Multi-Task Semi-Supervised Learning For Pulmonary Lobe Segmentation

  title={Multi-Task Semi-Supervised Learning For Pulmonary Lobe Segmentation},
  author={Jingnan Jia and Zhiwei Zhai and M. Els Bakker and Irene Hernandez-Giron and Marius Staring and Berend C. Stoel},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
  • Jingnan JiaZ. Zhai B. Stoel
  • Published 13 April 2021
  • Computer Science
  • 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)
Pulmonary lobe segmentation is an important preprocessing task for the analysis of lung diseases. Traditional methods relying on fissure detection or other anatomical features, such as the distribution of pulmonary vessels and airways, could provide reasonably accurate lobe segmentations. Deep learning based methods can outperform these traditional approaches, but require large datasets. Deep multi-task learning is expected to utilize labels of multiple different structures. However, commonly… 
1 Citations

Figures and Tables from this paper



Pathological Pulmonary Lobe Segmentation from CT Images Using Progressive Holistically Nested Neural Networks and Random Walker

This work proposes a novel PPLS method that couples deep learning with the random walker (RW) algorithm, and first employs the recent progressive holistically-nested network (P-HNN) model to identify potential lobar boundaries, then generates final segmentations using a RW that is seeded and weighted by the P- HNN output.

End-to-End Supervised Lung Lobe Segmentation

Both quantitative and qualitative results show that the proposed method can learn to produce correct lobe segmentations even when trained on a reduced dataset.

Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation

This work proposes a novel semi-supervised image segmentation method that simultaneously optimizes a supervised segmentation and an unsupervised reconstruction objectives and analyzes the features learned by different methods and finds that the attention mechanism helps to learn more discriminative features in the deeper layers of encoders.

Med3D: Transfer Learning for 3D Medical Image Analysis

A heterogeneous 3D network called Med3D is designed to co-train multi-domain 3DSeg-8 so as to make a series of pre-trained models which can accelerate the training convergence speed of target 3D medical tasks and improve accuracy ranging from 3% to 20%.

FissureNet: A Deep Learning Approach For Pulmonary Fissure Detection in CT Images

FissureNet, a supervised discriminative learning framework for simultaneous feature extraction and classification, is a coarse-to-fine cascade of two convolutional neural networks that alleviates the challenges associated with training a network to segment a thin structure that represents a small fraction of the image voxels.

Automatic Segmentation of the Pulmonary Lobes From Chest CT Scans Based on Fissures, Vessels, and Bronchi

An analysis of the relation between segmentation quality and fissure completeness showed that the method is robust against incomplete fissures, and an automated segmentation approach is presented that performs a marker-based watershed transformation on CT scans to subdivide the lungs into lobes.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

Fully Automated Lung Lobe Segmentation in Volumetric Chest CT with 3D U-Net: Validation with Intra- and Extra-Datasets

A fully automated lung lobe segmentation method with 3D U-Net developed and validated with internal and external datasets showed reasonable segmentation accuracy and computational time and could be adapted and applied to severe lung diseases in a clinical workflow.

Lung vessel segmentation in CT images using graph-cuts

A new graph-cuts cost function combining appearance and shape, where CT intensity represents appearance and vesselness from a Hessian-based filter represents shape is proposed, which produced a more accurate vessel segmentation compared to the previous methods.