A Multi-Task Cross-Task Learning Architecture for Ad Hoc Uncertainty Estimation in 3D Cardiac MRI Image Segmentation

  title={A Multi-Task Cross-Task Learning Architecture for Ad Hoc Uncertainty Estimation in 3D Cardiac MRI Image Segmentation},
  author={S. M. Kamrul Hasan and Cristian A. Linte},
  journal={2021 Computing in Cardiology (CinC)},
  • S. Hasan, C. Linte
  • Published 13 September 2021
  • Engineering, Computer Science
  • 2021 Computing in Cardiology (CinC)
Medical image segmentation has significantly benefitted thanks to deep learning architectures. Furthermore, semi-supervised learning (SSL) has recently been a growing trend for improving a model's overall performance by leveraging abundant unlabeled data. Moreover, learning multiple tasks within the same model further improves model generalizability. To generate smooth and accurate segmentation masks from 3D cardiac MR images, we present a Multi-task Cross-task learning consistency approach to… 

Figures and Tables from this paper


A Distance Map Regularized CNN for Cardiac Cine MR Image Segmentation
Several cardiac indices that often serve as diagnostic biomarkers, specifically blood pool volume, myocardial mass, and ejection fraction, computed using the proposed regularization method are better correlated with the indices computed from the reference, ground truth segmentation.
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
A novel uncertainty-aware semi-supervised framework for left atrium segmentation from 3D MR images that can effectively leverage the unlabeled data by encouraging consistent predictions of the same input under different perturbations.
L-CO-Net: Learned Condensation-Optimization Network for Segmentation and Clinical Parameter Estimation from Cardiac Cine MRI
  • S. Hasan, C. Linte
  • Medicine, Computer Science
    2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
  • 2020
A fully convolutional segmenter featuring both a learned group structure and a regularized weight-pruner to reduce the high computational cost in volumetric image segmentation and has the potential to become an efficient and competitive cardiac images segmentation tool that may be used for cardiac computer-aided diagnosis, planning, and guidance applications.
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.
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.
Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow
An explainable, simple and flexible model for pathology classification based on a novel approach to extract image derived features to characterize the shape and motion of the heart, comparable to that of the state-of-the-art.
Adversarial Learning for Semi-supervised Semantic Segmentation
It is shown that the proposed discriminator can be used to improve semantic segmentation accuracy by coupling the adversarial loss with the standard cross entropy loss of the proposed model.
Deep Learning for Medical Image Analysis
Different novel methods based on deep learning for brain abnormality detection, recognition, and segmentation for analyzing medical images using deep learning algorithm are explored.
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
A Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty is presented, which makes the loss more robust to noisy data, also giving new state-of-the-art results on segmentation and depth regression benchmarks.
Learning to Multitask
Experiments on benchmark datasets show the effectiveness of the proposed L2MT framework, which uses a proposed layerwise graph neural network to learn task embeddings for all the tasks in a multitask problem and learns an estimation function to estimate the relative test error.