Manual Intervention Research Articles

Heritage Iconographic Content Structuring: from Automatic Linking to Visual Validation

This article presents a global framework dedicated to the structuring of iconographic heritage collections. To alleviate the poor interlinking both between collections and contents, a first step of automatic linking exploiting content-based image retrieval approaches is evaluated and adapted to the visual variability of such heritage contents. To ensure understanding and analysis of the contents in a structured fashion, a 3D immersive web platform is also introduced alongside visual-based analysis tools. Finally, by exploiting both automatic linking and manual interventions in the visualization platform, an iterative, semi-automatic structuring pipeline is proposed to solve difficult cases missed by automatic structuring, and then improve structuring optimally. Here, we demonstrate the potential of the proposal on the geographic iconographic heritage of Paris, with a dataset of 10k images belonging to several institutions, thus poorly connected nor organized globally.

Active Learning in Feature Extraction for Glass-in-Glass Detection

In the food industry, ensuring product quality is crucial due to potential hazards to consumers. Though metallic contaminants are easily detected, identifying non-metallic ones like wood, plastic, or glass remains challenging and poses health risks. X-ray-based quality control systems offer deeper product inspection than RGB cameras, making them suitable for detecting various contaminants. However, acquiring sufficient defective samples for classification is costly and time-consuming. To address this, we propose an anomaly detection system requiring only non-defective samples, automatically classifying anything not recognized as good as defective. Our system, employing active learning on X-ray images, efficiently detects defects like glass fragments in food products. By fine tuning a feature extractor and autoencoder based on non-defective samples, our method improves classification accuracy while minimizing the need for manual intervention over time. The system achieves a 97.4% detection rate for foreign glass bodies in glass jars, offering a fast and effective solution for real-time quality control on production lines.

Psychedelic-assisted psychotherapy: where is the psychotherapy research?

Psychedelic-assisted psychotherapy (PAP) has emerged as a potential treatment for a variety of mental health conditions, including substance use disorders and depression. Current models of PAP emphasize the importance of psychotherapeutic support before, during, and after ingestion of a psychedelic to maximize safety and clinical benefit. Despite this ubiquitous assumption, there has been surprisingly little empirical investigation of the "psychotherapy" in PAP, leaving critical questions about the necessary and sufficient components of PAP unanswered. As clinical trials for psychedelic compounds continue the transition from safety- and feasibility-testing to evaluating efficacy, the role of the accompanying psychotherapy must be better understood to enhance scientific understanding of the mechanisms underlying therapeutic change, optimize clinical outcomes, and inform cost-effectiveness. The present paper first reviews the current status of psychotherapy in the PAP literature, starting with recent debates regarding "psychotherapy" versus "psychological support" and then overviewing published clinical trial psychotherapy models and putative models informed by theory. We then delineate lessons that PAP researchers can leverage from traditional psychotherapy research regarding standardizing treatments (e.g., publish treatment manuals, establish eligibility criteria for providers), identifying mechanisms of change (e.g., measure established mechanisms in psychotherapy), and optimizing clinical trial designs (e.g., consider dismantling studies, comparative efficacy trials, and cross-lagged panel designs). Throughout this review, the need for increased research into the psychotherapeutic components of treatment in PAP is underscored. PAP is a distinct, integrative, and transdisciplinary intervention. Future research designs should consider transdisciplinary research methodologies to identify best practices and inform federal guidelines for PAP administration.

Chemical desiccation of potato haulms to increase skin hardness and potato yield

Desiccation of potato crops using herbicides is one of the methods widely used by farmers. Desiccation affects several key aspects such as tuber yield and potato skin hardness. This study aimed to investigate the effects of desiccation on potato (Solanum tuberosum L.) on skin hardness and yield. Experimental methods were used by varying the level of desiccation on different herbicide groups. Ammonium glufosinate, glyphosate, paraquat and saflufenacil herbicides were used in this study which were then compared with manual trimming and no desiccation treatment. The results showed that all herbicides reached a percentage of desiccation above 95% on the 15 days after application. All herbicide treatments other than glyphosate showed the same potato skin hardness as the manual trimming treatment and were harder than potato tubers without desiccation treatment. Desiccation using ammonium glufosinate herbicide at 375 g a.i./ha had the highest potato tuber yield compared to other herbicide applications.

