TECH OFFERS

In radiotherapy for patients with gastrointestinal (GI) cancer, real-time, continuous monitoring of X-ray radiation in the GI track can greatly improve the precision of the treatment. This proposed technology consists of a swallowable X-ray dosimeter capsule for real-time monitoring of absolute absorbed radiation dose and changes in pH and temperature in the GI tract. Using a neural network-based regression model and a luminescence of nanoscintillators fiber, the capsule is able to estimate radiation dose from radioluminescence and afterglow intensity and temperature. Initial preclinical study in a rabbit model showed that the dosimeter was approximately five times more accurate than standard methods for dose determination. Hence, these swallowable dosimeters may help to improve radiotherapy and understand how radiotherapy affects tumour pH and temperature. The technology owner is seeking for collaborations and out-licensing with medical institutions and medical device companies for clinical testing and further research identifying the capsule's position and posture after ingestion, developing a robust positioning system. The capsule hardware includes a highly sensitive optical fiber embedded with NaLuF4:Tb@NaYF4 nanoscintillators for monitoring low dosage of X-rays, a pH-responsive polyaniline-coated film, a customized multi-inlet microfluidic module for dynamic gastric juice sampling, two colour sensors with integrated temperature sensors, a small-sized PCB board with MCU, and a button-sized silver oxide battery. The capsule software includes APP for data collection, storage and analysis. The capsules can monitor dose, pH change and temperature on the spot in real time, and the size is small (close to the dimensions for standard size 2 capsule: 16 mm length and 7 mm outer diameter). The capsule dosimeter can be easily inserted into the rectum to monitor brachytherapy for prostate cancer. With further size optimization, the capsule could be placed in the upper nasal cavity to allow accurate real-time measurement of effective radiotherapy dose in nasopharyngeal or brain tumors, minimizing radiation damage and possible side-effects to surrounding structures. This technology can be adapted for the development of highly sensitive in vivo sensors on gas molecules, reactive oxygen species, and other physiological or biochemical indicators. To the best of the knowledge, there is no electronic capsule on the market that monitors dose delivery, pH and temperature during radiotherapy. The technology will be the first method to integrate an X-ray detector with pH and temperature detectors. In addition, the proposed technology enables X-ray detection with much higher sensitivity than other technologies.  According to a market report, the cost of radiotherapy is between USD$10,000 to USD$50,000, depending on the type of cancer, number of the treatments needed, and the type of radiation used. The cost of the capsules to monitor the accuracy of radiotherapy is less than USD$200. This market is expected to reach $279.16 million by 2025, with an estimated CAGR of 12% from 2021 to 2025. In vivo monitoring of dose delivery, pH, and temperature during radiotherapy is essential for smart medical applications. The ingestible electronic capsule that enables multifunctional characterisation is of high detection sensitivity, low cost, and simple manufacturing process. This technology offers the following benefits: High sensitivity: Synthesized materials are sensitive to X-rays. Small size: Patients can swallow comfortably. Low power consumption for long-term monitoring of pH, dose and temperature. Suitable for in vivo test and real-time detection of dose and pH changes during radiotherapy. Injestible dosimeters, Radioluminescence, Gastrointestinal cancer, Radiotherapy Healthcare, Diagnostics, Medical Devices, Telehealth, Medical Software & Imaging

Thermal management is an essential part of the design of high power density electronics. As the power density of electronic devices increases, so does the amount of heat they generate, and this heat must be dissipated effectively to prevent the devices from overheating and failing. This technology offers a method to produce high thermal conductivity boron nitride (BN) composites that aim to improve thermal management in high power density electronics, leading to more efficient, more compact, and safer electronic systems. BN composites are a group of materials made by combining boron nitride with another material, such as a polymer, metal, or ceramic. A key advantage of such composites is that they exhibit higher thermal conductivity than any commercially available material that is electrically insulating. The resultant BN composites are also low in weight, easily shaped, exhibit good mechanical properties, and offer the unique capability of designing the path by which the heat will be conducted. These properties fulfil the demanding requirements for electronic packaging in emerging markets like Internet of Things and embedded systems, autonomous vehicles, high speed computers, satellites to name a few. The technology owner is seeking for co-development and out-licensing opportunities with semiconductor and device-assembling companies that require high thermal conductivity materials. This technology consists of a method to fabricate porous boron nitride composites that exhibit high thermal conductivity for improved heat management. Using a simple and scalable process, BN microcrystal powder is functionalised with iron oxide nanoparticles. BN microplatelets are then orientated to channel heat along the direction of alignment of the microplatelets to yield BN composites of high thermal conductivity. Some features of the BN composites include: Utilises a green process to fabricate (water is used as a solvent) Exhibits higher thermal conductivity (12 W/mK) Lightweight (~1.3 g/cm3) Good mechanical properties (Stiffness ~400 MPa, strength ~3 MPa, hardness 0.5-1.5 kgf/mm2) Electrical resistivity (~30 MΩ.cm) Tunable shape and size Excellent thermal stability till 200 ºC The BN composites can be attached to electronic chips and other components, making them suitable as a thermal interface material for 3D electronics of high packing density. Possible applications include (but are not limited to): Semiconductor Aerospace Automotive Higher thermal conductivity than conventional thermal interface materials with electrical insulation Ability to customise and tailor the BN composites’ properties to efficiently channel heat into specific directions thermal management, high power electronics, thermal conductivity, electrical insulation, composite, electronics, packaging, insulation, boron nitride, microplatelet, temperature, heat conductivity Materials, Composites, Electronics, Semiconductors

