scholarly journals Deep learning for in vivo near-infrared imaging

2020 ◽  
Vol 118 (1) ◽  
pp. e2021446118
Author(s):  
Zhuoran Ma ◽  
Feifei Wang ◽  
Weizhi Wang ◽  
Yeteng Zhong ◽  
Hongjie Dai

Detecting fluorescence in the second near-infrared window (NIR-II) up to ∼1,700 nm has emerged as a novel in vivo imaging modality with high spatial and temporal resolution through millimeter tissue depths. Imaging in the NIR-IIb window (1,500–1,700 nm) is the most effective one-photon approach to suppressing light scattering and maximizing imaging penetration depth, but relies on nanoparticle probes such as PbS/CdS containing toxic elements. On the other hand, imaging the NIR-I (700–1,000 nm) or NIR-IIa window (1,000–1,300 nm) can be done using biocompatible small-molecule fluorescent probes including US Food and Drug Administration-approved dyes such as indocyanine green (ICG), but has a caveat of suboptimal imaging quality due to light scattering. It is highly desired to achieve the performance of NIR-IIb imaging using molecular probes approved for human use. Here, we trained artificial neural networks to transform a fluorescence image in the shorter-wavelength NIR window of 900–1,300 nm (NIR-I/IIa) to an image resembling an NIR-IIb image. With deep-learning translation, in vivo lymph node imaging with ICG achieved an unprecedented signal-to-background ratio of >100. Using preclinical fluorophores such as IRDye-800, translation of ∼900-nm NIR molecular imaging of PD-L1 or EGFR greatly enhanced tumor-to-normal tissue ratio up to ∼20 from ∼5 and improved tumor margin localization. Further, deep learning greatly improved in vivo noninvasive NIR-II light-sheet microscopy (LSM) in resolution and signal/background. NIR imaging equipped with deep learning could facilitate basic biomedical research and empower clinical diagnostics and imaging-guided surgery in the clinic.

2021 ◽  
Author(s):  
Timothy Wan Hei Luk

Optical coherence tomography (OCT) is an imaging modality that uses near infrared light interferometry for non-invasive, near-histological resolution imaging at the micron level. Concepts from dynamic light scattering (DLS) can be adapted to OCT to detect and measure the motions in the target tissue. Tissue dynamics can be observed by measuring the speckle decorrelation time (DT) of the tissue. DT analysis was performed in a preclinical study to demonstrate the repeatability and feasibility of using DLS-OCT to observe mouse tumours undergoing cisplatin treatment over a 48-hour period. Differences in the average DT data were observed for control and cisplatin-injected mice. Image segmentation based on DT values was also performed to subtract the DT contributions of pixels at blood vessel locations, resulting in the improvement of average DT calculations of the tumour tissue. The results presented are a preliminary step to analyzing and monitoring tumour growth and treatment response in vivo.


2021 ◽  
Author(s):  
Timothy Wan Hei Luk

Optical coherence tomography (OCT) is an imaging modality that uses near infrared light interferometry for non-invasive, near-histological resolution imaging at the micron level. Concepts from dynamic light scattering (DLS) can be adapted to OCT to detect and measure the motions in the target tissue. Tissue dynamics can be observed by measuring the speckle decorrelation time (DT) of the tissue. DT analysis was performed in a preclinical study to demonstrate the repeatability and feasibility of using DLS-OCT to observe mouse tumours undergoing cisplatin treatment over a 48-hour period. Differences in the average DT data were observed for control and cisplatin-injected mice. Image segmentation based on DT values was also performed to subtract the DT contributions of pixels at blood vessel locations, resulting in the improvement of average DT calculations of the tumour tissue. The results presented are a preliminary step to analyzing and monitoring tumour growth and treatment response in vivo.


Author(s):  
Anthony J. Durkin ◽  
Jae G. Kim ◽  
David J. Cuccia

We present a wide-field, near infrared spectral imaging modality called modulated imaging (MI) that shows great promise for quantitatively imaging superficial (1–5 mm depth) tissues. We have applied this method to a dorsal pedicle skin flap model to determine in-vivo local concentrations of oxy- and deoxy-hemoglobin and water.


