Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology
Abstract
Automated pollen analysis supports veterinary cytology, but brightfield microscopy is costlier and more complex than lens-less digital in-line holographic microscopy. We evaluate whether reconstructed holograms can narrow this gap and whether model explanations remain reliable under modality change. Six pollen species were imaged by brightfield and holographic microscopy. Raw, single back-propagation and iterative phase retrieval holograms were evaluated with YOLOv26s detection and MobileNetV4 classification after anchor-based annotation transfer. Six attribution methods were assessed for spatial grounding and faithfulness with the Attribution Health Inspection and Repair (AHIR) protocol, which tests model brittleness under weak noise and corrects attribution-map granularity when needed. Brightfield achieved 0.6890 mAP50-95 (0.8865 mAP50) for detection and 0.9687 macro-F1 (0.9705 accuracy) for classification. Reconstructed holograms narrowed the gap with a task-dependent split: p-type was strongest for detection at 0.5324 mAP50-95 (0.8229 mAP50), while r-type was strongest for classification at 0.7695 macro-F1 (0.7866 accuracy), both far above raw-hologram baselines. Activation-based explanations localized strongly on grains, and region-based methods retained ~60 to ~80% of faithfulness under holography. The holographic detector was highly brittle to weak perturbations, saturating deletion-based evaluation while insertion remained informative. Pixel-level gradient explanations approached random floor, yet spatial smoothing restored p-type gradient faithfulness from 0.05 to 0.51. For holographic classification, perturbation-based explanations remained faithful while gradient-based methods fell below random floor. Reconstruction improves low-cost holographic pollen analysis, while AHIR distinguishes genuine attribution failure from artifacts caused by model brittleness and map granularity.
Related
- Characterization and evaluation of the anti-streptococcal activity of a novel zoocin A-like endopeptidase for potential veterinary applications
- Evaluation of the collaborative process of public-private partnerships in the veterinary domain: The case of the sanitary mandate in Tunisia
- Computational modeling and preclinical evaluation support targeting somatic instability for Huntington’s disease treatment
- Computational Design and Evaluation of De Novo Protein Minibinders Targeting Specific Sites of STAT3
- Novel 5-Phenylmorphans as Opioid Receptor Antagonists: Synthesis, Structure-Activity Relationship, Biological Evaluation and Computational Modeling
BibTeX
@misc{warshaneyan2026reconstructed,
title = {{Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology}},
author = {Swarn Warshaneyan and Joial Danyal and Blaž Cugmas and Mindaugas Tamošiūnas and Edgars Kviesis-Kipge and Kirishanth Manivannan and Roberts Kadiķis},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23017},
eprint = {2609.23017},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23017},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology
AU - Swarn Warshaneyan
AU - Joial Danyal
AU - Blaž Cugmas
AU - Mindaugas Tamošiūnas
AU - Edgars Kviesis-Kipge
AU - Kirishanth Manivannan
AU - Roberts Kadiķis
PY - 2026
DA - 2026/09/19
PB - arXiv
DO - 10.48550/arxiv.2609.23017
UR - https://arxiv.org/abs/2609.23017
AB - Automated pollen analysis supports veterinary cytology, but brightfield microscopy is costlier and more complex than lens-less digital in-line holographic microscopy. We evaluate whether reconstructed holograms can narrow this gap and whether model explanations remain reliable under modality change. Six pollen species were imaged by brightfield and holographic microscopy. Raw, single back-propagation and iterative phase retrieval holograms were evaluated with YOLOv26s detection and MobileNetV4 classification after anchor-based annotation transfer. Six attribution methods were assessed for spatial grounding and faithfulness with the Attribution Health Inspection and Repair (AHIR) protocol, which tests model brittleness under weak noise and corrects attribution-map granularity when needed. Brightfield achieved 0.6890 mAP50-95 (0.8865 mAP50) for detection and 0.9687 macro-F1 (0.9705 accuracy) for classification. Reconstructed holograms narrowed the gap with a task-dependent split: p-type was strongest for detection at 0.5324 mAP50-95 (0.8229 mAP50), while r-type was strongest for classification at 0.7695 macro-F1 (0.7866 accuracy), both far above raw-hologram baselines. Activation-based explanations localized strongly on grains, and region-based methods retained ~60 to ~80% of faithfulness under holography. The holographic detector was highly brittle to weak perturbations, saturating deletion-based evaluation while insertion remained informative. Pixel-level gradient explanations approached random floor, yet spatial smoothing restored p-type gradient faithfulness from 0.05 to 0.51. For holographic classification, perturbation-based explanations remained faithful while gradient-based methods fell below random floor. Reconstruction improves low-cost holographic pollen analysis, while AHIR distinguishes genuine attribution failure from artifacts caused by model brittleness and map granularity.
ER -