arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2105.11277cs.CVeess.IV
收藏

什么是计算机视觉辅助细胞学的最新技术?一项系统性文献综述

What is the State of the Art of Computer Vision-Assisted Cytology? A Systematic Literature Review

Federal University of Santa Catarina(圣卡塔琳娜联邦大学)
André Victória Matias, João Gustavo Atkinson Amorim, Luiz Antonio Buschetto Macarini, Allan Cerentini, Alexandre Sherlley Casimiro Onofre, Fabiana Botelho de Mi… 展开作者

André Victória Matias, João Gustavo Atkinson Amorim, Luiz Antonio Buschetto Macarini, Allan Cerentini, Alexandre Sherlley Casimiro Onofre, Fabiana Botelho de Miranda Onofre, Felipe Perozzo Daltoé, Marcelo Ricardo Stemmer, Aldo von Wangenheim

摘要:

细胞学是一种低成本和非侵入性的诊断程序,用于支持广泛的病理诊断。计算机视觉技术通过自动生成对检查内容的定量和客观描述,可以帮助减少误诊的机会并缩短分析所需的时间。为了确定目前应用于细胞学的最新计算机视觉技术,我们进行了系统性文献综述。我们分析了过去5年发表的论文。初步检索于2020年9月执行,共检索到431篇文章。在应用纳入/排除标准后,剩下157篇论文,我们分析了这一研究领域存在的趋势和问题,突出了计算机视觉方法,染色技术,评估指标以及所用数据集和计算机代码的可用性。因此,我们发现分析的作品中使用最多的方法是基于深度学习的(70篇论文),而较少的作品仅采用经典的计算机视觉(101篇论文)。用于分类和目标检测的最经常使用的度量是准确度(33篇论文和5篇论文),而用于分割的是Dice相似系数(38篇论文)。关于染色技术,Papanicolaou是使用最多的(130篇),其次是H&E(20篇)和Feulgen(5篇)。论文中使用的12个数据集是公开的,DTU/Herlev数据集是使用最多的数据集。我们的结论是,仍然缺乏高质量的数据集,许多类型的染色和大多数的作品还不够成熟,可以应用于日常的临床诊断程序。我们还发现,越来越多的人倾向于采用基于深度学习的方法作为首选方法。

英文摘要:

Cytology is a low-cost and non-invasive diagnostic procedure employed to support the diagnosis of a broad range of pathologies. Computer Vision technologies, by automatically generating quantitative and objective descriptions of examinations' contents, can help minimize the chances of misdiagnoses and shorten the time required for analysis. To identify the state-of-art of computer vision techniques currently applied to cytology, we conducted a Systematic Literature Review. We analyzed papers published in the last 5 years. The initial search was executed in September 2020 and resulted in 431 articles. After applying the inclusion/exclusion criteria, 157 papers remained, which we analyzed to build a picture of the tendencies and problems present in this research area, highlighting the computer vision methods, staining techniques, evaluation metrics, and the availability of the used datasets and computer code. As a result, we identified that the most used methods in the analyzed works are deep learning-based (70 papers), while fewer works employ classic computer vision only (101 papers). The most recurrent metric used for classification and object detection was the accuracy (33 papers and 5 papers), while for segmentation it was the Dice Similarity Coefficient (38 papers). Regarding staining techniques, Papanicolaou was the most employed one (130 papers), followed by H&E (20 papers) and Feulgen (5 papers). Twelve of the datasets used in the papers are publicly available, with the DTU/Herlev dataset being the most used one. We conclude that there still is a lack of high-quality datasets for many types of stains and most of the works are not mature enough to be applied in a daily clinical diagnostic routine. We also identified a growing tendency towards adopting deep learning-based approaches as the methods of choice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