2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Hongwei Zhao ◽  
Hasaan Hayat ◽  
Xiaohong Ma ◽  
Daguang Fan ◽  
Ping Wang ◽  
...  

Abstract Artificial Intelligence (AI) algorithms including deep learning have recently demonstrated remarkable progress in image-recognition tasks. Here, we utilized AI for monitoring the expression of underglycosylated mucin 1 (uMUC1) tumor antigen, a biomarker for ovarian cancer progression and response to therapy, using contrast-enhanced in vivo imaging. This was done using a dual-modal (magnetic resonance and near infrared optical imaging) uMUC1-specific probe (termed MN-EPPT) consisted of iron-oxide magnetic nanoparticles (MN) conjugated to a uMUC1-specific peptide (EPPT) and labeled with a near-infrared fluorescent dye, Cy5.5. In vitro studies performed in uMUC1-expressing human ovarian cancer cell line SKOV3/Luc and control uMUC1low ES-2 cells showed preferential uptake on the probe by the high expressor (n = 3, p < .05). A decrease in MN-EPPT uptake by SKOV3/Luc cells in vitro due to uMUC1 downregulation after docetaxel therapy was paralleled by in vivo imaging studies that showed a reduction in probe accumulation in the docetaxel treated group (n = 5, p < .05). The imaging data were analyzed using deep learning-enabled segmentation and quantification of the tumor region of interest (ROI) from raw input MRI sequences by applying AI algorithms including a blend of Convolutional Neural Networks (CNN) and Fully Connected Neural Networks. We believe that the algorithms used in this study have the potential to improve studying and monitoring cancer progression, amongst other diseases.


Cosmetics ◽  
2018 ◽  
Vol 5 (4) ◽  
pp. 66 ◽  
Author(s):  
Paola Perugini ◽  
Mariella Bleve ◽  
Fabiola Cortinovis ◽  
Antonio Colpani

Bacterial cellulose (BC) has become of great interest in recent years, as a delivery system in several areas of application, including food, drugs, and cosmetics, thanks to its exclusive advantages, such as high biocompatibility, water holding capacity, and good gas permeability. The novel approach of the authors has led to a protocol for checking the quality and safety of bacterial cellulose matrices in the manufacture of cosmetic masks. Two non-destructive techniques, near-infrared spectroscopy (NIR) and multiple light scattering (MLS), were used to verify different parameters affecting the quality of BC sheets, allowing cellulose masks to be checked over time. NIR spectroscopy allowed for discovering changes in the water content, depending on filling/packaging procedures, like flat-folding. Multiple light scattering was used to ascertain the stability of solutions in contact with masks. From a clinical standpoint, the cutaneous tolerability of biocellulose masks, and their effect on skin parameters, were evaluated through some specific “in vivo” tests. Also, a safety evaluation during application was conducted through different studies: a short-term one after single application, and a long-term one upon continued use.


2018 ◽  
Author(s):  
Wei Chen ◽  
ChiAn Cheng ◽  
Emily Cosco ◽  
Shyam Ramakrishnan ◽  
Jakob Lingg ◽  
...  

Tissue is translucent to shortwave infrared (SWIR) light, rendering optical imaging superior in this region. However, the widespread use of optical SWIR imaging has been limited, in part, by the lack of bright, biocompatible contrast agents that absorb and emit light above 1000 nm. J-aggregation offers a means to transform stable, near-infrared (NIR) fluorophores into red-shifted SWIR contrast agents. Here we demonstrate that hollow mesoporous silica nanoparticles (HMSNs) can template the J-aggregation of NIR fluorophore IR-140 to result in nanomaterials that absorb and emit SWIR light. The J-aggregates inside PEGylated HMSNs are stable for multiple weeks in buffer and enable high resolution imaging <i>in vivo</i>with 980 nm excitation.


2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 212-212
Author(s):  
S. Khatri ◽  
J. Hansen ◽  
M. H. Clausen ◽  
T. W. Kragstrup ◽  
S. C. Hung ◽  
...  

