3D digital pathology imagingAI auxiliary diagnosis platform integrates 3D pathology sample preparation, high speed image scanning,intelligent software analysis into a novel system. We have collaborated with clinical pathologists to develop both 3D biopsy pathology imaging workflowthe world first 3D pathology image analysis software MetaLite, along with AI models pathology feature annotationquantitative analysis of solid tumor with high accuracy can be rapidly processed. We have transferred patented technology to start up JelloX Biotech Inc. at NTHU for further operation.

Endometriosis is a serious gynecological disease with a global incidence of 10. This disease will have a serious impact on women’s daily lives, including severe abdominal pain, massive organ bleeding, sexual behavior difficulties, infertility,even high-risk cancer progression. We discover that the karyotype variation of ribosomes is closely related to the deterioration of endometriosis. We collaborate with Hospital on human clinical trials to develop in vitro diagnostic devices that can screen early stage of Endometriosis. It can avoid unnecessary riskscosts of discovering diseases.

We propose an AI dynamics drug repurposing platform applicate on COVID-19. This platform analyzed a large number of structures of SARS-CoV, MERS,cross-species coronavirus 3CL protease-ligand complexes to construct uncovering six flexible active site conformationspharmacophore clusters for SARS-CoV-2 3CL protease screening all FDA drugsfound four inhibitors within three months. Among them, JM206 had even demonstrated ten times better efficacy than Remdesivir in-vitro assayalso show the effect on the in-vivo hamster model to alleviate the symptoms caused by COVID-19.

Multi-axis force/torque sensors are key components of precision machinesrobot arms. Development of the multi-axis force/torque sensor is a popular research topic in Taiwan. This research developed design methods, calibration machinescalibration algorithms for multi-axis force/torque sensors. These efforts contribute the enhancement of precision of 0.20 (1.25 times than commercialize pro

An innovative ointment solves an unmet clinical need to cure keloid wounds The composition of the ointment can precisely modulate the cell functionsgene expression of keloid fibroblasts, making them close to the performance of normal fibroblasts. Thereby, when applying the ointment to keloid woundsthe human body prone to the formation of keloid wounds, the wound is smoothed, healing close to normal skin.

This technology uses deep learning technology to establish six automatic organ segmentation models for six organsa graphical user interface for doctors. The data is exchanged with the existing radiotherapy planning system by standard formats. Analysis of the dosimetric parameters of the 3D printed customized bolus demonstrated that it is provided good dose escalationgood contact with the irregular surface.

An intelligent multi-wavelength lighting system was developed and the wavelength and brightness of the lighting system can be adjusted for clinical use by physicians. It is also equipped with several functions such as reminder of lighting, parameter records of use time, lighting brightness and wavelengths. The systems could help the patients adjust the physiological parameters based on the deployment of lighting system. The using lighting parameters would upload to the data base in cloud, and which can compare with the psychological evaluation parameters for treatment physical impact analysis in hospital. With the lighting system, the problem such as poor sleep quality can be greatly improved, and the occurrence probability of mild cognitive impairment and dementia can be deferred.

"The primary goal of this project is to establish a complete hospital-based liver cancer database, profiles for data feature extraction,develop different cancer, prediction models. A Medical AI program to predict the poster treatment (including operationradiofrequency ablation) recurrence of liver cancer will be established. The program system will assist doctors in the medical decision, identify high-risk patients,adjust clinical follow-up programs."

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.

CRISPR/Cas9 is the powerfulpopular genome editing technology which can recognize target gene by a single guide RNA with the advantages of precision, high efficiency, easy manipulation,low cost to be applied to promote the precision breeding of aquatic organisms. The potentials of genome editing in the precision breeding of ornamental fish are mainly focused on infertility control, alternation of colorshape, growth promotion, sex control, stress tolerance, virus resistance, etc.

