Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function

05/29/2020

∙

Fully-automatic lung lobe segmentation is challenging due to anatomical variations, pathologies, and incomplete fissures. We trained a 3D u-net for pulmonary lobe segmentation on 49 mainly publically available datasets and introduced a weighted Dice loss function to emphasize the lobar boundaries. To validate the performance of the proposed method we compared the results to two other methods. The new loss function improved the mean distance to 1.46 mm (compared to 2.08 mm for simple loss function without weighting).

READ FULL TEXT

Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function

A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

Estimation of mitral valve hinge point coordinates – deep neural net for echocardiogram segmentation

Interactive segmentation using U-Net with weight map and dynamic user interactions

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images

A Deep Learning-Based and Fully Automated Pipeline for Regurgitant Mitral Valve Anatomy Analysis from 3D Echocardiography

CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss

Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation

Automatic segmentation of the pulmonary lobes with a 3D u-net and optimized loss function

Related Research

A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

Estimation of mitral valve hinge point coordinates – deep neural net for echocardiogram segmentation

Interactive segmentation using U-Net with weight map and dynamic user interactions

A new method incorporating deep learning with shape priors for left ventricular segmentation in myocardial perfusion SPECT images

A Deep Learning-Based and Fully Automated Pipeline for Regurgitant Mitral Valve Anatomy Analysis from 3D Echocardiography

CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss

Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation