MEF-UNet: An end-to-end ultrasound image segmentation algorithm based on multi-scale feature extraction and fusion

Ultrasound image segmentation is a challenging task due to the complexity of lesion types, fuzzy boundaries, and low-contrast images along with the presence of noises and artifacts. To address these issues, we propose an end-to-end multi-scale feature extraction and fusion network (MEF-UNet) for the automatic segmentation of ultrasound images. Specifically, we first design a selective feature extraction encoder, including detail extraction stage and structure extraction stage, to precisely capture the edge details and overall shape features of the lesions. In order to enhance the representation capacity of contextual information, we develop a context information storage module in the skip-connection section, responsible for integrating information from adjacent two-layer feature maps. In addition, we design a multi-scale feature fusion module in the decoder section to merge feature maps with different scales. Experimental results indicate that our MEF-UNet can significantly improve the segmentation results in both quantitative analysis and visual effects.

Multi-task learning for segmentation and classification of breast tumors from ultrasound images

Segmentation and classification of breast tumors are critical components of breast ultrasound (BUS) computer-aided diagnosis (CAD), which significantly improves the diagnostic accuracy of breast cancer. However, the characteristics of tumor regions in BUS images, such as non-uniform intensity distributions, ambiguous or missing boundaries, and varying tumor shapes and sizes, pose significant challenges to automated segmentation and classification solutions. Many previous studies have proposed multi-task learning methods to jointly tackle tumor segmentation and classification by sharing the features extracted by the encoder. Unfortunately, this often introduces redundant or misleading information, which hinders effective feature exploitation and adversely affects performance. To address this issue, we present ACSNet, a novel multi-task learning network designed to optimize tumor segmentation and classification in BUS images. The segmentation network incorporates a novel gate unit to allow optimal transfer of valuable contextual information from the encoder to the decoder. In addition, we develop the Deformable Spatial Attention Module (DSAModule) to improve segmentation accuracy by overcoming the limitations of conventional convolution in dealing with morphological variations of tumors. In the classification branch, multi-scale feature extraction and channel attention mechanisms are integrated to discriminate between benign and malignant breast tumors. Experiments on two publicly available BUS datasets demonstrate that ACSNet not only outperforms mainstream multi-task learning methods for both breast tumor segmentation and classification tasks, but also achieves state-of-the-art results for BUS tumor segmentation. Code and models are available at https://github.com/qqhe-frank/BUS-segmentation-and-classification.git.

A multi-task model for reliable classification of thyroid nodules in ultrasound images

Thyroid nodules are common, and patients with potential malignant lesions are usually diagnosed using ultrasound imaging to determine further treatment options. This study aims to propose a computer-aided diagnosis method for benign and malignant classification of thyroid nodules in ultrasound images. We propose a novel multi-task framework that combines the advantages of dense connectivity, Squeeze-and-Excitation (SE) connectivity, and Atrous Spatial Pyramid Pooling (ASPP) layer to enhance feature extraction. The Dense connectivity is used to optimize feature reuse, the SE connectivity to optimize feature weights, the ASPP layer to fuse feature information, and a multi-task learning framework to adjust the attention of the network. We evaluate our model using a 10-fold cross-validation approach based on our established Thyroid dataset. We assess the performance of our method using six average metrics: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and AUC, which are 93.49, 95.54, 91.52, 91.63, 95.47, and 96.84%, respectively. Our proposed method outperforms other classification networks in all metrics, achieving optimal performance. We propose a multi-task model, DSMA-Net, for distinguishing thyroid nodules in ultrasound images. This method can further enhance the diagnostic ability of doctors for suspected cancer patients and holds promise for clinical applications.

