Non-Local Based Denoising Framework for In Vivo Contrast-Free Ultrasound Microvessel Imaging.

Vascular networks can provide invaluable information about tumor angiogenesis. Ultrafast Doppler imaging enables ultrasound to image microvessels by applying tissue clutter filtering methods on the spatio-temporal data obtained from plane-wave imaging. However, the resultant vessel images suffer from background noise that degrades image quality and restricts vessel visibilities. In this paper, we addressed microvessel visualization and the associated noise problem in the power Doppler images with the goal of achieving enhanced vessel-background separation. We proposed a combination of patch-based non-local mean filtering and top-hat morphological filtering to improve vessel outline and background noise suppression. We tested the proposed method on a flow phantom, as well as in vivo breast lesions, thyroid nodules, and pathologic liver from human subjects. The proposed non-local-based framework provided a remarkable gain of more than 15 dB, on average, in terms of contrast-to-noise and signal-to-noise ratios. In addition to improving visualization of microvessels, the proposed method provided high quality images suitable for microvessel morphology quantification that may be used for diagnostic applications.

An overview of methods to mitigate artifacts in optical coherence tomography imaging of the skin.

BACKGROUND: Optical coherence tomography (OCT) of skin delivers three-dimensional images of tissue microstructures. Although OCT imaging offers a promising high-resolution modality, OCT images suffer from some artifacts that lead to misinterpretation of tissue structures. Therefore, an overview of methods to mitigate artifacts in OCT imaging of the skin is of paramount importance. Speckle, intensity decay, and blurring are three major artifacts in OCT images. Speckle is due to the low coherent light source used in the configuration of OCT. Intensity decay is a deterioration of light with respect to depth, and blurring is the consequence of deficiencies of optical components. METHOD: Two speckle reduction methods (one based on artificial neural network and one based on spatial compounding), an attenuation compensation algorithm (based on Beer-Lambert law) and a deblurring procedure (using deconvolution), are described. Moreover, optical properties extraction algorithm based on extended Huygens-Fresnel (EHF) principle to obtain some additional information from OCT images are discussed. RESULTS: In this short overview, we summarize some of the image enhancement algorithms for OCT images which address the abovementioned artifacts. The results showed a significant improvement in the visibility of the clinically relevant features in the images. The quality improvement was evaluated using several numerical assessment measures. CONCLUSION: Clinical dermatologists benefit from using these image enhancement algorithms to improve OCT diagnosis and essentially function as a noninvasive optical biopsy.

Swept-Source Optical Coherence Tomography-Supervised Biopsy.

BACKGROUND: Currently, only skin biopsy can provide definitive histological confirmation for the diagnosis of skin diseases. To improve the diagnostic accuracy and to assist the dermatologist, various imaging techniques have been added to the examination of skin. Among all these techniques, the recent advances in optical coherence tomography (OCT) have made it possible to image the skin up to 2 millimeters in depth. OBJECTIVE: To testify the feasibility of OCT imaging in skin biopsy, the authors investigated the OCT imaging for real-time visualization of needle insertion and punch biopsy techniques in both a tissue phantom and biological tissue. MATERIALS AND METHODS: A swept-source OCT with 1,305-nm central wavelength was used in this study. The euthanized mouse was used for real-time visualization of needle insertion. A gelatin phantom with India ink was used to demonstrate the punch biopsy using OCT. RESULTS: Optical coherence tomography can provide guidance for skin injections as well as real-time imaging to assist in the performance of punch biopsy. CONCLUSION: Optical coherence tomography holds potential not only as a diagnostic tool in dermatology. It can also allow for visualization for more accurate drug delivery, and noninvasively assess the response to treatment.

High-resolution wavelet-fractal compressed optical coherence tomography images.

