International Journal of Advanced Research in Computer and Communication Engineering

Abstract: Cancer is recognized as one of the most severe health threats, causing millions of deaths worldwide each year. Among its various types, lung cancer stands out as the most aggressive, with the highest mortality rate. Hence, the development of reliable and precise methods for detecting lung cancer is critical to ensure timely and effective treatment. Designing a strong and accurate classification model is particularly important in medical diagnostics. Due to its widespread occurrence and tendency to remain hidden during the initial stages, lung cancer underscores the urgent need for efficient detection and classification techniques. Globally, it is one of the most common and deadliest cancers, making a significant contribution to cancer-related deaths. Its silent progression during early phases often leads to late diagnosis, when treatment options become less effective.

Robust classification systems can help bridge this diagnostic gap by identifying subtle and complex patterns in medical images. Positron Emission Tomography (PET) is widely applied for diagnosing and staging multiple cancers, including lung, liver, and lymphoma. Correct subtype identification is vital for tailoring effective treatment strategies. For instance, lung cancer includes subtypes such as adenocarcinoma, squamous cell carcinoma, and small cell carcinoma, while liver cancer can present as hepatocellular carcinoma or cholangiocarcinoma. Likewise, lymphoma has categories such as Hodgkin’s lymphoma and diffuse large B-cell lymphoma. Subtype classification using PET imaging, therefore, carries substantial clinical importance. However, a key limitation in real-world clinical settings is the scarcity and imbalance of subtype-specific datasets. The major challenge, then, is achieving accurate subtype classification when working with limited data.

Keywords: Lung Cancer, Positron Emission Tomography, early-stage manifestation

Downloads: | DOI: 10.17148/IJARCCE.2025.14823