Restoration of normal central pain processing following manual therapy in nonspecific chronic neck pain.

To determine if a 4-week manual therapy treatment restores normal functioning of central pain processing mechanisms in non-specific chronic neck pain (NSCNP), as well as the existence of a possible relationship between changes in pain processing mechanisms and clinical outcome. Cohort study. Sixty-three patients with NSCNP, comprising 79% female, with a mean age of 45.8 years (standard deviation: 14.3), received four treatment sessions (once a week) of manual therapy including articular passive mobilizations, soft tissue mobilization and trigger point treatment. Pressure pain thresholds (PPTs), conditioned pain modulation (CPM) and temporal summation of pain (TSP) were evaluated at baseline and after treatment completion. Therapy outcome was measured using the Global Rating of Change Scale (GROC), the Neck disability Index (NDI), intensity of pain during the last 24 hours, Tampa Scale of Kinesiophobia (TSK) and Pain Catastrophizing Scale (PCS). Two sets of generalized linear mixed models with Gaussian response and the identity link were employed to evaluate the effect of the intervention on clinical, psychological and psychophysical measures and the association between psychophysical and clinical outcomes. Following treatment, an increased CPM response (Coefficient: 0.89; 95% credibility interval = 0.14 to 1.65; P = .99) and attenuated TSP (Coefficient: -0.63; 95% credibility interval = -0.82 to -0.43; P = 1.00) were found, along with amelioration of pain and improved clinical status. PPTs at trapezius muscle on the side of neck pain were increased after therapy (Coefficient: 0.22; 95% credibility interval = 0.03 to 0.42; P = .98), but not those on the contralateral trapezius and tibialis anterior muscles. Only minor associations were found between normalization of TSP/CPM and measures of clinical outcome. Clinical improvement after manual therapy is accompanied by restoration of CPM and TSP responses to normal levels in NSCNP patients. The existence of only minor associations between changes in central pain processing and clinical outcome suggests multiple mechanisms of action of manual therapy in NSCNP.

Research on 2D Animation Simulation Based on Artificial Intelligence and Biomechanical Modeling

Animation techniques have been completely transformed by the union of Artificial Intelligence (AI) and biomechanical modeling, particularly in 2D animation. This study looks at a combination of AI and biomechanics to address the challenges of simulating 2D animation. Current approaches in 2D animation often struggle to achieve lifelike and fluid movements, especially when representing complex motion or interaction. These traditional techniques rely on manual keyframing or physics simulation, which may be time-consuming and do not provide the rich detail needed for realism in animations. To meet these aspects, this study suggested 2D animation using Artificial Intelligence with Biomechanical Modeling (2D-AI-BM). Our approach thus harnesses Deep Neural Network (DNN) for moving forecasts and improvement using biopsychological principles to help us imitate natural human actions better. In addition to character animation, it could apply to interactive storytelling and educational simulations. As a result, animators get more control over motion generation while drastically reducing the necessity for manual intervention through this fusion of AI and biomechanics, which smoothens the production pipeline for animations. This paper considers several important metrics to evaluate the proposed approach’s effectiveness, including user satisfaction, computational efficiency, motion smoothness and realism. Comparative studies with classical animation methods showed that the method generates realistic movements on 2D characters while saving time during production. The numerical findings exemplify that the recommended 2D-AI-BM model improves an accuracy rate of 97.4%, computational efficiency ratio of 96.3%, motion control ratio of 95.4%, pose detection ratio of 94.8% and scalability ratio of 93.2% compared to other popular techniques.

AN OPTIMIZED PORTABLE INTEGRATED NEBULIZER WITH AUTOMATIC OVERHEAT SHUTDOWN AND TIME-SPECIFIC APPLICATION CONTROL ENHANCING LONG-TERM PATIENT CARE

Compressor nebulizers play a crucial role in treating respiratory conditions by facilitating the effective delivery of medications to the lungs. However, prolonged usage necessitates careful management to prevent overheating, which can compromise both device performance and patient safety. This study investigates the integration of an automated temperature controller into compressor nebulizers to address this issue along with its specific time of application to prevent excess use. Existing nebulizers on the market often lack overheating prevention mechanisms, requiring manual intervention to avoid damage. Leveraging the LM-35 temperature sensor, this research proposes a system that automatically shuts off the nebulizer when specific time of use is over or overheating is detected, subsequently resuming operation once temperatures have stabilized. By ensuring optimal device performance and patient support over extended periods, this innovation represents a significant advancement in respiratory care technology. KEYWORDS: Compressor, Nebulizer, Temperature, Prevention, Overheating, LM-35, Care, Technology.

