Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Implicit neural representations for larval zebrafish brain microscopy: a reproducible benchmark on the MapZebrain atlas

Agnieszka Pregowska

Abstract

Implicit neural representations (INRs) offer continuous coordinate-based encodings for atlas registration, cross-modality resampling, sparse-view completion, and compact sharing of neuroanatomical data. Yet reproducible evaluation is lacking for high-resolution larval zebrafish microscopy, where preserving neuropil boundaries and fine neuronal processes is critical. We present a reproducible INR benchmark for the MapZebrain larval zebrafish brain atlas. Using a unified, seed-controlled protocol, we compare SIREN, Fourier features, Haar positional encoding, and a multi-resolution grid on 950 grayscale microscopy images, including atlas slices and single-neuron projections. Images are normalized with per-image (1,99) percentiles estimated from 10% of pixels in non-held-out columns, and spatial generalization is tested with a deterministic 40% column-wise hold-out along the X-axis. Haar and Fourier achieve the strongest macro-averaged reconstruction fidelity on held-out columns (about 26 dB), while the grid is moderately behind. SIREN performs worse in macro averages but remains competitive on area-weighted micro averages in the all-in-one regime. SSIM and edge-focused error further show that Haar and Fourier preserve boundaries more accurately. These results indicate that explicit spectral and multiscale encodings better capture high-frequency neuroanatomical detail than smoother-bias alternatives. For MapZebrain workflows, Haar and Fourier are best suited to boundary-sensitive tasks such as atlas registration, label transfer, and morphology-preserving sharing, while SIREN remains a lightweight baseline for background modelling or denoising.

Implicit neural representations for larval zebrafish brain microscopy: a reproducible benchmark on the MapZebrain atlas

Abstract

Implicit neural representations (INRs) offer continuous coordinate-based encodings for atlas registration, cross-modality resampling, sparse-view completion, and compact sharing of neuroanatomical data. Yet reproducible evaluation is lacking for high-resolution larval zebrafish microscopy, where preserving neuropil boundaries and fine neuronal processes is critical. We present a reproducible INR benchmark for the MapZebrain larval zebrafish brain atlas. Using a unified, seed-controlled protocol, we compare SIREN, Fourier features, Haar positional encoding, and a multi-resolution grid on 950 grayscale microscopy images, including atlas slices and single-neuron projections. Images are normalized with per-image (1,99) percentiles estimated from 10% of pixels in non-held-out columns, and spatial generalization is tested with a deterministic 40% column-wise hold-out along the X-axis. Haar and Fourier achieve the strongest macro-averaged reconstruction fidelity on held-out columns (about 26 dB), while the grid is moderately behind. SIREN performs worse in macro averages but remains competitive on area-weighted micro averages in the all-in-one regime. SSIM and edge-focused error further show that Haar and Fourier preserve boundaries more accurately. These results indicate that explicit spectral and multiscale encodings better capture high-frequency neuroanatomical detail than smoother-bias alternatives. For MapZebrain workflows, Haar and Fourier are best suited to boundary-sensitive tasks such as atlas registration, label transfer, and morphology-preserving sharing, while SIREN remains a lightweight baseline for background modelling or denoising.

Paper Structure

This paper contains 15 sections, 5 equations, 10 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Biological motivation
  3. Methods
  4. Implicit Neural Representations
  5. Database
  6. Regimes
  7. Preprocessing
  8. Evaluation
  9. Numerical Results
  10. Interpretation of results based on biological experiment
  11. Discussion
  12. Practical implications for atlas workflows
  13. Limitations
  14. Conclusions
  15. Reproducibility

Figures (10)

  • Figure 1: Overall distribution of $\mathrm{PSNR}_{\text{test\_mean}}$ for the four INR variants (all images). Fourier and Haar have similar medians but a broader upper tail. SIREN is the most concentrated.
  • Figure 2: Mean $\mathrm{PSNR}_{\text{test\_mean}}$ (macro) across methods. Haar and Fourier achieve the highest averages.
  • Figure 3: Box plot of $\mathrm{PSNR}_{\text{test\_mean}}$ showing broad distributions with occasional outliers.
  • Figure 4: Violin plot of $\mathrm{PSNR}_{\text{test\_mean}}$ illustrating per-image variability.
  • Figure 5: Representative reconstructions for selected MapZebrain regions using different positional encodings. Fourier and Haar preserve morphological detail and boundaries, SIREN smooths fine structures, and Grid exhibits strong blurring and vertical artifacts. Rightmost panels show column-wise MAE profiles.
  • ...and 5 more figures