscopic surgical training system.

BACKGROUND: Virtual reality (VR) surgery training has become a trend in clinical education. Many research papers validate the effectiveness of VR-based surgical simulators in training medical students. However, most existing articles employ subjective methods to study the residents' surgical skills improvement. Few of them investigate how to improve the surgery skills on specific dimensions substantially. METHODS: Our paper resorts to physiological approaches to objectively study the quantitative influence and performance analysis of VR laparoscopic surgical training system for medical students. Fifty-one participants were recruited from a pool of medical students. They conducted four pre and post experiments in the training box. They were trained on VR-based laparoscopic surgery simulators (VRLS) in the middle of pre and post experiments. Their operation and physiological data (heart rate and electroencephalogram) are recorded during the pre and post experiments. The physiological data is used to compute cognitive load and flow experience quantitatively. Senior surgeons graded their performance using newly designed hybrid standards for fundamental tasks and Global operative assessment of laparoscopic skills (GOALS) standards for colon resection tasks. Finally, the participants were required to fill the questionnaires about their cognitive load and flow experience. RESULTS: After training on VRLS, the time of the experimental group to complete the same task could drop sharply (p < 0.01). The performance scores are enhanced significantly (p < 0.01). The performance and cognitive load computed from EEG are negatively correlated (p < 0.05). CONCLUSION: The results show that the VRLS could highly improve medical students' performance and enable the participants to obtain flow experience with a lower cognitive load. Participants' performance is negatively correlated with cognitive load through quantitative physiological analysis. This might provide a new way of assessing skill acquirement.

Comparison between MassARRAY and pyrosequencing for CYP2C19 and ABCB1 gene variants of clopidogrel efficiency genotyping.

Clopidogrel is one of the most frequently used drugs in patients to reduce cardiovascular events. Since patients with different genetic variations respond quite differently to clopidogrel therapy, the related genetic testing plays a vital role in its dosage and genetic testing related to clopidogrel therapy is currently considered as routine test worldwide. In this study, we aim to use two different methods MALDI-TOF mass spectrometry and pyrosequencing to detect gene variant of CYP2C19 and ABCB1. Six single nucleotides polymorphisms (SNP) within CYP2C19 (*2, *3, *4, *5, *17) and ABCB1 C3435T in 458 Chinese Han patients were determined using both MassARRAY and Pyrosequencing. Sanger sequencing was used for verification. Results of both methods were analyzed and compared. Allele frequencies of each SNP and distribution of different genotypes were calculated based on the MassARRAY and Sanger sequencing results. Both methods provided 100% call rates for gene variants, while results of six samples were different with two methods. With Sanger sequencing as the reference results, MassARRAY generated all the same results. The minor allele frequencies of the above six SNPs were 27.1% (CYP2C19*), 5.9% (CYP2C19*3), 0% (CYP2C19*4), 0% (CYP2C19*5), 1.1% (CYP2C19*17), 40.9% (ABCB1), respectively. MassARRAY provides accurate clopidogrel related genotyping with relatively high cost-efficiency, throughput and short time when compared with pyrosequencing.

Molecular and Hematological Characterization of a Novel Translation Initiation Codon Mutation of the α2-Globin Gene (ATG>ATC or HBA2: c.3G>C).

Although mutations causing α-thalassemia (α-thal) are mainly larger deletions involving one or both of the duplicated α-globin genes, point mutations are not rare. We have identified a novel mutation of the translation initiation codon of the α2-globin gene with DNA sequencing and allele-specific multiplex ligation-dependent probe amplification (MLPA) in a Chinese family. RNA analysis was performed with reverse transcription-MLPA (RT-MLPA). A novel mutation at the translation initiation codon of the α2-globin gene (HBA2: c.3G>C) was identified. The proband and his father, who were both carriers of this mutation, had a hematological phenotype of mild α+-thalassemia (α+-thal) trait with low-normal limit of mean corpuscular volume (MCV) and normal Hb A2. RNA analysis showed markedly decreased levels of α-globin mRNA and the presence of a small amount of mutant mRNA. The HBA2: c.3G>C mutation most likely caused α-thal by lowering levels of wild α-globin chain. Our study increases the mutation spectrum of α-thal.

3D reconstruction from endoscopy images: A survey.

