Lung cancer is a kind of harmful cancer type that originates from the lungs. In this research, the lung lobe segmentation is carried out using Markov Random Field (MRF)-based Artificial Hummingbird Cuckoo algorithm (AHCA). The AHCA algorithm is modelled by considering the benefits of both the Artificial Hummingbird algorithm (AHA) and the Cuckoo search (CS) algorithm. Moreover, the lung cancer classification is done with ShuffleNet, which is trained by the Artificial Hummingbird Firefly optimization algorithm (AHFO) which is the integration of AHA and Firefly algorithm (FA). In this research, two algorithms are devised for both segmentation and classification. From these two algorithms, the AHA algorithm is used for updating the location. The AHA algorithm had three phases, such as foraging, guided foraging and migrating foraging where the guided foraging stage is selected to update the location for both segmentation and classification. Besides, the developed AHFO-based ShuffleNet scheme attained superior performance with respect to the testing accuracy of 0.9071, sensitivity of 0.9137 and specificity of 0.9039. The performance improvement of the proposed method for testing accuracy is 6.615%, 3.197%, 2.756%, and 1.764% higher than the existing methods. In future, the performance will be boosted by the advanced scheme for identifying the grade of disease.