Lab Automation Improves Efficiency and Insight

Computer vision and other types of artificial intelligence accelerate work in the lab.

Lab Automation Overview:

  • In hospitals and health systems, clinical lab automation enables high accuracy and fast turnaround time for diagnostic testing.

  • In research and pharmaceutical development, lab automation helps scientists perform a large number of experiments in a short amount of time.

  • Intel® technologies power lab automation solutions that range from computer vision–enabled robotic arms to high-performance image analysis.

BUILT IN - ARTICLE INTRO SECOND COMPONENT

Laboratory automation is freeing technicians and scientists from time-consuming manual tasks, so they can focus on more important work. Patients can receive their diagnoses fast, getting the timely care they need. New drugs can be tested rapidly, leading to breakthrough treatments. In this lab of the future, artificial intelligence is taking automation to the next level.

 

Whether running a simple blood test or analyzing the effects of a potential treatment on a cell culture, some of the most important answers in health and life sciences come from the lab. A lab thrives on high accuracy, fast speeds, and high throughput. The more efficiently a lab runs, the faster researchers can make discoveries and clinicians can make diagnoses, accelerating the delivery of world-class care.

Lab automation involves a set of technologies to automate manual, high-volume tasks in clinical or research labs. In a growing number of cases, these technologies involve lab robotics and artificial intelligence (AI), including machine learning, deep learning, and computer vision. Laboratory robotics and automation can be applied to a range of processes and equipment, from benchtop instruments to stand-alone systems to microscopes. Depending on how they’re used, lab automation systems may be single-function or combine many different functions.

Clinical Lab Automation

Automation in a clinical laboratory focuses mainly on ensuring accuracy while accelerating the time and efficiency of diagnostic testing. Clinical labs tend to run around the clock. It’s extremely important for technicians in these labs to manage the large number of tests coming in from one or more hospitals or clinics.

The latest solutions in clinical lab automation use computer vision to read barcodes, identify samples, and help robotic arms make accurate movements. Clinical labs are also exploring the use of machine learning in areas like digital pathology, which requires a high level of compute performance on edge servers.

Research and Pharmaceutical Development

Liquid-handling robots, genomics sequencers, high-content screening (HCS), and high-throughput screening (HTS) are among the lab automation systems helping scientists accelerate research and pharmaceutical development. Researchers can perform an incredibly large number of experiments, which can lead to the discovery of new drugs, cancer therapeutics, and other treatments. Machine learning and deep learning are particularly valuable in research labs, with algorithms that accelerate HCS and other imaging workloads.

For example, to support early drug discovery through HCS acceleration, Intel and Novartis used deep neural networks (DNN) to cut the time to train image analysis models from 11 hours to 31 minutes1. The team used eight CPU-based servers, a high-speed fabric interconnect, and optimized TensorFlow to process microscopic images significantly faster. This solution helps researchers study the effects of thousands of chemical treatments on different cell cultures and evaluate the potential effectiveness of various drugs.

Benefits of Lab Automation

Automating manual processes in the lab leads to a number of benefits, most notably time savings. But even more important is what’s at stake when tasks are completed faster while maintaining accuracy. For example, when researchers can rapidly run a million compounds against a drug target, they can discover a breakthrough treatment at a speed never before possible.

  • Error reduction. By design, lab automation reduces the possibility of human error by taking manual work out of the process2. This also supports reproducibility and consistency in testing.
  • Fast turnaround time. Automated systems can perform high-throughput screening and other experiments at a pace not possible when performed by humans, all while maintaining accuracy.2
  • Strategic use of human staff. Lab technicians and scientists can work at the higher end of their skill sets and focus their attention on strategic tasks, rather than being tied up with repetitive work.
  • Cost reduction. Lab automation systems may help lower costs by reducing reagent volumes needed and minimizing waste.
  • Workplace safety. By minimizing the need for human intervention, lab automation can help technicians limit exposure to pathogens and harmful chemicals or injuries caused by repetitive motions.

Intel and Novartis used deep neural networks (DNN) to cut the time to train image analysis models from 11 hours to 31 minutes1.

Lab Automation Technologies

From robotic arms to image processing, Intel® technologies power the latest lab automation solutions. Our broad portfolio of compute technologies gives instrument manufacturers a range of computing options that meet power and performance requirements, along with software-enabled capabilities for vision and other types of AI.

Additionally, servers and storage built on Intel® technologies provide a strong foundation for data management throughout the lab. This supports the principles of FAIR data—making data findable, accessible, interoperable, and reusable to automated systems without human intervention.

Intel® Technologies for Lab Automation
Intel® Core™ processors and Intel Atom® processors Intel processors deliver the right level of performance and power consumption needed to automate processes in the lab. Ideal for sample handling and retrieval, sorting, centrifugation, and other pre- and postanalytical functions.
Intel® Xeon® Scalable processors Intel® Xeon® Scalable processors deliver high performance for edge servers in the lab, especially useful for high-content screening (HCS) and other types of imaging.
Intel® Movidius™ VPUs Intel® Movidius™ VPUs are designed for computer vision at the edge. These low-power VPUs enable barcode reading, robotic arm movement, sample analysis, and much more.
Intel® Optane™ persistent memory and SSDs Intel® Optane™ persistent memory and solid state drives (SSDs) support large in-memory applications, ideal for imaging and AI workloads in lab automation.
AI Software Tools3 For developers, Intel offers software libraries and optimizations for popular frameworks like TensorFlow and Caffe to boost performance on Intel® architecture. The Intel® Distribution of OpenVINO™ toolkit streamlines the development of vision applications on Intel platforms, including VPUs and CPUs.
Intel® Wi-Fi 6 and Intel 5G With support for the latest Wi-Fi and 5G standards, Intel is streamlining the process of connecting instruments in the lab. High-speed connectivity enables remote control, real-time monitoring, and other edge-to-cloud use cases.

