Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal
By Steven Guan, Amir A. Khan, Siddhartha Sikdar, Parag V. Chitnis. IEEE journal of biomedical and health informatics, 2018
497 citations recorded by the source corpus.
Photoacoustic imaging is an emerging imaging modality that is based upon the photoacoustic effect. In photoacoustic tomography (PAT), the induced acoustic pressure waves are measured by an array of detectors and used to reconstruct an image of the initial pressure distribution. A common challenge faced in PAT is that the measured acoustic waves can only be sparsely sampled. Reconstructing sparsely sampled data using standard methods results in severe artifacts that obscure information within the image. We propose a modified convolutional neural network (CNN) architecture termed fully dense UNet (FD-UNet) for removing artifacts from two-dimensional PAT images reconstructed from sparse data and compare the proposed CNN with the standard UNet in terms of reconstructed image quality.
Subfields: Biomedical Engineering, Mechanics of Materials
View Paper: https://www.semanticscholar.org/paper/06e39ff951f8a137ba871a3f62de19bef1c128a8
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
Citations in the corpus
- IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks (2019, methodology): “Another recent model [21, 22], named DenseBlock-UNet transforms the convolutional modules in the common UNet model into the dense block introduced in [23].”
- Medical Image Segmentation Using Deep Learning: A Survey (2020, methodology): “[27] proposed an improved U-Net by replacing each subblock of U-Net with a form of dense connections as shown in Fig.”
- Medical Image Segmentation Review: The Success of U-Net (2022, background): “BDE Residual U-Net [60], [61], [121] Multi-Res U-Net [15], [123] Dense U-Net [125], [188] H-DenseUNet [62] DUNet [65], [126] S3D U-Net [13] The backbone defines how the layers in the encoder are arranged and its counterpart is therefore used to describe the decoder architecture.”