Dr. Alexander Beasley with one of the powerful PC boards needed to develop a fast neural network.
Ziath reports on the development of Artificial Intelligence that enables discrimination between empty wells in sample tube racks from wells with a tube present which may have an obscured or poorly rendered barcode.
This work, done in conjunction with the University of Hertfordshire (UK), is part of a program of development for the next generation of Ziath barcoded tube scanners due to launch around the end of 2021.
Ziath has implemented the new Empty Well Detection feature in the latest version of its popular DP5 control software to give customers the full benefit of the new technology immediately.
The company specialises in development of innovative instrumentation control and information management products using 2D Data Matrix bar-coded tubes to simplify automation processes in life science organisations, from academia, to the biotech and pharma industries.
DataMatrix barcodes play a key role in tracking and tracing both biological and compound samples. These barcodes are usually laser-etched onto the underside of sample tubes, and the tubes are then stored in racks. Tube identification using a barcode reader that scans the bottom of the rack and decodes all the barcodes in one go has recognised issues with correctly identifying which location has a tube and which is an “empty well”.
Ambient lighting, background image noise, variation in barcode lasering and material quality all contribute to detection difficulties using traditional machine vision techniques. To further improve sample tracking and tracing – the next generation of tube scanners and readers must be able to genuinely discriminate between empty wells and wells with a tube present which may have an obscured or poorly rendered barcode.
Dr. Alexander Beasley, from the University of Hertfordshire, is an expert embedded systems design engineer with experience in machine learning. Working closely with Ziath, Dr. Beasley has used a Convolutional Neural Network (CNN) technique for feature extraction of images from a Ziath camera-based barcode reader. In this developmental project he has applied CNN to discriminate empty wells from full wells in DataMatrix-barcoded tube racks.
“The CNN I have chosen is designed to be very lightweight allowing for quick execution. When compared to the pre-existing heuristic methods, the CNN approach was almost ten times faster to execute with virtually 100% accuracy,” Dr Beasley explained.
Neil Benn, Managing Director of Ziath, said: “This is just the first deliverable from our collaboration with Alexander and the University of Hertfordshire team. We are expecting this project to revolutionise the way we decode DataMatrix tubes and help us produce the next generation of faster, lighter, go-anywhere tube rack readers. It’s an exciting development that will, very soon, improve sample tracking and tracing for scientists everywhere.”
Ziath uses Artificial Intelligence to facilitate empty well detection
, /in Product News /by panglobalDr. Alexander Beasley with one of the powerful PC boards needed to develop a fast neural network.
Ziath reports on the development of Artificial Intelligence that enables discrimination between empty wells in sample tube racks from wells with a tube present which may have an obscured or poorly rendered barcode.
This work, done in conjunction with the University of Hertfordshire (UK), is part of a program of development for the next generation of Ziath barcoded tube scanners due to launch around the end of 2021.
Ziath has implemented the new Empty Well Detection feature in the latest version of its popular DP5 control software to give customers the full benefit of the new technology immediately.
The company specialises in development of innovative instrumentation control and information management products using 2D Data Matrix bar-coded tubes to simplify automation processes in life science organisations, from academia, to the biotech and pharma industries.
DataMatrix barcodes play a key role in tracking and tracing both biological and compound samples. These barcodes are usually laser-etched onto the underside of sample tubes, and the tubes are then stored in racks. Tube identification using a barcode reader that scans the bottom of the rack and decodes all the barcodes in one go has recognised issues with correctly identifying which location has a tube and which is an “empty well”.
Ambient lighting, background image noise, variation in barcode lasering and material quality all contribute to detection difficulties using traditional machine vision techniques. To further improve sample tracking and tracing – the next generation of tube scanners and readers must be able to genuinely discriminate between empty wells and wells with a tube present which may have an obscured or poorly rendered barcode.
