Digital diatom analysis: investigating advanced deep learning-based approaches for gigapixel-sized virtual slides
Digital diatom analysis: investigating advanced deep learning-based approaches for gigapixel-sized virtual slides
批准号:
463395318
负责人:
Professor Dr. Bánk Beszteri
金额:
$0.0万
依托单位:
依托单位国家:
德国
项目类别:
Research Grants
财政年份:
--
资助国家:
德国
项目状态:
未结题
起止时间:
中文摘要
硅藻是一类微藻,在广泛的水生生境中起着重要的生态作用。它们的硅酸盐壳的光显微研究是最古老的方法之一,但在生态学、古生态学和应用研究中仍然广泛应用于确定它们的组合组成。这些方法向数字方法的过渡已经持续了一段时间,在生态/形态计量学研究中,有大量迹象表明,在一致性、透明度、精度和统计能力方面存在改进。到目前为止,这种数字硅藻分析大多只针对一个或几个分类群,或者在复杂群落的情况下需要大量的手工注释工作来进行分类鉴定。然而,试点研究现在已经明确表明,深度卷积网络可能很快就能使数字硅藻分析在物种丰富的“现实生活”条件下工作。我们确定了目前阻碍这一点的三个主要问题领域,与1)尽管背景复杂(由沉积物和其他颗粒引起),硅藻图像的分割;2)在自然群落中,面对凹级丰度关系,有效提高训练数据集的分类覆盖率;3)大小、轮廓形状和纹理对硅藻算法识别的相对重要性。我们希望通过一系列深度学习实验来解决这些问题,并为深度学习模型支持的数字硅藻分析在群落生态学、古生态学和其他类型硅藻研究中的常规应用铺平道路。
英文摘要
Diatoms are a speciose group of microalgae playing important ecological roles in a broad range of aquatic habitats. Light microscopic investigation of their silicate shells is one of the oldest, but still widely used approaches to determining their assemblage composition in ecological, paleo-ecological and applied research. A transition of these methods to digital counterparts has been ongoing for some time now, with abundant indications for improvements related to consistency, transparency, precision and statistical power in ecological / morphometric studies. Thus far, such digital diatom analyses have mostly targeted only one or a few taxa, or required substantial manual annotation effort for taxonomic identification in the case of complex communities. Pilot studies have, however, now made it clear that deep convolutional networks will probably soon be able to also enable digital diatom analysis to work in “real life” conditions, with species rich communities. We identified three main problem fields presently hindering this, related to 1) segmentation of diatom images in spite of complex backgrounds (caused by sediment and other particles); 2) efficiently increasing taxonomic coverage of training data sets in the face of concave rank-abundance relationships in natural communities; and 3) the relative importance of size, outline shape and texture for algorithmic diatom identification. We would like to address these problems by a series of deep learning experiments and pave the way for a routine application of digital diatom analysis supported by deep learning models in community ecology, paleoecology and other types of diatom investigations.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Deep mobilization of natural history collections of microscopic organisms using high throughput image analyses and interlinking with molecular data (MobiDiC - MOBIlization of a DIatom Collection)
-
批准号:350992967
-
项目类别:Priority Programmes
-
资助金额:$0.0万
-
财政年份:2017
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
Genomic signatures of neutral and adaptive microevolutionary processes in Fragilariopsis kerguelensis, a main silicate sinker of the Southern Ocean
-
批准号:315170671
-
项目类别:Infrastructure Priority Programmes
-
资助金额:$0.0万
-
财政年份:2016
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
Assessing species distributions and morphometrics in Southern Ocean diatoms using high throughput imaging and semi-automated image analysis
-
批准号:257060905
-
项目类别:Infrastructure Priority Programmes
-
资助金额:$0.0万
-
财政年份:2014
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
Integrating biodiversity and oceanographic information for modeling and predicting Southern Ocean diatom biogeography
-
批准号:197778705
-
项目类别:Infrastructure Priority Programmes
-
资助金额:$0.0万
-
财政年份:2011
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
Teilnahme an einem Sommerkurs "Computational phyloinformatics", am National Evolutionary Synthesis Center, Durham, USA 24. Juli bis 04. August 2008
-
批准号:100328670
-
项目类别:Research Grants
-
资助金额:$0.0万
-
财政年份:2008
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
DNAquaIMG: Innovating transnational aquatic biodiversity monitoring using high-throughput DNA tools and automated image recognition
-
批准号:532140722
-
项目类别:Research Grants
-
资助金额:$0.0万
-
财政年份:--
-
负责人:Professor Dr. Bánk Beszteri
-
依托单位:
海外基金