A New Standard in Lung Cancer Screening: AI-Powered LDCT and the Temple Lung Center Model

Why Is Early Detection of Lung Cancer So Difficult?

Lung cancer remains the leading cause of cancer-related deaths worldwide. One of the key challenges is that it often progresses without noticeable symptoms, and many cases are diagnosed at an advanced stage (Stage III or higher).

To address this issue, the U.S. National Cancer Institute (NCI) launched the National Lung Screening Trial (NLST)—a large randomized clinical trial involving over 53,000 high-risk individuals aged 55–74 with a smoking history of 30 pack-years or more. The study compared chest X-rays with low-dose computed tomography (LDCT) and found that LDCT reduced lung cancer mortality by 20% and overall mortality by 6.7%, marking a paradigm shift in how early detection of lung cancer could be approached through more advanced screening modalities.

These findings led to a major shift in clinical guidelines:

• In 2013, the U.S. Preventive Services Task Force (USPSTF) recommended LDCT for high-risk individuals aged 55–80.
• The Centers for Medicare & Medicaid Services (CMS) followed by approving LDCT screening coverage for adults aged 55–77.

Why We Need Smarter Screening

Current USPSTF guidelines recommend annual LDCT screening for individuals who meet all of the following:

• Aged 50 to 80 years
• Smoking history of at least 20 pack-years
• Currently smoking or have quit within the past 15 years
   

Despite this, less than 10% of eligible individuals in the U.S. actually receive screening. This gap is concerning because early-stage lung cancer has a significantly higher survival rate than late-stage disease. When detected early, some cases may be treated more effectively with localized interventions, whereas late-stage diagnosis often requires complex systemic treatments.

In addition to low screening adherence, structural limitations of traditional screening systems have also been a major barrier. Chest X-rays are often insufficient for early lesion detection. Radiologists face heavy image interpretation workloads, and access to high-quality screening remains limited in many regions.

These challenges highlight the need for AI-powered LDCT workflows that can not only support early detection but also reduce delays through radiology automation and consistent structured CT reporting. Recognizing this opportunity, Temple Health introduced a new AI-supported screening model aimed at improving both accuracy and accessibility.

Why Did Temple Lung Center Turn to AI?

Temple Lung Center became one of the first academic centers in the U.S. to incorporate AI-powered analysis into LDCT lung screening. By combining LDCT with advanced software, the team aimed to assist in the detection and triage of various thoracic findings—such as lung nodules, emphysema, and coronary artery calcifications.

The program, launched in the greater Philadelphia region, was designed to enhance clinical efficiency and provide a more comprehensive view of lung health. This included integrating spirometry with the LDCT scan, enabling a 3-in-1 assessment during a single visit.
 

Introducing the Temple Healthy Chest Initiative

To support its AI strategy, Temple Health established the Temple Healthy Chest Initiative (THCI)—a dedicated lung screening program built to proactively serve high-risk populations.
Operating across five centers in the Philadelphia area, THCI targets individuals aged 50–80 with a history of 20 pack-years of smoking, who either currently smoke or quit within the past 15 years.
What makes the program unique is its integration of:

• Low-dose chest CT (LDCT)
• AI-based image analysis (powered by Coreline Soft)
• Spirometry
  — all in a single visit.

The AI platform assists in identifying pulmonary nodules, emphysema, interstitial lung disease, and coronary artery calcification, generating structured CT reports that support physician decision-making. Clinicians review these AI-assisted results and follow up with patients as needed—helping to reduce time to intervention and improve care continuity.

Since its launch in 2023, the program has conducted over 10,000 scans and is currently scaling its monthly volume from 400 to over 1,000 scans. The THCI model has been featured in leading healthcare publications, including Becker’s Hospital Review and The Imaging Wire, as a prime example of how AI-powered LDCT workflows can enhance clinical outcomes and operational efficiency in lung health.

 

Setting a New Standard for AI Lung Screening

Lung cancer continues to be one of the most devastating cancers worldwide—but early detection can change the story.

AI-assisted screening offers not only improved accuracy but also faster interpretation, better access, and reduced burden on radiology teams through scalable radiology automation. Temple Health has not just adopted this technology—they’ve embedded it into a patient-centered care model supported by multidisciplinary collaboration.

Interested in learning more about how Temple Lung Center is using AI to support its lung screening workflow and improve patient care pathways?
Join our upcoming webinar featuring experts from Temple Health and Coreline Soft to explore real-world examples of how AI is redefining the future of early lung disease detection.