Authors Outline Steps to Better Imaging in Oncology

Precision medicine starts with getting the right diagnosis. Delivering the right medicine to the right patient at the right time can’t happen without good imaging and precise interpretations to guide treatment.

As the opportunities expand to tailor therapy to an individual patient’s cancer, the stakes are higher than ever. The days of relying on an imaging report that simply revealed a tumor’s size and location are long gone, as authors note in the current issue of the Journal of Clinical Oncology.¹ Unfortunately, the authors write, training in oncology imaging doesn’t always keep pace with technology, and that has both clinical and financial repercussions.

Authors led by Sharyl J. Nass, PhD, say the complexities of cancer diagnosis can cause 3 major types of diagnostic errors: in test selection and execution, in image interpretation, and in communication among physicians and with patients and families. Errors in interpreting imaging results are the top cause of cancer malpractice claims, the authors write, so there are incentives to incentives to train radiologists and fund fellowships for subspecialists to do the job correctly.

What are health systems to do?

The paper outlines a series of steps to improve patient access to high-quality imaging in oncology, many of which start with improving education and training, including:

• Update curricula, and use peer-to-peer learning to promote quality improvement
• Use tracking tools to assess tumor characteristics over time
• Expand fellowship training and recognize oncology subspecialization
• Promote intra- and interdisciplinary collaboration

To reduce the risk of errors, the authors call for forming second-opinion networks and cancer imaging consortia, using telemedicine to expand expertise and resources at the community level, and developing tools to boost referrals.

To increase integration and collaboration, they call for engaging tumor boards to integrate specialties for diagnosis and care management, and offer incentives for interdisciplinary collaboration.

To improve clinical support, they recommend collaborating with patients and doctors to design support tools, use patient-reported outcome measures to assess success, and embed the systems into the workflow.

Machine learning methods are needed to process the complex, time-based data, and artificial intelligence can build efficiencies that will bring more precision to the process. Training is essential before these new technologies work their way across clinical practice.

Data collection and sharing, including information from diverse populations, are needed. The authors call for “systematic approaches for data curation, anonymization, and aggregation,” as well as use of the FAIR principles: findable, accessible, interoperable, and reusable.

Such an approach could aid the transition from narrative reporting to structured image reporting, the authors say.

“With the emergence of precision oncology and the frequent introduction of new treatment strategies, the essential role for precise oncologic imaging to guide treatment decisions is growing,” they write. “The potential for harm when patients lack access to high-quality oncologic imaging can no longer be ignored.”

Reference

1. Nass SL, Cogle CR, Brink JA, et al. Improving cancer diagnosis and care: patient access to oncologic imaging expertise. J Clin Oncol. 2019;37(20):1690-1694. doi:10.1200/JCO.18.01970.