Lithium-ion (Li-ion) batteries are the most developed and widespread rechargeable batteries and is expected to dominate the market in coming years. Despite the wide adoption, Li-ion batteries face challenges that result in degradation of electrochemical performance due to side reaction with the electrolyte, dissolution of electrode components, transformation and pulverization of its structure and so on. The patent pending technology proposed herein aims at improving the performance of Li-ion batteries through the application of ultrathin oxide layers which increases the cycling stability and C-rate capability of lithium-ion batteries. The technology modifies the surface of the silicon-based anode of the Li-ion battery with a thin layer of Zinc Oxide (ZnO) applied by atomic layer deposition (ALD) technology. Typically, the ZnO thickness is of order of few nanometers. The ZnO layer suppress side reactions by limiting the excessive growth of the passivation layer at the anode interface and liquid electrolyte, inhibiting the dissolution of the electrode components, and enhancing conductivity and Li-ion transfer. This resulted in  increased battery capacity particularly during fast charging and discharging and increases cycle life of battery. The technology owner is seeking to license the technology to a battery manufacturing partner who have access to ALD equipment to facilitate the integration of the anode surface modification technology into their battery manufacturing process. A special deposition technology adapted for porous materials should be applied. The deposition take place at the temperature of 100 °C. The technique can be up-scaled to roll-to-roll process suitable for industrial production. Competitive advantage includes increased service life of the Li-ion battery during fast charging and discharging, elimination of the battery capacity reduction, creation of an artificial protective and corrosion resistant passivation layer. The technology can be used in energy storage, especially in the automotive industry. As a part of electromobility (electrical vehicles, bicycles, scooters), it will ensure fast and efficient charging of the battery while maintaining the total capacity and eliminating the drop in battery capacity during charging/discharging cycles. According to the Strategic Research and Innovation Agenda - BATT4EU up to 900 GWh of batteries is estimated to be produced annually in 2030 only for electrical vehicles (~ 20 000 batteries). After 2035 only electrical vehicles will be presumably produced. The Global Lithium-Ion Battery market reached about USD 85 billion in 2022 and is projected to grow significantly, reaching a market value of more than USD 400 billion by 2030. ZnO coated silicon-graphite based anode offer improvement in capacity over the current state-of-the-art in particular at high charging/discharging rates. Capacity of the ZnO coated anode can be 5 times higher applying fast charging/discharging during 30 min. Silicon-based anode for Li-ion battery, Fast charging/discharging, Atomic layer deposition Energy, Battery & SuperCapacitor

