deep-learning-colonoscopy

deep-learning-colonoscopy

深度学习在结肠镜息肉检测和分类中的应用进展

本项目汇集了深度学习在结肠镜息肉检测和分类领域的前沿研究。内容涵盖息肉检测定位、分类及同步检测分类三大方向,并提供数据集信息、深度学习架构和性能指标等技术细节。这些研究成果有望提升结肠癌筛查的准确度和效率,推动相关临床应用的发展。

深度学习结肠镜检查息肉检测息肉分类医学影像Github开源项目

Deep Learning for Polyp Detection and Classification in Colonoscopy

This repository was created from the following review paper: A. Nogueira-Rodríguez; R. Domínguez-Carbajales; H. López-Fernández; Á. Iglesias; J. Cubiella; F. Fdez-Riverola; M. Reboiro-Jato; D. Glez-Peña (2020) Deep Neural Networks approaches for detecting and classifying colorectal polyps. Neurocomputing.

Please, cite it if you find it useful for your research.

AI4PolypNet

AI4PolypNet

As part of AI4PolypNet, we are involved in a challenge that will be developed at iSMIT (September 2024). In this edition we will focus only on colonoscopy images and, apart from classical polyp detection and segmentation we present an extended version of polyp classification, including the challenging serrated sessile adenoma class. All the information is available here.

About this repository

This repository collects the most relevant studies applying Deep Learning for Polyp Detection and Classification in Colonoscopy from a technical point of view, focusing on the low-level details for the implementation of the DL models. In first place, each study is categorized in three types: (i) polyp detection and localization (through bounding boxes or binary masks, i.e. segmentation), (ii) polyp classification, and (iii) simultaneous polyp detection and classification (i.e. studies based on the usage of a single model such as YOLO or SSD to performs simultaneous polyp detection and classification). Secondly, a summary of the public datasets available as well as the private datasets used in the studies is provided. The third section focuses on technical aspects such as the Deep Learning architectures, the data augmentation techniques and the libraries and frameworks used. Finally, the fourth section summarizes the performance metrics reported by each study.

Suggestions are welcome, please check the contribution guidelines before submitting a pull request.

Table of Contents:

Research

Polyp Detection and Localization

StudyDateEndoscopy typeImaging technologyLocalization typeMultiple polypReal time
Tajbakhsh et al. 2014, Tajbakhsh et al. 2015Sept. 2014 / Apr. 2015ConventionalN/ABounding boxNoYes
Zhu R. et al. 2015Oct. 2015ConventionalN/ABounding box (16x16 patches)YesNo
Park and Sargent 2016March 2016ConventionalNBI, WLBounding boxNoNo
Yu et al. 2017Jan. 2017ConventionalNBI, WLBounding boxNoNo
Zhang R. et al. 2017Jan. 2017ConventionalNBI, WLNoNoNo
Yuan and Meng 2017Feb. 2017WCEN/ANoNoNo
Brandao et al. 2018Feb. 2018Conventional/WCEN/ABinary maskYesNo
Zhang R. et al. 2018May 2018ConventionalWLBounding boxNoNo
Misawa et al. 2018June 2018ConventionalWLNoYesNo
Zheng Y. et al. 2018July 2018ConventionalNBI, WLBounding boxYesYes
Shin Y. et al. 2018July 2018ConventionalWLBounding boxYesNo
Urban et al. 2018Sep. 2018ConventionalNBI, WLBounding boxNoYes
Mohammed et al. 2018, GitHubSep. 2018ConventionalWLBinary maskYesYes
Wang et al. 2018, Wang et al. 2018Oct. 2018ConventionalN/ABinary maskYesYes
Qadir et al. 2019Apr. 2019ConventionalNBI, WLBounding boxYesNo
Blanes-Vidal et al. 2019March 2019WCEN/ABounding boxYesNo
Zhang X. et al. 2019March 2019ConventionalN/ABounding boxYesYes
Misawa et al. 2019June 2019ConventionalN/ANoYesNo
Zhu X. et al. 2019June 2019ConventionalN/ANoNoYes
Ahmad et al. 2019June 2019ConventionalWLBounding boxYesYes
Sornapudi et al. 2019June 2019Conventional/WCEN/ABinary maskYesNo
Wittenberg et al. 2019Sept. 2019ConventionalWLBinary maskYesNo
Yuan Y. et al. 2019Sept. 2019WCEN/ANoNoNo
Ma Y. et al. 2019Oct. 2019ConventionalN/ABounding boxYesNo
Tashk et al. 2019Dec. 2019ConventionalN/ABinary maskNoNo
Jia X. et al. 2020Jan. 2020ConventionalN/ABinary maskYesNo
Ma Y. et al. 2020May 2020ConventionalN/ABounding boxYesNo
Young Lee J. et al. 2020May 2020ConventionalN/ABounding boxYesYes
Wang W. et al. 2020July 2020ConventionalWLNoNoNo
Li T. et al. 2020Oct. 2020ConventionalN/ANoNoNo
Sánchez-Peralta et al. 2020Nov. 2020ConventionalNBI, WLBinary maskNoNo
Podlasek J. et al. 2020Dec. 2020ConventionalN/ABounding boxNoYes
Qadir et al. 2021Feb. 2021ConventionalWLBounding boxYesYes
Xu J. et al. 2021Feb. 2021ConventionalWLBounding boxYesYes
Misawa et al. 2021Apr. 2021ConventionalWLNoYesYes
Livovsky et al. 2021June 2021ConventionalN/ABounding boxYesYes
Pacal et al. 2021July 2021ConventionalWLBounding boxYesYes
Liu et al. 2021July 2021ConventionalN/ABounding boxYesYes
Nogueira-Rodríguez et al. 2021Aug. 2021ConventionalNBI, WLBounding boxYesYes
Yoshida et al. 2021Aug. 2021ConventionalWL, LCIBounding boxYesYes
Ma Y. et al. 2021Sep. 2021ConventionalWLBounding boxYesNo
Pacal et al. 2022Nov. 2021ConventionalWLBounding boxYesYes
Nogueira-Rodríguez et al. 2022April 2022ConventionalNBI, WLBounding boxYesYes
Nogueira-Rodríguez et al. 2023March 2023ConventionalNBI, WLBounding boxYesYes

