Heterogeneity of Lung Cancer: The Histopathological Diversity and Tumour Classification in the Artificial Intelligence Era.

Abstract

Background: Lung cancer is the most common cancer worldwide and is also the leading cause of cancer-related mortality. Its poor prognosis is primarily attributed to unspecific symptoms that result in late diagnosis, and its heterogeneous nature that further complicates treatment. This heterogeneity is largely driven by the diversity in histological subtypes, significantly impacting the clinical course of patients. Therefore, tumour subtyping using haematoxylin and eosin staining and immunohistochemistry is crucial for predicting patients' outcomes, making an accurate diagnosis, and choosing the appropriate treatment approach. Small-cell lung cancer and non-small cell lung cancer are the two major types, and subclassifying non-small cell lung cancer is essential to identify genetic alterations and, consequently, choose an adequate targeted therapy.

Summary: This article reviews all these lung tumour characteristics, specifying histological types and subtypes, and presenting their distinct features. To aid understanding, complementary images from Unilabs illustrate various lung tumour subtypes. Additionally, alternative approaches using artificial intelligence to improve tumour classification are reviewed, along with a discussion of their limitations.

Key messages: Thus, lung tumour classification is crucial for cancer treatment; nonetheless, it can be a subjective process, reliant on the pathologist's interpretation. In the era of artificial intelligence and deep/machine learning, the classification of lung cancer subtypes has the potential to become more efficient, accurate, and consistent. These advancements could lead to faster diagnosis and treatment decisions, ultimately improving patient survival and quality of care. Harnessing AI tools may address the limitations of subjective interpretation, offering a promising avenue for enhancing precision in lung cancer diagnostics.