Imaging of eosin-stained brain section using two-photon excitation fluorescence microscopy DOI
Guozhong Hou, Zhiwei Dong, Sheng Zhang

et al.

Optical Engineering, Journal Year: 2022, Volume and Issue: 61(07)

Published: July 1, 2022

A two-photon excitation fluorescence (TPEF) microscopy system under broadband of femtosecond pulses is built in this study. The TPEF spectrum an eosin stain recorded, and the equipped with a suitable detection window matching stain. demonstrated using solid sample eosin-stained mouse brain sections through detecting signal from staining. Three-dimensional (3D) reconstruction section across its thickness realized several imaging frames acquired via z-axis scanning step size 1 μm. Two-dimensional 3D high performance observation biological sections.

Language: Английский

Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy DOI Creative Commons
Shu Wang,

Junlin Pan,

Xiao Zhang

et al.

Light Science & Applications, Journal Year: 2024, Volume and Issue: 13(1)

Published: Sept. 14, 2024

Language: Английский

Citations

7
Toward next-generation endoscopes integrating biomimetic video systems, nonlinear optical microscopy, and deep learning DOI Creative Commons
Stefan G. Stanciu,

Karsten König,

Young Min Song

et al.

Biophysics Reviews, Journal Year: 2023, Volume and Issue: 4(2)

Published: June 1, 2023

According to the World Health Organization, proportion of world's population over 60 years will approximately double by 2050. This progressive increase in elderly lead a dramatic growth age-related diseases, resulting tremendous pressure on sustainability healthcare systems globally. In this context, finding more efficient ways address cancers, set diseases whose incidence is correlated with age, utmost importance. Prevention cancers decrease morbidity relies identification precursor lesions before onset disease, or at least diagnosis an early stage. article, after briefly discussing some most prominent endoscopic approaches for gastric cancer diagnostics, we review relevant progress three emerging technologies that have significant potential play pivotal roles next-generation endoscopy systems: biomimetic vision (with special focus compound eye cameras), non-linear optical microscopies, and Deep Learning. Such are urgently needed enhance major steps required successful diagnostics gastrointestinal cancers: detection, characterization, confirmation suspicious lesions. final part, discuss challenges lie en route translating these endoscopes could imaging, depict possible configuration system capable (i) enabling easier detection lesions, (ii) label-free vivo tissue (iii) intelligently automated diagnostic.

Language: Английский

Citations

13
Combined flat-field and frequency filter approach to correcting artifacts of multichannel two-photon microscopy DOI Creative Commons
Thomas G. Knapp, Natzem Lima, Noelle Daigle

et al.

Journal of Biomedical Optics, Journal Year: 2024, Volume and Issue: 29(01)

Published: Jan. 23, 2024

SignificanceMultiphoton microscopy (MPM) is a useful biomedical imaging tool for its ability to probe labeled and unlabeled depth-resolved tissue biomarkers at high resolution. Automated MPM tile scanning allows whole-slide image acquisition but can suffer from tile-stitching artifacts that prevent accurate quantitative data analysis.AimWe have investigated postprocessing artifact correction methods using ImageJ macros custom Python code. Quantitative qualitative comparisons of these were made autofluorescence second-harmonic generation images human duodenal tissue.ApproachImage quality after removal assessed by evaluating the processed unprocessed counterpart root mean square error, structural similarity index, histogram measurements.ResultsConsideration both results suggest combination flat-field-based frequency filtering processing step provide improved when compared with each method used independently correct tiling tile-scan images.ConclusionsWhile some remain methods, further optimization steps may result in computational-efficient removing are ubiquitous large-scale imaging. Removal retention original information would facilitate use this modality research clinical settings, where it highly collecting detailed morphologic optical properties tissue.

Language: Английский

Citations

3
Collagen signature adds prognostically significant information to staging for breast cancer DOI Creative Commons
Zhijun Li, Dong-Hoon Kang, Simiao Xu

et al.