Polyp Classification

StudyDateEndoscopy typeImaging technologyClassesReal time
Ribeiro et al. 2016Oct. 2016ConventionalWLNeoplastic vs. Non-neoplasticNo
Zhang R. et al. 2017Jan. 2017ConventionalNBI, WLAdenoma vs. hyperplastic <br/> Resectable vs. non-resectable<br/> Adenoma vs. hyperplastic vs. serratedNo
Byrne et al. 2017Oct. 2017ConventionalNBIAdenoma vs. hyperplasticYes
Komeda et al. 2017Dec. 2017ConventionalNBI, WL, ChromoendoscopyAdenoma vs. non-adenomaNo
Chen et al. 2018Feb. 2018ConventionalNBINeoplastic vs. hyperplasticNo
Lui et al. 2019Apr. 2019ConventionalNBI, WLEndoscopically curable lesions vs. endoscopically incurable lesionNo
Kandel et al. 2019June 2019ConventionalN/AAdenoma vs. hyperplastic vs. serrated (sessile serrated adenoma/traditional serrated adenoma)No
Zachariah et al. 2019Oct. 2019ConventionalNBI, WLAdenoma vs. serratedYes
Bour et al. 2019Dec. 2019ConventionalN/AParis classification: not dangeours (types Ip, Is, IIa, and IIb) vs. dangerous (type IIc) vs. cancer (type III)No
Patino-Barrientos et al. 2020Jan. 2020ConventionalWLKudo's classification: malignant (types I, II, III, and IV) vs. non-malignant (type V)No
Cheng Tao Pu et al. 2020Feb. 2020ConventionalNBI, BLIModified Sano's (MS) classification: MS I (Hyperplastic) vs. MS II (Low-grade tubular adenomas) vs. MS

编辑推荐精选

讯飞智文

讯飞智文

一键生成PPT和Word,让学习生活更轻松

讯飞智文是一个利用 AI 技术的项目,能够帮助用户生成 PPT 以及各类文档。无论是商业领域的市场分析报告、年度目标制定,还是学生群体的职业生涯规划、实习避坑指南,亦或是活动策划、旅游攻略等内容,它都能提供支持,帮助用户精准表达,轻松呈现各种信息。

AI办公办公工具AI工具讯飞智文AI在线生成PPTAI撰写助手多语种文档生成AI自动配图热门
讯飞星火

讯飞星火

深度推理能力全新升级,全面对标OpenAI o1

科大讯飞的星火大模型,支持语言理解、知识问答和文本创作等多功能,适用于多种文件和业务场景,提升办公和日常生活的效率。讯飞星火是一个提供丰富智能服务的平台,涵盖科技资讯、图像创作、写作辅助、编程解答、科研文献解读等功能,能为不同需求的用户提供便捷高效的帮助,助力用户轻松获取信息、解决问题,满足多样化使用场景。

热门AI开发模型训练AI工具讯飞星火大模型智能问答内容创作多语种支持智慧生活
Spark-TTS

Spark-TTS

一种基于大语言模型的高效单流解耦语音令牌文本到语音合成模型

Spark-TTS 是一个基于 PyTorch 的开源文本到语音合成项目,由多个知名机构联合参与。该项目提供了高效的 LLM(大语言模型)驱动的语音合成方案,支持语音克隆和语音创建功能,可通过命令行界面(CLI)和 Web UI 两种方式使用。用户可以根据需求调整语音的性别、音高、速度等参数,生成高质量的语音。该项目适用于多种场景,如有声读物制作、智能语音助手开发等。

Trae

Trae

字节跳动发布的AI编程神器IDE

Trae是一种自适应的集成开发环境(IDE),通过自动化和多元协作改变开发流程。利用Trae,团队能够更快速、精确地编写和部署代码,从而提高编程效率和项目交付速度。Trae具备上下文感知和代码自动完成功能,是提升开发效率的理想工具。

AI工具TraeAI IDE协作生产力转型热门
咔片PPT

咔片PPT

AI助力,做PPT更简单!

咔片是一款轻量化在线演示设计工具,借助 AI 技术,实现从内容生成到智能设计的一站式 PPT 制作服务。支持多种文档格式导入生成 PPT,提供海量模板、智能美化、素材替换等功能,适用于销售、教师、学生等各类人群,能高效制作出高品质 PPT,满足不同场景演示需求。

讯飞绘文

讯飞绘文

选题、配图、成文,一站式创作,让内容运营更高效

讯飞绘文,一个AI集成平台,支持写作、选题、配图、排版和发布。高效生成适用于各类媒体的定制内容,加速品牌传播,提升内容营销效果。

热门AI辅助写作AI工具讯飞绘文内容运营AI创作个性化文章多平台分发AI助手
材料星

材料星

专业的AI公文写作平台,公文写作神器

AI 材料星,专业的 AI 公文写作辅助平台,为体制内工作人员提供高效的公文写作解决方案。拥有海量公文文库、9 大核心 AI 功能,支持 30 + 文稿类型生成,助力快速完成领导讲话、工作总结、述职报告等材料,提升办公效率,是体制打工人的得力写作神器。

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

下拉加载更多