Background:Rheumatoid arthritis (RA) is an immune mediated inflammatory disease with autoimmune features, including antibodies to citrullinated proteins and peptides (ACPAs). Several in vitro studies have suggested a pathogenic role of ACPAs in RA. However, in vivo proof of this concept has been hampered by the lack of therapeutic strategies to reduce or deplete ACPA in serum and synovial fluid. Previously, we constructed a chitosan-hyaluronic acid nanoparticle formulation with the ability to use neutrophil recruitment as a delivery mechanism to inflamed joints. Specifically, nanoparticles got phagocytosed and then released to synovial fluid upon death of the short-lived neutrophilsObjectives:We hypothesized that reducing ACPA levels would have a therapeutic effect by blocking cytokine production. In this study, we prepared and tested a series of therapeutic nanoparticles for specific targeting of ACPA in synovial fluid.Methods:Nanoparticles were prepared by the microdroplet method and then decorated with synthetic cyclic citrullinated peptide aptamer PEP2, PEG/hexanoic acid and fluorophore (Cy5.5). Nanoparticles were characterized by dynamic light scattering (DLS), scanning electron microscopy (SEM) and high-performance liquid chromatography (HPLC). Nanoparticles were then used in a series of in vitro assays, including cell uptake with flow cytometry (FACS) detection, and in vivo studies including disease activity scores, cytokine measurements and near-infrared imaging.Results:We screened a series of citrullinated peptide epitopes and identified a fibrinogen-derived 21-amino-acid-long citrullinated peptide showing high selectivity toward autoantibodies in RA samples. We incorporated this aptamer in the chitosan-hyaluronic acid nanoparticle formulation previously described. Average nanoparticle size was 230 nm ± 10 nm by DLS and SEM; z potential was -0.0012. Purity by HPLC was over 95%. Attachment efficiency of the aptamer was 92% by HPLC. FACS study showed selective uptake of Cy5.5 labelled aptamer-nanoparticle conjugates by neutrophils in the concentration range 0.5-4 nM. Similar to previous studies,1there was no apparent immunogenicity for this nanoparticle formulation measured by cytokine secretion from human peripheral blood leukocytes. In vivo, over 50% reduction of disease activity was achieved in three weeks treatment using as little as 1 nM drug candidate (dosed every 48 hours) in the collagen-induced (CIA) mouse model of RA (N=30; p<0.001 for treated vs placebo). Same was observed in the serum transfer model (N=10). The aptamer-nanoparticle conjugate significantly reduced IL-6 and TNFα levels in the mouse sera (p<0.01). The effects were not inferior to tocilizumab treated controls (N=30). To confirm mode of action, we applied Cy5.5-labelled aptamer-nanoparticles in the collagen-induced mouse model (N=10) and analyzed the resulting uptake by near-infrared imaging. We confirmed over 6-fold higher signal accumulation in inflamed vs healthy joints (p<0.01), which strongly supports the fact that the aptamer is highly specific to the inflammatory process.Conclusion:Overall, we have designed a first-in-class therapeutic nanoparticle drug for specific targeting of anti-citrullinated protein antibodies. The marked effect of this nanoparticle observed in vivo holds promise for targeting ACPAs as a therapeutic option in RA.References:[1]Khatri S, Hansen J, Mendes AC, Chronakis IS, Hung S-C, Mellins ED, Astakhova K. Bioconjug Chem. 2019 Oct 16;30(10):2584–259Disclosure of Interests:Sangita Khatri: None declared, Jonas Hansen: None declared, Mads Hartvig Clausen Shareholder of: iBio Tech ApS, Tue Wenzel Kragstrup Shareholder of: iBio Tech ApS, Consultant of: Bristol-Myers Squibb, Speakers bureau: TWK has engaged in educational activities talking about immunology in rheumatic diseases receiving speaking fees from Pfizer, Bristol-Myers Squibb, Eli Lilly, Novartis, and UCB., Shu-Chen Hung: None declared, Elisabeth Mellins: None declared, Kira Astakhova: None declared


Lab on a Chip ◽  
2021 ◽  
Author(s):  
Xiaopeng Chen ◽  
Junyu Ping ◽  
Yixuan Sun ◽  
Chengqiang Yi ◽  
Sijian Liu ◽  
...  

Volumetric imaging of dynamic signals in a large, moving, and light-scattering specimen is extremely challenging, owing to the requirement on high spatiotemporal resolution and difficulty in obtaining high-contrast signals. Here...


Sign in / Sign up

Export Citation Format

Share Document