Powered by
06:07 CET
NH 14 - The new horizon for radiology
Management/Leadership Imaging Informatics Evidence-Based Imaging Professional Issues
Saturday, March 3, 12:30 - 13:45
Room: M 1
Moderators: L. Donoso (Barcelona/ES), B. Hamm (Berlin/DE)
Chairpersons' introduction (part 1)
L. Donoso; Barcelona/ES
Learning Objectives

1. To become familiar with the challenge and opportunities of artificial intelligence.
2. To become familiar with the Department of Diagnostics of the future.
3. To learn from experts how to organise integrated diagnostics.
4. To learn about integrated diagnostics from the European and American experience.

Chairpersons' introduction (part 2)
B. Hamm; Berlin/DE
Learning Objectives

1. To become familiar with the challenge and opportunities of artificial intelligence.
2. To become familiar with the Department of Diagnostics of the future.
3. To learn from experts how to organise integrated diagnostics.
4. To learn about integrated diagnostics from the European and American experience.

What will the radiologist’s job look like in 2025?
W. Kim; Los Angeles/US
Learning Objectives

1. To appreciate why some radiologists fear artificial intelligence (AI).
2. To learn about the role AI can play beyond interpretation of images.
3. To learn about how AI can augment radiologists and what we can do to maximise its positive potential.


Today, plenty of fear, hope, and hype encompass the use of artificial intelligence (AI) in radiology. Many AI experts have predicted the demise of radiology by having AI replace radiologists in the near future. These predictions have impacted the career choices of medical students, caused worries for the radiology trainees, and brought concerns to many practising radiologists. However, much of these so-called expert opinions are based on a very simplified view of what we do as radiologists. Furthermore, when it comes to AI in radiology, with media attention and many startups focused on using AI to identify findings within medical images, it is easy for us in the radiology profession to have "tunnel vision" about AI in our field. It is important to widen our view to see the many other ways AI can benefit medical imaging. In 2014, there was a Journal of the American College of Radiology article on something called the “imaging value chain” that described various processes within radiology from ordering to reporting and communication. This value chain illustrates various areas where AI can augment and improve radiology. Throughout history, radiologists have adapted to technological innovations and made adjustments to integrate them into our workflow. AI will soon become an integral part of our lives and our profession. As we learn to integrate AI into radiology, we must have a wider view to take full advantage of this emerging technology and maximise our role in patient care.

Transforming the integrated diagnosis (ID) opportunity into the Diagnostic Institute (DI) innovative change management
P. Ros; Cleveland/US
Learning Objectives

1. To learn the concept of integrated diagnosis (ID) combining the practices of radiology, pathology and genomics into an innovative diagnostic tool.
2. To understand how the computational resolution provides the technology basis for the cross-disciplinary implementation of ID.
3. To share the early experience of first Diagnostic Institute established in a large Academic Health System in the US in 2017.


In recent years, voices have been calling for tighter integration between radiology, pathology, and genomics. This multidisciplinary convergence is captured by the term Integrated Diagnostics (ID). Now is the right time for a move toward ID, based on current technology advances. One major change is that anatomic pathology is transforming from an analogue (slide and microscope) approach to a digital workflow at a rapid pace, thanks to whole slide imaging scanners and pathology picture archiving and communication systems (PACS) for large scale, clinical use. With digital pathology, the cross-disciplinary IT tools greatly expand. Moreover, there is the strong trend for quantification of image contents to enable large-scale computational analysis. We discuss three pillars for an effective ID practice The first pillar standardizes the pathways through diagnostics that can be quite complex. In our design of an ID practice, the diagnosticians would take on a larger responsibility and would directly decide on follow-up studies when the next step in the pathway is clear. The second pillar is facilitated joint radiology -genomics decision-making. The third pillar is dependent on the service level provided and perceived by the customers—the referring clinicians, patients, and, ultimately,, society. This is essential to ensure the ultimate success of radiology, pathology and genetics. The opportunities described sum up a strong call for focusing on ID as one of the key forefronts of health-care development forming diagnostic institutes.

Medical imaging and clinical laboratories: a fruitful liaison
J. E. Wildberger; Maastricht/NL
Learning Objectives

1. To understand why we should cluster the entire diagnostic chain.
2. To learn how “unity in diversity” can be achieved in a clinical setting.
3. To become familiar with the opportunities of this approach for bioinformatics, data sciences and artificial intelligence.


Setting up a global diagnostic chain offers new opportunities to optimise patient logistics and to become more (cost-)effective. As a first step, all diagnostic departments in our center were clustered into the “division of medical imaging and clinical laboratories” in 2011. In December 2016, the departments of radiology and nuclear medicine were fused. Based on lean principles (operational excellence), a framework of breakthrough objectives has been established. Achievements are shared and updated on a regular basis. From a radiological perspective, the next step to be taken is the implementation of an uniform reporting platform for imaging and pathology. In parallel, all diagnostic laboratory information systems are to be homogenised and clustered. This set-up forms the basis for a deep integration of underlying logistics, shared infrastructure, as well as for optimisation of current management information and reporting. By doing so, bioinformatics can be further developed, not only for the clinics but also in the scientific setting. Standardisation throughout the entire diagnostic chain will guarantee high quality data sets for new insights on a larger scale. Sharing this information openly and cross-disciplinary will help to further optimise patient care.

Panel discussion: How to be prepared?