Lung cancer screening is undergoing significant improvements with the integration of low-dose computed tomography (LDCT) and artificial intelligence (AI), especially important as about half of lung cancer patients in Singapore have never smoked, according to a National Cancer Centre Singapore (NCCS) study.

Dr Peter Goh, group medical director and interventional oncologist at Parkway Radiology, highlighted that early lung cancers detected and treated before spreading have an almost 100% five-year survival rate. However, chest X-rays can miss 20% to 50% of early lung cancers depending on lesion size and location. LDCT reduces radiation exposure to about 1 to 2.5 millisieverts (mSv), compared to around 6 mSv from standard chest CT scans.

A new generation of CT scanners offers ultra-low-dose CT (ULDCT) imaging, with radiation doses ranging from 0.12 mSv to 0.76 mSv—equivalent to one to seven conventional chest X-rays—while maintaining image quality. Each scan produces 400 to 700 images, detecting nodules as small as 4mm to 8mm.

AI assistance has notably increased radiologists' sensitivity in detecting early lung cancers from 76.55% to 91.22%. The AI software improves nodule detection rates by up to 26% and reduces report generation time by up to 31%.

Dr Goh emphasized that these technological advances aim to identify lung cancer before symptoms develop, when treatment is most effective. "Almost every cancer we have detected early that was subsequently treated, whether through surgery or ablation, underscores the critical role of early detection in making a meaningful difference to patient outcomes," he said.

These developments mark a significant step forward in lung cancer screening across the Asia-Pacific region, potentially improving survival rates and reducing unnecessary radiation exposure for patients.

Sources