In recent times, for the diagnosis of several diseases, many Computer-Aided Diagnosis (CAD) systems have been designed. Among many life-threatening diseases, lung cancer is one of the leading causes of cancer-related deaths in humans worldwide. It is a malignant lung tumor distinguished by the uncontrolled growth of cells in the tissues of the lungs. Diagnosis of cancer is a challenging task due to the structure of cancer cells. Predicting lung cancer at its initial stage plays a vital role in the diagnosis process and also increases the survival rate of patients. People with lung cancer have an average survival rate ranging from 14 to 49% if they are diagnosed in time. The current study focuses on lung cancer classification and prediction based on Histopathological images by using effective deep learning techniques to attain better accuracy. For the classification of lung cancer as Benign, Adenocarcinoma, or Squamous Cell Carcinoma, some pre trained deep neural networks such as VGG-19 were used. A database of 15000 histopathological images was used in which 5000 benign tissue images and 10000 malignant lung cancer-related images to train and test the classifier. The experimental results show that the VGG-19 architecture can achieve an accuracy of 95%.