Výsledky vyhledávání

Report

EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis

Autor: Yang, Ruijie, Zhu, Yan, Fu, Peiyao, Zhang, Yizhe, Wang, Zhihua, Li, Quanlin, Zhou, Pinghong, Yang, Xian, Wang, Shuo

Determining the necessity of resecting malignant polyps during colonoscopy screen is crucial for patient outcomes, yet challenging due to the time-consuming and costly nature of histopathology examination. While deep learning-based classification mod

Externí odkaz: http://arxiv.org/abs/2407.11401

Zobrazit plný text záznamu

Report

Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models

Autor: Wang, Shuo, Zhu, Yan, Luo, Xiaoyuan, Yang, Zhiwei, Zhang, Yizhe, Fu, Peiyao, Wang, Manning, Song, Zhijian, Li, Quanlin, Zhou, Pinghong, Guo, Yike

The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text colonoscopy rec

Externí odkaz: http://arxiv.org/abs/2310.11173

Zobrazit plný text záznamu

Report

RCDN -- Robust X-Corner Detection Algorithm based on Advanced CNN Model

Autor: Chen, Ben, Xiong, Caihua, Li, Quanlin, Wan, Zhonghua

Accurate detection and localization of X-corner on both planar and non-planar patterns is a core step in robotics and machine vision. However, previous works could not make a good balance between accuracy and robustness, which are both crucial criter

Externí odkaz: http://arxiv.org/abs/2307.03505

Zobrazit plný text záznamu

Report

EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)

Autor: Wang, Haoran, Zhu, Yan, Qin, Wenzheng, Zhang, Yizhe, Zhou, Pinghong, Li, Quanlin, Wang, Shuo, Song, Zhijian

The advance of computer-aided detection systems using deep learning opened a new scope in endoscopic image analysis. However, the learning-based models developed on closed datasets are susceptible to unknown anomalies in complex clinical environments

Externí odkaz: http://arxiv.org/abs/2212.12204

Zobrazit plný text záznamu