Upcoming WebinarsMore Webinars
David Burden explaining recent developments around Virtual Humans
Author of Virtual Humans: Today and Tomorrow
AI Business is part of the Informa Tech Division of Informa PLC
This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067.
Machines are getting smarter and for many professionals working in the sector, the improvement in cognitive technologies offers many exciting implications. For radiologists, faced with shrinking workforces and increasing rates of interpretation and errors, this could provide answers and solutions.
From the 1996 checkmate of Deep Blue against Garry Kasparov, to the 2011 machine vs. man victory on Jeopardy, and finally, one of the world’s best Go players admitting defeat in 2016, It is clear that we are now at an inflection point. Broader applications, made possible by the exponential growth of computing power, are offering manufacturers like Siemens Healthineers, opportunities to develop solutions that will help their customers transform their field.
Medical imaging of course plays a major role in the rapidly evolving realm of Artificial Intelligence (AI), but the disruption will go much further. According to The Economist many in the sector are now embracing the technology as a tool for augmentation in the workplace:
54% of healthcare leaders believe that in 5 years, the role of AI in medical decisions will expand considerably
“Radiology is set to transition from just an image-based specialty to something that integrates more and more information into the diagnostic process and into the process of guiding treatment and treatment decision support. So the way we see it, radiology has the chance to become the information integration and interpretation platform within medicine,” argues Walter Maerzendorfer, President Diagnostic Imaging, Siemens Healthineers.
AI is a computer-aided process for solving complex problems, like pattern recognition, speech recognition, and knowledge-based decision support. While classic algorithms follow fixed paths laid out by the programmer, machine learning (ML) algorithms work out the way to the solution independently, based on exemplary data.
There is also “Deep Learning”, which in many cases is superior to traditional ML algorithms. These algorithms are trained and improved by adding high volumes of data simultaneously, equipping them to continuously improve their error rate performance expectations. Siemens Healthineers has been involved in the field of Machine Learning since the 1990s. This is reflected by more than 400 patents in the field of machine learning, 75 basic patents in the field of "Deep Learning" and more than 30 AI-powered applications.
Unlike the AI pioneers in the 1980s and 1990s, today we have sufficient volumes of training data and the computing capacities to allow the implementation of deep - neuronal networks.
High quality data is recognized as the fuel for continuously improving results. Therefore, over the last few years, Siemens Healthineers has invested in a dedicated advanced reading and annotation team, building a database of more than 100 million curated images, reports, clinical, and operational data to train their algorithms on. This database serves as the backbone of the fast-growing Siemens Healthineers portfolio, making numerous products and services with built-in AI a reality for the sector.
The fields of application of AI in Diagnostic Imaging range from workflow optimisation on the scanner to support for the radiologist in diagnostics by means of quantitative biomarkers. The goal is therefore not a competition between man and machine but clinical improvement where the machine augments the working capacity of the professional.
In the clinical workflow, there are five main areas where “man + machine” can achieve tangible clinical improvements. The first is in the examination phase, where intelligent and automated scan procedures can support the image acquisition. Secondly, is in the detection phase, measurements, segmentation, and land marking, complemented with AI, can play a major role. Thirdly, in the characterization phase, AI helps finding abnormalities, then comparing it to the normal population. Next, AI also assists in fully computer-acquired diagnoses, findings, and also disease biomarkers. And finally, AI is transforming the therapy decision support phase, listing and ranking treatment options to support faster, more confident decisions.
In the last two years, Siemens Healthineers has completed extensive strategic research to draw the picture of the future in radiology: From analysis of mega-trends in the market to technology trends and deep machine learning, big data, and data analytics, technology with built-in AI is proving to be transformational in the healthcare market.
“Our R&D activities are being infused with AI technology, creating a range of new opportunities. We can see this in population health management level, where the episodes of single patients are accumulated in a collective data pool, even beyond the country level. And these data pools can be used to tap into with data analytics to learn what works in healthcare, and what doesn’t, and draw conclusions for the right standards of care for the individual patients”, argues Siemens’ Maerzendorfer.
Ultimately, the healthcare sector seems to be well on the way when it comes to AI. Translating the learnings from these big data pools into tailor-made diagnostics, then designing treatment approaches for the individual patient by drawing on data-driven precision medicine. That’s what it’s all about.
More on AI at Siemens Healthineers
The Economist, 'The future of healthcare 22 November 2017'
Author of Virtual Humans: Today and Tomorrow