Enabling the Lab of the Future

The Internet of Things has already begun to break down data silos and enable a new level of automation. Microscopic images are processed in real time. Experiment results can be analyzed and shared with labs around the world. Sensor data can be applied to AI algorithms to inform predictive maintenance, which in turn prevents instrument downtime.

Faster processing, storage, and network technologies will continue to enhance the efficiency of the lab of the future. For example, researchers at the Translational Genomics Research Institute (TGen) are sequencing patient genomes, then performing genomics analytics on a high performance computing (HPC) infrastructure powered by Intel® Xeon® Scalable processors. Using modern HPC hardware to perform analytics faster enables genetics counselors and physicians to identify more-timely treatment options. Modern HPC hardware also provides a foundation that empowers researchers to apply machine learning methods to massive amounts of data, revealing insights that can take precision medicine to new heights.

TGen has built a high-performance computing (HPC) infrastructure. Optimized for life sciences, it includes Intel® Xeon® Scalable processors, Intel® Optane™ memory, and Dell rack servers.

As clinical, research, and pharmaceutical laboratories become more connected and automated, Intel will provide a foundation of technology that moves, stores, and processes data efficiently. Whether it’s genomics analytics in the cloud or robotic arms at the edge, Intel® technologies enable intelligence at every step in the automated lab.

Frequently Asked Questions

Lab automation uses robotics, AI, and other technologies to automate manual, high-volume tasks in clinical or research labs.

Automation can accelerate turnaround time and discoveries in both clinical and research labs. This includes labs in hospitals, pharmaceutical and biotech companies, universities, and other research institutions.

Laboratory robotics and automation are powered by a range of hardware and software, sometimes with special capabilities for computer vision or other types of AI.

Notices and Disclaimers

Intel® technologies may require enabled hardware, software, or service activation.

No product or component can be absolutely secure.

Your costs and results may vary.

제품 및 성능 정보

1

단일 노드 시스템에서 8소켓 클러스터로 확장하여 21.7배 속도를 기반으로 하는 20배 클레임 8소켓 클러스터 노드 구성: CPU: 인텔® 제온® 6148 프로세서 @2.4 GHz, 코어: 40, 소켓: 2, 하이퍼스레딩: 사용, 메모리/노드: 192 GB, 2666MHz,NIC: 인텔® Omni-Path 호스트 패브릭 인터페이스 (인텔® OP HFI), TensorFlow: v1.7.0, Horovod: 0.12.1, Open MPI: 3.0.0, 클러스터: ToR Switch: 인텔® Omni-Path Switch. 단일 노드 구성: CPU: 인텔® 제온 Phi™ 프로세서 7290F, 192 GB DDR4 RAM, 1x 1.6 TB 인텔® SSD DC S3610 시리즈 SC2BX016T4, 1x 480 GB 인텔® 수학 커널 라이브러리 (인텔® MKL) 2017/DAAL/인텔 Caffe. *참조: BBBC-021: Ljosa V, Sokolnicki KL, Carpenter AE, 검증을 위한 주석을 단 고처리량 현미경 이미지 세트, Nature Methods, 2012. ImageNet: Russakovsky O et al, ImageNet 대규모 비주얼 인식 챌린지, IJCV, 2015. TensorFlow: Abadi M et al, 이종 시스템에 대한 대규모 머신 러닝, tensorflow.org에서 제공되는 소프트웨어. 특정 시스템의 특정 테스트에서 구성 요소의 문서 성능을 테스트하십시오. 하드웨어, 소프트웨어 또는 구성의 차이가 실제 성능에 영향을 줄 수 있습니다. 구매를 고려하고 있는 경우 다른 정보 소스도 참조하여 성능을 평가하십시오. 성능 및 벤치마크 결과에 대한 더 자세한 내용은 www.intel.co.kr/benchmarks를 참조하십시오. 인텔® 기술의 기능 및 이점은 시스템 구성에 따라 달라지며 지원되는 하드웨어, 소프트웨어 또는 서비스 활성화가 필요할 수 있습니다. 성능은 시스템 구성에 따라 달라집니다. 어떠한 컴퓨터 시스템도 절대적으로 안전하지는 않습니다. 시스템 제조업체 또는 소매점을 통해 확인하거나 intel.co.kr에서 자세한 내용을 알아보십시오.

2“Advantages and limitations of total laboratory automation: a personal overview,” Clinical Chemistry and Laboratory Medicine (CCLM), February 2019, degruyter.com/view/journals/cclm/57/6/article-p802.xml.
3

성능은 사용, 구성 및 기타 요인에 따라 다릅니다. www.Intel.com/PerformanceIndex에서 자세한 정보를 확인하십시오.