High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks

Abstract High-throughput mesoscopic optical imaging technology has tremendously boosted the efficiency of procuring massive mesoscopic datasets from mouse brains. Constrained by the imaging field of view, the image strips obtained by such technologies typically require further processing, such as cr...

Full description

Saved in:
Bibliographic Details
Main Authors: Hong Zhang, Zhikang Lu, Peicong Gong, Shilong Zhang, Xiaoquan Yang, Xiangning Li, Zhao Feng, Anan Li, Chi Xiao
Format: Article
Language:English
Published: SpringerOpen 2024-12-01
Series:Brain Informatics
Subjects:
Online Access:https://doi.org/10.1186/s40708-024-00246-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846111991603658752
author Hong Zhang
Zhikang Lu
Peicong Gong
Shilong Zhang
Xiaoquan Yang
Xiangning Li
Zhao Feng
Anan Li
Chi Xiao
author_facet Hong Zhang
Zhikang Lu
Peicong Gong
Shilong Zhang
Xiaoquan Yang
Xiangning Li
Zhao Feng
Anan Li
Chi Xiao
author_sort Hong Zhang
collection DOAJ
description Abstract High-throughput mesoscopic optical imaging technology has tremendously boosted the efficiency of procuring massive mesoscopic datasets from mouse brains. Constrained by the imaging field of view, the image strips obtained by such technologies typically require further processing, such as cross-sectional stitching, artifact removal, and signal area cropping, to meet the requirements of subsequent analyse. However, obtaining a batch of raw array mouse brain data at a resolution of $$0.65 \times 0.65 \times 3 \,\upmu \hbox {m}^{3}$$ 0.65 × 0.65 × 3 μ m 3 can reach 220TB, and the cropping of the outer contour areas in the disjointed processing still relies on manual visual observation, which consumes substantial computational resources and labor costs. In this paper, we design an efficient deep differential guided filtering module (DDGF) by fusing multi-scale iterative differential guided filtering with deep learning, which effectively refines image details while mitigating background noise. Subsequently, by amalgamating DDGF with deep learning network, we propose a lightweight deep differential guided filtering segmentation network (DDGF-SegNet), which demonstrates robust performance on our dataset, achieving Dice of 0.92, Precision of 0.98, Recall of 0.91, and Jaccard index of 0.86. Building on the segmentation, we utilize connectivity analysis for ascertaining three-dimensional spatial orientation of each brain within the array. Furthermore, we streamline the entire processing workflow by developing an automated pipeline optimized for cluster-based message passing interface(MPI) parallel computation, which reduces the processing time for a mouse brain dataset to a mere 1.1 h, enhancing manual efficiency by 25 times and overall data processing efficiency by 2.4 times, paving the way for enhancing the efficiency of big data processing and parsing for high-throughput mesoscopic optical imaging techniques.
format Article
id doaj-art-9d267ece6c9f4dc3bf74c92a6851823f
institution Kabale University
issn 2198-4018
2198-4026
language English
publishDate 2024-12-01
publisher SpringerOpen
record_format Article
series Brain Informatics
spelling doaj-art-9d267ece6c9f4dc3bf74c92a6851823f2024-12-22T12:56:43ZengSpringerOpenBrain Informatics2198-40182198-40262024-12-0111111510.1186/s40708-024-00246-7High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networksHong Zhang0Zhikang Lu1Peicong Gong2Shilong Zhang3Xiaoquan Yang4Xiangning Li5Zhao Feng6Anan Li7Chi Xiao8Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityKey Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan UniversityAbstract High-throughput mesoscopic optical imaging technology has tremendously boosted the efficiency of procuring massive mesoscopic datasets from mouse brains. Constrained by the imaging field of view, the image strips obtained by such technologies typically require further processing, such as cross-sectional stitching, artifact removal, and signal area cropping, to meet the requirements of subsequent analyse. However, obtaining a batch of raw array mouse brain data at a resolution of $$0.65 \times 0.65 \times 3 \,\upmu \hbox {m}^{3}$$ 0.65 × 0.65 × 3 μ m 3 can reach 220TB, and the cropping of the outer contour areas in the disjointed processing still relies on manual visual observation, which consumes substantial computational resources and labor costs. In this paper, we design an efficient deep differential guided filtering module (DDGF) by fusing multi-scale iterative differential guided filtering with deep learning, which effectively refines image details while mitigating background noise. Subsequently, by amalgamating DDGF with deep learning network, we propose a lightweight deep differential guided filtering segmentation network (DDGF-SegNet), which demonstrates robust performance on our dataset, achieving Dice of 0.92, Precision of 0.98, Recall of 0.91, and Jaccard index of 0.86. Building on the segmentation, we utilize connectivity analysis for ascertaining three-dimensional spatial orientation of each brain within the array. Furthermore, we streamline the entire processing workflow by developing an automated pipeline optimized for cluster-based message passing interface(MPI) parallel computation, which reduces the processing time for a mouse brain dataset to a mere 1.1 h, enhancing manual efficiency by 25 times and overall data processing efficiency by 2.4 times, paving the way for enhancing the efficiency of big data processing and parsing for high-throughput mesoscopic optical imaging techniques.https://doi.org/10.1186/s40708-024-00246-7High-throughput mesoscopic optical imagingDifferential guided filteringMachine learning and deep learningMouse brain data parsing
spellingShingle Hong Zhang
Zhikang Lu
Peicong Gong
Shilong Zhang
Xiaoquan Yang
Xiangning Li
Zhao Feng
Anan Li
Chi Xiao
High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
Brain Informatics
High-throughput mesoscopic optical imaging
Differential guided filtering
Machine learning and deep learning
Mouse brain data parsing
title High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
title_full High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
title_fullStr High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
title_full_unstemmed High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
title_short High-throughput mesoscopic optical imaging data processing and parsing using differential-guided filtered neural networks
title_sort high throughput mesoscopic optical imaging data processing and parsing using differential guided filtered neural networks
topic High-throughput mesoscopic optical imaging
Differential guided filtering
Machine learning and deep learning
Mouse brain data parsing
url https://doi.org/10.1186/s40708-024-00246-7
work_keys_str_mv AT hongzhang highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT zhikanglu highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT peiconggong highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT shilongzhang highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT xiaoquanyang highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT xiangningli highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT zhaofeng highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT ananli highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks
AT chixiao highthroughputmesoscopicopticalimagingdataprocessingandparsingusingdifferentialguidedfilteredneuralnetworks