Speckle characterization methods in ultrasound images – A review

Semiautomatic contour tracking method for biological object segmentation in thin-section electron microscope images with modified zero DC component-type Gabor wavelets

In electron microscopic image processing, artificial intelligence (AI) is a powerful method for segmentation. Because creating training data remains time-consuming and burdensome, a simple and accurate segmentation tool, which is effective and does not rely on manual drawings, is necessary to create training data for AI and to support immediate image analysis. A Gabor wavelet-based contour tracking method has been devised as a step toward realizing such a tool. Although many papers on Gabor filter-based and Gabor filter bank-based texture segmentations have been published, previous studies did not apply the Gabor wavelet-based method to straightforwardly detect membrane-like ridges and step edges for segmentation because earlier works used a nonzero DC component-type Gabor wavelets. The DC component has a serious flaw in such detection. Although the DC component can be removed by a formula that satisfies the wavelet theory or by a log-Gabor function, this is not practical for the proposed scheme. Herein, we devised modified zero DC component-type Gabor wavelets. The proposed method can practically confine a wavelet within a small image area. This type of Gabor wavelet can appropriately track various contours of organelles appearing in thin-section transmission electron microscope images prepared by the freeze-substitution fixation method. The proposed method not only more accurately tracks ridge and step edge contours but also tracks pattern boundary contours consisting of slightly different image patterns. Simulations verified these results.

Bandwidth Improvement in Ultrasound Image Reconstruction Using Deep Learning Techniques

Ultrasound (US) imaging is a medical imaging modality that uses the reflection of sound in the range of 2-18 MHz to image internal body structures. In US, the frequency bandwidth (BW) is directly associated with image resolution. BW is a property of the transducer and more bandwidth comes at a higher cost. Thus, methods that can transform strongly bandlimited ultrasound data into broadband data are essential. In this work, we propose a deep learning (DL) technique to improve the image quality for a given bandwidth by learning features provided by broadband data of the same field of view. Therefore, the performance of several DL architectures and conventional state-of-the-art techniques for image quality improvement and artifact removal have been compared on in vitro US datasets. Two training losses have been utilized on three different architectures: a super resolution convolutional neural network (SRCNN), U-Net, and a residual encoder decoder network (REDNet) architecture. The models have been trained to transform low-bandwidth image reconstructions to high-bandwidth image reconstructions, to reduce the artifacts, and make the reconstructions visually more attractive. Experiments were performed for 20%, 40%, and 60% fractional bandwidth on the original images and showed that the improvements obtained are as high as 45.5% in RMSE, and 3.85 dB in PSNR, in datasets with a 20% bandwidth limitation.

De-Speckling Breast Cancer Ultrasound Images Using a Rotationally Invariant Block Matching Based Non-Local Means (RIBM-NLM) Method

The ultrasonic technique is an indispensable imaging modality for diagnosis of breast cancer in young women due to its ability in efficiently capturing the tissue properties, and decreasing nega-tive recognition rate thereby avoiding non-essential biopsies. Despite the advantages, ultrasound images are affected by speckle noise, generating fine-false structures that decrease the contrast of the images and diminish the actual boundaries of tissues on ultrasound image. Moreover, speckle noise negatively impacts the subsequent stages in image processing pipeline, such as edge detec-tion, segmentation, feature extraction, and classification. Previous studies have formulated vari-ous speckle reduction methods in ultrasound images; however, these methods suffer from being unable to retain finer edge details and require more processing time. In this study, we propose a breast ultrasound de-speckling method based on rotational invariant block matching non-local means (RIBM-NLM) filtering. The effectiveness of our method has been demonstrated by com-paring our results with three established de-speckling techniques, the switching bilateral filter (SBF), the non-local means filter (NLMF), and the optimized non-local means filter (ONLMF) on 250 images from public dataset and 6 images from private dataset. Evaluation metrics, including Self-Similarity Index Measure (SSIM), Peak Signal to Noise Ratio (PSNR), and Mean Square Error (MSE) were utilized to measure performance. With the proposed method, we were able to record average SSIM of 0.8915, PSNR of 65.97, MSE of 0.014, RMSE of 0.119, and computational speed of 82 seconds at noise variance of 20dB using the public dataset, all with p-value of less than 0.001 compared against NLMF, ONLMF, and SBF. Similarly, the proposed method achieved av-erage SSIM of 0.83, PSNR of 66.26, MSE of 0.015, RMSE of 0.124, and computational speed of 83 seconds at noise variance of 20dB using the private dataset, all with p-value of less than 0.001 compared against NLMF, ONLMF, and SBF.

