Radiology Moving Beyond Imaging Through Patient Care and Management
Radiologists from All over the World Discussed the Expanding Role of Medical Imaging in Patient Care and the New Direction of Radiology.
Linda Brookes | Dec 28, 2016
At the 102nd Annual Meeting of the Radiological Society of North America held in Chicago November 27–December 2 (RSNA 2016), radiologists were encouraged to commit to building multidisciplinary teams in pursuit of better clinical outcomes – and to position themselves as an essential component of the patient healthcare continuum. Over 52,000 international delegates attended forums and had the opportunity to explore new trends and innovations in image technique. The conference also provided an opportunity for the delegates to discuss and view new technology with Siemens Healthineers at their booth.
The theme of RSNA 2016 was “Beyond Imaging” signifying that radiologists must extend their experiences beyond the constraints of the image to stay abreast of advancing subspecialty medicals knowledge and more actively collaborate with referring physicians to improve patient outcomes. Leaders expressed during RSNA discussion boards that radiologists should be instrumental in building comprehensive healthcare teams and need to be a driving force in advancing patient care.
Radiology must be part of the digital revolution and stay at the forefront of clinical imaging research and clinical practice to drive future innovation. Acknowledging the recent rapid pace of innovation, radiologists at the meeting were reminded to keep in mind the patients’ point of view. Treatment decisions should focus on what is best for the patient as opposed to what is more convenient, efficient or lucrative.
Lung cancer screening
Lung cancer screening is an important, though disputed topic in radiology, Prof. Christian Herold, MD, Chairman, Department of Radiology, Medical University of Vienna, told a media session. Lung cancer remains the most common cancer worldwide and is the leading cause of cancer mortality, accounting for one fifth of all cancer deaths, he explained.1 The 5-year survival in lung cancer patients is around 18%, but if diagnosed at early stage (localized) disease, survival rises to 55% of cases.2 Low-dose (spiral) CT (LDCT), with high resolution to define small nodules is the only effective imaging technique for early lung cancer detection, Prof. Herold stressed. Low dose is key to minimize the radiation exposure to the patient. Image acquisition and reconstruction yielding spatial resolution of at least 1 mm are needed, with additional reconstruction algorithms to identify the lesions and to perform volumetric analysis to be able to efficiently detect early growth in high-resolution, 3D- data-sets with several hundreds of slices.
“A number of significant players in the healthcare field” recommend lung cancer screening, including the US Preventive Services Task Force (USPSTF) and the National Comprehensive Cancer Network (NCCN), as well as a number of US professional medical organizations, Prof. Herold noted. In Europe, the European Society of Radiology (ESR) and the European Respiratory Society (ERS) recommend lung cancer screening. All recommendations are based on evidence from the National Lung Screening Trial (NLST), the only prospective, randomized study to show that it decreases lung cancer mortality. In over 53,000 participants, all heavy or former smokers aged 55-74 years, there was a significant 20.3% reduction in lung cancer mortality with LDCT compared with chest radiography.3 “Lung cancer screening is not an inexpensive tool,” Prof. Herold cautioned. The cost can be reduced by only screening individuals at highest risk (smokers, older than 55 years, 30 years pack, etc.), he noted.
“Adverse effects and potential harms seem to be outweighed through screening-induced mortality reduction,” Prof. Herold said. In general, radiation is a risk factor and has to be carefully considered especially in a screening procedure.. But radiation doses in lung cancer screening trials ranged from 0.6 to 1.5 mSv per CT scan. With SOMATOM Definition series scanner the CTDIvol in lung cancer screening CT would be 0.5-1.7 mGy compared with ≤3.0 mGy requirement for a standard-sized patient (170 cm, 70 kg, BMI 24), Prof. Herold noted. “So the benefit clearly outweighs the risk,” he said. It is also cost-effective, based on data from the NLST.
Artificial intelligence in radiology
Speakers at RSNA 2016 urged radiologists to embrace artificial intelligence (AI) and machine learning (ML) as tools to improve efficiency, precision and standardization. As radiologists deal with more studies per day and more images per study, AI will be able to help identify abnormalities. One potential application, discussed at the RSNA 2016, by Siemens Healthineers leveraging its collaboration with IBM Watson Health in the field of population health management (PHM), focuses on abdominal aortic aneurysm. By combining data from electronic medical records and imaging reports, it will be possible to better ensure that patients with aortic aneurysm receive appropriate monitoring, hence closing a potentially fatal care gap which can otherwise occur, when follow-ups are neglected.
