Envisioning the future of radiology

In many countries, the number of radiology examinations is skyrocketing, while the number of radiologists and imaging specialists is not keeping up with the trend. The result is a dramatically increased workload for radiologists.¹On average, they spend 11 hours each week on tackling paperwork.² A huge 61% of physicians cite bureaucratic tasks as the main cause of burnout.² Finding the right way to navigate the future successfully can seem daunting.

Artificial intelligence (AI) marks a well-established route offering holistic solutions to the growing imbalance of workload versus workforce. AI has started to transform healthcare, from bridging the gap between the number of radiologists and the demands of ever-increasing, highly complex data, to simplifying data interpretation through sophisticated algorithms that enhance the diagnostic process. When combined with the human expertise of radiologists and clinicians, this valuable tool offers vast potential to the healthcare industry.

Smart data acquisition and integration with the Syngo Carbon³ imaging and reporting solution and teamplay digital health platform has saved more than 150 administrative hours according to a study in Australia.⁴ It may also support reducing reporting time by up to 50% by automatically transferring findings to reports.⁵ The AI-Rad Companion, our family of AI-powered, augmented workflow solutions, not only reduces reporting time by more than 20% per case through automated image interpretation⁶, it also delivers more than 43% greater efficiency in radiotherapy planning.⁷

All of this industry-leading innovation in radiology is transforming productivity and patient care in terms of:

Automated actionable reporting
Smartly integrated holistic patient data
Continuously engaged and transparent patient management

The next level of AI-enhanced radiology will be marked by enriching the smart imaging value chain with groundbreaking solutions based on the latest leap forward in the field of AI: generative AI, or GenAI.

What exactly is GenAI?

This advanced form of machine learning known as GenAI generates valuable new data based on prompts and access to vast amounts of pre-existing data. Like previous AI solutions, GenAI should be understood as an almost universal enabling technology rather than one specific medical device or technology. It can empower healthcare professionals to redesign and optimize medical care at all stages, from screening and early detection to follow-up and survivorship.

As demand for imaging exams continues to grow, GenAI holds the promise of taking productivity in radiology and personalized patient care to the next level by complementing established innovations around AI and automation.

Transforming volume-based services into value-based care

Healthcare is one of the most innovative fields in our society and radiology holds huge potential for GenAI-powered solutions. But every innovation is only as effective as its adoption into the daily routine. For healthcare, this means all new solutions need to be seamlessly integrated in the clinical workflow.

At Siemens Healthineers, we envision and are developing GenAI-based solutions that can be fully integrated into the entire imaging value chain, from patient history and smart scanning to reading, reporting and communication.

This rapidly developing technological innovation can empower you to turn volume-based services into value-based care fit for the future. It can help ease the repetitive tasks and challenges faced by radiologists and technicians, easing the impact of workforce shortage and optimizing cross-system interoperability. By harnessing the revolutionary power of GenAI, you could deliver more precise patient diagnoses and treatment decisions than ever before.

Envisioning a future where tedious tasks throughout the imaging workflow are largely automated

We foresee Generative AI improving the clinical journey of patients in radiology in four key areas:

Thoroughly consolidated patient history for instant access to key patient information

Incomplete patient data can impact diagnosis, as radiologists often lack the time to consult prior data. According to the RSNA, 21% of radiology cases in hospitals have incomplete or inaccurate clinical history. GenAI has the potential to consolidate patient data across various systems for better-informed decisions on subsequent scans and protocols. It can also allow technologists and radiologists to query different sources for additional information such as lab values and co-morbidities, saving valuable time on manual and time-consuming searches.

Smartly assisted and intelligent scanning for more time to care for patients

GenAI has the potential to streamline radiology workflows and deliver tailored, reproducible, consistent exams by recommending the most suitable scanner configurations, including standard and personalized scanning protocols based on patient history. And, AI-curated patient-specific imaging and post-processing allows to focus on the most relevant information, gives optimized reading support making full use of high-end image applications.

Reliable assisted reading and reporting to handle increasing case volumes with ease

The most common errors in reporting are flawed communication (44%), under-reading (27%), and insufficient history (21%). These are exacerbated by the increasing volume of screenings and the large amount of data created from scans. GenAI has the potential to help prioritize cases based on urgency and severity and allocate them to the most available and specialized radiologist. It can also speed up image reading with optimal and predefined views. And GenAI facilitates quicker report generation by complementing existing AI based prepopulated reports with a dynamically AI-built report that includes actionable and traceable data points with graphical correlations to the original images or text sources. This enables patient data to remain structured, relevant, traceable and actionable throughout the patient journey for better disease monitoring.

Effective personalized communication for engaged patients and satisfied referrers

78.3% of radiologists have reported receiving questions from patients about their report findings, and 84% have experienced an increase in patient calls. Although this demand is justified, the radiologist’s main objective is to dedicate more time to more sensitive cases in person. GenAI can play a crucial role in enhancing patient and referrer satisfaction by providing those with no or minor findings with a personalized explanatory video. This is automatically generated upon report finalization and includes introductions, details of the procedure and cinematic renderings of the findings or key images.

¹The Royal College of Radiologists. Clinical radiology, UK workforce census 2018 report. London: The Royal College of Radiologists, 2019. www.rcr.ac.uk/publication/clinical-radiology-uk-workforce-census-report-2018

²Medscape Physician Compensation Report 2023 www.medscape.com/sites/public/physician-comp/2023

³Syngo Carbon consists of several products which are (medical) devices in their own right. Some products are under development and not commercially available. Future availability cannot be ensured.

⁴Study Dr Jones & Partners Australia, Teamplay Dose and teamplay Protocols. The statements by Siemens Healthineers’ customers described herein are based on results that were achieved in the customer's unique setting. Because there is no “typical” hospital or laboratory and many variables exist (e.g., hospital size, samples mix, case mix, level of IT and/or automation adoption) there can be no guarantee that other customers will achieve the same results.

⁵Kim, S.H., Sobez, L.M., Spiro, J.E. et al. Structured reporting has the potential to reduce reporting times of dual-energy x-ray absorptiometry exams. BMC Musculoskelet Disord 21, 248 (2020). https://doi.org/10.1186/s12891-020-03200-w

⁶Yacoub B, Varga-Szemes A, Schoepf UJ, Kabakus IM, Baruah D, Burt JR, Aquino GJ, Sullivan AK, Doherty JO, Hoelzer P, Sperl J, Emrich T. Impact of Artificial Intelligence Assistance on Chest CT Interpretation Times: A Prospective Randomized Study. AJR Am J Roentgenol. 2022 Nov;219(5):743-751. doi: 10.2214/AJR.22.27598. Epub 2022 Jun 15. PMID: 35703413. https://pubmed.ncbi.nlm.nih.gov/35703413/

⁷Ginn, J.S., et al. A clinical and time savings evaluation of a deep learning automatic contouring algorithm - Medical Dosimetry (meddos.org) https://doi.org/10.1016/j.meddos.2022.11.001

Envisioning the future of radiology

A proven track record in smart radiology

What exactly is GenAI?

Transforming volume-based services into value-based care

Envisioning a future where tedious tasks throughout the imaging workflow are largely automated

Thoroughly consolidated patient history for instant access to key patient information

Smartly assisted and intelligent scanning for more time to care for patients

Reliable assisted reading and reporting to handle increasing case volumes with ease

Effective personalized communication for engaged patients and satisfied referrers

Generative AI makes diagnosis easier in radiology

Are you interested?

Contact Us

Share

Learn more

You are entering a global domain of Siemens Healthineers.