Jim Mulshine, MD
The US Preventive Task Force recommends annual lung cancer screening with low-dose computed tomography in ever-smokers aged 55 to 80 years who have smoked 30 packs of cigarettes per year, as well as those who currently smoke. However, findings presented at the 2018 ASCO Annual Meeting revealed that less than 2% of the 7.6 million patients in the United States who are eligible for screening were tested in 2016.
Low screening uptake could be attributable to several factors, including a lack of familiarity among providers about computed tomography (CT)-based testing. To address this, the International Association for the Study of Lung Cancer (IASLC) recently developed and piloted a project known as the Early Lung Imaging Confederation (ELIC). Healio spoke with Jim Mulshine, MD, chair of the IASLC’s Prevention and Early Detection Committee and professor of internal medicine at Rush Medical College in Chicago, to learn more about ELIC and how it can potentially improve lung cancer screening.
Many cancers can be best cured through early detection, encouraged through screening and supporting research and public health programs. It has been shown that early detection by low-dose CT screening can decrease lung cancer mortality by 20% to 61% among high-risk populations. However, currently only 16% of lung cancer patients are diagnosed with stage 1 disease, which means many people are not aware of this new detection option.
Clearly, screening is a challenge. Forty-five million patients have successfully stopped smoking but are still at a high risk for lung cancer. A number of major cancer centers have found that most of their newly diagnosed lung cancers are in former smokers. Fortunately, we have developed a method to complement the smoking cessation efforts and encourage screening among this population as well as other high-risk groups, including current smokers. Working with an international consortium of investigators and clinicians, we are developing a repository of scanned images and clinical data that could support the development of deep learning methods or artificial intelligence approaches. Such tools could be trained to detect and assist in managing early lung cancer and other diseases using thoracic CT images. The IASLC ELIC project has functionality to facilitate the high-quality implementation of low-dose CT screening by disseminating validated software tools for the early detection of thoracic diseases.
The ELIC project has created a globally-accessible, privacy-secured environment for the analysis of large collections of quality-controlled CT lung cancer images and associated biomedical data from around the world. Currently, we are refining the foundations of this environment to ensure robust data security and ease of user navigation. The IASLC ELIC pilot project represents what global collaboration, cutting edge science and technological advancement can achieve. This novel approach can assist in improving lung cancer screening and reversing the trend where lung cancer is overwhelmingly detected in a later and more deadly stage.
It makes sense for the IASLC to lead this project because it is the largest international association dedicated solely to the study of lung cancer and thoracic malignancies. IASLC members are thought leaders who collaborate across borders in their mission to conquer thoracic cancers worldwide.
The IASLC ELIC pilot program consisted of a central server, hub and 10 globally distributed servers running on a cloud service. Each spoke server contained a de-identified and publicly-available CT image collection and was programmed to run one of two quantitative CT lung image measurement algorithms upon request by the hub server. Its success indicates the exciting potential for this project to conduct important quantitative analysis on lung cancer imaging cases without needing to move datasets from their geographical location.
We are developing ELIC as an open-science platform that will be accessible within the constraints of responsible scientific research. Registries like this rely on participants to agree to share their information so that others may benefit. Those accessing the images will be better able to tell the difference between how aggressive tumors look and act compared to indolent tumors. There will emerge an impetus to share these images across institutions so that individual researchers who might only have access to a small number of CT images in their center can access thousands of images as well as validated software analysis tools to expand their knowledge base. We have great engagement in this effort with many of the countries represented by the IASLC membership. This will accelerate the number of images that all researchers can access and learn from.
It is still very early in the life of this project. We successfully demonstrated our concept will work by distributing a test panel of 100 thoracic images to 10 international cloud sites and we examined those images with two tools to measure different factors about those images. We found the reproducibility of the analyses of those images was very good, so whether you are a researcher in Virginia or Mumbai, you will have consistent measurements to guide clinical management. Additionally, we conducted several live demonstrations at the IASLC 19th World Conference on Lung Cancer to showcase ELIC’s capabilities.
The ELIC website will be hosted by the IASLC and access to it will be shared via scholarly journal and research channels. We plan for ELIC to be accessible to any serious lung cancer researcher who has legitimate research protocols or goals in mind. ELIC can also be used to perform image acquisition quality analysis. And we are working with Accumetra to make this site safe and secure via encryption to ensure it’s done in a best-practice manner. We will have very robust security provisions to enable ELIC to emerge as a useful international resource.
Other groups have created similar models — we are doing it with lung cancer. As cloud technology matures, more and more researchers will find new uses for it that are similar to ELIC.
Working with Professor John Field (University of Liverpool, UK) and the rest of the IASLC stakeholders, it is a shared hope that ELIC will serve to accelerate progress with lung cancer screening and early detection. Those of us who are involved with ELIC see it as eventually housing millions of images so that its automated screening tools can continually improve in detecting and curing early stage lung cancer as well as other major intrathoracic diseases such as chronic obstructive pulmonary disease  and coronary artery disease by improving treatment decisions and saving more lives.
Disclosure: Mulshine reports no relevant financial disclosures.
Please click on Next tab to advance through activity.