Recent advances in soft robotics revolutionize the way robots interact with the environment, empowering robots to undertake complex tasks using soft and compliant grippers. Compared to traditional rigid structures. Soft grippers have excellent adaptability for a variety of objects and tasks. However, the existing gripper systems faces some challenges, such as handling delicate, wet, and slippery items, the risk of damaging valuable items, and high production cost. Based on pneumatic jamming of 3D-printed fabrics, the technology owner has developed a variable-stiffness soft pneumatic gripper that can apply small forces for pinching and pick-up heavy objects via stiffening. The invented grippers are soft and adaptive to handle delicate items with various shapes and weights, minimising the damaging risk of items during the gripping process. In addition, such gripper with adjustable stiffness could handle heavy and bulky items by increasing its gripping strength. These benefits make the gripper more versatile and adaptable to various applications in agriculture, food processing, packaging, manufacturing, and human-robot interaction (HRI). The technology owner is seeking to do R&D collaboration, IP licensing, and test-bedding with industrial partners intending to integrate variable-stiffness gripper in their applications.  The technology owner has incorporated the jamming of 3D-printed structured fabrics into variable-stiffness soft gripper design. The innovative gripper can actively apply small forces for pinching and pick up heavy objects via stiffening. The key features of the technology are: Lightweight and comfortable structural structured fabrics Vacuum-powered stiffness change High gripping-to-pinching force ratio Adaptable to items with various shapes and weights Safe and high precision gripping process Low material cost (made from elastic silicone) Easy fabrication (all 3D printed key parts assembled with standard components) Agriculture: food harvesting, packaging etc. Food processing: vegetable and fruit picking, food sorting, food packaging, etc. Manufacturing: packaging, assembly, dedicate item handling, etc. Human-robot interaction (HRI) Enhanced robotic performance: universal gripper with high adaptability, versatility, and precision Safe gripping process: good comfortability and high gripping-to-pitch force ratio Cost-effective system: 3D-printed parts assembled with standard components Highly customisable: meet requirements of various industrial applications Jamming, pneumatic gripper, adjustable stiffness, 3D printing, robotic gripper, agricultural gripper Materials, Plastics & Elastomers, Manufacturing, Assembly, Automation & Robotics, Additive Manufacturing

A microfluidic chip-based mechanism has been developed as a Point-of-Care Testing (POCT) device to replace Lateral Flow Assays (LFA) for fast and convenient blood analysis. The microchip system utilises the principle of immunoassays but with high accuracy and compatibility to different signalling tags, providing a quantitative readout. Conventional immunoassays involve multistep procedure and long process time. While LFAs are fast and convenient, they are qualitative. The device demonstrated a one-step assay that can achieve equal or higher sensitivities than standard methods within significantly shorter total processing time. In a microfluidic device, the sample flows in precisely defined microchannels, which allow better control of fluid behaviour and higher consistency in testing results compared to LFA in which the sample flows by wicking through the porous paper-based material. This technology resides in the assembly of components and materials to immobilise antibodies or antigens onto the chip which can be easily scaled for commercial production. The technology owner is seeking collaborations with manufacturers of IVD devices or Medtech companies to out-license the technology and expand the range of antibodies targets for the microchip. The core technologies of the invention include: Methods to prepare nitrocellulose substrate for antibody immobilization. The materials, fabrication methods and reagent integration techniques are readily compatible with high-volume manufacturing, allowing the prototype to have high potential for commercialization. Methods to prepare and storage of dried reagent on chip. The shelf-life of the dried reagents is around 3 months. The Limit of Detection (LOD) is 0.1 ng/mL with a total process time of 15 minutes. No washing steps required. The device is compatible with all antibodies and antigen immobilisation. Signalling antibodies can be fluorescence or colorimetric which can be easily paired with off-the-shelf detector. Any biomarkers that can be analysed by LFA can be used on this platform. The device can be used in medical, veterinary and other related industries for diagnosis or screening purposes. The device provides fast and accurate method for detecting biomarkers in blood. The device has been used to measure the blood concentration of Anti-Mullerian Hormone (AMH), which is an indicator for women fertility (a high AMH levels is more likely to achieve a successful pregnancy than low levels). Some examples of LFA that can be transferred to the microfluidic platform includes HCG pregnancy test, Covid ART, AMH fertility test etc. The significance for the microfluidic device is the accuracy and reliability of the results for quantitative analysis. Microfludics, Lateral Flow, Immunoassays, Blood Analysis Healthcare, Diagnostics, Medical Devices, Life Sciences, Industrial Biotech Methods & Processes

