In the field of ultrasound imaging, resolution enhancement is an up-to-date challenging task. Many device-based approaches have been proposed to overcome the low resolution nature of ultrasound images but very few works deal with post-processing methods. This paper investigates a novel approach based on semi-blind deconvolution formulation and alternating direction method framework in order to perform the ultrasound image restoration task. The algorithm performance is addressed using optical images and synthetic ultrasound data for a various range of criteria. The results demonstrate that our technique is more robust to uncertainties in the a priori ultrasonic pulse than classical non-blind deconvolution methods.

/pdf/semi-blind-deconvolution-for-resolution-enhancement-in-3s8jsq19lu.pdf

Semi-blind deconvolution for resolution enhancement in ultrasound imaging

Fundus fluorescein angiography (FFA) imaging is a standard diagnostic tool for many retinal diseases such as age-related macular degeneration and diabetic retinopathy High-resolution FFA images facilitate the detection of small lesions such as microaneurysms, and other landmark changes, in the early stages; this can help an ophthalmologist improve a patient’s cure rate However, only low-resolution images are available in most clinical cases Super-resolution (SR), which is a method to improve the resolution of an image, has been successfully employed for natural and remote sensing images To the best of our knowledge, no one has applied SR techniques to FFA imaging so far In this work, we propose a SR method-based pipeline for FFA imaging The aim of this pipeline is to enhance the image quality of FFA by using SR techniques Several SR frameworks including neighborhood embedding, sparsity-based, locally-linear regression and deep learning-based approaches are investigated Based on a clinical FFA dataset collected from Second Affiliated Hospital to Xuzhou Medical University, each SR method is implemented and evaluated for the pipeline to improve the resolution of FFA images As shown in our results, most SR algorithms have a positive impact on the enhancement of FFA images Super-resolution forests (SRF), a random forest-based SR method has displayed remarkable high effectiveness and outperformed other methods Hence, SRF should be one potential way to benefit ophthalmologists by obtaining high-resolution FFA images in a clinical setting

/pdf/a-super-resolution-method-based-pipeline-for-fundus-1fyj799cjz.pdf

A super-resolution method-based pipeline for fundus fluorescein angiography imaging.

https://hal.archives-ouvertes.fr/hal-01278901/document

Motion estimation-based image enhancement in ultrasound imaging.

Ultrasound offers a safe, non-invasive, and inexpensive way of imaging. However, due to its natural intrinsic imaging characteristics, it produces poor quality images with low resolution (LR) compared to other medical imaging modalities. Various image enhancement techniques have been extensively studied to overcome these shortcomings. Super-resolution (SR) is one of these methods, which endeavor to obtain high resolution (HR) images from LR images while enlarging them. Numerous studies have already utilized different SR techniques in various stages of ultrasound imaging (USI). Unlike other studies, which aimed at obtaining SR in the pre-processing phase or early stages of the post-processing phase of USI, we achieved SR on B-mode ultrasound images, which is the last stage of USI. We constructed a deep convolutional neural network (CNN) and trained it with a very large dataset of B-mode ultrasound images for the scale factors 2, 3, 4, and 8. We evaluated the performance of our proposed model quantitatively with eight image quality measures. The quantitative results revealed that our algorithm is much more successful than other methods at each magnification factor. Furthermore, we also verified that there is a statistically significant difference between our approach and others. Besides, qualitative analysis of the reconstructed images also confirms that it produces much better quality HR images than other methods in terms of the human visual system.