Three-dimensional (3D) optical coherence tomography (OCT) images could assist specialists in the diagnosis of a disease in a tissue by providing morphological information from it. Since the size of such images is usually extremely large, an appropriate image compression method can help in the storage and transmission of these images. Fractal image compression provides very high compression ratios, and discrete wavelet transform (DWT) retains frequency and spatial information in the signal. In order to combine these two techniques, fractal coding has to be performed in the wavelet domain. In this work, we propose a three-dimensional extension version of the wavelet-fractal coding algorithm. The use of 3D fractal approximation to encode 3D wavelet coefficients allows us to exploit inter- and intra-redundancy of the image sequences. The compression results of several OCT images using the 3D wavelet-fractal algorithm are evaluated qualitatively and quantitatively and are compared with the results of the two-dimensional approach. The numerical results illustrate the superior performance of 3D wavelet-fractal algorithm in terms of compression ratio.

Semi-automated localization of dermal epidermal junction in optical coherence tomography images of skin.

Identifying the location of the dermal epidermal junction (DEJ) in skin images is essential in several clinical applications of dermatology such as epidermal thickness determination in healthy versus unhealthy skins, such as basal cell carcinoma. Optical coherence tomography (OCT) facilitates the visual detection of DEJ in vivo. However, due to the granular texture of speckle and a low contrast between dermis and epidermis, a skin border detection method is required for DEJ localization. Current DEJ algorithms work well for skins with a visible differentiable epidermal layer but not for the skins of different body sites. In this paper, we present a semi-automated DEJ localization algorithm based on graph theory for OCT images of skin. The proposed algorithm is performed in an interactive framework by a graphical representation of an attenuation coefficient map through a uniform-cost search method. For border thinning, a fuzzy-based nonlinear smoothing technique is used. For evaluation, the DEJ detection method is used by several experts, and the results are compared with manual segmentation. The mean thickness error between the proposed algorithm and the experts' opinion in the Bland-Altman plot is computed as 14 µm; this is comparable to the resolution of the OCT. The results suggest that the proposed image processing method successfully detects DEJ.

Predicting 3D dose distribution with scale attention network for prostate cancer radiotherapy.

The growing demand for radiation therapy to treat cancer has been directed to focus on improving treatment planning flow for patients. Accurate dose prediction, therefore, plays a prominent role in this regard. In this study, we propose a framework based on our newly developed scale attention networks (SA-Net) to attain voxel-wise dose prediction. Our network 's dynamic scale attention model incorporates low-level details with high-level semantics from feature maps at different scales. To achieve more accurate results, we used distance data between each local voxel and the organ surfaces instead of binary masks of organs at risk as well as CT image as input of the network. The proposed method is tested on prostate cancer treated with Volumetric Modulated Arc Therapy (VMAT), where the model was training with 120 cases and tested on 20 cases. The average dose difference between the predicted dose and the clinical planned dose was 0.94 Gy, which is equivalent to 2.1% as compared to the prescription dose of 45 Gy. We also compared the performance of SA-Net dose prediction framework with different input format, the signed distance map vs. binary mask and showed the signed distance map was a better format as input to the model training. These findings show that our deep learning-based strategy of dose prediction is effectively feasible for automating the treatment planning in prostate cancer radiography.

Predictive value of comb-push ultrasound shear elastography for the differentiation of reactive and metastatic axillary lymph nodes: A preliminary investigation.

OBJECTIVES: To evaluate the predictive performance of comb-push ultrasound shear elastography for the differentiation of reactive and metastatic axillary lymph nodes. METHODS: From June 2014 through September 2018, 114 female volunteers (mean age 58.1±13.3 years; range 28-88 years) with enlarged axillary lymph nodes identified by palpation or clinical imaging were prospectively enrolled in the study. Mean, standard deviation and maximum shear wave elastography parameters from 117 lymph nodes were obtained and compared to fine needle aspiration biopsy results. Mann-Whitney U test and ROC curve analysis were performed. RESULTS: The axillary lymph nodes were classified as reactive or metastatic based on the fine needle aspiration outcomes. A statistically significant difference between reactive and metastatic axillary lymph nodes was observed based on comb-push ultrasound shear elastography (CUSE) results (p<0.0001) from mean and maximum elasticity values. Mean elasticity showed the best separation with a ROC analysis resulting in 90.5% sensitivity, 94.4% specificity, 0.97 area under the curve, 95% positive predictive value, and 89.5% negative predictive value with a 30.2-kPa threshold. CONCLUSIONS: CUSE provided a quantifiable parameter that can be used for the assessment of enlarged axillary lymph nodes to differentiate between reactive and metastatic processes.