The technology consists in a new type of neural networks, providing explainable, verifiable, compact and private AI solutions. Explainability: the technology provides precise global explanations and the exact rules learned by the AI model, even with large datasets. We transform clients' raw data and/or models into meaningful results through high-quality visual analytics, empowering them to enhance the model based on these explanations. Formal Verification: the technology allows the client to formally verify certain properties of the model, such as its robustness to adversarial attacks, its fairness according to certain features, etc. Our training and testing processes are fully automated and we are currently developing a client’s side software so that users can train/verify/modify/improve/protect the models themselves. In addition the interface will provide the client a complete explanation of the inference of their models, by providing a set of logical rules that describe exactly the model.   Compactness/AI for Embedded Systems: the models resulting from our technology are extremely small, requiring much fewer logical gates and/or latency than other existing solutions, even for large datasets. There are suited for both constrained software and hardware environments. Privacy-preserving AI: Privacy-preserving AI technologies are necessary if you want to protect the data of the client during inference, but they are extremely costly in terms of computation and memory. Using our technology, you can largely reduce this cost and eventually obtain practical privacy-preserving AI solutions for tabular datasets and more. - Banking (credit scoring, customer churn, anti-money laundering, etc.) - Insurance (claims management, fraud mitigation, etc.) - Healthcare (clinical workflow, predicting ICU transfers, etc.) - Data analytics (pricing optimization, etc.) and marketing companies (content personalization, lead scoring, etc.) - Research teams (DNA, health, environment, energy) and academia - Autonomous cars (embedded AI) - Energy (AI for edge computing) - Security / Military (private, safe, compact, verified AI) and Gov agencies / Customs (responsible, fair AI) - Manufacturing, logistic, supply chain (predictive maintenance, transportation optimization, etc.) - Individual users: data analysts, AI professionals  Our AI models are the first to be optimized to work on encrypted inputs, fully guaranteeing the privacy of the user’s data. In particular, we provide the first practical solution of a privacy-preserving AI model for tabular datasets.   Our AI models are very compact and can fit even in tiny microcontrollers (software) or in a very small area (hardware). It can be naturally transformed into a set of logical rules, providing global and exact interpretability of the inference. This would be impossible with current AI models that scale to large datasets. Our AI models can formally verify if certain properties are present, such as robustness to a certain noise level, fairness, etc.). Again, this is impossible with most AI models, and especially those who scale to large datasets.   Infocomm, Artificial Intelligence

Neurological diseases are the second leading cause of death. CT scans have been used as the primary modality to diagnose brain abnormalities such as Intracranial Haemorrhage (ICH) and neurodegeneration. Radiologists usually have to deal with an overwhelming scan backlog and writing radiology reports is a time consuming process. Manual segmentation of lesions is tedious and existing heuristics have been shown to overestimate lesion volumes. Clinicians are also wary of the ‘black box’ nature of deep learning models. Hence, an automated tool in the workflow could substantially improve clinical productivity and interpretability is crucial to build trust with clinical stakeholders. Our proposed technology is an AI solution that automates ICH detection and brain tissue segmentation on CT scans, producing accurate volumetric information to assist triaging. Our technology also comes with a set of tools to interact with the AI models and generate reports easily. Moreover, we strengthen our AI transparency with interpretable models. Our platform also focuses on model robustness tests to assure AI safety.   Our core technology is our trained deep learning detection and segmentation models. Our web user interface allows visualization of the medical images and the AI predictions. Users can upload their scan using our web interface (deployed locally or in a private cloud) and obtain the results and report instantly. In the report section, users can also customize the layout of the radiology report to suit their workflow. We look forward to deploying our solution in healthcare institutions that work with CT scanners. Our technology can be deployed locally or on a secured cloud platform and integrated with local PACS systems. Our current focus area is in neurology but our solutions can be generalisable across modalities and tasks. The size of the AI medical imaging market is projected to be 20.9 billion USD in 2030. The addressable market size in Neurology and CT is 2.85 billion USD (13.6%). Our AI solution is tailored to learn Asian population brain anatomical data, which is unique in the market, therefore we are targeting to serve the Asia Pacific market which is estimated to be around 769 million USD (27%). While some available products offer solution to predict whether ICH exists in the scan, our technology automates ICH segmentation that allows accurate calculation of the lesion volume from CT scans. Secondly, most available products in the market rely on MRI scans for brain tissue segmentation, but our technology allows fast inference on CT scans. Our technology is also able to perform Alzheimer’s Disease detection using CT scans. Crucially, our solution provides ways to identify drifts, quantify uncertainty and explain model decisions in discriminative tasks, which can help build trust with clinicians. Healthcare, Telehealth, Medical Software & Imaging

Digitalisation is a global trend with digital twin technology increasingly adopted in various industrial segments including smart factories and plants, digital facility management and operation & maintenance, building and construction, etc. Rapid generation of digital twin of physically existing is desired. Conventionally, digital twin is mainly generated using design software which requires professional modellers to spend substantial design time pending on the complexity of the physical twin (to be constructed) and the manpower available. Building information modelling (BIM) is increasingly used as a representation for the digital twin. For existing environments, scan to BIM technology and authoring software products are used for the process of reconstructing of BIM models from LiDAR scanned point clouds. This manual process is typically time consuming, tedious and error prone. Often, meshed models are used for visualization purpose of the digital twin. Our innovation is an integrated solution being able to autonomously scan physical environments using robotised LiDAR cameras, automatically stitch scanned point clouds using in-house developed software algorithms, automatically recognise BIM components as well as mechanical & electrical plumping using our innovated AI techniques, and automatically convert the reconstructed BIM (not mesh models) from point cloud in IFC4.0. The solution can significantly reduce manpower needs and improve productivity from days/weeks down to hours. Ideal collaboration partners include but are not limited to builders, government agencies, smart city or smart factory planners, construction project management service providers, architecture, engineering and construction companies.   Building & Construction, Safety, Oil & Gas，etc. are relevant Industries. Potential applications include Audit & Inspection, Altering & Addition, Construction Project Management, Smart City, Smart Factory, Smart Process Plant, Smart Power Grids, etc.  A cloud-based solution can be marketed as a product for this technological innovation. Automatic BIM conversion (not mesh models) from LiDAR scanned point clouds is a significant improvement over the current manual conversion; and Rapid BIM reconstruction (not mesh models) in IFC 4.0 format is another UVP with substantial productivity improvement. Infocomm, Green ICT

