THE CABINET

Artificial vision

Combining optical technology and artificial intelligence to improve diagnostic and industrial processes

Technical file

Type of innovation: Procedure

Scope: Clinical Analysis

Innovation leader: Shared leadership

Year: 1996

Period: 1972-2002

Geographical scope: International

Economic impact: High

Level of innovation: Disruptive

Patent: Yes

Interdisciplinary connections: -

The origins of artificial vision

The origins of artificial vision can be traced back to the invention of photography. The first ever photograph was taken by French chemist, Nicéphore Niépce, in 1826 and the science of photography developed steadily throughout the 19th and 20th centuries, and by the 1960s the first efforts to simulate human vision in computers were in progress. However, the challenge of combining optical technology with artificial intelligence to mimic human vision proved far greater than had initially been imagined. The more neuroscientists learned about how the brain processes visual images, the more aware they became of just how difficult it would be to reproduce the human visual faculty.

Using artificial vision to study clotting reactions

Instead, attention focused on specific applications of artificial vision. In hematology, one such application was in the study of clotting reactions. Such tests were performed manually, with a technician or clinician observing the formation or dissolution of the blood clot.

“A viability study into a system to detect coagulation brought important developments: the visual detection techniques on which the system was based were found to be viable and Grifols acquired technology that would lay the foundations for future efforts.”

Developing the new technology

In 1991, in partnership with the Polytechnic University of Barcelona, Grifols undertook a viability study into the development of a system to detect coagulation. Although this system never got beyond the initial stage, the project brought two developments. Firstly, the visual detection techniques on which the system was based were found to be viable. And secondly, Grifols had acquired a range of technology for the project that would lay the foundations for future efforts.

Artificial vision technology in Diagnostic Grifols products

Diagnostic Grifols would go on to incorporate artificial vision technology into a wide range of its products, including immunohematology autoanalyzers, agglutination readers, card readers, and the QPID (Quasi Positive Identification) system to safely identify cards, reagents, and samples.

Artificial vision and industrial control processes

The use of artificial vision expanded beyond the diagnostic division and was incorporated into other industrial processes, including:

  • in-line inspection of ticket printing and of application of tickets to cards.
  • in-line parameter control of gel dispensation into cards.
  • parameter control of gel and supernatant levels for card manufacturing lines.
  • in-line control of particles and foreign bodies on gel cards.
  • particle control in filling lines for bottles of parenteral solutions.
  • in-line control of labels and handles for bottles of parenteral solutions.
  • positioning control for sterile filling for manufacturing of plasma-derived medicines.

Bibliography

  • Avellà, R., & Miquel, B. (Eds.). (2015). Cuando un sueño se cumple. Crónica ilustrada de 75 años de Grifols. Barcelona: Grupo Grifols, S.A.
  • Pagès Pinyol, Josep (1993). Càlcul del temps de coagulació de la sang mitjançant processament paral·lel d'imatges en temps real. Barcelona: Universitat Politècnica de Catalunya U.P.C., E.T.S. de Telecomunicació de Barcelona, Departament de Teoria del senyal i comunicacions.