Balaga. Yaswanth, Mr. P. Satyanarayana, Bodaka. Vijaya,Goona. Dileep, Doddi. Sampath Srinivas 03 03 Lung cancer kills more people each year than almost any other cancer and the main reason is late diagnosis Once a tumour reaches an advanced stage treatment options shrink dramatically Screening programs that use Computed Tomography CT imaging can catch nodules early but reading hundreds of CT slices per patient is slow and two radiologists looking at the same scan often disagree This paper describes an automated segmentation system built on a deep UNet architecture that takes raw CT slices as input and returns pixellevel nodule masks without any human in the loop The encoder half of the network compresses the image into a compact feature representation while capturing broad context the decoder half reconstructs a fullresolution map and skip connections carry fine spatial detail directly from each encoder stage to its matching decoder stage so that thin nodule boundaries are not smeared during upsampling The model was trained on the publicly available LIDCIDRI dataset using an Adam optimizer with binary crossentropy loss Segmentation quality was measured with the Dice Similarity Coefficient and Intersection over Union both of which reward precise overlap rather than raw pixel accuracy On the heldout test split the system reached a Dice score of approximately 089 and an IoU of approximately 082 outperforming classical regiongrowing methods and shallow convolutional baselines The results suggest this pipeline can meaningfully support radiologists in routine screening workflows Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026