A Deep Learning Based Model that Reduces Speed of Sound Aberrations for Improved In Vivo Photoacoustic Imaging

The rapidly evolving field of photoacoustic tomography utilizes endogenous chromophores to extract both functional and structural information from deep within tissues. It is this power to perform precise quantitative measurements in vivo—with endogenous or exogenous contrast —that makes photoacoustic tomography highly promising for clinical translation in functional brain imaging, early cancer detection, real-time surgical guidance, and the visualization of dynamic drug responses. Considering photoacoustic tomography has benefited from numerous engineering innovations, it is of no surprise that many of photoacoustic tomography’s current cutting-edge developments incorporate advances from the equally novel field of artificial intelligence. More specifically, alongside the growth and prevalence of graphical processing unit capabilities within recent years has emerged an offshoot of artificial intelligence known as deep learning. Rooted in the solid foundation of signal processing, deep learning typically utilizes a method of optimization known as gradient descent to minimize a loss function and update model parameters. There are already a number of innovative efforts in photoacoustic tomography utilizing deep learning techniques for a variety of purposes, including resolution enhancement, reconstruction artifact removal, undersampling correction, and improved quantification. Most of these efforts have proven to be highly promising in addressing long-standing technical obstacles where traditional solutions either completely fail or make only incremental progress. This concise review focuses on the history of applied artificial intelligence in photoacoustic tomography, presents recent advances at this multifaceted intersection of fields, and outlines the most exciting advances that will likely propagate into promising future innovations.

Download Full-text

Force estimation from 4D OCT data in a human tumor xenograft mouse model

Current Directions in Biomedical Engineering ◽

10.1515/cdbme-2020-0022 ◽

2020 ◽

Vol 6 (1) ◽

Author(s):

Maximilian Neidhardt ◽

Nils Gessert ◽

Tobias Gosau ◽

Julia Kemmling ◽

Susanne Feldhaus ◽

...

Keyword(s):

Deep Learning ◽

Mouse Model ◽

Haptic Feedback ◽

Human Tumor ◽

Tumor Xenograft ◽

Human Tumor Xenograft ◽

Force Estimation ◽

Xenograft Mouse Model ◽

Dead Tissue

AbstractMinimally invasive robotic surgery offer benefits such as reduced physical trauma, faster recovery and lesser pain for the patient. For these procedures, visual and haptic feedback to the surgeon is crucial when operating surgical tools without line-of-sight with a robot. External force sensors are biased by friction at the tool shaft and thereby cannot estimate forces between tool tip and tissue. As an alternative, vision-based force estimation was proposed. Here, interaction forces are directly learned from deformation observed by an external imaging system. Recently, an approach based on optical coherence tomography and deep learning has shown promising results. However, most experiments are performed on ex-vivo tissue. In this work, we demonstrate that models trained on dead tissue do not perform well in in vivo data. We performed multiple experiments on a human tumor xenograft mouse model, both on in vivo, perfused tissue and dead tissue. We compared two deep learning models in different training scenarios. Training on perfused, in vivo data improved model performance by 24% for in vivo force estimation.

Download Full-text

Development of mesoporous silica-based nanoprobes for optical bioimaging applications

Biomaterials Science ◽

10.1039/d1bm00204j ◽

2021 ◽

Author(s):

Bo Sun ◽

Xu Zhen ◽

Xiqun Jiang

Keyword(s):

Mesoporous Silica ◽

Fluorescence Imaging ◽

Photoacoustic Imaging

This review mainly introduced the MSNs-based nanoprobes for in vivo bioimaging applications including fluorescence imaging and photoacoustic imaging.

Download Full-text

Review of deep learning for photoacoustic imaging

Photoacoustics ◽

10.1016/j.pacs.2020.100215 ◽

2021 ◽

Vol 21 ◽

pp. 100215

Author(s):

Changchun Yang ◽

Hengrong Lan ◽

Feng Gao ◽

Fei Gao

Keyword(s):

Deep Learning ◽

Photoacoustic Imaging

Download Full-text

In Vivo Nano Contrast-enhanced Photoacoustic Imaging for Dynamically Lightening the Molecular Changes of Rheumatoid Arthritis

Materials & Design ◽

10.1016/j.matdes.2021.109862 ◽

2021 ◽

pp. 109862

Author(s):

Shuyi Xiao ◽

Yufu Tang ◽

Yimu Lin ◽

Zhuang Lv ◽

Liang Chen

Keyword(s):

Rheumatoid Arthritis ◽

Photoacoustic Imaging ◽

Molecular Changes ◽

Contrast Enhanced

Download Full-text

In Vitro and In Vivo Multispectral Photoacoustic Imaging for the Evaluation of Chromophore Concentration

Sensors ◽

10.3390/s21103366 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3366

Author(s):

Aneline Dolet ◽

Rita Ammanouil ◽

Virginie Petrilli ◽

Cédric Richard ◽

Piero Tortoli ◽

...

Keyword(s):

Remote Sensing ◽

Photoacoustic Imaging ◽

Hyperspectral Remote Sensing ◽

Reference Spectrum ◽

In Vivo Experiments ◽

Mouse Tumors ◽

Chromophore Concentration ◽

Saturation Rate

Multispectral photoacoustic imaging is a powerful noninvasive medical imaging technique that provides access to functional information. In this study, a set of methods is proposed and validated, with experimental multispectral photoacoustic images used to estimate the concentration of chromophores. The unmixing techniques used in this paper consist of two steps: (1) automatic extraction of the reference spectrum of each pure chromophore; and (2) abundance calculation of each pure chromophore from the estimated reference spectra. The compared strategies bring positivity and sum-to-one constraints, from the hyperspectral remote sensing field to multispectral photoacoustic, to evaluate chromophore concentration. Particularly, the study extracts the endmembers and compares the algorithms from the hyperspectral remote sensing domain and a dedicated algorithm for segmentation of multispectral photoacoustic data to this end. First, these strategies are tested with dilution and mixing of chromophores on colored 4% agar phantom data. Then, some preliminary in vivo experiments are performed. These consist of estimations of the oxygen saturation rate (sO2) in mouse tumors. This article proposes then a proof-of-concept of the interest to bring hyperspectral remote sensing algorithms to multispectral photoacoustic imaging for the estimation of chromophore concentration.

Download Full-text

Molecular imaging and deep learning analysis of uMUC1 expression in response to chemotherapy in an orthotopic model of ovarian cancer

Scientific Reports ◽

10.1038/s41598-020-71890-2 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Hongwei Zhao ◽

Hasaan Hayat ◽

Xiaohong Ma ◽

Daguang Fan ◽

Ping Wang ◽

...

Keyword(s):

Neural Networks ◽

Ovarian Cancer ◽

Deep Learning ◽

Cancer Progression ◽

In Vivo Imaging ◽

Near Infrared ◽

Response To Therapy ◽

Response To Chemotherapy

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.

Download Full-text