Xiang ‘Sean’ Zhou, PhD, Senior Director of R&D, Head of Innovation and Software Development at Siemens Healthineers in the United States reviewed progress in the “second wave of machinist revolution” of AI, powered mostly by deep learning (the first wave started at the turn of the Millennium, when machine learning started to bring improvements in many AI fields). “This just means that machines become even more capable.” he explained “Algorithms become more autonomous and can learn with less supervision.” Deep learning-based algorithms can deal with complex and ambiguous image content and also help doctors to make complex and difficult disease decisions, he noted. One prototype, developed by Siemens and the Essen University Hospital, Germany was reported at RSNA 2016 to improve the diagnostic accuracy of a non-expert radiologist in differentiating between usual interstitial pneumonia (UIP), a disease that is fatal within 3-5 years, and non-UIP on thoracic CT. “We should view AI as a continuation of the human effort in automation and innovation, then as long as we don’t get into irrational exuberance or over-promise, it should, like many innovations in history, improve our lives and improve healthcare,” Zhou declared.
Driving value through imaging
Radiology and healthcare at large have entered a new era driven by changes to reimbursement models and an emphasis on value in patient care delivery, “There is a growing awareness among radiology professionals that value-based care is changing a perception of imaging from a revenue-producer to a cost center in healthcare organizations, highlighting the need to improve the ability to share images and avoid unnecessary procedures and duplication of studies,” commented Bernd Montag, PhD, Siemens Healthineers CEO, at a media event. “Worldwide, healthcare providers are reacting by using the paradigms of industry to improve productivity, improve quality, and standardize processes, and there is a trend from treating disease towards managing health. Our role as Siemens Healthineers is to be their partner on this journey,” he said. Whereas 20 years ago healthcare was based on a single hospital, with physicians as department heads, “now we see multi-hospital provider systems with an active C-suite management, with team-based care and quality/outcome-based performance incentives,” he noted. The goal of Siemens Healthineers is to enable better outcomes at lower cost, he declared. Siemens Healthineers is helping in the expansion of imaging, especially in fields of molecular diagnostics, advanced therapy, and digital services as well as offering strategies for customized long-term managed equipment services (MES).
“Radiology is mostly still very ‘classical’, with a patient referred, an image taken, and a short report of the findings transferred to the referring physician,” Walter Maerzendorfer, President, Diagnostic Imaging, Siemens Healthineers, observed. “But radiology is opening up, integrating more information in the diagnostic process. This offers the opportunity for radiology to transform from an image-based specialty into a more general holistic diagnostic specialty driving prevention, early detection, diagnosis, treatment, and aftercare” he said, “We at Siemens Healthineers would like to support that transformation by our technologies and our services.” He added that, “we are using our unique high-end technology position to translate this know-how into value products to make it available on a broad scale, and to make imaging affordable, also in developing countries.”
At their booth Siemens debuted a range of products and solutions designed to meet the current requirements in radiology departments and to increase clinical efficiency and decrease costs.
About the Author
Linda Brookes, medical writer based in New York and London.
About Siemens Healthineers
Our new name expresses our mission and what we stand for: Helping healthcare providers become more successful in caring for their patients.
Our new name is unique. It embodies our pioneering spirit and our engineering expertise in the healthcare industry. It reflects the fact that this industry is increasingly driven by the skills of individuals. It also contains a commitment and a promise to our customers that we will use our pioneering spirit and our engineering expertise to help drive their success.
1World Health Organization Lung Cancer Estimated Incidence http://globocan.iarc.fr/Pages/fact_sheets_cancer.aspx
2(National Cancer Institute Seer Stat Fact Sheets: Lung and Bronchus Cancer https://seer.cancer.gov/statfacts/html/lungb.html)
3(N Engl J Med. 2011;365:395−409 http://www.nejm.org/doi/full/10.1056/NEJMoa1102873#)
The statements by Siemens’ customers described herein are based on results that were achieved in the customer's unique setting. Since there is no "typical" hospital and many variables exist (e.g., hospital size, case mix, level of IT adoption) there can be no guarantee that other customers will achieve the same results.