Fusion of transfer learning models with LSTM for detection of breast cancer using ultrasound images

Breast Cancer (BC) is one of the top reasons for fatality in women worldwide. As a result, timely identification is critical for successful therapy and excellent survival rates. Transfer Learning (TL) approaches have recently shown promise in aiding in the early recognition of BC. In this work, three TL models, MobileNetV2, ResNet50, and VGG16, were combined with LSTM to extract the features from Ultrasound Images (USIs). Furthermore, the Synthetic Minority Over-sampling Technique (SMOTE) with Tomek (SMOTETomek) was employed to balance the extracted features. The proposed method with VGG16 achieved an F1 score of 99.0 %, Matthews Correlation Coefficient (MCC) and Kappa Coefficient of 98.9 % with an Area Under Curve (AUC) of 1.0. The K-fold method was applied for cross-validation and achieved an average F1 score of 96 %. Moreover, the Gradient-weighted Class Activation Mapping (Grad-CAM) method was applied for visualization, and the Local Interpretable Model-agnostic Explanations (LIME) method was applied for interpretability. The Normal Approximation Interval (NAI) and bootstrapping methods were used to calculate Confidence Intervals (CIs). The proposed method achieved a Lower CI (LCI), Upper CI (UCI), and Mean CI (MCI) of 96.50 %, 99.75 %, and 98.13 %, respectively, with the NAI, while 95 % LCI of 93.81 %, an UCI of 96.00 %, and a bootstrap mean of 94.90 % with the bootstrap method. Furthermore, the performance of the six state-of-the-art (SOTA) TL models, such as Xception, NASNetMobile, InceptionResNetV2, MobileNetV2, ResNet50, and VGG16, were compared with the proposed method.

Deep learning-based osteochondritis dissecans detection in ultrasound images with humeral capitellum localization

PURPOSE

Osteochondritis dissecans (OCD) of the humeral capitellum is a common cause of elbow disorders, particularly among young throwing athletes. Conservative treatment is the preferred treatment for managing OCD, and early intervention significantly influences the possibility of complete disease resolution. The purpose of this study is to develop a deep learning-based classification model in ultrasound images for computer-aided diagnosis.

METHODS

This paper proposes a deep learning-based OCD classification method in ultrasound images. The proposed method first detects the humeral capitellum detection using YOLO and then estimates the OCD probability of the detected region probability using VGG16. We hypothesis that the performance will be improved by eliminating unnecessary regions. To validate the performance of the proposed method, it was applied to 158 subjects (OCD: 67, Normal: 91) using five-fold-cross-validation.

RESULTS

The study demonstrated that the humeral capitellum detection achieved a mean average precision (mAP) of over 0.95, while OCD probability estimation achieved an average accuracy of 0.890, precision of 0.888, recall of 0.927, F1 score of 0.894, and an area under the curve (AUC) of 0.962. On the other hand, when the classification model was constructed for the entire image, accuracy, precision, recall, F1 score, and AUC were 0.806, 0.806, 0.932, 0.843, and 0.928, respectively. The findings suggest the high-performance potential of the proposed model for OCD classification in ultrasonic images.

CONCLUSION

This paper introduces a deep learning-based OCD classification method. The experimental results emphasize the effectiveness of focusing on the humeral capitellum for OCD classification in ultrasound images. Future work should involve evaluating the effectiveness of employing the proposed method by physicians during medical check-ups for OCD.

Research related to the diagnosis of prostate cancer based on machine learning medical images: A review

BACKGROUND

Prostate cancer is currently the second most prevalent cancer among men. Accurate diagnosis of prostate cancer can provide effective treatment for patients and greatly reduce mortality. The current medical imaging tools for screening prostate cancer are mainly MRI, CT and ultrasound. In the past 20 years, these medical imaging methods have made great progress with machine learning, especially the rise of deep learning has led to a wider application of artificial intelligence in the use of image-assisted diagnosis of prostate cancer.

METHOD

This review collected medical image processing methods, prostate and prostate cancer on MR images, CT images, and ultrasound images through search engines such as web of science, PubMed, and Google Scholar, including image pre-processing methods, segmentation of prostate gland on medical images, registration between prostate gland on different modal images, detection of prostate cancer lesions on the prostate.

CONCLUSION

Through these collated papers, it is found that the current research on the diagnosis and staging of prostate cancer using machine learning and deep learning is in its infancy, and most of the existing studies are on the diagnosis of prostate cancer and classification of lesions, and the accuracy is low, with the best results having an accuracy of less than 0.95. There are fewer studies on staging. The research is mainly focused on MR images and much less on CT images, ultrasound images.

DISCUSSION

Machine learning and deep learning combined with medical imaging have a broad application prospect for the diagnosis and staging of prostate cancer, but the research in this area still has more room for development.

FHUSP-NET: A Multi-task model for fetal heart ultrasound standard plane recognition and key anatomical structures detection

In prenatal ultrasound screening, rapid and accurate recognition of the fetal heart ultrasound standard planes(FHUSPs) can more objectively predict fetal heart growth. However, the small size and movement of the fetal heart make this process more difficult. Therefore, we design a deep learning-based FHUSP recognition network (FHUSP-NET), which can automatically recognize the five FHUSPs and detect tiny key anatomical structures at the same time. 3360 ultrasound images of five FHUSPs from 1300 mid-pregnancy pregnant women are included in this study. 10 fetal heart key anatomical structures are manually annotated by experts. We apply spatial pyramid pooling with a fully connected spatial pyramid convolution module to capture information about targets and scenes of different sizes as well as improve the perceptual ability and feature representation of the model. Additionally, we adopt the squeeze-and-excitation networks to improve the sensitivity of the model to the channel features. We also introduce a new loss function, the efficient IOU loss, which makes the model effective for optimizing similarity. The results demonstrate the superiority of FHUSP-NET in detecting fetal heart key anatomical structures and recognizing FHUSPs. In the detection task, the value of mAP@0.5, precision, and recall are 0.955, 0.958, and 0.931, respectively, while the accuracy reaches 0.964 in the recognition task. Furthermore, it takes only 13.6 ms to detect and recognize one FHUSP image. This method helps to improve ultrasonographers' quality control of the fetal heart ultrasound standard plane and aids in the identification of fetal heart structures in a less experienced group of physicians.

Super-resolution of 2D ultrasound images and videos

This paper proposes a novel deep-learning framework for super-resolution ultrasound images and videos in terms of spatial resolution and line reconstruction. To this end, we up-sample the acquired low-resolution image through a vision-based interpolation method; then, we train a learning-based model to improve the quality of the up-sampling. We qualitatively and quantitatively test our model on different anatomical districts (e.g., cardiac, obstetric) images and with different up-sampling resolutions (i.e., 2X, 4X). Our method improves the PSNR median value with respect to SOTA methods of [Formula: see text] on obstetric 2X raw images, [Formula: see text] on cardiac 2X raw images, and [Formula: see text] on abdominal raw 4X images; it also improves the number of pixels with a low prediction error of [Formula: see text] on obstetric 4X raw images, [Formula: see text] on cardiac 4X raw images, and [Formula: see text] on abdominal 4X raw images. The proposed method is then applied to the spatial super-resolution of 2D videos, by optimising the sampling of lines acquired by the probe in terms of the acquisition frequency. Our method specialises trained networks to predict the high-resolution target through the design of the network architecture and the loss function, taking into account the anatomical district and the up-sampling factor and exploiting a large ultrasound data set. The use of deep learning on large data sets overcomes the limitations of vision-based algorithms that are general and do not encode the characteristics of the data. Furthermore, the data set can be enriched with images selected by medical experts to further specialise the individual networks. Through learning and high-performance computing, the proposed super-resolution is specialised to different anatomical districts by training multiple networks. Furthermore, the computational demand is shifted to centralised hardware resources with a real-time execution of the network's prediction on local devices.

