NeoUNet: Towards accurate colon polyp segmentation and neoplasm
detection
- URL: http://arxiv.org/abs/2107.05023v1
- Date: Sun, 11 Jul 2021 11:10:12 GMT
- Title: NeoUNet: Towards accurate colon polyp segmentation and neoplasm
detection
- Authors: Phan Ngoc Lan, Nguyen Sy An, Dao Viet Hang, Dao Van Long, Tran Quang
Trung, Nguyen Thi Thuy, Dinh Viet Sang
- Abstract summary: We propose a fine-grained formulation for the polyp segmentation problem.
Our formulation aims to not only segment polyp regions, but also identify those at high risk of malignancy with high accuracy.
We present a UNet-based neural network architecture called NeoUNet, along with a hybrid loss function to solve this problem.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Automatic polyp segmentation has proven to be immensely helpful for endoscopy
procedures, reducing the missing rate of adenoma detection for endoscopists
while increasing efficiency. However, classifying a polyp as being neoplasm or
not and segmenting it at the pixel level is still a challenging task for
doctors to perform in a limited time. In this work, we propose a fine-grained
formulation for the polyp segmentation problem. Our formulation aims to not
only segment polyp regions, but also identify those at high risk of malignancy
with high accuracy. In addition, we present a UNet-based neural network
architecture called NeoUNet, along with a hybrid loss function to solve this
problem. Experiments show highly competitive results for NeoUNet on our
benchmark dataset compared to existing polyp segmentation models.
Related papers
- 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) - Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation [7.31341312596412]
We propose a novel framework composed of ConvNeXt backbone and Multi Kernel Positional Embedding block.
Our model achieves the Dice coefficient of 0.8818 and the IOU score of 0.8163 on the Kvasir-SEG dataset.
arXiv Detail & Related papers (2023-01-17T03:12:57Z) - 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) - BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse
Bounding Box Annotations [79.17754846553866]
We propose a boosted BoxPolyp model to make full use of both accurate mask and extra coarse box annotations.
In practice, box annotations are applied to alleviate the over-fitting issue of previous polyp segmentation models.
Our proposed model outperforms previous state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2022-12-07T07:45:50Z) - Self-Supervised U-Net for Segmenting Flat and Sessile Polyps [63.62764375279861]
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.
arXiv Detail & Related papers (2021-10-17T09:31:20Z) - 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) - Advances in Artificial Intelligence to Reduce Polyp Miss Rates during
Colonoscopy [0.7619404259039283]
We introduce a new deep neural network architecture, which achieves state-of-the-art performance for polyp segmentation.
Our algorithm could be integrated into colonoscopy practice and assist gastroenterologists by reducing the number of polyps missed.
arXiv Detail & Related papers (2021-05-16T16:10:32Z) - AG-CUResNeSt: A Novel Method for Colon Polyp Segmentation [0.0]
This paper proposes a novel neural network architecture called AG-CUResNeSt, which enhances Coupled UNets using the robust ResNeSt backbone and attention gates.
We show that our proposed method achieves state-of-the-art accuracy compared to existing methods.
arXiv Detail & Related papers (2021-05-02T06:36:36Z) - 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.