Simulated augmented reality-based calibration of optical see-through head mound display for surgical navigation.

Calibration of an optical see-through head-mounted display is critical for augmented reality-based surgical navigation. While conventional methods have advanced, calibration errors remain significant. Moreover, prior research has focused primarily on calibration accuracy and procedure, neglecting the impact on the overall surgical navigation system. Consequently, these enhancements do not necessarily translate to accurate augmented reality in the optical see-through head mount due to systemic errors, including those in calibration. This study introduces a simulated augmented reality-based calibration to address these issues. By replicating the augmented reality that appeared in the optical see-through head mount, the method achieves calibration that compensates for augmented reality errors, thereby reducing them. The process involves two distinct calibration approaches, followed by adjusting the transformation matrix to minimize displacement in the simulated augmented reality. The efficacy of this method was assessed through two accuracy evaluations: registration accuracy and augmented reality accuracy. Experimental results showed an average translational error of 2.14mm and rotational error of 1.06° across axes in both approaches. Additionally, augmented reality accuracy, measured by the overlay regions' ratio, increased to approximately 95%. These findings confirm the enhancement in both calibration and augmented reality accuracy with the proposed method. The study presents a calibration method using simulated augmented reality, which minimizes augmented reality errors. This approach, requiring minimal manual intervention, offers a more robust and precise calibration technique for augmented reality applications in surgical navigation.

Swift Tag: Advancing Toll Collection Through Automated Number Plate Recognition and OCR Technologies

Swift Tag presents a novel approach to toll collection, leveraging Automated Number Plate Recognition (ANPR), Optical Character Recognition (OCR), and modern frontend/backend technologies to streamline operations, enhance accuracy, and improve user experience. By automating the identification and processing of vehicles at toll booths, Swift Tag eliminates manual intervention, reduces congestion, and minimizes errors. Utilizing YOLOv8 for object detection and EasyOCR for character recognition, Swift Tag ensures real-time capture and extraction of license plate information with remarkable precision. Complemented by a comprehensive frontend interface developed using React and JavaScript, and a robust backend infrastructure for seamless integration with existing toll management systems, Swift Tag offers a scalable, cost-effective, and universally applicable solution to toll collection challenges

Role of Sport Vision in Performance: Systematic Review.

Sport Vision is a speciality of multidisciplinary interest aimed at improving the performance of the visual system to achieve benefits in practiced sports, as well as in daily life and in preventive care. The type of training practiced by the athlete, his or her physical condition, cognitive level, and level of fatigue condition affects the speed of the reaction time and, consequently, the speed of motor response. Specific orthoptic exercises, the use of technological devices, the recovery of static and dynamic postural stability by using unstable platforms and the dual-task paradigm can help to achieve the expected results. The aim of this systematic review of Sport Vision was to assess the overall existing literature on Sport Vision, paying particular attention to the effects of visual training and its application in different sports and in rehabilitation and preventive settings. We analysed published English language studies about the role of sport vision in athletic performance from 1950 to 2023. We searched through the Medline database. The PRISMA 2020 checklist was used to assess the transparency and reproducibility of this review. The enrolled papers were evaluated with the Jadad Scale, Amstar 2 Scale and Newcastle-Ottawa Scale. 25 (16 studies, 5 reviews, 2 comments, 1 editorial, 1 descriptive paper) out of 476 studies met the inclusion criteria. Due to the variability in the age of the samples, the different techniques, the treatments among the participants in the studies and the finding of non-evaluable articles, a meta-analysis was not conducted. The limitations of this review are the single database research, the studies analyzed contain a non-statistically representative sample size and the lack of a control group. There is no standardized test to measure performance. It was shown that the development of visual skills can benefit athletes in injury prevention, and can lead to improved sports performance and motor function at any age, acquiring adaptive motor behaviour even when the visual system is impaired, due to task repetition and familiarity of the gesture. We intended to identify a multidisciplinary approach and a manual treatment scheme to optimize the circuitry involved in sport vision in order to increase the results that are achieved, but further studies will be needed to this end.