Three-dimensional reconstruction of images acquired through endoscopes is playing a vital role in an increasing number of medical applications. Endoscopes used in the clinic are commonly classified as monocular endoscopes and binocular endoscopes. We have reviewed the classification of methods for depth estimation according to the type of endoscope. Basically, depth estimation relies on feature matching of images and multi-view geometry theory. However, these traditional techniques have many problems in the endoscopic environment. With the increasing development of deep learning techniques, there is a growing number of works based on learning methods to address challenges such as inconsistent illumination and texture sparsity. We have reviewed over 170 papers published in the 10 years from 2013 to 2023. The commonly used public datasets and performance metrics are summarized. We also give a taxonomy of methods and analyze the advantages and drawbacks of algorithms. Summary tables and result atlas are listed to facilitate the comparison of qualitative and quantitative performance of different methods in each category. In addition, we summarize commonly used scene representation methods in endoscopy and speculate on the prospects of deep estimation research in medical applications. We also compare the robustness performance, processing time, and scene representation of the methods to facilitate doctors and researchers in selecting appropriate methods based on surgical applications.

Real-time soft body dissection simulation with parallelized graph-based shape matching on GPU.

BACKGROUND AND OBJECTIVE: Interactive soft tissue dissection has been a fundamental procedure in virtual surgery systems. Existing cutting algorithms involve complex topology changes of simulation meshes, which can increase simulation overhead and produce visual artifacts. In this paper, we proposed a novel graph-based shape-matching method that allows for real-time, flexible, progressive, and discontinuous cuts on soft tissue. METHODS: We employed shape-matching constraints within the position-based dynamics (PBD) framework, a widely adopted approach for real-time simulation applications. The soft tissue was effectively modeled using overlapping clusters, each governed by shape-matching constraints. The dissection process was bifurcated into two distinct stages. In the first stage, the surgical scalpel presses the surface of the soft tissue. The soft tissue is cut apart when the surface pressure exceeds a threshold, entering the second stage. To address the discrepancy between the visual mesh and the simulation model during cluster separation, we developed an Aggregate Finding Connected Components (AFCC) algorithm, optimized for GPU computation and integrated with a background grid. This approach also avoids ghost forces and fragmentation artifacts. To control the increase in the number of clusters, we also propose a merging strategy that can run in parallel. RESULTS: Our simulation outcomes demonstrated that the AFCC dissection algorithm effectively manages cluster separation and expansion with robustness. There were no ghost forces between the cutting surface and unrealistic fragments. Our simulation capability extended to supporting intricate and discontinuous cutting routes. Our dissection simulation maintained real-time performance even with over 100,000 particles constituting the soft tissue. CONCLUSIONS: Our real-time and robust surgical dissection simulation technique enables the performance of complex cuts in various surgical scenarios, demonstrating its potential in virtual surgery applications.

Multimodal Physiological Analysis of Impact of Emotion on Cognitive Control in VR.

Cognitive control is often perplexing to elucidate and can be easily influenced by emotions. Understanding the individual cognitive control level is crucial for enhancing VR interaction and designing adaptive and self-correcting VR/AR applications. Emotions can reallocate processing resources and influence cognitive control performance. However, current research has primarily emphasized the impact of emotional valence on cognitive control tasks, neglecting emotional arousal. In this study, we comprehensively investigate the influence of emotions on cognitive control based on the arousal-valence model. A total of 26 participants are recruited, inducing emotions through VR videos with high ecological validity and then performing related cognitive control tasks. Leveraging physiological data including EEG, HRV, and EDA, we employ classification techniques such as SVM, KNN, and deep learning to categorize cognitive control levels. The experiment results demonstrate that high-arousal emotions significantly enhance users' cognitive control abilities. Utilizing complementary information among multi-modal physiological signal features, we achieve an accuracy of 84.52% in distinguishing between high and low cognitive control. Additionally, time-frequency analysis results confirm the existence of neural patterns related to cognitive control, contributing to a better understanding of the neural mechanisms underlying cognitive control in VR. Our research indicates that physiological signals measured from both the central and autonomic nervous systems can be employed for cognitive control classification, paving the way for novel approaches to improve VR/AR interactions.

Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer.

In recent years, an increasing number of medical engineering tasks, such as surgical navigation, pre-operative registration, and surgical robotics, rely on 3D reconstruction techniques. Self-supervised depth estimation has attracted interest in endoscopic scenarios because it does not require ground truth. Most existing methods depend on expanding the size of parameters to improve their performance. There, designing a lightweight self-supervised model that can obtain competitive results is a hot topic. We propose a lightweight network with a tight coupling of convolutional neural network (CNN) and Transformer for depth estimation. Unlike other methods that use CNN and Transformer to extract features separately and then fuse them on the deepest layer, we utilize the modules of CNN and Transformer to extract features at different scales in the encoder. This hierarchical structure leverages the advantages of CNN in texture perception and Transformer in shape extraction. In the same scale of feature extraction, the CNN is used to acquire local features while the Transformer encodes global information. Finally, we add multi-head attention modules to the pose network to improve the accuracy of predicted poses. Experiments demonstrate that our approach obtains comparable results while effectively compressing the model parameters on two datasets.