[An Improved Object Detection Algorithm for Thyroid Nodule Ultrasound Image Based on Faster R-CNN]

Objective

To propose an improved algorithm for thyroid nodule object detection based on Faster R-CNN so as to improve the detection precision of thyroid nodules in ultrasound images.

Methods

The algorithm used ResNeSt50 combined with deformable convolution (DC) as the backbone network to improve the detection effect of irregularly shaped nodules. Feature pyramid networks (FPN) and Region of Interest (RoI) Align were introduced in the back of the trunk network. The former was used to reduce missed or mistaken detection of thyroid nodules, and the latter was used to improve the detection precision of small nodules. To improve the generalization ability of the model, parameters were updated during backpropagation with an optimizer improved by Sharpness-Aware Minimization (SAM).

Results

In this experiment, 6 261 thyroid ultrasound images from the Affiliated Hospital of Xuzhou Medical University and the First Hospital of Nanjing were used to compare and evaluate the effectiveness of the improved algorithm. According to the findings, the algorithm showed optimization effect to a certain degree, with the AP50 of the final test set being as high as 97.4% and AP@50:5:95 also showing a 10.0% improvement compared with the original model. Compared with both the original model and the existing models, the improved algorithm had higher detection precision and improved capacity to detect thyroid nodules with better accuracy and precision. In particular, the improved algorithm had a higher recall rate under the requirement of lower detection frame precision.

Conclusion

The improved method proposed in the study is an effective object detection algorithm for thyroid nodules and can be used to detect thyroid nodules with accuracy and precision.

BSMNet: Boundary-salience multi-branch network for intima-media identification in carotid ultrasound images

Carotid artery intima-media thickness (CIMT) is an essential factor in signaling the risk of cardiovascular diseases, which is commonly evaluated using ultrasound imaging. However, automatic intima-media segmentation and thickness measurement are still challenging due to the boundary ambiguity of intima-media and inherent speckle noises in ultrasound images. In this work, we propose an end-to-end boundary-salience multi-branch network, BSMNet, to tackle the carotid intima-media identification from ultrasound images, where the prior shape knowledge and anatomical dependence are exploited using a parallel linear structure learning modules followed by a boundary refinement module. Moreover, we design a strip attention model to boost the thin strip region segmentation with shape priors, in which an anisotropic kernel shape captures long-range global relations and scrutinizes meaningful local salient contexts simultaneously. Extensive experimental results on an in-house carotid ultrasound (US) dataset demonstrate the promising performance of our method, which achieves about 0.02 improvement in Dice and HD95 than other state-of-the-art methods. Our method is promising in advancing the analysis of systemic arterial disease with ultrasound imaging.

Establishment and Evaluation of Intelligent Diagnostic Model for Ophthalmic Ultrasound Images Based on Deep Learning

OBJECTIVE

The goal of the work described here was to construct a deep learning-based intelligent diagnostic model for ophthalmic ultrasound images to provide auxiliary analysis for the intelligent clinical diagnosis of posterior ocular segment diseases.

METHODS

The InceptionV3-Xception fusion model was established by using two pre-trained network models-InceptionV3 and Xception-in series to achieve multilevel feature extraction and fusion, and a classifier more suitable for the multiclassification recognition task of ophthalmic ultrasound images was designed to classify 3402 ophthalmic ultrasound images. The accuracy, macro-average precision, macro-average sensitivity, macro-average F1 value, subject working feature curves and area under the curve were used as model evaluation metrics, and the credibility of the model was assessed by testing the decision basis of the model using a gradient-weighted class activation mapping method.

RESULTS

The accuracy, precision, sensitivity and area under the subject working feature curve of the InceptionV3-Xception fusion model on the test set reached 0.9673, 0.9521, 0.9528 and 0.9988, respectively. The model decision basis was consistent with the clinical diagnosis basis of the ophthalmologist, which proves that the model has good reliability.

CONCLUSION

The deep learning-based ophthalmic ultrasound image intelligent diagnosis model can accurately screen and identify five posterior ocular segment diseases, which is beneficial to the intelligent development of ophthalmic clinical diagnosis.

