An Auxiliary Task for Learning Nuclei Segmentation in 3D Microscopy Images

被引:0
|
作者
Hirsch, Peter [1 ]
Kainmueller, Dagmar [1 ]
机构
[1] Berlin Inst Hlth, Max Delbrueck Ctr Mol Med Helmholtz Assoc, Berlin, Germany
关键词
machine learning; image analysis; instance segmentation; instance detection; nuclei segmentation; auxiliary training task;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Segmentation of cell nuclei in microscopy images is a prevalent necessity in cell biology. Especially for three-dimensional datasets, manual segmentation is prohibitively time-consuming, motivating the need for automated methods. Learning-based methods trained on pixel-wise ground-truth segmentations have been shown to yield state-of-the-art results on 2d benchmark image data of nuclei, yet a respective benchmark is missing for 3d image data. In this work, we perform a comparative evaluation of nuclei segmentation algorithms on a database of manually segmented 3d light microscopy volumes. We propose a novel learning strategy that boosts segmentation accuracy by means of a simple auxiliary task, thereby robustly outperforming each of our baselines. Furthermore, we show that one of our baselines, the popular three-label model, when trained with our proposed auxiliary task, outperforms the recent StarDist-3D. As an additional, practical contribution, we benchmark nuclei segmentation against nuclei detection, i.e. the task of merely pinpointing individual nuclei without generating respective pixel-accurate segmentations. For learning nuclei detection, large 3d training datasets of manually annotated nuclei center points are available. However, the impact on detection accuracy caused by training on such sparse ground truth as opposed to dense pixel-wise ground truth has not yet been quantified. To this end, we compare nuclei detection accuracy yielded by training on dense vs. sparse ground truth. Our results suggest that training on sparse ground truth yields competitive nuclei detection rates.
引用
收藏
页码:304 / 321
页数:18
相关论文
共 50 条
  • [1] Joint Segmentation and Pairing of Nuclei and Golgi in 3D Microscopy Images
    Narotamo, Hemaxi
    Ouarne, Marie
    Franco, Claudio Areias
    Silveira, Margarida
    [J]. 2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), 2021, : 3017 - 3020
  • [2] Automatic segmentation of nuclei in 3D microscopy images of C.elegans
    Long, Fuhui
    Peng, Hanchuan
    Myers, Eugene
    [J]. 2007 4TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING : MACRO TO NANO, VOLS 1-3, 2007, : 536 - 539
  • [3] Segmentation of Nuclei From 3D Microscopy Images of Tissue via Graphcut Optimization
    Nandy, Kaustav
    Chellappa, Rama
    Kumar, Amit
    Lockett, Stephen J.
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2016, 10 (01) : 140 - 150
  • [4] Microcrack Segmentation of 3D CT Images Based on Multi-Task Learning
    Peng, Junjie
    Li, Wenbin
    Liao, Suyu
    Zhu, Yining
    [J]. IEEE Access, 2024, 12 : 138192 - 138200
  • [5] 3D Nuclei Segmentation through Deep Learning
    Rojas, Roberto
    Navarro, Carlos F.
    Orellana, Gabriel A.
    Lemus, Carmen Gloria C.
    Castaneda, Victor
    [J]. 2023 IEEE CONFERENCE ON ARTIFICIAL INTELLIGENCE, CAI, 2023, : 309 - 310
  • [6] NU3D: 3D NUCLEI SEGMENTATION FROM LIGHT-SHEET MICROSCOPY IMAGES OF THE EMBRYONIC HEART
    Sarkar, Rituparna
    Darby, Daniel
    Foucambert, Heloise
    Meilhac, Sigolene
    Olivo-Marin, Jean-Christophe
    [J]. 2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2021, : 929 - 933
  • [7] AUTOMATED CELL SEGMENTATION WITH 3D FLUORESCENCE MICROSCOPY IMAGES
    Kong, Jun
    Wang, Fusheng
    Teodoro, George
    Liang, Yanhui
    Zhu, Yangyang
    Tucker-Burden, Carol
    Brat, Daniel J.
    [J]. 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), 2015, : 1212 - 1215
  • [8] Multi-task learning approach for volumetric segmentation and reconstruction in 3D OCT images
    Cahyo, Dheo A. Y.
    Yow, Ai Ping
    Saw, Seang-Mei
    Ang, Marcus
    Girard, Michael
    Schmetterer, Leopold
    Wong, Damon
    [J]. BIOMEDICAL OPTICS EXPRESS, 2021, 12 (12) : 7348 - 7360
  • [9] Automated Segmentation of Immunostained Cell Nuclei in 3D Ultramicroscopy Images
    Scherzinger, Aaron
    Kleene, Florian
    Dierkes, Cathrin
    Kiefer, Friedemann
    Hinrichs, Klaus H.
    Jiang, Xiaoyi
    [J]. PATTERN RECOGNITION, GCPR 2016, 2016, 9796 : 105 - 116
  • [10] SEGMENTATION OF CELL NUCLEI IN 3D MICROSCOPY IMAGES BASED ON LEVEL SET DEFORMABLE MODELS AND CONVEX MINIMIZATION
    Bergeest, Jan-Philip
    Rohr, Karl
    [J]. 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), 2014, : 637 - 640