The bibliometric analysis of extended reality in surgical training: Global and Chinese perspective.

Objectives: The prospect of extended reality (XR) being integrated with surgical training curriculum has attracted scholars. However, there is a lack of bibliometric analysis to help them better understand this field. Our aim is to analyze relevant literature focusing on development trajectory and research directions since the 21st century to provide valuable insights. Methods: Papers were retrieved from the Web of Science Core Collection. Microsoft Excel, VOSviewer, and CiteSpace were used for bibliometric analysis. Results: Of the 3337 papers published worldwide, China contributed 204, ranking fifth. The world's enthusiasm for this field has been growing since 2000, whereas China has been gradually entering since 2001. Although China had a late start, its growth has accelerated since around 2016 due to the reform of the medical postgraduate education system and the rapid development of Chinese information technology, despite no research explosive period has been yet noted. International institutions, notably the University of Toronto, worked closely with others, while Chinese institutions lacked of international and domestic cooperation. Sixteen stable cooperation clusters of international scholars were formed, while the collaboration between Chinese scholars was not yet stable. XR has been primarily applied in orthopedic surgery, cataract surgery, laparoscopic training and intraoperative use in neurosurgery worldwide. Conclusions: There is strong enthusiasm and cooperation in the international research on the XR-based surgical training. Chinese scholars are making steady progress and have great potential in this area. There has not been noted an explosive research phase yet in the Chinese pace. The research on several surgical specialties has been summarized at the very first time. AR will gradually to be more involved and take important role of the research.

Augmented-reality-based surgical navigation for endoscope retrograde cholangiopancreatography: A phantom study.

BACKGROUND: Endoscope retrograde cholangiopancreatography is a standard surgical treatment for gallbladder and pancreatic diseases. However, surgeons is at high risk and require sufficient surgical experience and skills. METHODS: (1) The simultaneous localisation and mapping technique to reconstruct the surgical environment. (2) The preoperative 3D model is transformed into the intraoperative video environment to implement the multi-modal fusion. (3) A framework for virtual-to-real projection based on hand-eye alignment. For the purpose of projecting the 3D model onto the imaging plane of the camera, it uses position data from electromagnetic sensors. RESULTS: Our AR-assisted navigation system can accurately guide physicians, which means a distance of registration error to be restricted to under 5 mm and a projection error of 5.76 ± 2.13, and the intubation procedure is done at 30 frames per second. CONCLUSIONS: Coupled with clinical validation and user studies, both the quantitative and qualitative results indicate that our navigation system has the potential to be highly useful in clinical practice.

Target-activated multicolor fluorescent dyes for 3D imaging of plasma membranes and tracking of apoptosis.

Real-time tracking of dynamic changes in the three-dimensional morphology of the cell plasma membrane is of great importance for a deeper understanding of physiological processes related to the cell plasma membrane. However, there is a lack of imaging dyes that can specifically be used for a long term labelling of plasma membranes, especially for plant cells. Here, we have used molecular engineering strategies to develop a series of target-activated multicolour fluorescent dyes that can be used for long-term and three-dimensional imaging of plant cell plasma membranes. By combining different electron acceptors and donors, four molecular backbones with different emission colours from green to NIR have been obtained. In the designed styrene-based dyes, referred to as the SD dyes, several functional groups were introduced into the backbones to achieve the properties of target-activated fluorescence, rapid and wash-free staining, high plasma membrane targeting ability and long-term imaging function. Using onion epidermal cells as a platform, these dye molecules can provide high-quality imaging of the plasma membrane for up to 6 hours, providing a powerful tool for long-term monitoring of plasma membrane-related biological events. Calcium-mediated apoptosis of plant cells has been tracked for the first time by monitoring the morphological changes of the plasma membrane in real time using SD dyes. These dyes also exhibit excellent 3D imaging performance of the plasma membrane and were further used to track in real time the 3D morphological changes of the plasma membrane during plasmolysis of plant cells, providing a powerful imaging tool for three-dimensional (3D) biology. This work provides a set of multi-colour dye tools for long-term and three-dimensional imaging of plant cell plasma membranes, and also provides molecular design principles for guiding the transmembrane transport of small molecules.

Charge-regulated fluorescent anchors enable high-fidelity tracking of plasma membrane dynamics during biological events.

