cs.CVNov 1, 2026

Biological Congruence: Evaluating Microscopy Generation Across Representations

Authors: Duway Nicolas Lesmes-Leon, Shumpei Takezaki, Fabian Schmeisser, Ryoma Bise, Gillian Lovell, Bianca Migliori, Andreas Dengel, Sheraz Ahmed

Organizations: German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany · RPTU Kaiserslautern-Landau, Kaiserslautern, Germany · Kyushu University, Fukuoka, Japan · Sartorius Corporate, Royston, UK

Abstract

Generative models increasingly produce realistic microscopy images, yet conventional evaluation primarily characterizes visual fidelity and distributional coverage rather than the biological information represented by synthetic data. We introduce biological congruence as an evaluation principle describing whether biologically relevant information forms a coherent description across representations and remains consistent with its empirical biological context. To study this principle, we develop a text-conditioned diffusion framework that jointly generates microscopy images and instance masks, exposing the same generated biological state through conditioning, visual appearance, and instance structure. Across prompt--mask, prompt--image, image--mask, and population-level analyses, we find strongly feature-dependent behavior: density and confluency are consistently preserved, morphology exhibits recurrent disagreement, while nearest-neighbor distance reveals that strong image--mask agreement can coexist with weaker conditioning and population fidelity. Stress testing increasingly unsupported phenotype combinations further shows that target controllability can increase while untargeted phenotypes reorganize and the complete generated state moves toward configurations better supported by real data. These findings demonstrate that generative quality, controllability, cross-representation agreement, and population fidelity capture complementary properties, motivating biological congruence as a relational perspective for evaluating scientific generative models.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Assessing Sample Quality in Conditional Generation under Compositional Shift

    Jun 8, 2026Berker Demirel, Valentino Maiorca, Marco Fumero +2Distribution ShiftConditional Generation

  2. Rethinking Microscopy Generation: Co-Designed Diffusion for Biologically Interpretable Single-Cell Synthesis

    Oct 24, 2026Shumpei Takezaki, Duway Nicolas Lesmes-Leon, Ryoma Bise +4Image GenerationControllable Image Generation

  3. Assessment of Conditional Diffusion Model for Synthetic Histopathology Image Generation

    Aug 4, 2026Seyed Kahaki, Shijie Li, Weijie Chen +1Medical Image SynthesisImage Generation Evaluation