A 3D wireless tracking system for minimally invasive spine surgery navigation is developed based on the mm-wave radar technique. It has the benefit of multi-target trackingsmall-sized transponder. With the cooperation of radar systemtriangulation algorithm, the maximum error of 3D positioning is less than 1.8 mm in the distance of 1.2 m

The Air/Ground cooperation for optimal rice harvesting model is established to provide a visual harvesting decision service on a cloud platform. Drones and mobile devices are employing to estimate grain moisture and forecast the variation of harvest moisture content (HMC) in the coming days by huge amounts of imagery data, deep learning algorithms, and weather forecasts. This model can benefit in several aspects, such as setting an accurate and comprehensive optimal harvest schedule, reducing the cost of agricultural apparatus and barn ovens, ensuring the rice quality, and maximizing farmers' benefits. The potential value of the model practice could be more than a billion in Taiwan.

This project will establish a National biobank consortium of Taiwan through the fund support from the government. The National Health Research Institutes will establish a Central Office for the collaboration works, which includes collecting the number of samples of the human biological database in each biobank that agreed to join the Consortium. All Alliance need to follow the same SOP for the collection processthe quality of the biosample. Adequateconsistent clinical data will also be established under the Information Security Management Treaty. Since the contents of the biobanks from different institute are quite different, we will be able to quickly establish a largecomprehensive biobank network.In line with the need of biotechnologypharmaceutical industries.

This project will establish a National biobank consortium of Taiwan (NBCT) through the fund supportgovernance from the government. All Alliance will follow the same SOP for the biomaterial collectionhave the same quality of the biosample. Adequateconsistent clinical data will also be established under well information security management. Since the contents of the biobanks from different institute are quite different, we will be able to quickly establish a largecomprehensive biobank network. In line with the needs of biotechnology pharmaceutical, artificial intelligence, auxiliary medicalother industries.

"The Crowdsourcing UAV Platform for AI Agricultural Survey(AIAS) provides automatic mosaicing serviceis equipped with four breakthrough technologies, including (1)massive images gridㄒding, (2)parallel computing technology, (3)UAV task specification standardization,(4)UAV task matchmaking. AIAS platform is committed to creating aerial UBER crowdsourcing services in various aspects, such as (1)crop distribution surveys, (2)large-scale lodging surveys, (3)agricultural insurance investigation, (4)surveys on illegal use of farmland,(5)surveys on the subsidy of fallow."

In the context of FinTech, we present Financial Graph Attention Networks (FinGAT) to recommend high-profitable stocks in terms of return ratio using time series of stock pricessector info. Our FinGAT can learn the long-short-term price tendency,model the latent interactionsinfluence between stockssectors without any hand-crafted effort. Experiments conducted on Taiwan Stock, S&P 500,NASDAQ stock markets exhibit remarkable accuracy of FinGAT, comparing to state-of-the-arts (by 11, 14,12 performance improvement). The tech is published in IEEE TKDE 2021.

We are proposing a pipeline including de novo genome assemblywhole genome SNP array design to improve the practice in precision medicineprecision agriculture. We design GABOLA, a de novo genome assembly system, combining advantages in leading sequencing platform, to construct completeaccurate individual genomes. GABOLA can resolve large structural variants, fills the gap in human reference genome,avoid the bias from reference genome. We combine the knowledge of population geneticsfunctional information to design whole genome SNP array to aid future genomic study.

Harmoscope is a virtual biopsy technology for dermatology. The superior performances of in vivo Harmoscope has been clinically validated by NTU hospital for 14 years, with the deepest penetration, super-resolution,the highest contrast all at the same time. Without imaging processinglabeling, Harmoscope raw images provide the same level of resolutioninformation as the time-consuming gold standard H&E histopathology, allowing dermatologists and pathologists to grade and classify various skin lesions for immediate therapeutic decision without physical biopsy. This award-winning technology will release the saturated loading of skin biopsy examination, greatly improve the quality of point of care, while providing a trauma-free real-time alternative for skin lesion patients.

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.

Six synchronized high-speed cameras were installed in the baseball stadium in NTUS. We established the calibration equation of the multi-camera systemestablished an electronic strike zone system, KarmaZone, that can automatically coordinates when the pitch crossed the home plate. From the slow motion videos recorded, the markerless 3D human posture estimation has been developed with the deep

Epidermolysis bullosa (EB) is an inherited blistering skin diseaseis also one of the most "urgent, severe, difficultrare" diseases. Since there are at least 21 disease-causing genes involved in EB with markedly variable manifestations, it is particularly difficult for accurate diagnosis. In recent years, next generation sequencing (NGS) has been widely applied in the genetic diagnosis of rare hereditary disorders. The EB team in NCKU established the protocol of EB diagnosis by combining NGSvarious tools of pathologymolecular studies. Till now, we have completed the genetic diagnosis for more than 50 Taiwanese EB patients.

