Evaluation of various speckle reduction filters on medical ultrasound images

Identification of lesion location and discrimination between benign and malignant findings in thyroid ultrasound imaging

Thyroid nodules are a common thyroid disorder, and ultrasound imaging, as the primary diagnostic tool, is susceptible to variations based on the physician's experience, leading to misdiagnosis. This paper constructs an end-to-end thyroid nodule detection framework based on YOLOv8, enabling automatic detection and classification of nodules by extracting grayscale and elastic features from ultrasound images. First, an attention-weighted DCN is introduced to enhance superficial feature extraction and capture local information. Next, the CPCA mechanism is employed to reduce the interference of redundant information. Finally, a feature fusion network based on an aggregation-distribution mechanism is utilized to improve the learning capability of fine-grained features, enhancing the performance of early nodule detection. Experimental results demonstrate that our method is accurate and effective for thyroid nodule detection, achieving diagnostic rates of 89.3% for benign and 90.4% for malignant nodules based on tests conducted on 611 clinical ultrasound images, with a mean Average Precision at IoU = 0.5 (mAP@50) of 95.5%, representing a 6.6% improvement over baseline models.

MLMSeg: A multi-view learning model for ultrasound thyroid nodule segmentation

Accurate segmentation of the thyroid gland in ultrasound images is an essential initial step in distinguishing between benign and malignant nodules, thus facilitating early diagnosis. Most existing deep learning-based methods to segment thyroid nodules are learned from only a single view or two views, which limits the performance of segmenting nodules at different scales in complex ultrasound scanning environments. To address this limitation, this study proposes a multi-view learning model, abbreviated as MLMSeg. First, a deep convolutional neural network is introduced to encode the features of the local view. Second, a multi-channel transformer module is designed to capture long-range dependency correlations of global view between different nodules. Third, there are semantic relationships of structural view between features of different layers. For example, low-level features and high-level features are endowed with hidden relationships in the feature space. To this end, a cross-layer graph convolutional module is proposed to adaptively learn the correlations of high-level and low-level features by constructing graphs across different layers. In addition, in the view fusion, a channel-aware graph attention block is devised to fuse the features from the aforementioned views for accurate segmentation of thyroid nodules. To demonstrate the effectiveness of the proposed method, extensive comparative experiments were conducted with 14 baseline methods. MLMSeg achieved higher Dice coefficients (92.10% and 83.84%) and Intersection over Union scores (86.60% and 73.52%) on two different thyroid datasets. The exceptional segmentation capability of MLMSeg for thyroid nodules can greatly assist in localizing thyroid nodules and facilitating more precise measurements of their transverse and longitudinal diameters, which is of significant clinical relevance for the diagnosis of thyroid nodules.

Combinatorial active contour bilateral filter for ultrasound image segmentation

Purpose: Utilization of computer-aided diagnosis (CAD) on radiological ultrasound (US) imaging has increased tremendously. The prominent CAD applications are found in breast and thyroid cancer investigation. To make appropriate clinical recommendations, it is important to accurately segment the cancerous object called a lesion. Segmentation is a crucial step but undoubtedly a challenging problem due to various perturbations, e.g., speckle noise, intensity inhomogeneity, and low contrast.

Approach: We present a combinatorial framework for US image segmentation using a bilateral filter (BF) and hybrid region-edge-based active contour (AC) model. The BF is adopted to smooth images while preserving edges. Then the hybrid model of region and edge-based AC is applied along the scales in a global-to-local manner to capture the lesion areas. The framework was tested in segmenting 258 US images of breast and thyroid, which were validated by manual ground truths.

Results: The proposed framework is accessed quantitatively based on the overlapping values of the Dice coefficient, which reaches 90.05±5.81%. The evaluation with and without the BF shows that the enhancement procedure improves the framework well.

Conclusions: The high performance of the proposed method in our experimental results indicates its potential for practical implementations in CAD radiological US systems.

Lipid-weighted intraoperative photoacoustic tomography of breast tumors: Volumetric comparison to preoperative MRI

With a lifetime risk of 1 in 8, breast cancer continues to be a major concern for women and their physicians. The optimal treatment of the disease depends on the stage of the cancer at diagnosis, which is typically assessed using medical imaging. However, currently employed imaging systems for breast tumor measurement rarely agree perfectly. Our group developed an Intraoperative Photoacoustic Screening (iPAS) soft tissue scanner featuring high bulk tissue sensitivity, a clinically compatible scan-time of 6 min, imaging depths greater than 2 cm and the capability to visualize whole breast tumors based on their lipid, rather than hemoglobin, profile. Here, we report on the first clinical experience with breast cancer patients by comparing tumor-measurement using iPAS, preoperative dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) and gold-standard pathology. Tumor size was measured volumetrically for iPAS and DCE-MRI, and separately using maximum diameters for pathology, DCE-MRI and iPAS. Comparisons were performed using Pearson's correlation coefficients, and the non-parametric Wilcoxon signed-rank test. Twelve consecutive patients were included in the study, contingent on pathologically documented invasive carcinoma. iPAS volumetric tumor size was positively correlated to DCE-MRI (Pearson's r = 0.78, p = 0.003) and not significantly different (Wilcoxon, p = 0.97). In comparison to pathology, tumor diameters given by iPAS were positively correlated (Pearson's r = 0.87, p = 0.0002) and significantly different (Wilcoxon, p = 0.0015). The results indicated that volumetric-measurement of invasive breast tumors with iPAS is similar to that of DCE-MRI. On the other hand, tumor diameter measurements were less reliable. Beyond enhancing surgical specimen examination, an extension of this technology to diagnostic imaging promises a new perspective on tumor assessment, potentially improving our current understanding and treatment of breast cancer.

