Browse
Submit Data
Databases
API
Help

Dataset Information

20 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties.

ABSTRACT: Conventional photoacoustic imaging may suffer from the limited view and bandwidth of ultrasound transducers. A deep learning approach is proposed to handle these problems and is demonstrated both in simulations and in experiments on a multi-scale model of leaf skeleton. We employed an experimental approach to build the training and the test sets using photographs of the samples as ground truth images. Reconstructions produced by the neural network show a greatly improved image quality as compared to conventional approaches. In addition, this work aimed at quantifying the reliability of the neural network predictions. To achieve this, the dropout Monte-Carlo procedure is applied to estimate a pixel-wise degree of confidence on each predicted picture. Last, we address the possibility to use transfer learning with simulated data in order to drastically limit the size of the experimental dataset.

SUBMITTER: Godefroy G

PROVIDER: S-EPMC7750172 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties.

Godefroy Guillaume G Arnal Bastien B Bossy Emmanuel E

Photoacoustics 20201027

Conventional photoacoustic imaging may suffer from the limited view and bandwidth of ultrasound transducers. A deep learning approach is proposed to handle these problems and is demonstrated both in simulations and in experiments on a multi-scale model of leaf skeleton. We employed an experimental approach to build the training and the test sets using photographs of the samples as ground truth images. Reconstructions produced by the neural network show a greatly improved image quality as compare ...[more]

PMID: 33364161

Similar Datasets

Improving needle visibility in LED-based photoacoustic imaging using deep learning with semi-synthetic datasets.

Project description:Photoacoustic imaging has shown great potential for guiding minimally invasive procedures by accurate identification of critical tissue targets and invasive medical devices (such as metallic needles). The use of light emitting diodes (LEDs) as the excitation light sources accelerates its clinical translation owing to its high affordability and portability. However, needle visibility in LED-based photoacoustic imaging is compromised primarily due to its low optical fluence. In this work, we propose a deep learning framework based on U-Net to improve the visibility of clinical metallic needles with a LED-based photoacoustic and ultrasound imaging system. To address the complexity of capturing ground truth for real data and the poor realism of purely simulated data, this framework included the generation of semi-synthetic training datasets combining both simulated data to represent features from the needles and in vivo measurements for tissue background. Evaluation of the trained neural network was performed with needle insertions into blood-vessel-mimicking phantoms, pork joint tissue ex vivo and measurements on human volunteers. This deep learning-based framework substantially improved the needle visibility in photoacoustic imaging in vivo compared to conventional reconstruction by suppressing background noise and image artefacts, achieving 5.8 and 4.5 times improvements in terms of signal-to-noise ratio and the modified Hausdorff distance, respectively. Thus, the proposed framework could be helpful for reducing complications during percutaneous needle insertions by accurate identification of clinical needles in photoacoustic imaging.

| S-EPMC9048160 | biostudies-literature

Deep learning acceleration of multiscale superresolution localization photoacoustic imaging.

Project description:A superresolution imaging approach that localizes very small targets, such as red blood cells or droplets of injected photoacoustic dye, has significantly improved spatial resolution in various biological and medical imaging modalities. However, this superior spatial resolution is achieved by sacrificing temporal resolution because many raw image frames, each containing the localization target, must be superimposed to form a sufficiently sampled high-density superresolution image. Here, we demonstrate a computational strategy based on deep neural networks (DNNs) to reconstruct high-density superresolution images from far fewer raw image frames. The localization strategy can be applied for both 3D label-free localization optical-resolution photoacoustic microscopy (OR-PAM) and 2D labeled localization photoacoustic computed tomography (PACT). For the former, the required number of raw volumetric frames is reduced from tens to fewer than ten. For the latter, the required number of raw 2D frames is reduced by 12 fold. Therefore, our proposed method has simultaneously improved temporal (via the DNN) and spatial (via the localization method) resolutions in both label-free microscopy and labeled tomography. Deep-learning powered localization PA imaging can potentially provide a practical tool in preclinical and clinical studies requiring fast temporal and fine spatial resolutions.

| S-EPMC9095876 | biostudies-literature

Fiducial markers visibility and artefacts in prostate cancer radiotherapy multi-modality imaging.