IoT based Water Tank Cleaner using STM32

Water tanks are essential for storing and supplying clean water in both residential and industrial settings. However, over time, these tanks can accumulate sediment, algae, and other contaminants that can compromise water quality. Cleaning and maintaining water tanks is a critical task to ensure the supply of safe and clean water to consumers. The IoT-Based Water Tank Cleaner using STM32 project aims to address this issue by developing an innovative solution that automates the cleaning process of water tanks. This project leverages the power of the Internet of Things (IoT) and the capabilities of the STM32 microcontroller to create an intelligent and efficient water tank cleaning system. This project presents an innovative solution for water tank cleaning using the STM32 microcontroller and IoT (Internet of Things) technology. The proposed system automates the process of cleaning and monitoring water tanks, ensuring efficient operation and minimizing manual intervention. Water scarcity is a pressing global issue, necessitating efficient management of water resources. One significant aspect of water management is maintaining the cleanliness of water storage tanks, which often harbor contaminants due to neglect or inadequate cleaning procedures. This project introduces an IoT-based solution leveraging the STM32 microcontroller to automate the cleaning process of water tanks. The system employs sensors to monitor water quality, an actuator for tank cleaning, and IoT connectivity for remote monitoring and control. Key Words: Water tank cleaning, IoT-based solution, STM32, Water quality, Sediment removal

Optimal Operation of Cryogenic Calorimeters Through Deep Reinforcement Learning

Cryogenic phonon detectors with transition-edge sensors achieve the best sensitivity to sub-GeV/c2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^2$$\\end{document} dark matter interactions with nuclei in current direct detection experiments. In such devices, the temperature of the thermometer and the bias current in its readout circuit need careful optimization to achieve optimal detector performance. This task is not trivial and is typically done manually by an expert. In our work, we automated the procedure with reinforcement learning in two settings. First, we trained on a simulation of the response of three Cryogenic Rare Event Search with Superconducting Thermometers (CRESST) detectors used as a virtual reinforcement learning environment. Second, we trained live on the same detectors operated in the CRESST underground setup. In both cases, we were able to optimize a standard detector as fast and with comparable results as human experts. Our method enables the tuning of large-scale cryogenic detector setups with minimal manual interventions.

PERANGKAT EKSTRAKSI JAHE TERINTEGRASI BERBASIS ARDUINO UNO DENGAN PENGUJIAN METODE SPEKTROFOTOMETRI VISIBEL

The Automatic Ginger Extractor Based on Arduino Uno consists of three main units: the input unit, the processing unit, and the output unit. The input unit is equipped with Up, Down, and Ok buttons for navigation, as well as a phototransistor sensor that detects the presence of ginger samples (ginger simplicia) to be extracted. The processing unit uses an Arduino Uno microcontroller to process signals from the sensor and control the output unit. The output unit includes a motor driver, a power window motor for operating the grinder to crush the samples, a 12V DC motor for operating the stirrer to mix the samples with the solvent, an electric solenoid valve for dispensing the extract, and an LCD to display the process status. The working principle of this device is that when the phototransistor sensor detects a sample, the sensor signal activates the power window motor to grind the ginger. The user can then manually set the dissolution time using the navigation buttons. The longer the dissolution time, the better the extraction result. The final product is a liquid containing curcumin, which is measured using a curcumin content meter to determine its concentration. The device shows an error rate of 2.74% compared to manual methods. With this design, the Arduino Uno-based automatic ginger extractor offers a more efficient and consistent extraction process. The automation system allows for better control and optimal results with minimal manual intervention.

Refining neural network algorithms for accurate brain tumor classification in MRI imagery

Brain tumor diagnosis using MRI scans poses significant challenges due to the complex nature of tumor appearances and variations. Traditional methods often require extensive manual intervention and are prone to human error, leading to misdiagnosis and delayed treatment. Current approaches primarily include manual examination by radiologists and conventional machine learning techniques. These methods rely heavily on feature extraction and classification algorithms, which may not capture the intricate patterns present in brain MRI images. Conventional techniques often suffer from limited accuracy and generalizability, mainly due to the high variability in tumor appearance and the subjective nature of manual interpretation. Additionally, traditional machine learning models may struggle with the high-dimensional data inherent in MRI images. To address these limitations, our research introduces a deep learning-based model utilizing convolutional neural networks (CNNs).Our model employs a sequential CNN architecture with multiple convolutional, max-pooling, and dropout layers, followed by dense layers for classification. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The precision, recall, and F1-scores ranging from 97 to 98% with a roc-auc ranging from 99 to 100% for each tumor category further substantiate the model’s effectiveness. Additionally, the utilization of Grad-CAM visualizations provides insights into the model’s decision-making process, enhancing interpretability. This research addresses the pressing need for enhanced diagnostic accuracy in identifying brain tumors through MRI imaging, tackling challenges such as variability in tumor appearance and the need for rapid, reliable diagnostic tools.