Many biological processes generally require long-term visualization tools for time-scale dynamic changes of the plasma membrane, but there is still a lack of design rules for such imaging tools based on small-molecule fluorescent probes. Herein, we revealed the key regulatory roles of charge number and species of fluorescent dyes in the anchoring ability of the plasma membrane and found that the introduction of multi-charged units and appropriate charge species is often required for fluorescent dyes with strong plasma membrane anchoring ability by systematically investigating the structure-function relationship of cyanostyrylpyridium (CSP) dyes with different charge numbers and species and their imaging performance for the plasma membrane. The CSP-DBO dye constructed exhibits strong plasma membrane anchoring ability in staining the plasma membrane of cells, in addition to many other advantages such as excellent biocompatibility and general universality of cell types. Such a fluorescent anchor has been successfully used to monitor chemically induced plasma membrane damage and dynamically track various cellular biological events such as cell fusion and cytokinesis over a long period of time by continuously monitoring the dynamic morphological changes of the plasma membrane, providing a valuable precise visualization tool to study the physiological response to chemical stimuli and reveal the structural morphological changes and functions of the plasma membrane during these important biological events from a dynamic perspective. Furthermore, CSP-DBO exhibits excellent biocompatibility and imaging capability in vivo such as labelling the plasma membrane in vivo and monitoring the metabolic process of lipofuscin as an aging indicator.

Molecular engineering of fluorescent dyes for long-term specific visualization of the plasma membrane based on alkyl-chain-regulated cell permeability.

Long-term visualization of changes in plasma membrane dynamics during important physiological processes can provide intuitive and reliable information in a 4D mode. However, molecular tools that can visualize plasma membranes over extended periods are lacking due to the absence of effective design rules that can specifically track plasma membrane fluorescent dye molecules over time. Using plant plasma membranes as a model, we systematically investigated the effects of different alkyl chain lengths of FMR dye molecules on their performance in imaging plasma membranes. Our findings indicate that alkyl chain length can effectively regulate the permeability of dye molecules across plasma membranes. The study confirms that introducing medium-length alkyl chains improves the ability of dye molecules to target and anchor to plasma membranes, allowing for long-term imaging of plasma membranes. This provides useful design rules for creating dye molecules that enable long-term visualization of plasma membranes. Using the amphiphilic amino-styryl-pyridine fluorescent skeleton, we discovered that the inclusion of short alkyl chains facilitated rapid crossing of the plasma membrane by the dye molecules, resulting in staining of the cell nucleus and indicating improved cell permeability. Conversely, the inclusion of long alkyl chains hindered the crossing of the cell wall by the dye molecules, preventing staining of the cell membrane and demonstrating membrane impermeability to plant cells. The FMR dyes with medium-length alkyl chains rapidly crossed the cell wall, uniformly stained the cell membrane, and anchored to it for a long period without being transmembrane. This allowed for visualization and tracking of the morphological dynamics of the cell plasma membrane during water loss in a 4D mode. This suggests that the introduction of medium-length alkyl chains into amphiphilic fluorescent dyes can transform them from membrane-permeable fluorescent dyes to membrane-staining fluorescent dyes suitable for long-term imaging of the plasma membrane. In addition, we have successfully converted a membrane-impermeable fluorescent dye molecule into a membrane-staining fluorescent dye by introducing medium-length alkyl chains into the molecule. This molecular engineering of dye molecules with alkyl chains to regulate cell permeability provides a simple and effective design rule for long-term visualization of the plasma membrane, and a convenient and feasible means of chemical modification for efficient transmembrane transport of small molecule drugs.

State of the Art in Immersive Interactive Technologies for Surgery Simulation: A Review and Prospective.

Immersive technologies have thrived on a strong foundation of software and hardware, injecting vitality into medical training. This surge has witnessed numerous endeavors incorporating immersive technologies into surgery simulation for surgical skills training, with a growing number of researchers delving into this domain. Relevant experiences and patterns need to be summarized urgently to enable researchers to establish a comprehensive understanding of this field, thus promoting its continuous growth. This study provides a forward-looking perspective by reviewing the latest development of immersive interactive technologies for surgery simulation. The investigation commences from a technological standpoint, delving into the core aspects of virtual reality (VR), augmented reality (AR) and mixed reality (MR) technologies, namely, haptic rendering and tracking. Subsequently, we summarize recent work based on the categorization of minimally invasive surgery (MIS) and open surgery simulations. Finally, the study showcases the impressive performance and expansive potential of immersive technologies in surgical simulation while also discussing the current limitations. We find that the design of interaction and the choice of immersive technology in virtual surgery development should be closely related to the corresponding interactive operations in the real surgical speciality. This alignment facilitates targeted technological adaptations in the direction of greater applicability and fidelity of simulation.

Tucker network: Expressive power and comparison.

