Lung cancer presents a global health concern; there is a need for development of an accurate disease identification system. The mortality rate of individuals has a direct impact by proliferation of cells in the lung region for identifying lung cells using histopathological images. The contribution of such a system in detecting lung cancer cannot be overemphasized. There have been various proposed Computer-Aided Diagnosis aimed to assist radiologists in detection of lung cancer. Recent research shows that the DL specifically can be mostly utilized in computer vision works, including the detection of lung cancer. In comparison with traditional feature extraction-based systems, convolutional neural networks show good results and performance. The lung cancer cells identification from histopathological images is both rigorous and challenging due to the issue of class imbalance. This paper shows a summarized review of various proposed frameworks and methods based on different CNN for the detection of lung cancer cells by examining the outcomes and insights. The study explores the establishment of a comprehensive dataset, modification of Convolutional Neural Network architectures, and the adoption of data augmentation and transfer learning concepts for the analysis of histological images. This research aspires to show a robust solution for patient outcomes and optimizing healthcare efficiency. The objective of the review is to analysis of the current landscape of DL lung cancer cell detection systems, enhancing their potential to change the field of healthcare diagnostics.