影像

These stimuli-switchable nanoparticles coated with the cleavable outer polymer coatingmultifunctional peptides may afford a new platform for anticancer drugmiR. These nanoparticles possess characteristics of environmental response, active targeting,gene/chemo combinatorial therapeutics, thus providing spatiotemporal control of posttranｓｃｒｉｐｔional gene regulation, smart nuclear/mitochondrial localization,simultaneous inhibition of multiple progression pathways of tumor cells for enhancing antitumor efficacysafety of cancer therapy.

Inorganic porous nanofibers with surfaceinterface defects are prepared through humidity-controlled electrospinninghigh-temperature annealing technology. Under the irradiation of light sources of different wavelengths (380~780 nm), the bound electrons stored in the valence band can be excited to the conduction band to form free electrons on the surface of the material, generating different intensities of microcurrents, light sensitivitymicrocurrent changes. Because the "inorganic nanofiber" technology has high uniquenesshigh product compatibility, it can be applied to a wide range of markets.

Inorganic porous nanofibers with surfaceinterface defects are prepared through humidity-controlled electrospinninghigh-temperature annealing technology. Under the irradiation of light sources of different wavelengths (380~780 nm), the bound electrons stored in the valence band can be excited to the conduction band to form free electrons on the surface of the material, generating different intensities of microcurrents, light sensitivitymicrocurrent changes. Because the "inorganic nanofiber" technology has high uniquenesshigh product compatibility, it can be applied to a wide range of markets.

With the rise in computing power, deep-learning based computer-aided diagnosis systems have gained interest in the research community. Our system process the images to assist doctors to determine whether the patients have nodules in lungs. Meanwhile, we utilized the Feature Pyramid Network to extend the receptive field on the convolutional kernel, which improved the performance on the nodule detection with various locations in CXR. The semi-supervised learning mechanism also achieves the way of soft-annotation to reduce human effort in medical image annotation.

This study built an automatic insect pest image identification system based on tiny Yolov3 deep learning model. By optimizing the tiny Yolov3 detection model, images of insect pests on scanned sticky paper can be automatically identified. The system achieves a testing accuracy of 0.93, 0.90 for whitefliesthrips respectively.

The proposed TOA-STFM is a spatiotemporal image fusion technology that can preserve top-of-atmosphere (TOA) reflectance. By fusing high spatial (Landsat-8SPOT-6)high temporal resolution (Himawari-8) images, the fused 10-minute-6~30-meter-resolution images can solve the problem of existing air quality monitoring techniqueseffectively capture the dynamic changes of air quality in near-real-time.

Two indoor positioning techniques are presented. The first one is a monocular vision based landmark matching scheme for identifying absolute indoor locations. The scheme requires just one photo shotmatches it with a landmark database to obtain the location. The landmark data base can be easily adapted to different fields. The proposed scheme is highly computing efficient. The correct landmark identification rate is up to 90the positioning accuracy is 1.5m. The second one is a relative positioning scheme based on ultra-wide band (UWB) technology. It can be employed on an automatic guided vehicle (AGV) to implement the trailing function. The accuracy of positioning is 80cm.

This theme is designed to implement the robot＇s appearancepractical functions. Apply PSPNet to detect the walkable planeYolo to detect obstacles, so that the robot has the autonomous obstacle avoidance function, informing more information about the environmental obstacles around the visually impaired,apply CNN to locate indoor position with self-built indoor database.

High-accuracy 3D sensingAI image processing system for constructing high-quality immersion 3D image for AR/VR. Chaotic Lidar with APD arrayTOF sensors supports millimeter-accuracyinterference-avoiding capability. High-performance CNN processor supports high-performancelow DRAM bandwidth computations for various image AI applications.

A CMOS image sensor is developed for the national space organization (NSPO) 3rd generation high-resolution remote sensing satellite,the main achievement is its capability to satisfy the demanded ground resolution of 0.5 m. This CMOS image sensor with a new time delay integration circuit is implemented using Back-Side Illumination CIS 0.13 μm technology. The anti-radiation capability of the chip is also boosted to extend the lifetime of the chip. Measurement systemdata analysis programs are developed to provide performance parameters of the proposed CMOS image sensor.