This project proposes a smart contact lens ideally capable of simultaneously observing the tear evaporation rate, the tear osmolarity,the ocular surface temperature. To solve the shortcoming of the current difficulty in quantifying DES, assist doctors in the diagnosis of dry eye conditions, the effectivenessselectivity of drugs, the treatment statusrecovery level.

We have developed a low-costportable reader for thermometric lateral flow immunoassay (TLFIA) using colloidal goldlatex beads as reportersa continuous-wave green laser as the heating source. Instead of using infrared cameras, a single-element infrared sensor is employed for temperature sensing without compromising the sensitivity of the reader. The thermometric assay provides a 10× higher sensitivity than color visualizationthe results are sufficiently quantitative to support decision making in point-of-care testing for infectious diseases (such as COVID-19).

Here, we introduce an electricity-free centrifuge platform based on a manual centrifuge. The provided centrifugal force is sufficient to produce a plasma purity of 99 separated in as little as 2−3 min. We then performed an immunoassay on a paper devicethe results were observed by a portable reader. As a result, the detection limit of the C-Reactive Protein is 1 ng/mL, with a total turnaround time of 7 min.

This product provides "Microfluidic sensing system for on-site rapid detection of early-stage acute kidney injury" for the hospital＇s intensive care unit, operating room, nephrology departmentcardiology department. It can replace the lengthycumbersome traditional instrumentationeasily access at the point of care.

We use features such as asymmetric expression and crooked eyes to assess the risk of facial stroke. Observing the micro vibration of the head caused by the contraction of the heart, and develop a zero-contact facial heart rate and respiration rate detection technology in conjunction with the camera. The technology can accurately measure heart rate and respiration rate in real time, thereby reducing the risk of infection. This technology has obtained two ROC patents (M590433, I689285), two US patents (HEART RATE DETECTION METHOD AND DEVICE THEREOF,MOUTH AND NOSE OCCLUDED DETECTING METHOD AND SYSTEM THEREOF). The possibility of detecting strokes through AI machine learning methods is not only accurate, but also find out signs of stroke early to grasp the best time to seek medical treatment.

Surface-enhanced Raman spectroscopy (SERS) is a useful analytical technique for detecting extremely small amounts of molecules. Herein, we designed a paper-based quasi-three-dimensional SERS substrate (P-SERS) that can provide potential to improve Raman analyses for food safety, pesticide poisoning, precision medicine, drug abuse and DNA/RNA testing. The sensitive, low-cost, flexible and disposable SERS substrate could be easily fabricated by physical deposition of gold nanoparticles array onto a filter paper. In this case, we are able to create non-continuous Au islands on the fiber surfaces, where the gaps between AuNPs can dramatically generate the high electric field to enhance Raman signal of target molecules.

Monitoring PCDM-specific biomarkers, galectin-3S100A9, to serve as a risk assessment of pancreatic cancer on new-onset diabetes patients for early detection of PC.

Our technology combines optimized semiconductor manufacturing technique with unique biomediator preparation to achieve the first reliable POC biosensing platform. Sensors developed according to this method possess reproducibility, accuracy,stability that meet POC. Our sensors are portable, require low sample volume, do not require sample processing,are extremely suitable for use in POC settings. They can also be integrated into IoT systems to aide in rapid decision making,can be mass produced. Overall, we are the first to achieve accessible, reliable detection at the POC.

The screening kits were developed using miRNAs for high-risk populations for urothelial carcinoma (UC). Products 702703 are designed for chronic kidney diseasehemodialysis patients using urineblood samples, respectively. With high accuracyminimal invasiveness, the kits are intended to be used as a screeningregular monitoring of UC. If a test reveals a positive result, the patient then undergoes cystoscopic examination for further confirmation. Otherwise, the patent only needs to be monitored annually.