ACS roundtable maps advanced imaging priorities across lung cancer care
Lung cancer still leads cancer mortality in men and women, and the American Cancer Society National Lung Cancer Roundtable is framing advanced imaging as one of the few levers capable of changing that trajectory across the entire care continuum. The strategic plan from the roundtable’s Advanced Imaging Across the Lung Cancer Care Continuum Task Group does not present a single technology fix. Instead, it organizes the field around four development priorities: novel imaging technologies, quantitative imaging biomarkers, systems for sharing image data and algorithms, and imaging-related artificial intelligence solutions.
The structure is deliberate. Early detection matters, but imaging remains relevant long after a nodule is first seen on a scan. In lung cancer, the same infrastructure that identifies disease can also influence staging, treatment planning, response assessment, surveillance, and longitudinal risk stratification. The strategic plan treats imaging as a continuous clinical asset rather than a one-time screening event.
Four development priorities set the agenda for implementation
The first priority, novel imaging technologies, reflects the need to improve what clinicians can see and measure in the chest. Lung cancer care depends on precise visualization of small lesions, subtle growth, treatment-related change, and anatomic complexity that can obscure clinically important disease. Better image acquisition and interpretation can improve sensitivity at the front end and sharpen decisions later in the pathway, when distinguishing progression from scarring or treatment effect becomes just as important as identifying the tumor itself.
The second priority, quantitative imaging biomarkers, pushes the field beyond qualitative interpretation. Biomarkers derived from imaging can support more reproducible measurements of tumor burden, tissue characteristics, and change over time. In lung cancer, where management often hinges on small changes in size, density, or appearance, quantitative metrics offer a route toward more objective decision-making. They also create a bridge between imaging and the biologic behavior of the disease, which is essential if clinicians are going to use scans not only to detect cancer but also to anticipate how it will behave.
A single scan can be read; a biomarker can be tracked.
Data sharing and algorithm access remain the bottlenecks
The third priority addresses systems for sharing image data and algorithms. This is more than a technical convenience. Lung cancer imaging research depends on large, representative datasets and on the ability to validate algorithms across institutions, scanner types, and patient populations. Without shared data infrastructure, promising tools can remain trapped inside isolated centers, where they may perform well in development but fail when exposed to routine clinical variability.
The strategic plan also recognizes that algorithm sharing must work in both directions. Clinical systems need not only access to data, but also access to the computational tools that can analyze those data in reproducible ways. This matters because the lung cancer pathway is distributed across screening programs, radiology departments, pulmonology services, oncology clinics, and surgical teams. If image data and analytic methods cannot move reliably through that chain, advanced imaging will remain fragmented at the point of care.
The fourth priority, imaging-related artificial intelligence solutions, sits at the intersection of all the others. AI systems may improve detection, segmentation, classification, triage, and longitudinal monitoring, but their real-world value depends on trustworthy deployment. For lung cancer, the promise is especially relevant because imaging workloads are high and the clinical stakes are unforgiving. AI could help identify subtle lesions, standardize measurements, and support pattern recognition across large imaging volumes. Yet those same systems must be tested for generalizability, transparency, and operational safety before they can be relied on in routine practice.
Use cases stretch from early detection to downstream management
The task group links each priority to clinical use-case scenarios along the lung cancer care pathway. That approach is important because the needs of screening are not the same as the needs of staging or recurrence surveillance. In screening, the critical problem is finding actionable disease early enough to change outcomes. In diagnosis and treatment planning, imaging must support procedural decisions, staging accuracy, and multidisciplinary coordination. During follow-up, scans become a way to detect recurrence, monitor treatment response, and separate benign change from clinically meaningful progression.
This continuum creates different technical demands at different moments. A technology that improves nodule detection may not solve the problem of characterizing indeterminate lesions. A biomarker that predicts response in one context may not be robust enough for long-term surveillance. Data-sharing systems and AI tools must therefore be built with the full care pathway in mind, not just the screening stage where many discussions begin.
The plan’s value lies in that broad view. It treats advanced imaging as part of a workflow rather than a standalone innovation. That perspective is especially relevant in lung cancer, where the consequences of delay, misclassification, or inconsistent measurement can alter treatment eligibility and downstream outcomes.
Adoption will depend on workflow, evidence, and scale
The strategic plan does not claim that the field is ready to absorb these advances uniformly. It identifies challenges that hinder implementation and dissemination, and those barriers are likely to be as important as the technologies themselves. Imaging tools must fit into real clinical workflows, satisfy evidentiary standards, and operate across diverse health systems with different technical resources. They must also be usable by clinicians who face time pressure, variable image quality, and competing diagnostic priorities.
Evidence generation will remain central. Advanced imaging cannot improve lung cancer care unless it can be validated in the settings where patients actually receive care. The same is true for AI solutions, which will need consistent performance across populations and institutions. Shared data infrastructure can accelerate that validation, but only if the systems supporting it are interoperable and durable enough to survive beyond pilot projects.
There is also a practical bedside consequence to this work. When imaging is more quantitative, more shareable, and more intelligent, clinicians can potentially make faster and more consistent decisions about which lesions deserve biopsy, which patients need closer surveillance, and which treatment responses are real. In a disease where early detection remains essential and where treatment decisions often depend on subtle radiographic change, those gains could matter at multiple points in care.
A strategic plan built around obstacles, not slogans
The roundtable’s framework is notable for how directly it addresses the implementation problem. It does not treat advanced imaging as an abstract promise. It organizes the field around specific priorities, specific clinical scenarios, and specific barriers to adoption. Novel imaging technologies, quantitative biomarkers, shared data systems, and AI solutions each have a role, but none can realize its potential in isolation.
For now, the most important message is operational rather than speculative: progress in lung cancer imaging will depend on whether the field can move from isolated technical advances to integrated clinical systems. The unanswered challenge is how quickly those systems can be validated, standardized, and deployed across the settings where lung cancer is actually diagnosed and treated.