Colonoscopy Polyp Detection: Domain Adaptation From Medical Report
Images to Real-time Videos
- URL: http://arxiv.org/abs/2012.15531v1
- Date: Thu, 31 Dec 2020 10:33:09 GMT
- Title: Colonoscopy Polyp Detection: Domain Adaptation From Medical Report
Images to Real-time Videos
- Authors: Zhi-Qin Zhan, Huazhu Fu, Yan-Yao Yang, Jingjing Chen, Jie Liu, and
Yu-Gang Jiang
- Abstract summary: We propose an Image-video-joint polyp detection network (Ivy-Net) to address the domain gap between colonoscopy images from historical medical reports and real-time videos.
Experiments on the collected dataset demonstrate that our Ivy-Net achieves the state-of-the-art result on colonoscopy video.
- Score: 76.37907640271806
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automatic colorectal polyp detection in colonoscopy video is a fundamental
task, which has received a lot of attention. Manually annotating polyp region
in a large scale video dataset is time-consuming and expensive, which limits
the development of deep learning techniques. A compromise is to train the
target model by using labeled images and infer on colonoscopy videos. However,
there are several issues between the image-based training and video-based
inference, including domain differences, lack of positive samples, and temporal
smoothness. To address these issues, we propose an Image-video-joint polyp
detection network (Ivy-Net) to address the domain gap between colonoscopy
images from historical medical reports and real-time videos. In our Ivy-Net, a
modified mixup is utilized to generate training data by combining the positive
images and negative video frames at the pixel level, which could learn the
domain adaptive representations and augment the positive samples.
Simultaneously, a temporal coherence regularization (TCR) is proposed to
introduce the smooth constraint on feature-level in adjacent frames and improve
polyp detection by unlabeled colonoscopy videos. For evaluation, a new large
colonoscopy polyp dataset is collected, which contains 3056 images from
historical medical reports of 889 positive patients and 7.5-hour videos of 69
patients (28 positive). The experiments on the collected dataset demonstrate
that our Ivy-Net achieves the state-of-the-art result on colonoscopy video.
Related papers
- EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis [10.83700068295662]
EndoFinder is a content-based image retrieval framework.
It finds the 'digital twin' polyp in the reference database given a newly detected polyp.
The clinical semantics of the new polyp can be inferred referring to the matched ones.
arXiv Detail & Related papers (2024-07-16T05:40:17Z) - SSTFB: Leveraging self-supervised pretext learning and temporal self-attention with feature branching for real-time video polyp segmentation [4.027361638728112]
We propose a video polyp segmentation method that performs self-supervised learning as an auxiliary task and a spatial-temporal self-attention mechanism for improved representation learning.
Our experimental results demonstrate an improvement with respect to several state-of-the-art (SOTA) methods.
Our ablation study confirms that the choice of the proposed joint end-to-end training improves network accuracy by over 3% and nearly 10% on both the Dice similarity coefficient and intersection-over-union.
arXiv Detail & Related papers (2024-06-14T17:33:11Z) - REAL-Colon: A dataset for developing real-world AI applications in
colonoscopy [1.8590283101866463]
We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset.
It is a compilation of 2.7M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers.
The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists.
arXiv Detail & Related papers (2024-03-04T16:11:41Z) - YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast
Video Polyp Detection [80.68520401539979]
textbfYONA (textbfYou textbfOnly textbfNeed one textbfAdjacent Reference-frame) is an efficient end-to-end training framework for video polyp detection.
Our proposed YONA outperforms previous state-of-the-art competitors by a large margin in both accuracy and speed.
arXiv Detail & Related papers (2023-06-06T13:53:15Z) - Accurate Real-time Polyp Detection in Videos from Concatenation of
Latent Features Extracted from Consecutive Frames [5.2009074009536524]
Convolutional neural networks (CNNs) are vulnerable to small changes in the input image.
A CNN-based model may miss the same polyp appearing in a series of consecutive frames.
We propose an efficient feature concatenation method for a CNN-based encoder-decoder model.
arXiv Detail & Related papers (2023-03-10T11:51:22Z) - Contrastive Transformer-based Multiple Instance Learning for Weakly
Supervised Polyp Frame Detection [30.51410140271929]
Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images.
We formulate polyp detection as a weakly-supervised anomaly detection task that uses video-level labelled training data to detect frame-level polyps.
arXiv Detail & Related papers (2022-03-23T01:30:48Z) - 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) - Colorectal Polyp Classification from White-light Colonoscopy Images via
Domain Alignment [57.419727894848485]
A computer-aided diagnosis system is required to assist accurate diagnosis from colonoscopy images.
Most previous studies at-tempt to develop models for polyp differentiation using Narrow-Band Imaging (NBI) or other enhanced images.
We propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification.
arXiv Detail & Related papers (2021-08-05T09:31:46Z) - Generative Adversarial U-Net for Domain-free Medical Image Augmentation [49.72048151146307]
The shortage of annotated medical images is one of the biggest challenges in the field of medical image computing.
In this paper, we develop a novel generative method named generative adversarial U-Net.
Our newly designed model is domain-free and generalizable to various medical images.
arXiv Detail & Related papers (2021-01-12T23:02:26Z) - 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.