Technical Name |
全方位血液細胞影像與生化分析系統 |
Project Operator |
National Central University |
Project Host |
黃貞翰 |
Summary |
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. |
Technical Film |
|
Scientific Breakthrough |
Our system successfully transforms hugecomplex optical instruments into lightportable devices which break through the limitations of optical instrumentsfield of view of optical lens through the integration of diffractiondeep learning methods. It is verified that our system is capable of obtaining images under wide range up to 30 mm2resolution up to 40X microscope showing high application value in biomedical field. Importantly, high accuracy of 97.8 in blood cells resolution within 4 seconds is confirmed using our system when comparing with standard blood smear method. |
Industrial Applicability |
Chemotherapy-induced myelosuppression is a life-threatening side effect that has significantly affected the treatment to cancer patients by causing fatigue, fatal infection,excess bleeding. Our system is aiming to monitor blood cell counts of cancer patients at point-of-care setting while undergoing treatmentsCOVID-19 pandemic. Our system demonstrates great capabilities in not only prevention of neutropeniadecrease the cost of referral to hospitals, but also improve home care of cancer patientselderly comorbiditiestelemedicine to practically realize precision medicine. |
Matching Needs |
天使投資人、策略合作夥伴 |
Keyword |
Precision Medicine Deep Learning In Vitro Diagnostic Point of Care Complete Blood Count Chemotherapy High-Throughput Physical Optics Computational Imaging Image Reconstruction |