SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for
Semi-Supervised Medical Image Segmentation
- URL: http://arxiv.org/abs/2108.06227v2
- Date: Mon, 16 Aug 2021 15:12:28 GMT
- Title: SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for
Semi-Supervised Medical Image Segmentation
- Authors: Chenyu You, Yuan Zhou, Ruihan Zhao, Lawrence Staib, James S. Duncan
- Abstract summary: We present SimCVD, a simple contrastive distillation framework that significantly advances state-of-the-art voxel-wise representation learning.
SimCVD achieves an average Dice score of 90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to previous best results.
- Score: 7.779842667527933
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automated segmentation in medical image analysis is a challenging task that
requires a large amount of manually labeled data. However, most existing
learning-based approaches usually suffer from limited manually annotated
medical data, which poses a major practical problem for accurate and robust
medical image segmentation. In addition, most existing semi-supervised
approaches are usually not robust compared with the supervised counterparts,
and also lack explicit modeling of geometric structure and semantic
information, both of which limit the segmentation accuracy. In this work, we
present SimCVD, a simple contrastive distillation framework that significantly
advances state-of-the-art voxel-wise representation learning. We first describe
an unsupervised training strategy, which takes two views of an input volume and
predicts their signed distance maps of object boundaries in a contrastive
objective, with only two independent dropout as mask. This simple approach
works surprisingly well, performing on the same level as previous fully
supervised methods with much less labeled data. We hypothesize that dropout can
be viewed as a minimal form of data augmentation and makes the network robust
to representation collapse. Then, we propose to perform structural distillation
by distilling pair-wise similarities. We evaluate SimCVD on two popular
datasets: the Left Atrial Segmentation Challenge (LA) and the NIH pancreas CT
dataset. The results on the LA dataset demonstrate that, in two types of
labeled ratios (i.e., 20% and 10%), SimCVD achieves an average Dice score of
90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to
previous best results. Our method can be trained in an end-to-end fashion,
showing the promise of utilizing SimCVD as a general framework for downstream
tasks, such as medical image synthesis and registration.
Related papers
- LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical
Imaging via Second-order Graph Matching [59.01894976615714]
We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets.
We have collected approximately 1.3 million medical images from 55 publicly available datasets.
LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
arXiv Detail & Related papers (2023-06-20T22:21:34Z) - Realistic Data Enrichment for Robust Image Segmentation in
Histopathology [2.248423960136122]
We propose a new approach, based on diffusion models, which can enrich an imbalanced dataset with plausible examples from underrepresented groups.
Our method can simply expand limited clinical datasets making them suitable to train machine learning pipelines.
arXiv Detail & Related papers (2023-04-19T09:52:50Z) - Rethinking Semi-Supervised Medical Image Segmentation: A
Variance-Reduction Perspective [51.70661197256033]
We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation.
We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks.
We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
arXiv Detail & Related papers (2023-02-03T13:50:25Z) - Bootstrapping Semi-supervised Medical Image Segmentation with
Anatomical-aware Contrastive Distillation [10.877450596327407]
We present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation.
We first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs.
We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data.
arXiv Detail & Related papers (2022-06-06T01:30:03Z) - Using the Order of Tomographic Slices as a Prior for Neural Networks
Pre-Training [1.1470070927586016]
We propose a pre-training method SortingLoss on slices instead of volumes.
It performs pre-training on slices instead of volumes, so that a model could be fine-tuned on a sparse set of slices.
We show that the proposed method performs on par with SimCLR, while working 2x faster and requiring 1.5x less memory.
arXiv Detail & Related papers (2022-03-17T14:58:15Z) - Cascaded Robust Learning at Imperfect Labels for Chest X-ray
Segmentation [61.09321488002978]
We present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation.
Our model consists of three independent network, which can effectively learn useful information from the peer networks.
Our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.
arXiv Detail & Related papers (2021-04-05T15:50:16Z) - Towards Robust Partially Supervised Multi-Structure Medical Image
Segmentation on Small-Scale Data [123.03252888189546]
We propose Vicinal Labels Under Uncertainty (VLUU) to bridge the methodological gaps in partially supervised learning (PSL) under data scarcity.
Motivated by multi-task learning and vicinal risk minimization, VLUU transforms the partially supervised problem into a fully supervised problem by generating vicinal labels.
Our research suggests a new research direction in label-efficient deep learning with partial supervision.
arXiv Detail & Related papers (2020-11-28T16:31:00Z) - Image Translation for Medical Image Generation -- Ischemic Stroke
Lesions [0.0]
Synthetic databases with annotated pathologies could provide the required amounts of training data.
We train different image-to-image translation models to synthesize magnetic resonance images of brain volumes with and without stroke lesions.
We show that for a small database of only 10 or 50 clinical cases, synthetic data augmentation yields significant improvement.
arXiv Detail & Related papers (2020-10-05T09:12:28Z) - Uncertainty-aware multi-view co-training for semi-supervised medical
image segmentation and domain adaptation [35.33425093398756]
Unlabeled data is much easier to acquire than well-annotated data.
We propose uncertainty-aware multi-view co-training for medical image segmentation.
Our framework is capable of efficiently utilizing unlabeled data for better performance.
arXiv Detail & Related papers (2020-06-28T22:04:54Z) - ATSO: Asynchronous Teacher-Student Optimization for Semi-Supervised
Medical Image Segmentation [99.90263375737362]
We propose ATSO, an asynchronous version of teacher-student optimization.
ATSO partitions the unlabeled data into two subsets and alternately uses one subset to fine-tune the model and updates the label on the other subset.
We evaluate ATSO on two popular medical image segmentation datasets and show its superior performance in various semi-supervised settings.
arXiv Detail & Related papers (2020-06-24T04:05:12Z) - 3D medical image segmentation with labeled and unlabeled data using
autoencoders at the example of liver segmentation in CT images [58.720142291102135]
This work investigates the potential of autoencoder-extracted features to improve segmentation with a convolutional neural network.
A convolutional autoencoder was used to extract features from unlabeled data and a multi-scale, fully convolutional CNN was used to perform the target task of 3D liver segmentation in CT images.
arXiv Detail & Related papers (2020-03-17T20:20:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.