Acoustoelasticity Analysis of Transient Waves for Non-Invasive In Vivo Assessment of Urinary Bladder.

A non-invasive method for measurement of the bladder wall nonlinear elastic behavior is presented. The method is based on acoustoelasticity modeling of the elasticity changes in bladder tissue modulus at different volumetric strain levels. At each volume, tissue strain is obtained from the real-time ultrasound images. Using acoustic radiation force, a transient Lamb wave is excited on the bladder wall and instantaneous modulus of shear elasticity is obtained from the 2-D Fourier analysis of the spatial-temporal dispersion maps. Measured elasticity and strain data are then used in an acoustoelasticity formulation to obtain the third order elastic coefficient, referred to as nonlinearity parameter A, and initial resting elasticity µ0. The method was tested in ex vivo porcine bladder samples (N = 9) before and after treatment with formalin. The estimated nonlinearity parameter, A, was significantly higher in the treated samples compared to intact (p < 0.00062). The proposed method was also applied on 16 patients with neurogenic bladders (10 compliant and 6 non-compliant subjects). The estimated nonlinearity parameter A was significantly higher in the non-compliant cases compared to the compliant (p < 0.0293). These preliminary results promise a new method for non-invasive evaluation of the bladder tissue nonlinearity which may serve as a new diagnostic and prognostic biomarker for management of the patients with neurogenic bladders.

Double-Stage Delay Multiply and Sum Beamforming Algorithm: Application to Linear-Array Photoacoustic Imaging.

Photoacoustic imaging (PAI) is an emerging medical imaging modality capable of providing high spatial resolution of Ultrasound (US) imaging and high contrast of optical imaging. Delay-and-Sum (DAS) is the most common beamforming algorithm in PAI. However, using DAS beamformer leads to low resolution images and considerable contribution of off-axis signals. A new paradigm namely delay-multiply-and-sum (DMAS), which was originally used as a reconstruction algorithm in confocal microwave imaging, was introduced to overcome the challenges in DAS. DMAS was used in PAI systems and it was shown that this algorithm results in resolution improvement and sidelobe degrading. However, DMAS is still sensitive to high levels of noise, and resolution improvement is not satisfying. Here, we propose a novel algorithm based on DAS algebra inside DMAS formula expansion, double stage DMAS (DS-DMAS), which improves the image resolution and levels of sidelobe, and is much less sensitive to high level of noise compared to DMAS. The performance of DS-DMAS algorithm is evaluated numerically and experimentally. The resulted images are evaluated qualitatively and quantitatively using established quality metrics including signal-to-noise ratio (SNR), full-width-half-maximum (FWHM) and contrast ratio (CR). It is shown that DS-DMAS outperforms DAS and DMAS at the expense of higher computational load. DS-DMAS reduces the lateral valley for about 15 dB and improves the SNR and FWHM better than 13% and 30%, respectively. Moreover, the levels of sidelobe are reduced for about 10 dB in comparison with those in DMAS.

Linear-array photoacoustic imaging using minimum variance-based delay multiply and sum adaptive beamforming algorithm.

In photoacoustic imaging, delay-and-sum (DAS) beamformer is a common beamforming algorithm having a simple implementation. However, it results in a poor resolution and high sidelobes. To address these challenges, a new algorithm namely delay-multiply-and-sum (DMAS) was introduced having lower sidelobes compared to DAS. To improve the resolution of DMAS, a beamformer is introduced using minimum variance (MV) adaptive beamforming combined with DMAS, so-called minimum variance-based DMAS (MVB-DMAS). It is shown that expanding the DMAS equation results in multiple terms representing a DAS algebra. It is proposed to use the MV adaptive beamformer instead of the existing DAS. MVB-DMAS is evaluated numerically and experimentally. In particular, at the depth of 45 mm MVB-DMAS results in about 31, 18, and 8 dB sidelobes reduction compared to DAS, MV, and DMAS, respectively. The quantitative results of the simulations show that MVB-DMAS leads to improvement in full-width-half-maximum about 96%, 94%, and 45% and signal-to-noise ratio about 89%, 15%, and 35% compared to DAS, DMAS, MV, respectively. In particular, at the depth of 33 mm of the experimental images, MVB-DMAS results in about 20 dB sidelobes reduction in comparison with other beamformers.