Fine-Needle Aspiration Biopsy Evaluation-Oriented Thyroid Carcinoma Auxiliary Diagnosis

OBJECTIVE

Thyroid carcinoma is one of the most common diseases with an increasing incidence worldwide in recent years. In clinical diagnosis, medical practitioners normally take a preliminary thyroid nodule grading so that highly suspected thyroid nodules can be taken into the fine-needle aspiration (FNA) biopsy to evaluate the malignancy. However, subjective misinterpretations might lead to ambiguous risk stratification of thyroid nodules and unnecessary FNA biopsy.

METHODS

We propose a thyroid carcinoma auxiliary diagnosis method for fine-needle aspiration biopsy evaluation. Through integration of several deep learning models into a multibranch network for thyroid nodule risk stratification in the Thyroid Imaging Reporting and Data System (TIRADS) with pathological features and cascading of a discriminator, our proposed method provides an intelligent auxiliary diagnosis to assist medical practitioners in determining the necessity for further FNA.

DISCUSSION

Experimental results revealed that not only was the rate at which nodules are falsely diagnosed as malignant nodules effectively reduced, which avoids the unnecessary high cost and pain of aspiration biopsy, but also previously missing detected cases were identified with high possibility. By comparing the physicians' diagnosis alone with machine-assisted diagnosis, physicians' diagnostic performance improved with the aid of our proposed method, illustrating that our model can be very helpful in clinical practice.

CONCLUSION

Our proposed method might help medical practitioners avoid subjective interpretations and inter-observer variability. For patients, reliable diagnosis is provided and unnecessary painful diagnostics can be avoided. In other superficial organs such as metastatic lymph nodes and salivary gland tumors, the proposed method might also provide a reliable auxiliary diagnosis for risk stratification.

Segmentation of thyroid glands and nodules in ultrasound images using the improved U-Net architecture

BACKGROUND

Identifying thyroid nodules' boundaries is crucial for making an accurate clinical assessment. However, manual segmentation is time-consuming. This paper utilized U-Net and its improved methods to automatically segment thyroid nodules and glands.

METHODS

The 5822 ultrasound images used in the experiment came from two centers, 4658 images were used as the training dataset, and 1164 images were used as the independent mixed test dataset finally. Based on U-Net, deformable-pyramid split-attention residual U-Net (DSRU-Net) by introducing ResNeSt block, atrous spatial pyramid pooling, and deformable convolution v3 was proposed. This method combined context information and extracts features of interest better, and had advantages in segmenting nodules and glands of different shapes and sizes.

RESULTS

DSRU-Net obtained 85.8% mean Intersection over Union, 92.5% mean dice coefficient and 94.1% nodule dice coefficient, which were increased by 1.8%, 1.3% and 1.9% compared with U-Net.

CONCLUSIONS

Our method is more capable of identifying and segmenting glands and nodules than the original method, as shown by the results of correlational studies.

A study on the optimal condition of ground truth area for liver tumor detection in ultrasound images using deep learning

PURPOSE

In recent years, efforts to apply artificial intelligence (AI) to the medical field have been growing. In general, a vast amount of high-quality training data is necessary to make great AI. For tumor detection AI, annotation quality is important. In diagnosis and detection of tumors using ultrasound images, humans use not only the tumor area but also the surrounding information, such as the back echo of the tumor. Therefore, we investigated changes in detection accuracy when changing the size of the region of interest (ROI, ground truth area) relative to liver tumors in the training data for the detection AI.

METHODS

We defined D/L as the ratio of the maximum diameter (D) of the liver tumor to the ROI size (L). We created training data by changing the D/L value, and performed learning and testing with YOLOv3.

