Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 13 min ago
PreprintCC BY-NCbioRxiv

A general route to volumetric segmentation under annotation scarcity

  • s. radhakrishnan
  • s. mathur
  • a. aleksandrov
  • h. schweke
  • g. silvano
  • e. d. levy1
  1. 1University of Geneva
Read full textPDFDOICite

Abstract

Volumetric cell segmentation is limited by the scarcity of labelled data, because manual curation of three-dimensional datasets is prohibitively laborious. We find that this gap can be bridged with volumes in which synthetic 3D objects mirror the properties of real cells and of image formation, notably the axial spread of the point-spread function. Such volumes provide unlimited labelled training data, and we show that a model trained on them produces accurate segmentations of real biological data.

Related

  1. napari-TurboBox: Interactive Multi-Viewer Bounding Box Annotation for AI-Guided Volumetric Bioimaging
    Nils Friederich, Philip Kohle, Maximilian Beichter +11
    arXivPreprintCC BY 4.0Full textBioinformatics & computational biologyarXiv
  2. Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence
    Min Gao, Yukun Guo, Tristan T. Hormel +5
    arXivPreprintCC BY-NC-ND 4.0Full textBioinformatics & computational biologyarXiv
  3. Preprocessing strategies for plant disease instance segmentation: annotation efficiency, context signals, and dual-metric evaluation on PlantSeg.
    Youssef Natij, Hajar El Karch, Abdelmounaim Belaaribi +3
    Frontiers in artificial intelligencePeer-reviewedCC BYFull textPlant biologyEurope PMC
  4. Ventral Tegmental Area Dopamine Neuron Dynamics during Postpartum Scarcity-Adversity Depend on Caregiving Quality and Pup Proximity
    Christine H. Nguyen, Shreya Jayamohan, Millie Rincón-Cortés
    The Journal of NeurosciencePeer-reviewedPublisher termsFull textNeurosciencePMC
  5. Interactive effects of Nutrient Enrichment and Water Scarcity on Floral signaling and visitation
    M. Manavalan, D. Thakur, B. Panthi +1
    bioRxivPreprintCC BY-NC-NDFull textEcologybioRxiv

Cite

BibTeXRIS
BibTeX
@misc{radhakrishnan2026general,
  title = {{A general route to volumetric segmentation under annotation scarcity}},
  author = {s. radhakrishnan and s. mathur and a. aleksandrov and h. schweke and g. silvano and e. d. levy},
  howpublished = {bioRxiv},
  year = {2026},
  month = sep,
  doi = {10.64898/2026.09.16.752170},
  url = {https://www.biorxiv.org/content/10.64898/2026.09.16.752170v1},
  note = {CC BY-NC},
}
RIS
TY  - UNPB
TI  - A general route to volumetric segmentation under annotation scarcity
AU  - s. radhakrishnan
AU  - s. mathur
AU  - a. aleksandrov
AU  - h. schweke
AU  - g. silvano
AU  - e. d. levy
PY  - 2026
DA  - 2026/09/16
PB  - bioRxiv
DO  - 10.64898/2026.09.16.752170
UR  - https://www.biorxiv.org/content/10.64898/2026.09.16.752170v1
AB  - Volumetric cell segmentation is limited by the scarcity of labelled data, because manual curation of three-dimensional datasets is prohibitively laborious. We find that this gap can be bridged with volumes in which synthetic 3D objects mirror the properties of real cells and of image formation, notably the axial spread of the point-spread function. Such volumes provide unlimited labelled training data, and we show that a model trained on them produces accurate segmentations of real biological data.
ER  -