Deep neural networks have achieved great success in solving many machine learning and computer vision problems. In this paper, we propose a deep neural network called the Tucker network derived from the Tucker format and analyze its expressive power. The results demonstrate that the Tucker network has exponentially higher expressive power than the shallow network. In other words, a shallow network with an exponential width is required to realize the same score function as that computed by the Tucker network. Moreover, we discuss the expressive power between the hierarchical Tucker tensor network (HT network) and the proposed Tucker network. To generalize the Tucker network into a deep version, we combine the hierarchical Tucker format and Tucker format to propose a deep Tucker tensor decomposition. Its corresponding deep Tucker network is presented. Experiments are conducted on three datasets: MNIST, CIFAR-10 and CIFAR-100. The results experimentally validate the theoretical results and show that the Tucker network and deep Tucker network have better performance than the shallow network and HT network.

A Cross-Domain Weakly Supervised Diabetic Retinopathy Lesion Identification Method Based on Multiple Instance Learning and Domain Adaptation.

Accurate identification of lesions and their use across different medical institutions are the foundation and key to the clinical application of automatic diabetic retinopathy (DR) detection. Existing detection or segmentation methods can achieve acceptable results in DR lesion identification, but they strongly rely on a large number of fine-grained annotations that are not easily accessible and suffer severe performance degradation in the cross-domain application. In this paper, we propose a cross-domain weakly supervised DR lesion identification method using only easily accessible coarse-grained lesion attribute labels. We first propose the novel lesion-patch multiple instance learning method (LpMIL), which leverages the lesion attribute label for patch-level supervision to complete weakly supervised lesion identification. Then, we design a semantic constraint adaptation method (LpSCA) that improves the lesion identification performance of our model in different domains with semantic constraint loss. Finally, we perform secondary annotation on the open-source dataset EyePACS, to obtain the largest fine-grained annotated dataset EyePACS-pixel, and validate the performance of our model on it. Extensive experimental results on the public dataset FGADR and our EyePACS-pixel demonstrate that compared with the existing detection and segmentation methods, the proposed method can identify lesions accurately and comprehensively, and obtain competitive results using only coarse-grained annotations.

Implementation of a Virtual Reality Based Digital-Twin Robotic Minimally Invasive Surgery Simulator.

The rapid development of computers and robots has seen robotic minimally invasive surgery (RMIS) gradually enter the public's vision. RMIS can effectively eliminate the hand vibrations of surgeons and further reduce wounds and bleeding. However, suitable RMIS and virtual reality-based digital-twin surgery trainers are still in the early stages of development. Extensive training is required for surgeons to adapt to different operating modes compared to traditional MIS. A virtual-reality-based digital-twin robotic minimally invasive surgery (VRDT-RMIS) simulator was developed in this study, and its effectiveness was introduced. Twenty-five volunteers were divided into two groups for the experiment, the Expert Group and the Novice Group. The use of the VRDT-RMIS simulator for face, content, and structural validation training, including the peg transfer module and the soft tissue cutting module, was evaluated. Through subjective and objective evaluations, the potential roles of vision and haptics in robot surgery training were explored. The simulator can effectively distinguish surgical skill proficiency between experts and novices.

Highlight removal for endoscopic images based on accelerated adaptive non-convex RPCA decomposition.

OBJECTIVE: Highlights always occur in endoscopic images due to their special imaging environment. It not only increases the difficulty of observation and diagnosis from surgeons, but also influences the performance of Mixed/Augmented Reality techniques in surgery navigation. METHODS: In this paper, we propose a novel accelerated adaptive non-convex robust principal component analysis method (AANC-RPCA) to remove highlights in endoscopic images. We first detect absolute highlight pixels of the enhanced endoscopic images with adaptive threshold segmentation. The quasi-convex function is proposed to approximate a new non-convex objective function. With detected highlight pixels and quasi-convex function, it introduces gradient to shrink sparse matrix and obtains a faster speed of convergence. Then we divide the image into multiple blocks and perform the parallel computation to enhance the efficiency. Finally, we design a weighted template that decays outward with dilation and linear filtering to reconstruct the endoscopic images. Our approach is almost independent of hyper-parameters and can achieve adaptive decomposition. RESULTS: It has been verified on multiple types of endoscopic images through experiments and clinical blind tests. The results demonstrate that our method can obtain the best performance for the recovered images with more details in a shorter time (about 3-5 times). CONCLUSION: Coupled with the user study, both the quantitative and qualitative results indicate that our approach has the potential to be highly useful in endoscopy images. Compared with the existing highlight removal approaches, our method obtains the SOTA results and has the potential to be applied in the various medical processing processes.