Dr. Alexander Beasley, from the University of Hertfordshire, is an expert embedded systems design engineer with experience in machine learning. Working closely with Ziath, Dr. Beasley has used a Convolutional Neural Network (CNN) technique for feature extraction of images from a Ziath camera-based barcode reader. In this developmental project he has applied CNN to discriminate empty wells from full wells in DataMatrix-barcoded tube racks.
“The CNN I have chosen is designed to be very lightweight allowing for quick execution. When compared to the pre-existing heuristic methods, the CNN approach was almost ten times faster to execute with virtually 100% accuracy,” Dr Beasley explained.
Neil Benn, Managing Director of Ziath, said: “This is just the first deliverable from our collaboration with Alexander and the University of Hertfordshire team. We are expecting this project to revolutionise the way we decode DataMatrix tubes and help us produce the next generation of faster, lighter, go-anywhere tube rack readers. It’s an exciting development that will, very soon, improve sample tracking and tracing for scientists everywhere.”
Discovery shows human cells can write RNA sequences into DNA
, /in E-News /by panglobalCells contain machinery that duplicates DNA into a new set that goes into a newly formed cell. That same class of machines, called polymerases, also build RNA messages, which are like notes copied from the central DNA repository of recipes, so they can be read more efficiently into proteins.
SARS-CoV-2 research accelerator: Worldwide network headed by Goethe University develops protocols for labs
, /in E-News /by panglobalFor the development of drugs or vaccines against COVID-19, research needs virus proteins of high purity. For most of the SARS-CoV-2 proteins, scientists at Goethe University Frankfurt and a total of 36 partner laboratories have now developed protocols that enable the production of several milligrams of each of these proteins with high purity, and allow […]
Waters introduces SARS-CoV-2 LC-MS Kit to advance clinical research of infectious diseases
, /in Product News /by Waters CorporationWaters Corporation has introduced a new RUO LC-MS test method to advance critical infectious disease research. Waters SARSCoV- 2 LC-MS Kit (RUO) uses an orthogonal analytical method that directly detects and quantifies SARS-CoV-2 Nucleocapsid (NCAP) peptides that initial studies have shown to yield highly accurate, quantitative results.
Phase II study shows promising results for targeted treatment for IgA nephropathy
, /in E-News /by panglobalDue to the immunological pathogenesis of IgA nephropathy (IgAN), patients used to be given immunosuppressive therapy; however, this was shown to have no long-term benefit over optimal supportive therapy.
Uniqsis makes available plug and play reactor modules for flow chemistry
, /in Product News /by panglobalUniqsis is making flow chemistry accessible to everyone, while at the same time catering for multi-step and automated reactions sequences, through the availability of an expanding suite of affordable ‘plug and play’ reactor modules. Compatible with all Uniqsis coil reactors and with an operating temperature range of ambient to +300°C, the HotCoil reactor heating module […]
New glial cells discovered in the brain: Implications for brain repair
, /in E-News /by panglobalNeurons, nerve cells in the brain, are central players in brain function. However, a key role for glia, long considered support cells, is emerging. A research group at the University of Basel has now discovered two new types of glial cells in the brain, by unleashing adult stem cells from their quiescent state. These new […]
Thermo Fisher Scientific upgrades TSX Series ULT Freezers
, /in Product News /by Thermo Fisher CorporationThermo Fisher Scientific’s TSX Series Ultra- Low Temperature (ULT) Freezers have been fully upgraded to include additional functionality to provide research, pharmaceutical manufacturing, clinical, biorepository and industrial laboratories with safeguards to deliver environmentally sustainable protection of materials, such as vaccines, cell culture media, biologics and reagents.
Porvair Sciences introduces new kit for rapid extraction of total RNA
, /in Product News /by panglobalPorvair Sciences has launched new kit for rapid extraction of total RNA from a wide range of biological samples.
FDA approves aducanumab for treatment of Alzheimer’s
, /in E-News /by panglobalThe U.S. FDA has approved Aduhelm (aducanumab) developed by Biogen, Cambridge, Massachusetts, for the treatment of Alzheimer’s. Aduhelm was approved using the ‘accelerated approval pathway’.