Deep neural network automated segmentation of cellular structures in volume electron microscopy.
Deep neural network automated segmentation of cellular structures in volume electron microscopy.
复制标题
DOI：
10.1083/jcb.202208005
复制
发表时间：
2023-02-06
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
加卢瑟等人。提出了一种新的管道来训练卷积神经网络，以快速有效地自动检测通过体积电子显微镜成像的各种尺寸和复杂性的细胞内结构。体积电子显微镜是当代细胞生物学中重要的成像方式。细胞内结构的识别是一个费力的过程，限制了这种潜在强大工具的有效使用。我们通过电子显微镜中细胞内子结构的自动分割（ASEM）解决了这个瓶颈，这是一种训练卷积神经网络来检测各种大小和复杂性结构的新流程。我们基于仅来自一两个细胞的少量稀疏注释的地面实况图像，获得了每种结构的专用模型。通过快速、计算有效的策略来改进模型泛化，通过包含一些额外的注释来完善训练模型。我们通过聚焦离子束扫描电子显微镜成像鉴定了线粒体、高尔基体、内质网、核孔复合体、细胞膜窝、网格蛋白包被的小凹和囊泡。我们发现了单细胞内各种膜-核孔径，并从网格蛋白包被的凹坑和囊泡中导出了形态学指标，与经典的恒定生长组装模型一致。
Gallusser et al. present a new pipeline to train a convolutional neural network for rapid and efficient automated detection of intracellular structures of wide range in size and complexity imaged by volume electron microscopy. Volume electron microscopy is an important imaging modality in contemporary cell biology. Identification of intracellular structures is a laborious process limiting the effective use of this potentially powerful tool. We resolved this bottleneck with automated segmentation of intracellular substructures in electron microscopy (ASEM), a new pipeline to train a convolutional neural network to detect structures of a wide range in size and complexity. We obtained dedicated models for each structure based on a small number of sparsely annotated ground truth images from only one or two cells. Model generalization was improved with a rapid, computationally effective strategy to refine a trained model by including a few additional annotations. We identified mitochondria, Golgi apparatus, endoplasmic reticulum, nuclear pore complexes, caveolae, clathrin-coated pits, and vesicles imaged by focused ion beam scanning electron microscopy. We uncovered a wide range of membrane–nuclear pore diameters within a single cell and derived morphological metrics from clathrin-coated pits and vesicles, consistent with the classical constant-growth assembly model.
登录
查看更多内容
DOI：
10.1083/jcb.84.3.560
发表时间：
1980-03
期刊：
The Journal of cell biology
影响因子：
--
作者：
Heuser J
通讯作者：
Heuser J
影响因子：
48
作者：
Buhmann J;Sheridan A;Malin-Mayor C;Schlegel P;Gerhard S;Kazimiers T;Krause R;Nguyen TM;Heinrich L;Lee WA;Wilson R;Saalfeld S;Jefferis GSXE;Bock DD;Turaga SC;Cook M;Funke J
通讯作者：
Funke J
影响因子：
11.8
作者：
Chou YY;Upadhyayula S;Houser J;He K;Skillern W;Scanavachi G;Dang S;Sanyal A;Ohashi KG;Di Caprio G;Kreutzberger AJB;Vadakkan TJ;Kirchhausen T
通讯作者：
Kirchhausen T
DOI：
10.1126/science.aaq1392
发表时间：
2018-04-20
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Liu TL;Upadhyayula S;Milkie DE;Singh V;Wang K;Swinburne IA;Mosaliganti KR;Collins ZM;Hiscock TW;Shea J;Kohrman AQ;Medwig TN;Dambournet D;Forster R;Cunniff B;Ruan Y;Yashiro H;Scholpp S;Meyerowitz EM;Hockemeyer D;Drubin DG;Martin BL;Matus DQ;Koyama M;Megason SG;Kirchhausen T;Betzig E
通讯作者：
Betzig E
影响因子：
4.6
作者：
Guay MD;Emam ZAS;Anderson AB;Aronova MA;Pokrovskaya ID;Storrie B;Leapman RD
通讯作者：
Leapman RD