We have successfully developed a multiphoton-induced hyperspectral microscopy based on a 1064 nm femtosecond excitation source. Nonlinear excitation by the laser localized to the focal point allows efficient non-descanned detection (NDD) while achieving optically sectioned imaging. The use of 1064 nm laser excitation increases the imaging depth while minimizing sample damage. The system combines the advantages of NDD for 3D imagingrich spectral information through confocal hyperspectral imaging, leading to potential applications in the emerging material R&Dbiomedical research.

Our system is achieved by integrating diffractiondeep learning methods, which allows high-throughput lensless imaging system to display wide rangehigh-resolution images. In addition, the developed extraction chipsprototype were verified to accurately detect the numberproportion of blood cells under low blood demand. Our system shows great potential in point-of-care blood cells monitoring for cancer patients that could reduce infection riskmortality rate, increase efficacy of chemotherapysupport precision medicine.

Integrating deep learning, 3D information analysis, hyperspectral analysis, computer vision analysiscombined the multi-source images to develop fruit quality monitoring techniques, including: planting area monitoring, position monitoring, yield monitoring, harvesting time prediction, fruit maturity measurement, fruit quality testing, to achieve the goal of enhancing industrial value.

Artificial intelligence 3D sensing image processing system based on array sensing Lidar aims to construct 3D image with high-quality immersion for AR/VR. The developed 3D scene recording system is based on the color camerahigh-accuracy chaotic LiDAR. The chaotic Lidar with APD arrayTOF sensors supports millimeter-accuracyinterference-avoiding capability within 100 meter in both indooroutdoor environments. High-performance embedded CNN processor supports high-throughput, high energy-efficient,low DRAM bandwidth computations for various image AI applications.

Combined with monitors in markets, stores,transportation stations, AI image recognition technology is used to detect crowdspeople without masksbroadcast warnings,assist the government in epidemic prevention-related work.

The Al-based web diagnostic system provides an online assessment tool for diagnosing schizophrenia. The Explainable Deep Neural Network classifier is deployed to analyze gray matterwhite matter to derive diagnostic classification of schizophrenia. The structural brain abnormalities associated with schizophrenia is visualized on the AI-based web diagnostic system at individual level.

This product is a novel risk assessment tool for carotid artery stenosis and stroke. This is a revolutionary healthcare technology using motion analysis and quantification to extract information from pulses for risk assessments. The entire process is completed by taking a short video clip aimed at the neck with only one simple click on any mobile devices or our apparatus, anywhere, anytime. In less than five minutes, the user receives an evaluation report indicating low to high stroke risk. Our product accuracy stands higher than 90% when compared to the clinical outcome. The future indications of this product can be extended to arrhythmia, venous fistula obstruction, etc. This product has the great potential to achieve our dream of “personalized mobile hospital” in the future world.

This work synchronizes electrocardiograph to narrow-band imaging with high-power lens to observe the micro-circulation on the skin. The time difference among the arrivals of the cardiac pulse wave on different parts of the path is then used to calculate the pulse wave velocity of the arteries, providing very helpful diagnosis of diseases closely related to the peripheral circulation.

This project developed a CMOS Image Sensor (CIS) for the 2nd generation remote sensing satellite,its main achievement is to improve the ground resolution (also known as the Ground Sampling Distance, GSD) from 2 meters to sub-meter. The 12-cm large size chip of CMOS image sensor is implemented using Back-Side Illumination (BSI) CIS technology with mask stitching technologyutilizing the CMOS Time Delay Integration (CMOS TDI) technology in this design.

In CB-XLCT imaging, when nanophosphors are delivered to tumor tissues,irradiated by X-rays, luminescent light with wavelength range of 500-700 nm will be exciteddetected by optical camera from different directions. After reconstruction, it can provide tumor locations. The micro-CT subsystem also provide X-rays to excite nanoparticles for luminescence tomography.

