Rule-Based Synthesis of Microscopy Images by Diffusion Refinement.
Abstract: Deep learning methods in medical imaging often suffer from the limited availability of high-quality annotated data, especially for rare conditions. This data scarcity is largely due to the need for domain expertise and the time-consuming process of data collection and annotation. Recent ad...
| Publicado en: | Journal of Imaging Informatics in Medicine pp. 1 - 15 |
|---|---|
| Autores principales: | , , |
| Formato: | Journal Article |
| Publicado: |
Springer Nature
Apr2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=193274989&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 193274989 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 29482925 NR3A jtl: Journal of Imaging Informatics in Medicine issn: 29482925 maglogo: N pubinfo: dt: Apr2026 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 193274989 10.1007/s10278-026-01935-x 193274989 ppf: 1 ppct: 14 formats: tig: atl: Rule-Based Synthesis of Microscopy Images by Diffusion Refinement. aug: au: Kollár, Maroš Vajsová, Andrea Benesova, Wanda affil: Faculty of Informatics and Information Technologies, Slovak University of Technology sug: ab: Abstract: Deep learning methods in medical imaging often suffer from the limited availability of high-quality annotated data, especially for rare conditions. This data scarcity is largely due to the need for domain expertise and the time-consuming process of data collection and annotation. Recent advances in generative neural networks offer a promising solution by producing realistic synthetic images that can supplement or partially replace scarce real data. In this work, we propose a framework for synthesizing realistic microscopy images together with their corresponding structural annotations. The proposed method combines a procedural generator that encodes expert-defined diagnostic rules with a diffusion-based refinement that enhances visual realism while preserving the prescribed structure. We further introduce a multi-stage diffusion-based refinement process that utilizes a segmentation mask to guide refinement and ensure a predefined structure. We demonstrate the ability of the proposed framework on the use case of synthesizing microscopic images of motile cilia cross-sections, which are important for the diagnosis of Primary Ciliary Dyskinesia (PCD). Our results show that data created by the proposed approach can serve as both a complement to and a substitute for real training data in a downstream segmentation task.Graphical Abstract: Deep learning methods in medical imaging often suffer from the limited availability of high-quality annotated data, especially for rare conditions. This data scarcity is largely due to the need for domain expertise and the time-consuming process of data collection and annotation. Recent advances in generative neural networks offer a promising solution by producing realistic synthetic images that can supplement or partially replace scarce real data. In this work, we propose a framework for synthesizing realistic microscopy images together with their corresponding structural annotations. The proposed method combines a procedural generator that encodes expert-defined diagnostic rules with a diffusion-based refinement that enhances visual realism while preserving the prescribed structure. We further introduce a multi-stage diffusion-based refinement process that utilizes a segmentation mask to guide refinement and ensure a predefined structure. We demonstrate the ability of the proposed framework on the use case of synthesizing microscopic images of motile cilia cross-sections, which are important for the diagnosis of Primary Ciliary Dyskinesia (PCD). Our results show that data created by the proposed approach can serve as both a complement to and a substitute for real training data in a downstream segmentation task. pubtype: Academic Journal doctype: Journal Article ougenre: Unknown language: English refInfo: holdings: @attributes: islocal: N |
|---|