In this research work, an Efficient Segmentation and Classification (ESC) system for Lung Cancer Diagnosis (LCD) is developed. It consists of three main modules; Fusion of Different Lung Imaging Modalities (FDLIM) module, Segmentation of Lung Nodules (SLN) module and Classification of Lung Nodules (CLN) module. In the FDLIM module, two different imaging modalities Computed Tomography (CT) and Positron Emission Tomography (PET) lung images are fused. The lung nodules are detected in the SLN module and then in the CLN module they are classified into normal or abnormal. In the SLN module, the lung nodules are segmented from the fused images obtained from the aforementioned three fusion approaches. To the low frequency components of DTWT sub-bands are set zero before reconstruct the image by the inverse DTWT. Then, the fuzzy C-means clustering algorithm is employed to cluster the regions and post-processing is applied to detect the exact location of lung nodules. The performance metrics used to evaluate the SLN and CLN module are sensitivity, specificity and accuracy. The SLN module gives maximum average sensitivity of 97.92% with specificity of 97.84% while using the fused image obtained from the DTWT-CNN approach. It is observed that the CLN module that uses the fused image from the DTWT-CNN approach provides a higher sensitivity of 98% and specificity of 100%. It is noted that the performance of fusion approach in the frequency domain (WEFL and DTWT-CNN) is higher than spatial domain fusion approach (SSMR). The proposed system yields the overall accuracy of 99%. This research work mainly focused to reduce the diagnosis error through CAD. © 2024 Elsevier B.V., All rights reserved.