Artificial Intelligence in Medicine Radiology in digital transformation – The biggest revolution since X-ray

Related Vendors

GE Healthcare Europe GmbH

Grayling Deutschland GmbH

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

With the advent of artificial intelligence in medicine, radiology is taking a leading role. The use of AI in imaging aids in the evaluation of medical data and supports doctors with precise information.

Many modern medical devices already operate with artificial intelligence in the background. The algorithms improve the quality and efficiency of patient care. Among other factors, the pandemic has further accelerated digital transformation in healthcare.

Radiology, which visualizes and evaluates body structures using X-rays or sonography, up to complex imaging techniques such as CT or MRI, benefits significantly from this digital revolution in medicine: Computer systems can perform complex image analyses more accurately and in increasingly shorter times. Radiologists play a key role between information technology and medical care.

Faster and more precise images can save lives

An example from the emergency department of the University Hospital Jena shows how doctors and patients benefit from faster processes and more accurate images thanks to artificial intelligence – speed saves lives. New patients usually complain of pulling or stabbing in the chest, shortness of breath, or tightness. Not every new patient with such symptoms immediately has a life-threatening heart attack.

However, it is precisely these at-risk patients who need to be screened out immediately and treated without delay. To set priorities, the clinic staff must diagnose quickly and as accurately as possible and categorize accordingly as "harmless or life-threatening."

Deep Learning Image Reconstruction

Since the pilot phase in 2019, the doctors in Jena have been using a computed tomography scanner with Deep Learning Image Reconstruction (DLIR) by GE Healthcare. The device is a pioneer in deep learning radiology and allows for precise imaging of the heart and highly complex evaluations, such as a three-dimensional reconstruction of the surrounding vessels – and that in a shorter time.

This enables the treating physicians to quickly decide who needs to be treated most urgently. In the past, this level of clarity would have required increasing the radiation dose and spending more time on the scans.

What is Deep Learning Image Reconstruction (DLIR)?

Artificial Intelligence aims to solve problems autonomously by automating intelligent behavior through algorithms. Computer programs identify patterns and regularities in data by analyzing vast amounts of data at lightning speed with self-learning algorithms. This can involve patterns in images – such as certain cells or anatomical structures – or relationships between different types of data, such as laboratory results and information on the treatment process.

The learned information is generalized and stored in the form of mathematical models. After successful training, the computer program is capable of responding adequately to similar new events. GE Healthcare's DLIR technology "True Fidelity" for computer tomography creates images using artificial intelligence: DLIR enables datasets to be reconstructed in such a way that they are very sharp, low noise, and high contrast, yet require a low radiation dose and therefore minimal exposure for the patient.

The image reconstruction is integrated into an imaging chain at the highest technological level – from the detector element, through data transmission, to deep learning image reconstruction. DLIR represents a particularly complex form of machine learning: Data from phantom images on one hand and high-resolution images of the patient on the other are processed and learned from at multiple levels. Thanks to DLIR, radiologists, for example, can assess the health status of the heart, brain, soft tissues, bones, and joints even more quickly and accurately.

Reduce waiting times and use resources more efficiently

"Long waiting times lead to frustration among patients and referring doctors on the one hand and on the other hand, they pose the risk that optimal therapy for the respective clinical picture can no longer be carried out due to delayed diagnosis. No doctor wants dissatisfied patients," says Christian Bernhard, MBA, General Manager of GE Healthcare DACH.

In addition to continuously improved software for imaging devices, the company also offers AI-based applications for workflow optimization in clinic and radiological practice operations. "This offer, unlike an MRI or CT, is initially invisible, but the improvements in workflow are immediately noticeable," says Christian Bernhard.

A three-month test phase of the Imaging Insights software "Smart Scheduling" by GE Healthcare followed by subsequent checks showed less downtime and higher cost efficiency while maintaining consistent image quality:

• Suboptimal appointment and resource planning as well as examination protocols can be optimized and standardized.

  Subscribe to the newsletter now

  Don't Miss out on Our Best Content

  Business E-mail

  Please enter a valid mailadress.

  Subscribe

  By clicking on „Subscribe to Newsletter“ I agree to the processing and use of my data according to the consent form (please expand for details) and accept the Terms of Use. For more information, please see our Privacy Policy. The consent declaration relates, among other things, to the sending of editorial newsletters by email and to data matching for marketing purposes with selected advertising partners (e.g., LinkedIn, Google, Meta)

  Unfold for details of your consent

  Date: 08.12.2025

  Naturally, we always handle your personal data responsibly. Any personal data we receive from you is processed in accordance with applicable data protection legislation. For detailed information please see our privacy policy.

  Consent to the use of data for promotional purposes

  I hereby consent to Vogel Communications Group GmbH & Co. KG, Max-Planck-Str. 7-9, 97082 Würzburg including any affiliated companies according to §§ 15 et seq. AktG (hereafter: Vogel Communications Group) using my e-mail address to send editorial newsletters. A list of all affiliated companies can be found here

  Newsletter content may include all products and services of any companies mentioned above, including for example specialist journals and books, events and fairs as well as event-related products and services, print and digital media offers and services such as additional (editorial) newsletters, raffles, lead campaigns, market research both online and offline, specialist webportals and e-learning offers. In case my personal telephone number has also been collected, it may be used for offers of aforementioned products, for services of the companies mentioned above, and market research purposes.

