Super-resolution in medical imaging : An illustrative approach through ultrasound

Kouamé, Denis; Ploquin, Marie

doi:10.1109/isbi.2009.5193030

Cited by 32 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While parametric modelling approaches have been applied in order to enhance medical imaging [8], recent work using deep learning approaches has also shown the potential for the application of neural networks (NNs) for enhancing image resolution. Examples for such an application include, a 4x upscaling on photographic images [9], optical microscopy (improving the resolution from 40x to 100x) [10], dental imaging [11], phase imaging [12], fluorescence microscopy [13], magnetic resonance imaging [14], SEM imaging [15,16], positronemission tomography [17], stochastic optical reconstruction microscopy [18], and ultrasound imaging [19].…”

Section: Introductionmentioning

confidence: 99%

A neural lens for super-resolution biological imaging

et al. 2019

View full text Add to dashboard Cite

Visualizing structures smaller than the eye can see has been a driving force in scientific research since the invention of the optical microscope. Here, we use a network of neural networks to create a neural lens that has the ability to transform 20× optical microscope images into a resolution comparable to a 1500× scanning electron microscope image. In addition to magnification, the neural lens simultaneously identifies the types of objects present, and hence can label, colour-enhance and remove specific types of objects in the magnified image. The neural lens was used for the imaging of Iva xanthiifolia and Galanthus pollen grains, showing the potential for low cost, non-destructive, highresolution microscopy with automatic image processing.

show abstract

Section: Introductionmentioning

confidence: 99%

A neural lens for super-resolution biological imaging

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Image super-resolution (SR) is an effective and widely used post-processing method for image-quality improvement that has been utilized for various medical imaging modalities [3]- [6]. Algorithms that tackle the super-resolution problem can be mainly classified as either reconstructionor learning-based.…”

Section: Introductionmentioning

confidence: 99%

Enhancement of Retinal Image From Line-Scanning Ophthalmoscope Using Generative Adversarial Networks

He²,

Kong³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

A line-scanning ophthalmoscope (LSO) is a retinal imaging technique that has the characteristics of high imaging resolution, wide field of view, and high imaging speed. However, the highspeed imaging with rather short exposure time inevitably reduces the signal intensity, and many factors, such as speckle noise and intraocular scatter, further degrade the signal-to-noise ratio (SNR) of retinal images. To effectively improve the image quality without increasing the LSO system's complexity, the postprocessing method of image super-resolution (SR) is adopted. In this paper, we propose a learning-based multi-frame retinal image SR method that directly learns an end-to-end mapping from low-resolution (LR) image sequences to high-resolution (HR) images. This network was validated on down-sampled and real LSO image sequences. We evaluated the method on a down-sampled dataset with the metrics of peak signalto-noise ratio (PSNR), structural similarity (SSIM), and perceptual distance. Moreover, the power spectra and full width at half maximum (FWHM) were used as the no-reference image quality assessment (NR-IQA) algorithms to evaluate the reconstruction results of the real LSO image sequences. The experimental results indicate that the proposed method can significantly enhance the SNR of LSO images and efficiently improve the resolution of LSO retinal images, which has great practical significance for clinical diagnosis and analysis.INDEX TERMS Line-scanning ophthalmoscope, retinal images, multi-frame image super-resolution, learning-based.

show abstract

“…Recent advances in signal processing have provided many such techniques for leveraging additional a priori knowledge about the signal to improve reconstruction. Our goal in this paper is to compare three such methods, filter diagonalization [2][3][4][5][6][7], compressed sensing [3,[8][9][10][11][12][13][14], and super-resolution [1,[15][16][17][18][19], against a series of test signals in order to understand their relative strengths and weaknesses. Our comparison will be based on a subset of the signals contained in the Sparco toolbox [20], a Gaussian, a sum of random Lorentzians, and the Jacob's Ladder signal [2].…”

Section: Introductionmentioning

confidence: 99%

Benchmarking compressed sensing, super-resolution, and filter diagonalization

Markovich

Blau

Sanders

et al. 2016

Int. J. Quantum Chem.

View full text Add to dashboard Cite

Signal processing techniques have been developed that use different strategies to bypass the Nyquist sampling theorem in order to recover more information than a traditional discrete Fourier transform. Here we examine three such methods: filter diagonalization, compressed sensing, and super-resolution. We apply them to a broad range of signal forms commonly found in science and engineering in order to discover when and how each method can be used most profitably. We find that filter diagonalization provides the best results for Lorentzian signals, while compressed sensing and super-resolution perform better for arbitrary signals.

show abstract

Super-resolution in medical imaging : An illustrative approach through ultrasound

Cited by 32 publications

References 16 publications

A neural lens for super-resolution biological imaging

A neural lens for super-resolution biological imaging

Enhancement of Retinal Image From Line-Scanning Ophthalmoscope Using Generative Adversarial Networks

Benchmarking compressed sensing, super-resolution, and filter diagonalization

Contact Info

Product

Resources

About