The RL model develops a control policy directly from experience to predict statesrewards during a learning procedure. Hence, we designed a medical image environment including US images, different actions,rewards, agent learns in this environment to extract the ALN regionevaluates the status. The performance of our proposed method achieves an accuracy of 83.6, a sensitivity of 88.6,a specificity of 89.0.

In order to develop an AI model that can accuratelycompletely segment coronary arteries, our team, the TW-CVAI, has established a training dataset composed of strictly verified annotations of coronary lumen boundaries in coronary CT angiography (CCTA). We designed a deep learning model, two-channel 3D-UNet, with a priori prerequisite (vesselness prior) to facilitate identification of vascular structures. The final model, the TaiCAD-Net, greatly shortens the CCTA interpretation time from 6 hours to 10 minutes, with the overall segmentation accuracy of 86 by Dice similarity coefficient.

The HeaortaNet is developed by the TW-CVAI team. The HeaortaNet is a deep learning model trained by 70,000 axial images from 200 patients with verified annotations of the pericardiumaorta. It shortens the time for data processing from 60 minutes, by manual segmentation of both pericardiumaorta, to 0.4 seconds. The segmentation accuracy, as assessed by dice similarity coefficient, is 94.8 for the pericardium,91.6 for the aorta. The imaging-based Cardiovascular Risk Prediction module was constructed by analyzing data from the National Health Insurance Databank.

The technology is video-based blood pressure monitoring which will help people know the continuous BP status in real time. Also, the contactless measurement can make a daily health record. We have conducted clinical trials in hospitalsestablished a large database to optimize AI solution. The system joins the physicians＇ specialty to analyze the users＇ health status with AI,takes care of human life with technology.

This project is to implement a 37-40 GHz mmWave transceiver supporting 4096 QAM modulationis utilized for long-distance 4K/8K real-time image data transmission. The 37-40GHz band is divided into 500 channels,the AI technology is used for the TRx to carry out digital calibration. The achievement is TRx module (SoC/SiP)would be installed on the UAV for wildlife resources monitoring.

As we continue to face the rapid increase in confirmed Coronavirus cases around the world, we created an AI-based pneumonia detection platform for COVID-19. The system is able to automatically detect high-risk patients with pneumonia that will then send information to doctors. With that information, the doctors are then able to make follow-up decisions and provide a treatment plan after the diagnosis. In specific, doctors from the Department of Medical Imaging provided us thousands of positive and negative chest x-rays for pneumonia as a training set. Our system has already been tested with and adopted by doctors at the NCKU Hospital. The system achieved 95% accuracy to detect the pneumonia symptom, based on 1400 test images.

The AR-assisted endoscopic navigation system for brain surgery combines CT/MRI images, 3D cerebrovascular/nerve models,endoscopic images for surgical planningnavigation. AR glasses can display the 3D navigation inside the patient＇s skull, providing surgeons with intuitive 3D surgical navigation. In addition, the cerebrovascular/nerve model is also superimposed on the endoscopic image, allowing the surgeon to predict the upcoming surgical situation. The AR display endoscopic images can be simultaneously transmitted to the remote site for assistance through 5G communication.

The computer-aided nodule detection system in CT image consists of the search sliding window, YOLOv2 architecture, 3-D CapsNet, skip connection,post-processing. First, the CT image is divided into numerous VOIs by sliding window. Second, a 3-D CapsNet based on YOLOv2 architectureskip connection is applied to the VOIs for classifying VOIs as nodulenot. Finally, the non-maximum suppression algorithm is performed to decide the final detection result.

Our team construct an AIoT smart aquaculture management system. The management system mainly consists of: (1) Image Behavior MonitoringAnalysis Subsystem (2) Smart Feeding Subsystem (3) IOT Subsystem including underwater sensors, ROV,Drone (4) Cloud Subsystem (5) Big Data Analysis Subsystem.

Low-power deep learning accelerator integrates neural network design / training, model compressionaccelerator design. It uses a small amount of computationmemory footprint to realize high performance on the edge device. The image semantic segmentation technology can reach 80 frames per second (resolution:1024*2048) to meet real-time requirements for autonomous driving.