Accurate diagnosis and treatment of lung carcinoma depend on its pathological type and staging. Normally, pathological analysis is performed either by needle biopsy or surgery. Therefore, a noninvasive method to detect pathological types would be a good alternative. Hence, this work aims at categorizing different types of lung cancer from multimodality images. The proposed approach involves two stages. Initially, a Blind/Referenceless Image Spatial Quality Evaluator-based approach is adopted to extract the slices having lung abnormalities from the dataset. The slices then are transferred to a novel shallow convolutional neural network model to detect adenocarcinoma, squamous cell carcinoma, and small cell carcinoma from multimodality images. The classifier efficacy is then investigated by comparing precision, recall, area under curve, and accuracy with pretrained models and existing methods. The results narrate that the suggested system outperformed with a testing accuracy of 95% in Positron emission tomography/computed tomography (PET/CT), 93% in CT images of the Lung-PET-CT-DX dataset, and 98% in the Lung3 dataset. Furthermore, a kappa score of 0.92 in PET/CT of Lung-PETCT-DX and 0.98 in CT of Lung3 exhibited the effectiveness of the presented system in the field of lung cancer classification.