Learnable despeckling framework for optical coherence tomography images.

Optical coherence tomography (OCT) is a prevalent, interferometric, high-resolution imaging method with broad biomedical applications. Nonetheless, OCT images suffer from an artifact called speckle, which degrades the image quality. Digital filters offer an opportunity for image improvement in clinical OCT devices, where hardware modification to enhance images is expensive. To reduce speckle, a wide variety of digital filters have been proposed; selecting the most appropriate filter for an OCT image/image set is a challenging decision, especially in dermatology applications of OCT where a different variety of tissues are imaged. To tackle this challenge, we propose an expandable learnable despeckling framework, we call LDF. LDF decides which speckle reduction algorithm is most effective on a given image by learning a figure of merit (FOM) as a single quantitative image assessment measure. LDF is learnable, which means when implemented on an OCT machine, each given image/image set is retrained and its performance is improved. Also, LDF is expandable, meaning that any despeckling algorithm can easily be added to it. The architecture of LDF includes two main parts: (i) an autoencoder neural network and (ii) filter classifier. The autoencoder learns the FOM based on several quality assessment measures obtained from the OCT image including signal-to-noise ratio, contrast-to-noise ratio, equivalent number of looks, edge preservation index, and mean structural similarity index. Subsequently, the filter classifier identifies the most efficient filter from the following categories: (a) sliding window filters including median, mean, and symmetric nearest neighborhood, (b) adaptive statistical-based filters including Wiener, homomorphic Lee, and Kuwahara, and (c) edge preserved patch or pixel correlation-based filters including nonlocal mean, total variation, and block matching three-dimensional filtering.

Optical Coherence Tomography Technology and Quality Improvement Methods for Optical Coherence Tomography Images of Skin: A Short Review.

Optical coherence tomography (OCT) delivers 3-dimensional images of tissue microstructures. Although OCT imaging offers a promising high-resolution method, OCT images experience some artifacts that lead to misapprehension of tissue structures. Speckle, intensity decay, and blurring are 3 major artifacts in OCT images. Speckle is due to the low coherent light source used in the configuration of OCT. Intensity decay is a deterioration of light with respect to depth, and blurring is the consequence of deficiencies of optical components. In this short review, we summarize some of the image enhancement algorithms for OCT images which address the abovementioned artifacts.

Universal in vivo Textural Model for Human Skin based on Optical Coherence Tomograms.

Currently, diagnosis of skin diseases is based primarily on the visual pattern recognition skills and expertise of the physician observing the lesion. Even though dermatologists are trained to recognize patterns of morphology, it is still a subjective visual assessment. Tools for automated pattern recognition can provide objective information to support clinical decision-making. Noninvasive skin imaging techniques provide complementary information to the clinician. In recent years, optical coherence tomography (OCT) has become a powerful skin imaging technique. According to specific functional needs, skin architecture varies across different parts of the body, as do the textural characteristics in OCT images. There is, therefore, a critical need to systematically analyze OCT images from different body sites, to identify their significant qualitative and quantitative differences. Sixty-three optical and textural features extracted from OCT images of healthy and diseased skin are analyzed and, in conjunction with decision-theoretic approaches, used to create computational models of the diseases. We demonstrate that these models provide objective information to the clinician to assist in the diagnosis of abnormalities of cutaneous microstructure, and hence, aid in the determination of treatment. Specifically, we demonstrate the performance of this methodology on differentiating basal cell carcinoma (BCC) and squamous cell carcinoma (SCC) from healthy tissue.