Salvato in:
Dettagli Bibliografici
Autori principali: Chakraborty, Rajatsubhra, Espinosa-Momox, Ana, Haskin, Riley, Xu, Depeng, Porras-Aguilar, Rosario
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.00218
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912680798846976
author Chakraborty, Rajatsubhra
Espinosa-Momox, Ana
Haskin, Riley
Xu, Depeng
Porras-Aguilar, Rosario
author_facet Chakraborty, Rajatsubhra
Espinosa-Momox, Ana
Haskin, Riley
Xu, Depeng
Porras-Aguilar, Rosario
contents Cell segmentation in single-shot quantitative phase microscopy (ssQPM) faces challenges from traditional thresholding methods that are sensitive to noise and cell density, while deep learning approaches using simple channel concatenation fail to exploit the complementary nature of polarized intensity images and phase maps. We introduce DM-QPMNet, a dual-encoder network that treats these as distinct modalities with separate encoding streams. Our architecture fuses modality-specific features at intermediate depth via multi-head attention, enabling polarized edge and texture representations to selectively integrate complementary phase information. This content-aware fusion preserves training stability while adding principled multi-modal integration through dual-source skip connections and per-modality normalization at minimal overhead. Our approach demonstrates substantial improvements over monolithic concatenation and single-modality baselines, showing that modality-specific encoding with learnable fusion effectively exploits ssQPM's simultaneous capture of complementary illumination and phase cues for robust cell segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00218
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DM-QPMNET: Dual-modality fusion network for cell segmentation in quantitative phase microscopy
Chakraborty, Rajatsubhra
Espinosa-Momox, Ana
Haskin, Riley
Xu, Depeng
Porras-Aguilar, Rosario
Computer Vision and Pattern Recognition
Artificial Intelligence
Cell segmentation in single-shot quantitative phase microscopy (ssQPM) faces challenges from traditional thresholding methods that are sensitive to noise and cell density, while deep learning approaches using simple channel concatenation fail to exploit the complementary nature of polarized intensity images and phase maps. We introduce DM-QPMNet, a dual-encoder network that treats these as distinct modalities with separate encoding streams. Our architecture fuses modality-specific features at intermediate depth via multi-head attention, enabling polarized edge and texture representations to selectively integrate complementary phase information. This content-aware fusion preserves training stability while adding principled multi-modal integration through dual-source skip connections and per-modality normalization at minimal overhead. Our approach demonstrates substantial improvements over monolithic concatenation and single-modality baselines, showing that modality-specific encoding with learnable fusion effectively exploits ssQPM's simultaneous capture of complementary illumination and phase cues for robust cell segmentation.
title DM-QPMNET: Dual-modality fusion network for cell segmentation in quantitative phase microscopy
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.00218