Lung Carcinoma Taxonomy: Differentiating Adenocarcinoma, Small Cell Carcinoma, and Squamous Cell Carcinoma

Lung carcinoma represents a diverse group of malignancies that originate in the respiratory epithelium. The primary histological subtypes include adenocarcinoma, small cell carcinoma, and squamous cell carcinoma, each exhibiting distinct clinical, morphological, and genetic characteristics. This classification is critical for determining appropriate treatment strategies and predicting patient outcomes. This article provides an overview of the histopathological features, molecular profiles, and clinical implications of each subtype, highlighting the importance of accurate classification in the management of lung carcinoma. This study also explores various deep-learning algorithms applied to radiological imaging data for the classification of lung carcinoma. We analyze a dataset comprising Computed Tomography (CT) scans annotated with histopathological findings to distinguish between malignant and benign lung nodules. In deep learning models, Convolutional Neural Networks (CNNs) and their variants, have shown promising results in automated detection and classification tasks. Traditional Data augmentation and Gaussian blur techniques are used to enlarge the dataset and to smoothing the image by reducing noise. This model achieves an accurate classification accuracy of 97.74%, 98.96% precision, and 0.98 AUC-ROC compared to various deep learning algorithms used for classification.