Summary of Cross-organ Domain Adaptive Neural Network For Pancreatic Endoscopic Ultrasound Image Segmentation, by Zhichao Yan et al.
Cross-Organ Domain Adaptive Neural Network for Pancreatic Endoscopic Ultrasound Image Segmentation
by ZhiChao Yan, Hui Xue, Yi Zhu, Bin Xiao, Hao Yuan
First submitted to arxiv on: 7 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Accurate lesion segmentation in pancreatic endoscopic ultrasound (EUS) images is crucial for effective diagnosis and treatment. Domain adaptation (DA) has been employed to address this challenge by leveraging related knowledge from other domains. However, existing DA methods only focus on multi-view representations of the same organ, which limits their effectiveness. To address this issue, we propose Cross-Organ Tumor Segmentation Networks (COTS-Nets), comprising a universal network and an auxiliary network. The universal network utilizes boundary loss to learn common boundary information of different tumors, enabling accurate delineation despite limited data. We also incorporate consistency loss to align predictions with tumor boundaries from other organs, mitigating the domain gap. Additionally, we developed the Pancreatic Cancer Endoscopic Ultrasound (PCEUS) dataset, comprising 501 pathologically confirmed pancreatic EUS images, to facilitate model development. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Researchers are trying to improve how well doctors can diagnose and treat pancreatic cancer using ultrasound images taken during endoscopies. They want to use computers to help identify tumors in these images more accurately. Currently, it’s hard to collect enough good-quality images for this purpose. To solve this problem, the researchers developed a new computer model that uses information from other organs to improve its ability to detect pancreatic cancer. They also created a large dataset of ultrasound images to test their model and make it better. |
Keywords
» Artificial intelligence » Domain adaptation