RESULTS

Our results showed that the detection accuracy was highest when the training data were created with a D/L ratio between 0.8 and 1.0. In other words, it was found that the detection accuracy was improved by setting the ground true bounding box for detection AI training to be in contact with the tumor or slightly larger. We also found that when the D/L ratio was distributed in the training data, the wider the distribution, the lower the detection accuracy.

CONCLUSIONS

Therefore, we recommend that the detector be trained with the D/L value close to a certain value between 0.8 and 1.0 for liver tumor detection from ultrasound images.

A hybrid attentional guidance network for tumors segmentation of breast ultrasound images

PURPOSE

In recent years, breast cancer has become the greatest threat to women. There are many studies dedicated to the precise segmentation of breast tumors, which is indispensable in computer-aided diagnosis. Deep neural networks have achieved accurate segmentation of images. However, convolutional layers are biased to extract local features and tend to lose global and location information as the network deepens, which leads to a decrease in breast tumors segmentation accuracy. For this reason, we propose a hybrid attention-guided network (HAG-Net). We believe that this method will improve the detection rate and segmentation of tumors in breast ultrasound images.

METHODS

The method is equipped with multi-scale guidance block (MSG) for guiding the extraction of low-resolution location information. Short multi-head self-attention (S-MHSA) and convolutional block attention module are used to capture global features and long-range dependencies. Finally, the segmentation results are obtained by fusing multi-scale contextual information.

RESULTS

We compare with 7 state-of-the-art methods on two publicly available datasets through five random fivefold cross-validations. The highest dice coefficient, Jaccard Index and detect rate ([Formula: see text]%, [Formula: see text]%, [Formula: see text]% and [Formula: see text]%, [Formula: see text]%, [Formula: see text]%, separately) obtained on two publicly available datasets(BUSI and OASUBD), prove the superiority of our method.

CONCLUSION

HAG-Net can better utilize multi-resolution features to localize the breast tumors. Demonstrating excellent generalizability and applicability for breast tumors segmentation compare to other state-of-the-art methods.

Ultrasound Image-Based Deep Features and Radiomics for the Discrimination of Small Fat-Poor Angiomyolipoma and Small Renal Cell Carcinoma

We evaluated the performance of ultrasound image-based deep features and radiomics for differentiating small fat-poor angiomyolipoma (sfp-AML) from small renal cell carcinoma (SRCC). This retrospective study included 194 patients with pathologically proven small renal masses (diameter ≤4 cm; 67 in the sfp-AML group and 127 in the SRCC group). We obtained 206 and 364 images from the sfp-AML and SRCC groups with experienced radiologist identification, respectively. We extracted 4024 deep features from the autoencoder neural network and 1497 radiomics features from the Pyradiomics toolbox; the latter included first-order, shape, high-order, Laplacian of Gaussian and Wavelet features. All subjects were allocated to the training and testing sets with a ratio of 3:1 using stratified sampling. The least absolute shrinkage and selection operator (LASSO) regression model was applied to select the most diagnostic features. Support vector machine (SVM) was adopted as the discriminative classifier. An optimal feature subset including 45 deep and 7 radiomics features was screened by the LASSO model. The SVM classifier achieved good performance in discriminating between sfp-AMLs and SRCCs, with areas under the curve (AUCs) of 0.96 and 0.85 in the training and testing sets, respectively. The classifier built using deep and radiomics features can accurately differentiate sfp-AMLs from SRCCs on ultrasound imaging.

Ultrasonographic pathological grading of prostate cancer using automatic region-based Gleason grading network