Innovative road distress detection (IR-DD): an efficient and scalable deep learning approach

In the rapidly evolving landscape of transportation infrastructure, the quality and condition of road networks play a pivotal role in societal progress and economic growth. In the realm of road distress detection, traditional methods have long grappled with manual intervention and high costs, requiring trained observers for time-consuming and expensive data collection processes. The limitations of these approaches are compounded by challenges in adapting to diverse road surfaces and handling low-resolution data, particularly in early automated distress survey technologies. This article addresses the critical need for efficient road distress detection, a key component of ensuring safe and reliable transportation systems. Effectively addressing these challenges is crucial for enhancing the efficiency, accuracy, and safety of road distress detection systems. Leveraging advancements in object detection, we introduce the Innovative Road Distress Detection (IR-DD), a novel framework that integrates the YOLOv8 algorithm to enhance the accuracy and real-time capabilities of road distress detection, catering to applications such as smart cities and autonomous vehicles. Our approach incorporates bidirectional feature pyramid network (BiFPN) recursive feature fusion and bidirectional connections to optimize the utilization of multi-scale features, addressing challenges related to information loss and gradients encountered in traditional methods. Comprehensive experimental analysis demonstrates the superior performance, efficiency, and robustness of our integrated approach, positioning it as a cost-effective and compelling alternative to conventional road distress detection methods. Our findings demonstrate the superior performance of our approach compared to other state-of-the-art methods across various evaluation metrics, including precision, recall, F1 score, and mean average precision (mAP) at different intersection over union (IoU) thresholds. Specifically, our method achieves notable results with a precision of 0.666, F1 score of 0.630, mAP@0.5 of 0.650, all while operating at a speed of 86 frames per second (FPS). These outcomes underscore the effectiveness of our approach in real-time road distress detection. This article contributes to the ongoing innovation in object detection techniques, emphasizing the practicality and effectiveness of our proposed solution in advancing the field of road distress detection.

Feasibility and preliminary efficacy of behavioral activation for treatment of depression in autistic adolescents.

Depression is common among autistic youth and has a significant negative impact on quality of life and day-to-day functioning. Despite great need for efficacious treatments, there are currently limited research-supported interventions for depression symptoms in autistic young people. This study tested a novel, behavior-based approach or psychotherapy for treatment of depression symptoms in autistic adolescents without intellectual disability (i.e. Behavioral Activation for Autistic Adolescents, BA-A) with 15 youth (11-16 years old). BA-A is an individually delivered 12-session therapy that was developed for and to meet the needs of autistic youth with depression. Results found that autistic youth and their caregivers were able to participate in BA-A therapy sessions, and clinicians were able to deliver BA-A in accordance with the treatment manual. Notably, results demonstrated that autistic youth depression symptoms significantly improved after participating in BA-A. Furthermore, anxiety symptoms and social skills significantly improved following BA-A.

Therapeutic effect of manual massage on early postpartum rectus abdominis separation and postpartum depression.

Rectus abdominis separation (DRA) affects pelvic stability and body image. No studies have explored the effects of manual massage on early postpartum DRA and postpartum depression. To analyze the curative effect of massage on early postpartum DRA and its impact on postpartum depression and thus its ability promote the overall psychosomatic rehabilitation of postpartum women. Data were retrospectively collected on 70 primiparous women with postpartum DRA who underwent rehabilitation at the Postpartum Rehabilitation Center of Huzhou Maternal and Child Health Hospital from October 2022 to September 2023. The patients were divided into the Group S (35 cases, biomimetic electrical stimulation treatment) and Group L (35 cases, biomimetic electrical stimulation combined with manual massage treatment). Baseline data, the edinburgh postpartum depression scale (EPDS) score, and the visual analog scale (VAS) scores for rectus abdominis distance, waist circumference, and lower back pain before and after treatment were compared. No significant differences were found in the baseline data, rectus abdominis distance, waist circumference, and VAS and EPDS scores between the two groups before treatment (P > 0.05). After treatment, the distance between rectus abdominis and waist circumference in Group L were significantly smaller than those in Group S (P < 0.05). Furthermore, lower back pain (VAS score) and the EPDS score in Group L were significantly lower than those in Group S (P < 0.05). Manual massage can significantly reduce early postpartum DRA, waist circumference, and back pain and improve the patient's mental state and postpartum depression.

HyperMRI: hyperspectral and magnetic resonance fusion methodology for neurosurgery applications

PurposeMagnetic resonance imaging (MRI) is a common technique in image-guided neurosurgery (IGN). Recent research explores the integration of methods like ultrasound and tomography, among others, with hyperspectral (HS) imaging gaining attention due to its non-invasive real-time tissue classification capabilities. The main challenge is the registration process, often requiring manual intervention. This work introduces an automatic, markerless method for aligning HS images with MRI.MethodsThis work presents a multimodal system that combines RGB-Depth (RGBD) and HS cameras. The RGBD camera captures the patient’s facial geometry, which is used for registration with the preoperative MR through ICP. Once MR-depth registration is complete, the integration of HS data is achieved using a calibrated homography transformation. The incorporation of external tracking with a novel calibration method allows camera mobility from the registration position to the craniotomy area. This methodology streamlines the fusion of RGBD, HS and MR images within the craniotomy area.ResultsUsing the described system and an anthropomorphic phantom head, the system has been characterised by registering the patient’s face in 25 positions and 5 positions resulted in a fiducial registration error of 1.88 ± 0.19 mm and a target registration error of 4.07 ± 1.28 mm, respectively.ConclusionsThis work proposes a new methodology to automatically register MR and HS information with a sufficient accuracy. It can support the neurosurgeons to guide the diagnosis using multimodal data over an augmented reality representation. However, in its preliminary prototype stage, this system exhibits significant promise, driven by its cost-effectiveness and user-friendly design.

A case report to understand the use of an evidence-based approach of prolonged grief therapy in Chinese culture

Prolonged grief disorder (PGD) is a new diagnosis that may cause significant functional impairment. Prolonged grief therapy (PGT) is a manualized 16-session intervention, whose efficacy has been demonstrated in studies primarily from Western cultures. The current report aimed to present a case to illustrate the use of PGT in Chinese culture. The client was a bereaved adult suffering from PGD after the death of her mother ten years ago. Additionally, she lost her father three months ago. Questionnaires were completed before and after treatment. In-depth interview was conducted at a 3-month follow-up. The client’s scores for grief, functional impairment, grief-related beliefs and avoidance, depression and insomnia all decreased substantially after treatment. The follow-up feedbacks indicated that the beneficial effects of PGT persisted in the client’s life. This case report provides preliminary evidence that bereaved people in China could benefit greatly from PGT, with minimal cultural adaptation.

Integration of BMP-2/PLGA microspheres with the 3D printed PLGA/CaSO4 scaffold enhances bone regeneration

Treatment of large and complex irregular bone defects is a major clinical challenge in orthopedic surgery. The current treatment includes bone transportation using the Ilizarov technique and bone cement repair using the Masquelet technique, but they require long-term manual intervention or secondary operation. To improve this situation, we compared the different implanting materials in the literature published in the past 10 years, finding that glycolic acid copolymer (PLGA) and Calcium sulfate (CaSO4) are appropriated to be used as synthetic bone materials due to their advantages of easy-availability, nontoxicity, osteogenic properties and rapid degradation. Meanwhile, the development of 3D printing technique and devices makes it relatively easier to synthetize customized bio-mimetic porous scaffolds, thus facilitating the release of modified protein. In this study, we compounded BMP-2/PLGA microspheres with polylactic glycolic acid copolymer/CaSO4 (PC) 3D printed scaffold to improve the osteogenic properties of the scaffold. The result of our in vitro experiment demonstrated that the prepared PCB scaffold not only had satisfactory bio-compatibility, but also promoted osteogenic differentiation. This 3D printed scaffold is capable to accelerate the repair of complex bone defects by promoting new bone formation, suggesting that it may prove to be a potential bone tissue engineering substitute.