Lung adenocarcinoma is a frequent type of lung cancer among the Asian population and usually develops in individuals with a cigarette smoking history. The mortality risk due to this cancer can only be reduced with reliable early detection methods and screening programs. X-rays and computed tomography (CT) scans are commonly used to identify lung adenocarcinoma manually. However, manual analysis of lung radiographs is typically laborious and error-prone. Thus, an intuitive approach is advantageous. This paper employed a lightweight neural network comprising 2 hidden layers and efficient handcrafted features for the automatic detection of lung adenocarcinoma. A total of 4834 CT scans (2226 normal and 2608 adenocarcinoma infected lung) have been considered for training and testing purposes. The model achieved an accuracy of 100% with a unity value of each specificity, precision, recall, F1-Score, and area under the receiver operating characteristic (AUROC) on the benchmark lung adenocarcinoma dataset extracted from the lung image database consortium image collection (LIDC-IDRI). The suggested method is fast, efficient, and computationally less complex for the considered dataset compared to the current techniques available in the literature. It contributes to the medical community conducting large-scale screening programs.