Techniques for Improving Ultrasound Visualization of Biopsy Markers in Axillary Lymph Nodes

Objective:

Biopsy markers are often placed into biopsy-proven metastatic axillary lymph nodes to ensure later accurate node excision. Ultrasound is the preferred imaging modality in the axilla. However, sonographic identification of biopsy markers after neoadjuvant therapy can be challenging. This is due to poor conspicuity relative to surrounding parenchymal interfaces, treatment-related alteration of malignant morphology during neoadjuvant chemotherapy, or extrusion of the marker from the target. To the authors’ knowledge, the literature provides no recommendations for ultrasound scanning parameters that improve the detection of biopsy markers. The purpose of this manuscript is 3-fold: (1) To determine scanning parameters that improve sonographic conspicuity of biopsy markers in a phantom and cadaver model; (2) to implement these scanning parameters in the clinical setting; and (3) to provide strategies that might increase the likelihood of successful ultrasound detection of biopsy markers in breast imaging practices.

Materials and Methods:

An ex vivo study was performed using a phantom designed to simulate the heterogeneity of normal mammary or axillary soft tissues. A selection of available biopsy markers was deployed into this phantom and ultrasound (GE LOGIQ E9) was performed. Scanning parameters were adjusted to optimize marker conspicuity. For the cadaver study, the biopsy markers were deployed using ultrasound guidance into axillary lymph nodes of a female cadaver. Adjustments in transducer frequency, dynamic range, cross-beam (spatial compound imaging), beam steering, speckle reduction imaging, harmonic imaging, colorization, and speed of sound were evaluated. Settings that improved marker detection were used clinically for a year.

Results:

Sonographic scanning settings that improved biopsy marker conspicuity included increasing transducer frequency, decreasing dynamic range, setting cross-beam to medium hybrid, turning on beam steering, and setting speckle reduction imaging in the mid-range. There was no appreciable improvement with harmonic imaging, colorization, or speed of sound.

Conclusion:

On a currently available clinical ultrasound scanning system, ultrasound scanning parameters can be adjusted to improve the conspicuity of biopsy markers. Overall, optimization requires a balance between techniques that clinically increase contrast (dynamic range, harmonic imaging, and steering) and those that minimize graininess (spatial compound imaging, speckle reduction imaging, and steering). Additional scanning and procedural strategies have been provided to improve the confidence of sonographic detection of biopsy markers closely associated with the intended target.

Compensated Row-Column Ultrasound Imaging System Using Multilayered Edge Guided Stochastically Fully Connected Random Fields

The row-column method received a lot of attention for 3-D ultrasound imaging. By reducing the number of connections required to address the 2-D array and therefore reducing the amount of data to handle, this addressing method allows for real time 3-D imaging. Row-column still has its limitations: the issues of sparsity, speckle noise inherent to ultrasound, the spatially varying point spread function, and the ghosting artifacts inherent to the row-column method must all be taken into account when building a reconstruction framework. In this research, we build on a previously published system and propose an edge-guided, compensated row-column ultrasound imaging system that incorporates multilayered edge-guided stochastically fully connected conditional random fields to address the limitations of the row-column method. Tests carried out on simulated and real row-column ultrasound images show the effectiveness of our proposed system over other published systems. Visual assessment show our proposed system's potential at preserving edges and reducing speckle. Quantitative analysis shows that our proposed system outperforms previously published systems when evaluated with metrics such as Peak Signal-to-Noise Ratio, Coefficient of Correlation, and Effective Number of Looks. These results show the potential of our proposed system as an effective tool for enhancing 3-D row-column imaging.

Compensated Row-Column Ultrasound Imaging System Using Fisher Tippett Multilayered Conditional Random Field Model

3-D ultrasound imaging offers unique opportunities in the field of non destructive testing that cannot be easily found in A-mode and B-mode images. To acquire a 3-D ultrasound image without a mechanically moving transducer, a 2-D array can be used. The row column technique is preferred over a fully addressed 2-D array as it requires a significantly lower number of interconnections. Recent advances in 3-D row-column ultrasound imaging systems were largely focused on sensor design. However, these imaging systems face three intrinsic challenges that cannot be addressed by improving sensor design alone: speckle noise, sparsity of data in the imaged volume, and the spatially dependent point spread function of the imaging system. In this paper, we propose a compensated row-column ultrasound image reconstruction system using Fisher-Tippett multilayered conditional random field model. Tests carried out on both simulated and real row-column ultrasound images show the effectiveness of our proposed system as opposed to other published systems. Visual assessment of the results show our proposed system's potential at preserving detail and reducing speckle. Quantitative analysis shows that our proposed system outperforms previously published systems when evaluated with metrics such as Peak Signal to Noise Ratio, Coefficient of Correlation, and Effective Number of Looks. These results show the potential of our proposed system as an effective tool for enhancing 3-D row-column imaging.