Lung　cancer　is　one　of　the　primary　lung　malignant　tumour　with　the　fastest　increasing　morbidity　and　mortality　and　the　greatest　threat　to　people＇s　health　and　life.　Early　detection　of　lung　cancer　can　significantly　increase　patients＇　chance　of　survival.　Lung　parenchymal　segmentation　is　an　essential　pre-processing　step　for　analysing　thoracic　computed　tomography(CT)　images.　Conventional　methods　for　lung　segmentation　rely　on　user　generated　features,　and　do　not　segment　lung　parenchymal　with　juxta-pleural　nodules　accurately.　Deep　learning　has　outperformed　other　methods　in　image　classification　and　target　recognition　tasks.　In　this　study,　a　new　dilated　convolutional　based　weighted　fully　convolutional　network　(FCN)　has　been　proposed　for　the　segmentation　of　lung　parenchyma　to　minimize　the　juxta-pleural　nodule　issue.　The　effectiveness　of　this　method　was　verified　by　experiments　on　173,694　diagnosis　CT　images　of　lungs　and　their　corresponding　segmentation　maps.　The　Dice　similarity　coefficient　and　pixel　accuracy　achieved　are　0.9702　and　0.9833　respectively.　The　experiment　results　show　that　the　proposed　method　can　provide　more　accurate　and　robust　results　than　traditional　FCN.　©　2020　Journal　of　Physics:　Conference　Series.