  Additionally, my consent also includes the processing of my email address and telephone number for data matching for marketing purposes with select advertising partners such as LinkedIn, Google, and Meta. For this, Vogel Communications Group may transmit said data in hashed form to the advertising partners who then use said data to determine whether I am also a member of the mentioned advertising partner portals. Vogel Communications Group uses this feature for the purposes of re-targeting (up-selling, cross-selling, and customer loyalty), generating so-called look-alike audiences for acquisition of new customers, and as basis for exclusion for on-going advertising campaigns. Further information can be found in section “data matching for marketing purposes”.

  In case I access protected data on Internet portals of Vogel Communications Group including any affiliated companies according to §§ 15 et seq. AktG, I need to provide further data in order to register for the access to such content. In return for this free access to editorial content, my data may be used in accordance with this consent for the purposes stated here. This does not apply to data matching for marketing purposes.

  Right of revocation

  I understand that I can revoke my consent at will. My revocation does not change the lawfulness of data processing that was conducted based on my consent leading up to my revocation. One option to declare my revocation is to use the contact form found at https://contact.vogel.de. In case I no longer wish to receive certain newsletters, I have subscribed to, I can also click on the unsubscribe link included at the end of a newsletter. Further information regarding my right of revocation and the implementation of it as well as the consequences of my revocation can be found in the data protection declaration, section editorial newsletter.

• The patients' waiting time for an examination was reduced from six to eight weeks to one to two weeks, depending on the device (MR, CT, mammography, and ultrasound).

"Many repetitive tasks that actually under-challenge a medical professional or nursing staff but still need to be done are increasingly becoming simpler with the help of AI – for example, in oncological imaging. Well-trained individuals can thus focus more on what they do best and fully leverage their potential," says PD Dr. Felix Nensa, Head of the Artificial Intelligence (AI) research group at the Institute for Diagnostic and Interventional Radiology and Neuroradiology at the Medical Faculty of the University of Duisburg-Essen.

This is of great significance given the increasing demand for medical personnel and the overload of radiologists and radiology technologists. The World Health Organization predicts that the need for healthcare professionals in Europe will rise to 18.2 million by 2030 [1]. Health experts anticipate that AI-based workflow solutions in radiology will double or triple this year [2].

Better MRI scans through AI-optimized reconstruction algorithms

Artificial Intelligence manages the balancing act of producing high-resolution scans while significantly reducing scan times. Because faster scanning with today's generation of devices typically results in a deterioration of image quality. During fast scans, fewer data points are captured or the resolution is reduced. Too fast scans lead to noisy and grainy images, which are more difficult for the radiologist to interpret.

However, reconstruction is the core of every MRI scan. Essential for clear MRI images that can reveal even the smallest anatomical structures is the reduction of noise during image reconstruction. The newly developed algorithm by GE Healthcare, AIR™ Recon DL, was trained using deep learning to detect and remove image noise and ringing artifacts directly in the raw data.

Sharp and detailed MRI images

Thus, it's not the finished reconstructed MRI image that is altered or adjusted, but rather the optimized algorithm starts in the raw data space (k-space). In this way, it is ensured that only image noise and artifacts are removed, while the anatomy is depicted true to the original, and individual structures or pathologies are better represented than without the use of this technology.

The result is crystal-clear and detailed MRI images. Another advantage of MRI devices equipped with the DL algorithm is that it reduces scan times for certain anatomies by more than 50 percent, allowing for more patient appointments per day or for patients to be examined with higher resolution and more sequences to achieve greater confidence in diagnosis.

The potential future of AI in radiology

According to a survey in the Automation & AI Report 2021 by the international Data & Analytics Group YouGov, around one-third of respondents worldwide believe that medicine will be strongly influenced by AI in the future. At the same time, users surveyed in 17 markets around the world indicated that they generally endorse automation in the household, production, shopping, and mobility. Nevertheless, for two-thirds of the respondents, alongside education, medicine is one of the fields in which they prefer human action over automation.

Artificial Intelligence cannot and does not intend to replace medical empathy and expertise, let alone take over medical responsibility. However, it can provide important decision-making aids to doctors and optimize cost-effectiveness. Advantages such as more precise imaging, higher speed in examination and diagnosis, and lower radiation exposure are of interest to both patients and doctors alike.

How humans and machines can complement each other

PD Dr. Felix Nensa from the University of Duisburg-Essen emphasizes the synergy of collaboration between humans and AI: "Even AI or deep learning will never work perfectly, but will make mistakes just like we humans do. For example, in mammography screening, it can happen that the AI overlooks a table tennis ball-sized tumor that we humans, even as laypeople, would recognize."

However, the same AI detects a tiny lesion in other screenings that humans would miss in 80 percent of the cases. The capabilities of humans and machines do not compete with each other; rather, they complement each other.

AI tools support medical professionals

"And here the circle closes: To more firmly establish technological progress through AI, it is crucial to highlight this very synergy and thereby strengthen users' trust in the software. Together, human and machine achieve a more precise result. Good AI tools that make medicine more precise, create work relief, and also noticeably speed up or improve things for the patient, will continue to prevail."

Thus, the future potential lies in an even stronger interconnection of human and machine, and thereby also of computer science and health sciences. Even though AI raises ethical and legal questions, it offers a great opportunity: While computers scan through ever-larger volumes of data in ever-shorter times and search for anomalies, the radiologist can focus on the interpretation and verification of data and diagnoses, collaboration with colleagues in interdisciplinary teams, and, most importantly, on conversations with the patient.

References

[1] Transforming healthcare with AI: The impact on the workforce and organizations | McKinsey

[2] Global Medical Imaging and Informatics Outlook 2022, Frost and Sullivan.