pretrained denoising convolutional neural network (dncnn) approach  (MathWorks Inc)

Journal: Magma (New York, N.y.)

Article Title: Field-cycling imaging yields repeatable brain R 1 dispersion measurement at fields strengths below 0.2 Tesla with optimal fitting routine

doi: 10.1007/s10334-025-01230-w

Figure Lengend Snippet: R 1 mapping results for a single participant. Top right of figure shows the FLAIR image obtained from 3 T MRI and co-registered to FCI image space. Brain maps consist of quantitative maps of R 1 at 0.2 mT (left) and dispersion slope b (right). Maps are shown for each fitting model F1 and S1–S4, with motion correction and denoising applied before fitting. Image contrast contained within R 1 maps can be seen to differentiate between SVD regions (hypointense) and WM and GM regions (hyperintense). Matching histogram distributions of R 1 at 0.2 mT are shown for regions of WMH (black) and WM (red)

Article Snippet: After motion correction, images were denoised using a pretrained denoising convolutional neural network (dnCNN) approach contained within MATLAB, introduced in R2017b [ ].

Techniques: Dispersion

Journal: Scientific Reports

Article Title: Quantifying innervation facilitated by deep learning in wound healing

doi: 10.1038/s41598-023-42743-5

Figure Lengend Snippet: The experimental design and schematic depicting the methodology used to quantify skin innervation. ( A ) A biopsy punch of 8 mm in diameter is used to create the wound, and skin samples are collected and fixed on days 3, 7, 10 and 15. After fixation, the wounded tissue is paraffin-embedded and sectioned (5 μm thickness) for immunofluorescence analysis against PGP9.5 protein, a neuron-specific marker. ( B – E ) Illustration portraying different stages of wound healing. ( B ) The homeostatic phase lasts a few hours during which nerve fibers in the wound bed are damaged followed by the ( C ) inflammatory phase that can last between hours and days. ( D ) The proliferative phase lasts a few weeks during which re-innervation might be initiated and ( E ) during the remodeling phase wound matures and can last between weeks to years. In our study, we chose to quantify skin innervation at days 3, 7, 10 and 15 as an attempt to cover all phases of wound healing. ( F ) The immunohistochemistry (IHC) samples are analyzed using automated Matlab-assisted tools aided by DnCNN-based image denoising. The images were created with BioRender.com.

Article Snippet: Additionally, we have been able to find a strong correlation (R 2 = 0.926) between re-epithelization and nerve fiber density during time-series of wound healing, which not only corroborates the fact that the regeneration of nerve fibers is critical for proper wound healing in time but also validated our technique of using automated Matlab-assisted tool aided with DnCNN for denoising to precisely capture PGP9.5+ pixels, and thus calculate nerve fiber density.

Techniques: Immunofluorescence, Marker, Immunohistochemistry

Journal: Scientific Reports

Article Title: Quantifying innervation facilitated by deep learning in wound healing

doi: 10.1038/s41598-023-42743-5

Figure Lengend Snippet: DnCNN network architecture for image denoising. ( A ) Noisy image as DnCNN input. ( B ) The DnCNN network architecture consists of multiple convolutional layers. Each convolutional layer includes batch normalization (BN), convolution (Conv), and rectified linear unit (ReLU) layers. The first layer takes the noisy image as an input, and the subsequent layers process the image to remove noise. ( C ) Output image after de-noising.

Article Snippet: Additionally, we have been able to find a strong correlation (R 2 = 0.926) between re-epithelization and nerve fiber density during time-series of wound healing, which not only corroborates the fact that the regeneration of nerve fibers is critical for proper wound healing in time but also validated our technique of using automated Matlab-assisted tool aided with DnCNN for denoising to precisely capture PGP9.5+ pixels, and thus calculate nerve fiber density.

Techniques:

Journal: Scientific Reports

Article Title: Quantifying innervation facilitated by deep learning in wound healing

doi: 10.1038/s41598-023-42743-5

Figure Lengend Snippet: The experimental design and schematic depicting the methodology used to quantify skin innervation. ( A ) A biopsy punch of 8 mm in diameter is used to create the wound, and skin samples are collected and fixed on days 3, 7, 10 and 15. After fixation, the wounded tissue is paraffin-embedded and sectioned (5 μm thickness) for immunofluorescence analysis against PGP9.5 protein, a neuron-specific marker. ( B – E ) Illustration portraying different stages of wound healing. ( B ) The homeostatic phase lasts a few hours during which nerve fibers in the wound bed are damaged followed by the ( C ) inflammatory phase that can last between hours and days. ( D ) The proliferative phase lasts a few weeks during which re-innervation might be initiated and ( E ) during the remodeling phase wound matures and can last between weeks to years. In our study, we chose to quantify skin innervation at days 3, 7, 10 and 15 as an attempt to cover all phases of wound healing. ( F ) The immunohistochemistry (IHC) samples are analyzed using automated Matlab-assisted tools aided by DnCNN-based image denoising. The images were created with BioRender.com.

Article Snippet: Utilizing the Deep Learning Toolbox's pretrained DnCNN model, we integrated it within the MATLAB environment and invoked it through the MATLAB Deep Learning Toolbox.

Techniques: Immunofluorescence, Marker, Immunohistochemistry

Journal: Scientific Reports

Article Title: Quantifying innervation facilitated by deep learning in wound healing

doi: 10.1038/s41598-023-42743-5

Figure Lengend Snippet: DnCNN network architecture for image denoising. ( A ) Noisy image as DnCNN input. ( B ) The DnCNN network architecture consists of multiple convolutional layers. Each convolutional layer includes batch normalization (BN), convolution (Conv), and rectified linear unit (ReLU) layers. The first layer takes the noisy image as an input, and the subsequent layers process the image to remove noise. ( C ) Output image after de-noising.

Article Snippet: Utilizing the Deep Learning Toolbox's pretrained DnCNN model, we integrated it within the MATLAB environment and invoked it through the MATLAB Deep Learning Toolbox.

Techniques: