Automatic lobe segmentation using attentive cross entropy and end-to-end fissure generation
This work addresses lung disease diagnosis by improving segmentation accuracy, though it appears incremental with method refinements.
The paper tackled the challenge of automatic lung lobe segmentation in CT images by proposing a framework with an attentive cross-entropy loss and end-to-end fissure generation, achieving dice scores of 97.83% on a private dataset and 94.75% on a public dataset.
The automatic lung lobe segmentation algorithm is of great significance for the diagnosis and treatment of lung diseases, however, which has great challenges due to the incompleteness of pulmonary fissures in lung CT images and the large variability of pathological features. Therefore, we propose a new automatic lung lobe segmentation framework, in which we urge the model to pay attention to the area around the pulmonary fissure during the training process, which is realized by a task-specific loss function. In addition, we introduce an end-to-end pulmonary fissure generation method in the auxiliary pulmonary fissure segmentation task, without any additional network branch. Finally, we propose a registration-based loss function to alleviate the convergence difficulty of the Dice loss supervised pulmonary fissure segmentation task. We achieve 97.83% and 94.75% dice scores on our private dataset STLB and public LUNA16 dataset respectively.