In the analysis of diagnostic imaging data, the return of deep learning has become a game-changer. However, while those photographs are being captured, the technology behind them is also evolving. Indeed, lung disorders are respiratory system-impairing conditions that also affect the lung. One of the primary factors in human death rates around the globe has been lung cancer. Increased survival rates for people can result from early identification. The average lung cancer survivability rate increases from 14 - 49 percent if the disease is detected early. A complete diagnosis involves various imaging techniques to complement one another, even if CT (Computed tomography) is significantly more efficient than X-ray. The development and evaluation of a deep neural network in lung cancer detection using CT scans. Using a highly linked VGG16 (convolution neural network) as well as the Confusion Matrix technique, the lung picture was classified as benign or malignant. The proposed approach, according to experimental findings, has an accuracy rate of above 95%. Finally, we discuss some of the drawbacks of applying AI to medical practice as well as the potential they draw in this developingarea.

Lung disorders, Computed tomography, convolution neural network, Confusion Matrix technique