Coronary artery disease (CAD) is the leading cause of death worldwide. Computed Tomography Coronary Angiography (CTCA), as a non-invasive alternative to invasive catheterized coronary angiography, has emerged as a recommended first-line investigation for CAD. However, the current practice of generating reports involves a time-intensive process, with CT specialists spending 3-6 hours annotating scans. Furthermore, there is a lack of effective tools for analysing coronary calcium scores, stenosis severity, and plaque characterization. This AI driven platform is for CT data processing that provides a streamlined 'one-stop' solution spanning from diagnosis to clinical management and prognosis. Its key features include: AI-driven platform for CTCA, catering to clinical, research, and industrial applications. Large, shareable, de-identified, Personal Data Protection Act-compliant real-world CT data. Precision toolkits for anonymization, coronary calcium scoring, epicardial adipose tissue (EAT), stenosis severity assessment, plaque quantification, CT fractional flow reserve (FFR), and reporting. The platform’s highly automated features assist physicians in interpreting and synthesizing large volumes of CT data, while minimizing bias, increasing reproducibility, and providing numerical insights in a graphical manner. It offers a comprehensive ‘one-stop’ solution for diagnosis and clinical management of CAD. Seamless integration: The DICOM-compliant parser ensures compatibility with diverse CT scanners without interfering with hospitals’ original workflow processes. AI-driven workflow: It supports fully automated analysis, including deep learning-based segmentation of the coronary artery tree, extraction of artery centrelines, tracking and acquisition of cross-section lumen images, artery labelling, stenosis and plaque detection, and quantification with high accuracy within minutes.  Comprehensive modules for CAD assessment: The technology offers a comprehensive assessment of coronary calcium score, EAT, stenosis, and plaque phonotypes. Mixed Asian registry database: It houses a vast repository of multi-ethnic imaging and non-imaging data, serving as a valuable resource for research and analysis. Annotation by SCCT-certified experts: All annotations are performed and quality-checked by experts certified by the Society of Cardiovascular Computed Tomography (SCCT). Secure and reliable data platform: The data platform is certified by the Ministry of Health Singapore, ensuring the safety and reliability of data access. The technology can be applied across various industries: Software as a clinical service for healthcare institutions: It provides comprehensive CAD assessment and personalized treatment as a software-as-a-service (SaaS) solution for healthcare institutions. Pharmaceuticals: It enables objective and quantitative measurement of the effectiveness of treatments. MedTech and digital health industry: By harnessing state-of-the-art technology and big data capabilities, it provides the development of customized foreground intellectual property, addressing the specific needs of individual companies. Local MedTech industry development: It offers tailored solutions designed specifically for small and medium-sized enterprises (SMEs) and startups, empowering them to compete globally, foster innovation in product development and services that align with market demands, and enhance patient care. It provides a thorough evaluation of the coronary arteries using deep learning algorithms and patented post-processing technologies. It serves as a ‘one stop’ platform that spans from diagnosis to clinical management and prognosis, and aiding in predicting therapy response in the pharmaceutical industry. Superior diagnostic performance: The AI toolkits deliver exceptional accuracy, surpassing 90%, while processing the data within minutes. This remarkable speed is 20 times faster than the standard diagnostic and reporting process, enabling efficient and timely decision-making. Unparalleled big data repository: The platform houses the largest mixed Asian CAD registry, comprising 5,000 patients (n=3 million images). This vast collection contains a wealth of real-world imaging and non-imaging data, representing a unique and invaluable resource that is unmatched elsewhere. Trusted ground truth: Every CT scan has been meticulously annotated and quality-checked by SCCT-certified experts. This rigorous process ensures the accuracy and reliability of the data, establishing a safe and dependable foundation for clinical decision-making. Healthcare, Telehealth, Medical Software & Imaging