Hyperspectral Segmentation of Plants in Fabricated Ecosystems DOI Creative Commons
Petrus H. Zwart, Peter Andeer, Trent R. Northen

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 21, 2024

Abstract Hyperspectral imaging provides a powerful tool for analyzing above-ground plant characteristics in fabricated ecosystems, offering rich spectral information across diverse wavelengths. This study presents an efficient workflow hyperspectral data segmentation and subsequent analytics, minimizing the need user annotation through use of ensembles sparse mixed-scale convolution neural networks. The process leverages diversity to achieve high accuracy with minimal labeled data, reducing labor-intensive efforts. To further enhance robustness, we incorporate image alignment techniques address spatial variability dataset. Down-stream analysis focuses on using segmented processing enabling monitoring health. approach not only scalable solution but also facilitates actionable insights into conditions complex, controlled environments. Our results demonstrate utility combining advanced machine learning analytics high-throughput monitoring.

Language: Английский

Hyperspectral segmentation of plants in fabricated ecosystems DOI Creative Commons
Petrus H. Zwart, Peter Andeer, Trent R. Northen

et al.

Frontiers in High Performance Computing, Journal Year: 2025, Volume and Issue: 3

Published: Feb. 17, 2025

Hyperspectral imaging provides a powerful tool for analyzing above-ground plant characteristics in fabricated ecosystems, offering rich spectral information across diverse wavelengths. This study presents an efficient workflow hyperspectral data segmentation and subsequent analytics, minimizing the need user annotation through use of ensembles sparse mixed scale convolution neural networks. The process leverages diversity to achieve high accuracy with minimal labeled data, reducing labor-intensive efforts. To further enhance robustness, we incorporate image alignment techniques address spatial variability dataset. Downstream analysis focuses on using segmented processing enabling monitoring health. approach scalable solution segmentation, facilitates actionable insights into conditions complex, controlled environments. Our results demonstrate utility combining advanced machine learning analytics high-throughput monitoring.

Language: Английский

Citations

0
Mini Review: Highlight of Recent Advances and Applications of MALDI Mass Spectrometry Imaging in 2024 DOI Open Access

Yuen T. Ngai,

David C.W. Lau, Parul Mittal

et al.

Analytical Science Advances, Journal Year: 2025, Volume and Issue: 6(1)

Published: May 10, 2025

Abstract Matrix‐assisted laser desorption/ionisation mass spectrometry imaging (MALDI‐MSI) is an emerging tool that allows visualisation of hundreds analytes unbiasedly in a single experiment. This paper highlights the adaptations MALDI‐MSI different context 2024, such as clinical diagnostic, pharmacology, forensics applications, plant metabolism and biology. Challenges advancements were also discussed regarding sample preparation, instrumentations, data analysis, integration machine learning trend cell resolution multi‐omics. There are still rooms for improvements sensitivity, spatial resolution, acquisition algorithm across multi‐omics to enable at subcellular level.

Language: Английский

Citations

0
Hyperspectral Segmentation of Plants in Fabricated Ecosystems DOI Creative Commons
Petrus H. Zwart, Peter Andeer, Trent R. Northen

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 21, 2024

Abstract Hyperspectral imaging provides a powerful tool for analyzing above-ground plant characteristics in fabricated ecosystems, offering rich spectral information across diverse wavelengths. This study presents an efficient workflow hyperspectral data segmentation and subsequent analytics, minimizing the need user annotation through use of ensembles sparse mixed-scale convolution neural networks. The process leverages diversity to achieve high accuracy with minimal labeled data, reducing labor-intensive efforts. To further enhance robustness, we incorporate image alignment techniques address spatial variability dataset. Down-stream analysis focuses on using segmented processing enabling monitoring health. approach not only scalable solution but also facilitates actionable insights into conditions complex, controlled environments. Our results demonstrate utility combining advanced machine learning analytics high-throughput monitoring.

Language: Английский

Citations

0