ESMO Open, Journal Year: 2024, Volume and Issue: 9(12), P. 103990 - 103990

Published: Nov. 21, 2024

Language: Английский

Citations

2
Deep convolutional neural network for damaged vegetation segmentation from RGB images based on virtual NIR-channel estimation DOI Creative Commons
Artzai Picón, Arantza Bereciartúa-Pérez,

Itziar Eguskiza

et al.

Artificial Intelligence in Agriculture, Journal Year: 2022, Volume and Issue: 6, P. 199 - 210

Published: Jan. 1, 2022

Performing accurate and automated semantic segmentation of vegetation is a first algorithmic step towards more complex models that can extract biological information on crop health, weed presence phenological state, among others. Traditionally, based normalized difference index (NDVI), near infrared channel (NIR) or RGB have been good indicator presence. However, these methods are not suitable for accurately segmenting showing damage, which precludes their use downstream phenotyping algorithms. In this paper, we propose comprehensive method robust in images cope with damaged vegetation. The consists regression convolutional neural network to estimate virtual NIR from an image. Second, compute two newly proposed indices estimated NIR: the infrared-dark subtraction (IDCS) ratio (IDCR) indices. Finally, both image fed into deep train model segment regardless damage condition. was tested 84 plots containing thirteen species different degrees acquired over 28 days. results show best obtained when input augmented (F1=0.94) IDCR IDCS (F1=0.95) derived channel, while only lead inferior performance (RGB(F1=0.90) NIR(F1=0.82) NDVI(F1=0.89) channel). provides end-to-end land cover map directly simple has successfully validated real field conditions.

Language: Английский

Citations

11
Test Time Transform Prediction for Open Set Histopathological Image Recognition DOI
Adrián Galdrán, Katherine Hewitt, Narmin Ghaffari Laleh

et al.

Lecture notes in computer science, Journal Year: 2022, Volume and Issue: unknown, P. 263 - 272

Published: Jan. 1, 2022

Language: Английский

Citations

5
Context-aware augmentation for liver lesion segmentation: shape uniformity, expansion limit and fusion strategy DOI Open Access

Qiang He,

Yujie Duan,

Zhiyu Yang

et al.

Quantitative Imaging in Medicine and Surgery, Journal Year: 2023, Volume and Issue: 13(8), P. 5043 - 5057

Published: July 20, 2023

Data augmentation with context has been an effective way to increase the robustness and generalizability of deep learning models. However, our knowledge, shape uniformity, expansion limit, fusion strategy have yet be comprehensively studied, particularly in lesion segmentation medical images.

Language: Английский

Citations

2
TPF stitching imaging of rubber tree leaves. DOI
Meng Liu, Guozhong Hou, Yuan Li

et al.

Applied Optics, Journal Year: 2024, Volume and Issue: 63(31), P. 8189 - 8189

Published: Oct. 10, 2024

This paper presents a two-photon fluorescence (TPF) microscopy platform based on femtosecond oscillator. The system images rubber tree leaf samples by exciting and detecting TPF signals generated the tissue using broadband pulses. imaging utilizes detection window of 565–615 nm to capture from flavin adenine dinucleotide (FAD) in tissue. Additionally, multiple were acquired through sample movement Z-axis scanning, followed image stitching achieve large-area comprehensive visualization samples. study provides detailed observations analyses various biological structures within samples, contributing significantly understanding plant growth, physiological functions, environmental adaptability.

Language: Английский

Citations

0
Imaging of eosin-stained brain section using two-photon excitation fluorescence microscopy DOI
Guozhong Hou, Zhiwei Dong, Sheng Zhang

et al.

Optical Engineering, Journal Year: 2022, Volume and Issue: 61(07)

Published: July 1, 2022

A two-photon excitation fluorescence (TPEF) microscopy system under broadband of femtosecond pulses is built in this study. The TPEF spectrum an eosin stain recorded, and the equipped with a suitable detection window matching stain. demonstrated using solid sample eosin-stained mouse brain sections through detecting signal from staining. Three-dimensional (3D) reconstruction section across its thickness realized several imaging frames acquired via z-axis scanning step size 1 μm. Two-dimensional 3D high performance observation biological sections.

Language: Английский

Citations

2