Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation

Dalca, Adrian V.; Guttag, John V.; Sabuncu, Mert R.

doi:10.1109/cvpr.2018.00968

Cited by 139 publications

(108 citation statements)

References 41 publications

Supporting

Mentioning

107

Contrasting

Order By: Relevance

“…The authors attribute the inferior performance by Ravishankar et al (2017) to over-regularization, which they have overcome br replacing CDAE with a frozen encoder during training. Dalca et al (2018) suggest a segmentation VAE that leverages shape prior in order to learn from unpaired images and segmentation masks. The VAE consists of an image encoder, which is initialized from scratch, and a frozen decoder, which is selected from an auto-encoder that has previously been trained for the task of mask reconstruction.…”

Section: Deep Regularizationmentioning

confidence: 99%

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Tajbakhsh¹,

Jeyaseelan²,

Li³

et al. 2020

Medical Image Analysis

731

358

View full text Add to dashboard Cite

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large, representative, and high quality annotated datasets. However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire. Recently, a large body of research has studied the problem of medical image segmentation with imperfect datasets, tackling two major dataset limitations: scarce annotations where only limited annotated data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations. In this article, we provide a detailed review of the solutions above, summarizing both the technical novelties and empirical results. We further compare the benefits and requirements of the surveyed methodologies and provide our recommended solutions to the problems of scarce and weak annotations. We hope this review increases the community awareness of the techniques to handle imperfect datasets.

show abstract

Section: Deep Regularizationmentioning

confidence: 99%

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Tajbakhsh¹,

Jeyaseelan²,

Li³

et al. 2020

Medical Image Analysis

731

358

View full text Add to dashboard Cite

show abstract

“…where w k is a vector with one multiplicative coefficient per class k. Values smaller than 1 reduce, while values greater 1 increase the weighting of this class. This loss was introduced by Dalca et al 8 • Jaccard distance loss (JDL)…”

Section: Losses and Metricsmentioning

confidence: 99%

How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalize to rare congenital heart diseases for surgical planning?

Koehler

Tandon

Hussain

et al. 2020

Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

Planning the optimal time of intervention for pulmonary valve replacement surgery in patients with the congenital heart disease Tetralogy of Fallot (TOF) is mainly based on ventricular volume and function according to current guidelines. Both of these two biomarkers are most reliably assessed by segmentation of 3D cardiac magnetic resonance (CMR) images. In several grand challenges in the last years, U-Net architectures have shown impressive results on the provided data. However, in clinical practice, data sets are more diverse considering individual pathologies and image properties derived from different scanner properties. Additionally, specific training data for complex rare diseases like TOF is scarce.For this work, 1) we assessed the accuracy gap when using a publicly available labelled data set (the Automatic Cardiac Diagnosis Challenge (ACDC) data set) for training and subsequent applying it to CMR data of TOF patients and vice versa and 2) whether we can achieve similar results when applying the model to a more heterogeneous data base.Multiple deep learning models were trained with four-fold cross validation. Afterwards they were evaluated on the respective unseen CMR images from the other collection. Our results confirm that current deep learning models can achieve excellent results (left ventricle dice of 0.951±0.003/0.941±0.007 train/validation) within a single data collection. But once they are applied to other pathologies, it becomes apparent how much they overfit to the training pathologies (dice score drops between 0.072±0.001 for the left and 0.165±0.001 for the right ventricle).

show abstract

“…An advantage of these methods is their computational efficiency at test (segmentation) time, offering the potential to use automatic segmentation in new application areas, such as those involving very large test datasets [19,30]. Moreover, these algorithms can be combined with atlas priors for increased robustness [9,22,26] However, DL based techniques are notoriously sensitive to changes in the image intensity data distribution. For example, an upgrade to the MRI scanner or a change in the pulse sequence might alter contrast properties that can dramatically reduce the performance of a CNN-based segmentation model [17].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Deep Learning for Bayesian Brain MRI Segmentation

Dalca

Golland³

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Probabilistic atlas priors have been commonly used to derive adaptive and robust brain MRI segmentation algorithms. Widely-used neuroimage analysis pipelines rely heavily on these techniques, which are often computationally expensive. In contrast, there has been a recent surge of approaches that leverage deep learning to implement segmentation tools that are computationally efficient at test time. However, most of these strategies rely on learning from manually annotated images. These supervised deep learning methods are therefore sensitive to the intensity profiles in the training dataset. To develop a deep learningbased segmentation model for a new image dataset (e.g., of different contrast), one usually needs to create a new labeled training dataset, which can be prohibitively expensive, or rely on suboptimal ad hoc adaptation or augmentation approaches. In this paper, we propose an alternative strategy that combines a conventional probabilistic atlas-based segmentation with deep learning, enabling one to train a segmentation model for new MRI scans without the need for any manually segmented images. Our experiments include thousands of brain MRI scans and demonstrate that the proposed method achieves good accuracy for a brain MRI segmentation task for different MRI contrasts, requiring only approximately 15 seconds at test time on a GPU. The code is freely available at http://voxelmorph.mit.edu.

show abstract

Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation

Cited by 139 publications

References 41 publications

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation

How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalize to rare congenital heart diseases for surgical planning?

Unsupervised Deep Learning for Bayesian Brain MRI Segmentation

Contact Info

Product

Resources

About