Handheld Ultrasound Video High-Quality Reconstruction Using a Low-Rank Representation Multipathway Generative Adversarial Network

Recently, the use of portable equipment has attracted much attention in the medical ultrasound field. Handheld ultrasound devices have great potential for improving the convenience of diagnosis, but noise-induced artifacts and low resolution limit their application. To enhance the video quality of handheld ultrasound devices, we propose a low-rank representation multipathway generative adversarial network (LRR MPGAN) with a cascade training strategy. This method can directly generate sequential, high-quality ultrasound video with clear tissue structures and details. In the cascade training process, the network is first trained with plane wave (PW) single-/multiangle video pairs to capture dynamic information and then fine-tuned with handheld/high-end image pairs to extract high-quality single-frame information. In the proposed GAN structure, a multipathway generator is applied to implement the cascade training strategy, which can simultaneously extract dynamic information and synthesize multiframe features. The LRR decomposition channel approach guarantees the fine reconstruction of both global features and local details. In addition, a novel ultrasound loss is added to the conventional mean square error (MSE) loss to acquire ultrasound-specific perceptual features. A comprehensive evaluation is conducted in the experiments, and the results confirm that the proposed method can effectively reconstruct high-quality ultrasound videos for handheld devices. With the aid of the proposed method, handheld ultrasound devices can be used to obtain convincing and convenient diagnoses.

A novel ultrasound technique to detect early chronic kidney disease

Chronic kidney disease (CKD) of unknown etiology is recognized as a major public health challenge and a leading cause of morbidity and mortality in the dry zone in Sri Lanka. CKD is asymptomatic and are diagnosed only in late stages. Evidence points to strong correlation between progression of CKD and kidney fibrosis. Several biochemical markers of renal fibrosis have been associated with progression of CKD. However, no marker is able to predict CKD consistently and accurately before being detected with traditional clinical tests (serum creatinine, and cystatin C, urine albumin or protein, and ultrasound scanning). In this paper, we hypothesize that fibrosis in the kidney, and therefore the severity of the disease, is reflected in the frequency spectrum of the scattered ultrasound from the kidney. We present a design of a simple ultrasound system, and a set of clinical and laboratory studies to identify spectral characteristics of the scattered ultrasound wave from the kidney that correlates with CKD. We believe that spectral parameters identified in these studies can be used to detect and stratify CKD at an earlier stage than what is possible with current markers of CKD.

A novel ultrasound technique to detect early chronic kidney disease

Chronic kidney disease (CKD) of unknown etiology is recognized as a major public health challenge and a leading cause of morbidity and mortality in the dry zone in Sri Lanka. CKD is asymptomatic and are diagnosed only in late stages. Evidence points to strong correlation between progression of CKD and kidney fibrosis. Several biochemical markers of renal fibrosis have been associated with progression of CKD. However, no marker is able to predict CKD consistently and accurately before being detected with traditional clinical tests (serum creatinine, and cystatin C, urine albumin or protein, and ultrasound scanning).

In this paper, we hypothesize that fibrosis in the kidney, and therefore the severity of the disease, is reflected in the frequency spectrum of the scattered ultrasound from the kidney. We present a design of a simple ultrasound system, and a set of clinical and laboratory studies to identify spectral characteristics of the scattered ultrasound wave from the kidney that correlates with CKD. We believe that spectral parameters identified in these studies can be used to detect and stratify CKD at an earlier stage than what is possible with current markers of CKD.

Left ventricle segmentation in fetal echocardiography using a multi-texture active appearance model based on the steered Hermite transform

OBJECTIVE

Fetal echocardiographic analysis is essential for detecting cardiac defects at early gestational ages. Fetal cardiac function can be assessed by performing some measurements regarding the dimension and shape of the heart cavities. In this work we propose an automatic segmentation method applied to the analysis of the left ventricle in fetal echocardiography.

METHODS

For segmentation of the left ventricle, we designed a novel multi-texture active appearance model (AAM) based on the Hermite transform (HT). Local orientation analysis is addressed by steering the coefficients obtained with the HT. The method basically consists of an AAM-based scheme which uses the steered HT to efficiently code texture patterns of the input image. A wider and detailed description of the image features can be obtained with this method. Compared with classic AAM methods, the segmentation performance is substantially improved with the proposed scheme. Since AAM-based approaches process local information, an automatic method is also proposed to initialize the multi-texture AAM. For this purpose, a database of pre-segmented images was built. Then, techniques such as thresholding, mathematical morphology and correlation are combined to identify the position and orientation of the left ventricle. Typical issues found in fetal cardiac ultrasound images such as different orientations and shape variations of the heart cavities can be easily handled with the designed method.

RESULTS

Several images of fetal echocardiography were used to evaluate the proposed segmentation method. The algorithm performance was validated using different metrics. We used a database of 143 real images of fetal hearts acquired for different phases of the cardiac cycle. We obtained an average Dice coefficient of 0.8631 and a point-to-curve distance of 2.027 pixels. The proposed algorithm was also validated by comparing it with other segmentation methods.

CONCLUSIONS

We have designed an automatic algorithm for left ventricle segmentation in fetal echocardiography. The reported results demonstrate that the proposed approach can achieve an efficient segmentation of the left ventricular cavity. Typical problems found in images of fetal echocardiography are satisfactorily handled with the proposed multi-texture AAM scheme.