Project description:BACKGROUND:In this study, a novel pelvic phantom was developed and used to assess the visibility and presence of artefacts from different types of commercial fiducial markers (FMs) on multi-modality imaging relevant to prostate cancer. METHODS AND MATERIALS:The phantom was designed with 3D printed hollow cubes in the centre. These cubes were filled with gel to mimic the prostate gland and two parallel PVC rods were used to mimic bones in the pelvic region. Each cube was filled with gelatine and three unique FMs were positioned with a clinically-relevant spatial distribution. The FMs investigated were; Gold Marker (GM) CIVCO, GM RiverPoint, GM Gold Anchor (GA) line and ball shape, and polymer marker (PM) from CIVCO. The phantom was scanned using several imaging modalities typically used to image prostate cancer patients; MRI, CT, CBCT, planar kV-pair, ExacTrac, 6MV, 2.5MV and integrated EPID imaging. The visibility of the markers and any observed artefacts in the phantom were compared to in-vivo scans of prostate cancer patients with FMs. RESULTS:All GMs were visible in volumetric scans, however, they also had the most visible artefacts on CT and CBCT scans, with the magnitude of artefacts increasing with FM size. PM FMs had the least visible artefacts in volumetric scans but they were not visible on portal images and had poor visibility on lateral kV images. The smallest diameter GMs (GA) were the most difficult GMs to identify on lateral kV images. CONCLUSION:The choice between different FMs is also dependent on the adopted IGRT strategy. PM was found to be superior to investigated gold markers in the most commonly used modalities in the management of prostate cancer; CT, CBCT and MRI imaging.

| S-EPMC6933910 | biostudies-literature

Deep Learning Enables Superior Photoacoustic Imaging at Ultralow Laser Dosages.

Project description:Optical-resolution photoacoustic microscopy (OR-PAM) is an excellent modality for in vivo biomedical imaging as it noninvasively provides high-resolution morphologic and functional information without the need for exogenous contrast agents. However, the high excitation laser dosage, limited imaging speed, and imperfect image quality still hinder the use of OR-PAM in clinical applications. The laser dosage, imaging speed, and image quality are mutually restrained by each other, and thus far, no methods have been proposed to resolve this challenge. Here, a deep learning method called the multitask residual dense network is proposed to overcome this challenge. This method utilizes an innovative strategy of integrating multisupervised learning, dual-channel sample collection, and a reasonable weight distribution. The proposed deep learning method is combined with an application-targeted modified OR-PAM system. Superior images under ultralow laser dosage (32-fold reduced dosage) are obtained for the first time in this study. Using this new technique, a high-quality, high-speed OR-PAM system that meets clinical requirements is now conceivable.

| S-EPMC7856900 | biostudies-literature

Photoacoustic needle improves needle tip visibility during deep peripheral nerve block.

Project description:We developed a novel technology using the photoacoustic effect that improve needle tip visibility. We evaluated whether this technology improves needle tip visibility when performing a deep peripheral nerve block in a cadaver model. A photoacoustic needle was developed using a conventional echogenic needle with an intraluminal optical fiber. A pulsed laser sends light from a source through the fiber, which is converted to ultrasound at the needle tip using the photoacoustic effect. A nerve block expert performed deep nerve blocks using the photoacoustic needle and the ultrasound views recorded, with or without photoacoustic ultrasound at the needle tip. Needle tip visibility was evaluated by questionnaire (Likert scale 1: very poor, 5: very good) completed by anesthesiologists evaluating recorded images. The score was presented as median [first quartile, third quartile]. Statistical analysis was performed using the Wilcoxon matched-pairs signed rank test. The scores of needle tip visibility with photoacoustic ultrasound from the needle tip (4.3 [4.0, 4.5]) was significantly higher than that without photoacoustic ultrasound (3.5 [3.2, 3.8]) (p < 0.01). Ultrasound emitted at the needle tip using the photoacoustic effect improves needle tip visibility during deep peripheral nerve blocks.Clinical trial number University Hospital Medical Information Network Center Clinical Trials Registration System (UMIN000036974).

| S-EPMC8055898 | biostudies-literature

Automated sleep state classification of wide-field calcium imaging data via multiplex visibility graphs and deep learning.

Project description:BackgroundWide-field calcium imaging (WFCI) allows for monitoring of cortex-wide neural dynamics in mice. When applied to the study of sleep, WFCI data are manually scored into the sleep states of wakefulness, non-REM (NREM) and REM by use of adjunct EEG and EMG recordings. However, this process is time-consuming and often suffers from low inter- and intra-rater reliability and invasiveness. Therefore, an automated sleep state classification method that operates on WFCI data alone is needed.New methodA hybrid, two-step method is proposed. In the first step, spatial-temporal WFCI data is mapped to multiplex visibility graphs (MVGs). Subsequently, a two-dimensional convolutional neural network (2D CNN) is employed on the MVGs to be classified as wakefulness, NREM and REM.ResultsSleep states were classified with an accuracy of 84% and Cohen's κ of 0.67. The method was also effectively applied on a binary classification of wakefulness/sleep (accuracy=0.82, κ = 0.62) and a four-class wakefulness/sleep/anesthesia/movement classification (accuracy=0.74, κ = 0.66). Gradient-weighted class activation maps revealed that the CNN focused on short- and long-term temporal connections of MVGs in a sleep state-specific manner. Sleep state classification performance when using individual brain regions was highest for the posterior area of the cortex and when cortex-wide activity was considered.Comparison with existing methodOn a 3-hour WFCI recording, the MVG-CNN achieved a κ of 0.65, comparable to a κ of 0.60 corresponding to the human EEG/EMG-based scoring.ConclusionsThe hybrid MVG-CNN method accurately classifies sleep states from WFCI data and will enable future sleep-focused studies with WFCI.

| S-EPMC9006179 | biostudies-literature

Deep learning enables ultraviolet photoacoustic microscopy based histological imaging with near real-time virtual staining.