The Gleason scoring system is a reliable method for quantifying the aggressiveness of prostate cancer, which provides an important reference value for clinical assessment on therapeutic strategies. However, to the best of our knowledge, no study has been done on the pathological grading of prostate cancer from single ultrasound images. In this work, a novel Automatic Region-based Gleason Grading (ARGG) network for prostate cancer based on deep learning is proposed. ARGG consists of two stages: (1) a region labeling object detection (RLOD) network is designed to label the prostate cancer lesion region; (2) a Gleason grading network (GNet) is proposed for pathological grading of prostate ultrasound images. In RLOD, a new feature fusion structure Skip-connected Feature Pyramid Network (CFPN) is proposed as an auxiliary branch for extracting features and enhancing the fusion of high-level features and low-level features, which helps to detect the small lesion and extract the image detail information. In GNet, we designed a synchronized pulse enhancement module (SPEM) based on pulse-coupled neural networks for enhancing the results of RLOD detection and used as training samples, and then fed the enhanced results and the original ones into the channel attention classification network (CACN), which introduces an attention mechanism to benefit the prediction of cancer grading. Experimental performance on the dataset of prostate ultrasound images collected from hospitals shows that the proposed Gleason grading model outperforms the manual diagnosis by physicians with a precision of 0.830. In addition, we have evaluated the lesions detection performance of RLOD, which achieves a mean Dice metric of 0.815.

Automated measurement of total kidney volume from 3D ultrasound images of patients affected by polycystic kidney disease and comparison to MR measurements

PURPOSE

Total kidney volume (TKV) is the most important imaging biomarker for quantifying the severity of autosomal-dominant polycystic kidney disease (ADPKD). 3D ultrasound (US) can accurately measure kidney volume compared to 2D US; however, manual segmentation is tedious and requires expert annotators. We investigated a deep learning-based approach for automated segmentation of TKV from 3D US in ADPKD patients.

METHOD

We used axially acquired 3D US-kidney images in 22 ADPKD patients where each patient and each kidney were scanned three times, resulting in 132 scans that were manually segmented. We trained a convolutional neural network to segment the whole kidney and measure TKV. All patients were subsequently imaged with MRI for measurement comparison.

RESULTS

Our method automatically segmented polycystic kidneys in 3D US images obtaining an average Dice coefficient of 0.80 on the test dataset. The kidney volume measurement compared with linear regression coefficient and bias from human tracing were R² = 0.81, and - 4.42%, and between AI and reference standard were R² = 0.93, and - 4.12%, respectively. MRI and US measured kidney volumes had R² = 0.84 and a bias of 7.47%.

CONCLUSION

This is the first study applying deep learning to 3D US in ADPKD. Our method shows promising performance for auto-segmentation of kidneys using 3D US to measure TKV, close to human tracing and MRI measurement. This imaging and analysis method may be useful in a number of settings, including pediatric imaging, clinical studies, and longitudinal tracking of patient disease progression.

The Accuracy and Radiomics Feature Effects of Multiple U-net-Based Automatic Segmentation Models for Transvaginal Ultrasound Images of Cervical Cancer

Ultrasound (US) imaging has been recognized and widely used as a screening and diagnostic imaging modality for cervical cancer all over the world. However, few studies have investigated the U-net-based automatic segmentation models for cervical cancer on US images and investigated the effects of automatic segmentations on radiomics features. A total of 1102 transvaginal US images from 796 cervical cancer patients were collected and randomly divided into training (800), validation (100) and test sets (202), respectively, in this study. Four U-net models (U-net, U-net with ResNet, context encoder network (CE-net), and Attention U-net) were adapted to segment the target of cervical cancer automatically on these US images. Radiomics features were extracted and evaluated from both manually and automatically segmented area. The mean Dice similarity coefficient (DSC) of U-net, Attention U-net, CE-net, and U-net with ResNet were 0.88, 0.89, 0.88, and 0.90, respectively. The average Pearson coefficients for the evaluation of the reliability of US image-based radiomics were 0.94, 0.96, 0.94, and 0.95 for U-net, U-net with ResNet, Attention U-net, and CE-net, respectively, in their comparison with manual segmentation. The reproducibility of the radiomics parameters evaluated by intraclass correlation coefficients (ICC) showed robustness of automatic segmentation with an average ICC coefficient of 0.99. In conclusion, high accuracy of U-net-based automatic segmentations was achieved in delineating the target area of cervical cancer US images. It is feasible and reliable for further radiomics studies with features extracted from automatic segmented target areas.

