Self-Supervised U-Net for Segmenting Flat and Sessile Polyps
- URL: http://arxiv.org/abs/2110.08776v1
- Date: Sun, 17 Oct 2021 09:31:20 GMT
- Title: Self-Supervised U-Net for Segmenting Flat and Sessile Polyps
- Authors: Debayan Bhattacharya, Christian Betz, Dennis Eggert, Alexander
Schlaefer
- Abstract summary: Development of colorectal polyps is one of the earliest signs of cancer.
Early detection and resection of polyps can greatly increase survival rate to 90%.
Computer-Aided Diagnosis systems(CADx) has been proposed that detect polyps by processing the colonoscopic videos.
- Score: 63.62764375279861
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Colorectal Cancer(CRC) poses a great risk to public health. It is the third
most common cause of cancer in the US. Development of colorectal polyps is one
of the earliest signs of cancer. Early detection and resection of polyps can
greatly increase survival rate to 90%. Manual inspection can cause
misdetections because polyps vary in color, shape, size and appearance. To this
end, Computer-Aided Diagnosis systems(CADx) has been proposed that detect
polyps by processing the colonoscopic videos. The system acts a secondary check
to help clinicians reduce misdetections so that polyps may be resected before
they transform to cancer. Polyps vary in color, shape, size, texture and
appearance. As a result, the miss rate of polyps is between 6% and 27% despite
the prominence of CADx solutions. Furthermore, sessile and flat polyps which
have diameter less than 10 mm are more likely to be undetected. Convolutional
Neural Networks(CNN) have shown promising results in polyp segmentation.
However, all of these works have a supervised approach and are limited by the
size of the dataset. It was observed that smaller datasets reduce the
segmentation accuracy of ResUNet++. We train a U-Net to inpaint randomly
dropped out pixels in the image as a proxy task. The dataset we use for
pre-training is Kvasir-SEG dataset. This is followed by a supervised training
on the limited Kvasir-Sessile dataset. Our experimental results demonstrate
that with limited annotated dataset and a larger unlabeled dataset,
self-supervised approach is a better alternative than fully supervised
approach. Specifically, our self-supervised U-Net performs better than five
segmentation models which were trained in supervised manner on the
Kvasir-Sessile dataset.
Related papers
- PolypDB: A Curated Multi-Center Dataset for Development of AI Algorithms in Colonoscopy [31.54817948734052]
We introduce PolypDB, a large scale publicly available dataset that contains 3934 still polyp images.
The dataset has been developed and verified by a team of 10 gastroenterologists.
We provide a benchmark on each modality using eight popular segmentation methods and six standard benchmark polyp detection methods.
arXiv Detail & Related papers (2024-08-19T05:36:01Z) - ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic
Polyp Detection [88.4359020192429]
Existing methods either involve computationally expensive context aggregation or lack prior modeling of polyps, resulting in poor performance in challenging cases.
In this paper, we propose the Enhanced CenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training & end-to-end inference framework.
Box-assisted Contrastive Learning (BCL) during training to minimize the intra-class difference and maximize the inter-class difference between foreground polyps and backgrounds, enabling our model to capture concealed polyps.
In the fine-tuning stage, we introduce the IoU-guided Sample Re-weighting
arXiv Detail & Related papers (2024-01-10T07:03:41Z) - How Does Pruning Impact Long-Tailed Multi-Label Medical Image
Classifiers? [49.35105290167996]
Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance.
This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification.
arXiv Detail & Related papers (2023-08-17T20:40:30Z) - Lesion-aware Dynamic Kernel for Polyp Segmentation [49.63274623103663]
We propose a lesion-aware dynamic network (LDNet) for polyp segmentation.
It is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme.
This simple but effective scheme endows our model with powerful segmentation performance and generalization capability.
arXiv Detail & Related papers (2023-01-12T09:53:57Z) - TransResU-Net: Transformer based ResU-Net for Real-Time Colonoscopy
Polyp Segmentation [1.9875031133911856]
The miss rate of polyps, adenomas and advanced adenomas remains significantly high.
Deep learning-based computer-aided diagnosis (CADx) system may help gastroenterologists to identify polyps that may otherwise be missed.
TransResU-Net could be a strong benchmark for building a real-time polyp detection system.
arXiv Detail & Related papers (2022-06-17T19:36:37Z) - Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution
Network [3.1374864575817214]
In this study, we introduce a novel deep learning architecture, named textbfMKDCNet, for automatic polyp segmentation.
Experiments on four publicly available polyp datasets and cell nuclei dataset show that the proposed MKDCNet outperforms the state-of-the-art methods.
MKDCNet can be a strong benchmark for building real-time systems for clinical colonoscopies.
arXiv Detail & Related papers (2022-06-13T15:47:38Z) - PolypConnect: Image inpainting for generating realistic gastrointestinal
tract images with polyps [1.7915968197912802]
Early identification of a polyp in the lower gastrointestinal (GI) tract can lead to prevention of life-threatening colorectal cancer.
CAD systems to detect polyps can improve detection accuracy and efficiency and save the time of the domain experts called endoscopists.
We propose the PolypConnect pipeline, which can convert non-polyp images into polyp images to increase the size of training datasets for training.
arXiv Detail & Related papers (2022-05-30T20:20:19Z) - Automatic Polyp Segmentation via Multi-scale Subtraction Network [100.94922587360871]
In clinical practice, precise polyp segmentation provides important information in the early detection of colorectal cancer.
Most existing methods are based on U-shape structure and use element-wise addition or concatenation to fuse different level features progressively in decoder.
We propose a multi-scale subtraction network (MSNet) to segment polyp from colonoscopy image.
arXiv Detail & Related papers (2021-08-11T07:54:07Z) - DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation [0.3734402152170273]
We propose a novel architecture called DDANet'' based on a dual decoder attention network.
Experiments demonstrate that the model trained on the Kvasir-SEG dataset and tested on an unseen dataset achieves a dice coefficient of 0.7874, mIoU of 0.7010, recall of 0.7987, and a precision of 0.8577.
arXiv Detail & Related papers (2020-12-30T17:52:35Z) - PraNet: Parallel Reverse Attention Network for Polyp Segmentation [155.93344756264824]
We propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images.
We first aggregate the features in high-level layers using a parallel partial decoder (PPD)
In addition, we mine the boundary cues using a reverse attention (RA) module, which is able to establish the relationship between areas and boundary cues.
arXiv Detail & Related papers (2020-06-13T08:13:43Z)
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.