Q&A: FDA grants 510(k) clearance to AI-powered lung nodule management tool

Key takeaways:

• The FDA recently cleared Qure.ai’s qCT LN Quant AI solution for lung nodule management.
• Early detection, precise tracking and streamlined workflow are some pros of using AI in the lung cancer space.

The FDA has granted 510(k) clearance to qCT LN Quant, an AI solution that aids clinicians in finding lung nodule diameters, malignancy risk and management approaches, according to a manufacturer-issued press release.

Key features of qCT LN Quant (Qure.ai) outlined in the release include solid lung nodule quantitative characterization, growth tracking, 2D and 3D reconstructions and generation of Brock malignancy risk scores, as well as Fleischner Society guidelines-based management suggestions, all established from a patient’s chest CT scan.

To learn more about qCT LN Quant’s features, how clinicians can start using it and the pros and cons of using AI in the lung cancer space, Healio spoke with Bhargava Reddy, BTech, chief business officer for oncology at Qure.ai.

Healio: What was the inspiration behind qCT LN Quant?

Reddy: We at Qure.ai believe that there is always room to make good things better. With qCT LN Quant, the goal was clear: to create a tool that provides precise quantitative characterization of lung nodules on CT scans and enables the tracking of volumetric nodule growth over time, ultimately improving lung cancer surveillance and patient outcomes. Without AI, this task is a tedious manual effort, which increases the overall cycle time per CT.

The inspiration behind qCT LN Quant stemmed from the clinical need to take lung cancer care to the next level through advanced AI tools that support radiologists and pulmonologists in providing better clinical management to patients. It builds on the success of AI in detecting incidental pulmonary nodules using chest X-rays across various care settings, particularly in regions with low lung cancer screening CT uptakes.

Healio: How do the four different lung nodule diameter measurements found through qCT LN Quant benefit clinicians? Without this tool, how do clinicians find these diameters?

Reddy: The four different lung nodule diameter measurements — average, short-axis, long-axis and effective diameters — offer clinicians a comprehensive understanding of the size and shape of lung nodules. These detailed morphological data help in assessing the risk for malignancy, tracking changes in them over time and making better-informed clinical decisions. Without qCT LN Quant, clinicians typically rely on manual measurements using standard imaging tools, which can be time-consuming, prone to variability and less precise.

Healio: Other features of qCT LN Quant include Brock malignancy risk scores and Fleischner Society guidelines-based management suggestions. What was the reasoning behind incorporating these into this AI solution?

Reddy: Incorporating Brock malignancy risk scores and Fleischner Society guidelines into qCT LN Quant streamlines the process for clinicians by combining nodule quantification with evidence-based risk assessments and management suggestions, providing a one-stop solution. This integration promotes consistency, improves workflow efficiency and enhances patient safety and outcomes.

Healio: How can clinicians start using this AI solution?

Reddy: Clinicians can start using the qCT LN Quant AI solution by integrating it into their radiology workflows to enhance the analysis and management of lung nodules.

The tool offers advanced quantitative characterization, measuring average, short-axis, long-axis and effective diameters of solid lung nodules. It allows for detailed analysis of morphological data across single or multiple thoracic studies, including tracking nodules over time and estimating volume doubling time.

Additionally, qCT LN Quant provides 2D and 3D reconstructions of the nodules, Brock malignancy risk scores and Fleischner Society guidelines-based management suggestions, aiding in consistent and reliable clinical decision-making.

Importantly, qCT LN Quant is potentially eligible for reimbursement under two CPT codes — CPT 0722T for tissue quantification and a 3D reconstruction code — making it a financially viable option for health care providers.

Health care institutions interested in deploying qCT LN Quant can contact Qure.ai for more information on implementation and integration with their electronic medical records (EMRs) and other diagnostic tools. We have dedicated U.S.-based teams available to assist with this process. By incorporating qCT LN Quant into their practice, clinicians can optimize lung cancer detection and monitoring accuracy and efficiency, ultimately improving patient outcomes.

Healio: What other products are included in Qure.ai’s AI-powered Lung Cancer care continuum? What are the key features of each one?

Reddy: Qure.ai’s AI-powered Lung Cancer care continuum includes:

qXR LN: This FDA cleared AI software is designed for the early detection and localization of lung nodules on chest X-rays, supporting early lung cancer detection beyond traditional CT-based screening initiatives.

qTrack: A multi-modality lung nodule management platform that integrates with EMRs to help clinicians find, report, collaborate and prioritize lung cancer patient cases.

Key features of these tools include the ability to detect lung nodules on X-rays, manage and track nodule growth over time and integrate seamlessly with existing health care systems to support comprehensive lung cancer care. You can read more about the care continuum here.

Healio: What are the pros and cons of using AI in the lung cancer space?

Reddy: Pros of using AI in this space include:

Early detection: Using AI in the lung cancer space enhances early detection by identifying nodules that might be missed by human eyes, particularly in states with low lung cancer screening CT uptakes.

Precise tracking: It provides precise quantitative characterization and tracking of lung nodules, aiding in more accurate diagnosis and treatment planning.

Accuracy: AI algorithms can improve the accuracy of diagnoses by reducing human error and identifying patterns that may be missed by radiologists in routine care.

Streamlined workflow: AI streamlines workflow by automating tasks, reducing the time needed for analysis and minimizing human error.

On the other hand, cons include:

Over-reliance: Over-relying on AI could potentially lead to clinicians missing important contextual information that might not be captured by AI. This can of course be avoided by strong education and awareness during the deployment stage.

High cost of implementation: Implementing AI solutions may be costly for some settings, and there could be barriers to access in low-resource settings. We provide business case planning cost calculators to help clinicians and hospitals scenario plan and look for the value add and return on investment to justify an initial outlay.

Training and adaptation: There may be a learning curve for clinicians to fully understand and trust the AI outputs, requiring training and adaptation to new workflows. Our dedicated clinical education team ensures that users and decisionmakers at health care settings have deep training sessions to maximize confidence at an AI-go-live.

Qure.ai is committed to eliminating lung cancer as a cause of death. We are working alongside health care institutions and clinicians to ensure AI’s optimal use across health care settings without disrupting normal workflows. We are striving toward a future where health care is no longer a luxury, but a necessity. A world where AI creates equitable health care access for all.

Healio: What is the next goal Qure.ai hopes to accomplish?

Reddy: Our motivation is to shape the future of health care with AI for the best possible patient outcomes. The only goal we are chasing is to raise the bar for lung cancer care and other areas of medical imaging with our AI-powered solutions. We are hungry to do more and to progress from zero to one as a company.

We are investing significant time and effort into R&D and product development to level up and provide better patient outcomes. This involves obtaining additional regulatory approvals, expanding the adoption of our AI tools in more health care institutions globally and developing new AI solutions that address unmet clinical needs. We believe in the democratization of science and are constantly working to harness it to build a future with accessible, affordable and equitable health care.

Reference:

• Qure.ai launches FDA-cleared AI solution for advanced lung nodule quantification on CT scans at AABIP 2024. https://www.qure.ai/news_press_coverages/qure.ai-launches-FDA-cleared-AI-solution-for-advanced-lung-nodule-quantification-on-CT-scans-at-AABIP-2024. Published Aug. 21, 2024. Accessed Aug. 22, 2024.