Automatic 3D segmentation of pulmonary lobes using progressive dense v-net

Give the overall structure of the algorithm. Does your algorithm search for boundaries or fissures? Does it use airway or other information? Does it use an atlas and/or region growing? our algorithm is an end-to-end deep-learning based network which utilizes 3D context of the input and is supervised at different resolutions without the need for any prior knowledge of airways/vessels or anatomical knowledge or atlases.