Project description:Histological images can reveal rich cellular information of tissue sections, which are widely used by pathologists in disease diagnosis. However, the gold standard for histopathological examination is based on thin sections on slides, which involves inevitable time-consuming and labor-intensive tissue processing steps, hindering the possibility of intraoperative pathological assessment of the precious patient specimens. Here, by incorporating ultraviolet photoacoustic microscopy (UV-PAM) with deep learning, we show a rapid and label-free histological imaging method that can generate virtually stained histological images (termed Deep-PAM) for both thin sections and thick fresh tissue specimens. With the tissue non-destructive nature of UV-PAM, the imaged intact specimens can be reused for other ancillary tests. We demonstrated Deep-PAM on various tissue preparation protocols, including formalin-fixation and paraffin-embedding sections (7-µm thick) and frozen sections (7-µm thick) in traditional histology, and rapid assessment of intact fresh tissue (~ 2-mm thick, within 15 min for a tissue with a surface area of 5 mm × 5 mm). Deep-PAM potentially serves as a comprehensive histological imaging method that can be simultaneously applied in preoperative, intraoperative, and postoperative disease diagnosis.

| S-EPMC8521289 | biostudies-literature

Reconstructing Undersampled Photoacoustic Microscopy Images Using Deep Learning.

Project description:One primary technical challenge in photoacoustic microscopy (PAM) is the necessary compromise between spatial resolution and imaging speed. In this study, we propose a novel application of deep learning principles to reconstruct undersampled PAM images and transcend the trade-off between spatial resolution and imaging speed. We compared various convolutional neural network (CNN) architectures, and selected a Fully Dense U-net (FD U-net) model that produced the best results. To mimic various undersampling conditions in practice, we artificially downsampled fully-sampled PAM images of mouse brain vasculature at different ratios. This allowed us to not only definitively establish the ground truth, but also train and test our deep learning model at various imaging conditions. Our results and numerical analysis have collectively demonstrated the robust performance of our model to reconstruct PAM images with as few as 2% of the original pixels, which can effectively shorten the imaging time without substantially sacrificing the image quality.

| S-EPMC7858223 | biostudies-literature

Full-view in vivo skin and blood vessels profile segmentation in photoacoustic imaging based on deep learning.

Project description:Photoacoustic (PA) microscopy allows imaging of the soft biological tissue based on optical absorption contrast and spatial ultrasound resolution. One of the major applications of PA imaging is its characterization of microvasculature. However, the strong PA signal from skin layer overshadowed the subcutaneous blood vessels leading to indirectly reconstruct the PA images in human study. Addressing the present situation, we examined a deep learning (DL) automatic algorithm to achieve high-resolution and high-contrast segmentation for widening PA imaging applications. In this research, we propose a DL model based on modified U-Net for extracting the relationship features between amplitudes of the generated PA signal from skin and underlying vessels. This study illustrates the broader potential of hybrid complex network as an automatic segmentation tool for the in vivo PA imaging. With DL-infused solution, our result outperforms the previous studies with achieved real-time semantic segmentation on large-size high-resolution PA images.

| S-EPMC8603312 | biostudies-literature

Comparing Deep Learning Frameworks for Photoacoustic Tomography Image Reconstruction.

Project description:Conventional reconstruction methods for photoacoustic images are not suitable for the scenario of sparse sensing and geometrical limitation. To overcome these challenges and enhance the quality of reconstruction, several learning-based methods have recently been introduced for photoacoustic tomography reconstruction. The goal of this study is to compare and systematically evaluate the recently proposed learning-based methods and modified networks for photoacoustic image reconstruction. Specifically, learning-based post-processing methods and model-based learned iterative reconstruction methods are investigated. In addition to comparing the differences inherently brought by the models, we also study the impact of different inputs on the reconstruction effect. Our results demonstrate that the reconstruction performance mainly stems from the effective amount of information carried by the input. The inherent difference of the models based on the learning-based post-processing method does not provide a significant difference in photoacoustic image reconstruction. Furthermore, the results indicate that the model-based learned iterative reconstruction method outperforms all other learning-based post-processing methods in terms of generalizability and robustness.

| S-EPMC8165448 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data