/pdf/super-resolution-of-b-mode-ultrasound-images-with-deep-3lunlxn9zp.pdf

Super Resolution of B-Mode Ultrasound Images With Deep Learning

L'imagerie ultrasonore est une modalite d'imagerie medicale couramment utilisee pour l'etablissement de diagnostics de therapie ou de suivi divers (croissance du fœtus, detection de certains cancers, assistance a la realisation d'actes therapeutiques). Si cette modalite dispose de nombreux avantages comme son innocuite, sa facilite d'utilisation et son faible cout, elle souffre cependant d'une resolution spatiale limitee quand on la compare a d'autres modalites comme l'imagerie par resonance magnetique. L'amelioration de la resolution des images ultrasonores est un defi de taille et de tres nombreux travaux ont depuis longtemps explore des approches instrumentales portant sur l'optimisation du dispositif d'acquisition. L'imagerie echographique haute resolution permet ainsi d'atteindre cet objectif a l'aide de sondes particulieres mais se trouve aujourd'hui confrontee a des limitations d'ordre physique et technologique. L'objet de cette these est d'adopter une strategie de post-traitement afin de contourner ces contraintes inherentes aux approches instrumentales. Dans ce contexte, nous presentons deux approches pour l'amelioration de la resolution des images ultrasonores, selon que les donnees disponibles prennent la forme d'une sequence d'images ou d'une image unique. Dans le premier cas, l'adaptation d'une technique d'estimation du mouvement originellement proposee pour l'elastographie nous permet d'etablir un cadre de reconstruction haute resolution efficace dedie a la modalite qui nous interesse. Cette approche est evaluee a l'aide d'une simulation realiste d'images ultrasonores avant d'etre appliquee a des donnees in vivo. Nous proposons ensuite, dans le cadre du traitement d'une seule image, deux methodes de deconvolution rapide pour l'amelioration de la resolution. Ces approches prennent en compte, suivant leur disponibilite, certaines informations a priori sur les conditions d'acquisition comme la reponse impulsionnelle spatiale du systeme. Les resultats sont caracterises dans un premier temps a l'aide de donnees synthetiques et sont ensuite valides sur des images in vivo

Amélioration de la résolution en imagerie ultrasonore

Image resolution enhancement is a problem of considerable interest in all medical imaging modalities. Unlike general purpose imaging or video processing, for a very long time, medical image resolution enhancement has been based on optimization of the imaging devices. Although some recent works purport to deal with image postprocessing, much remains to be done regarding medical image enhancement via postprocessing, especially in ultrasound imaging. We face a resolution improvement issue in the case of medical ultrasound imaging. We propose to investigate this problem using multidimensional autoregressive (AR) models. Noting that the estimation of the envelope of an ultrasound radio frequency (RF) signal is very similar to the estimation of classical Fourier-based power spectrum estimation, we theoretically show that a domain change and a multidimensional AR model can be used to achieve super-resolution in ultrasound imaging provided the order is estimated correctly. Here, this is done by means of a technique that simultaneously estimates the order and the parameters of a multidimensional model using relevant regression matrix factorization. Doing so, the proposed method specifically fits ultrasound imaging and provides an estimated envelope. Moreover, an expression that links the theoretical image resolution to both the image acquisition features (such as the point spread function) and a postprocessing feature (the AR model) order is derived. The overall contribution of this work is threefold. First, it allows for automatic resolution improvement. Through a simple model and without any specific manual algorithmic parameter tuning, as is used in common methods, the proposed technique simply and exclusively uses the ultrasound RF signal as input and provides the improved B-mode as output. Second, it allows for the a priori prediction of the improvement in resolution via the knowledge of the parametric model order before actual processing. Finally, to achieve the previous goal, while classical parametric methods would first estimate the model order and then the model parameters, our approach estimates the model parameters and the order simultaneously. The effectiveness of the methodology is validated using two-dimensional synthetic and in vivo data. We show that, compared to other techniques, our method provides better results from a qualitative and a quantitative viewpoint.

/pdf/resolution-enhancement-in-medical-ultrasound-imaging-3j8is2k545.pdf

Resolution enhancement in medical ultrasound imaging.

High resolution medical ultrasound imaging is an ongoing challenge in many diagnosis applications and can
be achieved by instrumentation. Very few works have investigated ultrasound image resolution enhancement
whereas many works regarded general purpose optical image or video fields. Many algorithms were proposed
within these fields to achieve the "super-resolution" (SR), which consists in merging several low resolution
images to create a higher resolution image. However, the straightforward implementation of such techniques for
ultrasound imaging is unsuccessful, due to the intrinsic nature of ultrasound motions and speckle. We show how
to overcome the intrinsic limit of super-resolution in this framework by refining the registration part of common
multi-frame techniques. Classic super-resolution algorithms were implemented and evaluated using sequences of
ultrasound images. Such methods not only fail to estimate the true elastic motion but also break the speckle
characteristics, resulting in a degradation of the original image. Knowing that a registration error of only 1 pixel
leads to a high-resolution image worse than an interpolation, the registration must be adapted to the framework
of ultrasound imaging. For this purpose, we investigate different motion estimations. The process described
above was evaluated on ultrasound sequences containing up to 15 phantom images with an inclusion scanned
with a 7.5 MHz linear probe. Qualitative improvements were observable as soon as at least 5 low-resolution
images were used. Ultrasound B-mode profiles of radio-frequency lines were studied and the inclusion was more
accurately identified. The Contrast-to-Noise Ratio was increased by approximately 13%.

Marie Ploquin

Papers

Resolution enhancement in medical ultrasound imaging.

Post-processing multiple-frame super-resolution in ultrasound imaging