W-Net: Dense and diagnostic semantic segmentation of subcutaneous and breast tissue in ultrasound images by incorporating ultrasound RF waveform data

We study the use of raw ultrasound waveforms, often referred to as the "Radio Frequency" (RF) data, for the semantic segmentation of ultrasound scans to carry out dense and diagnostic labeling. We present W-Net, a novel Convolution Neural Network (CNN) framework that employs the raw ultrasound waveforms in addition to the grey ultrasound image to semantically segment and label tissues for anatomical, pathological, or other diagnostic purposes. To the best of our knowledge, this is also the first deep-learning or CNN approach for segmentation that analyzes ultrasound raw RF data along with the grey image. We chose subcutaneous tissue (SubQ) segmentation as our initial clinical goal for dense segmentation since it has diverse intermixed tissues, is challenging to segment, and is an underrepresented research area. SubQ potential applications include plastic surgery, adipose stem-cell harvesting, lymphatic monitoring, and possibly detection/treatment of certain types of tumors. Unlike prior work, we seek to label every pixel in the image, without the use of a background class. A custom dataset consisting of hand-labeled images by an expert clinician and trainees are used for the experimentation, currently labeled into the following categories: skin, fat, fat fascia/stroma, muscle, and muscle fascia. We compared W-Net and attention variant of W-Net (AW-Net) with U-Net and Attention U-Net (AU-Net). Our novel W-Net's RF-Waveform encoding architecture outperformed regular U-Net and AU-Net, achieving the best mIoU accuracy (averaged across all tissue classes). We study the impact of RF data on dense labeling of the SubQ region, which is followed by the analyses of the generalization capability of the networks to patients and analysis on the SubQ tissue classes, determining that fascia tissues, especially muscle fascia in particular, are the most difficult anatomic class to recognize for both humans and AI algorithms. We present diagnostic semantic segmentation, which is semantic segmentation carried out for the purposes of direct diagnostic pixel labeling, and apply it to breast tumor detection task on a publicly available dataset to segment pixels into malignant tumor, benign tumor, and background tissue class. Using the segmented image we diagnose the patient by classifying the breast lesion as either benign or malignant. We demonstrate the diagnostic capability of RF data with the use of W-Net, which achieves the best segmentation scores across all classes.

A Robust Breast ultrasound segmentation method under noisy annotations

BACKGROUND AND OBJECTIVE

A large-scale training data and accurate annotations are fundamental for current segmentation networks. However, the characteristic artifacts of ultrasound images always make the annotation task complicated, such as attenuation, speckle, shadows and signal dropout. Further complications arise as the contrast between the region of interest and background is often low. Without double-check from professionals, it is hard to guarantee that there is no noisy annotation in segmentation datasets. However, among the deep learning methods applied to ultrasound segmentation so far, no one can solve this problem.

METHOD

Given a dataset with poorly labeled masks, including a certain amount of noises, we propose an end-to-end noisy annotation tolerance network (NAT-Net). NAT-Net can detect noise by the proposed noise index (NI) and dynamically correct noisy annotations in the training stage. Simultaneously, noise index is used to correct the noise along with the output of the learning model. This method does not need any auxiliary clean datasets or prior knowledge of noise distributions, so it is more general, robust and easier to apply than the existing methods.

RESULTS

NAT-Net outperforms previous state-of-the-art methods on synthesized data with different noise ratio. For real-world dataset with more complex noise types, the IoU of NAT-Net is higher than that of state-of-art approaches by nearly 6%. Experimental results show that our method can also achieve good results compared with the existing methods for clean dataset.

CONCLUSION

The NAT-Net reduces manual interaction of data annotation, reduces dependence on medical personnel. After tumor segmentation, disease diagnosis efficiency is improved, which provides an auxiliary strategies for subsequent medical diagnosis systems based on ultrasound.

Shape constraint function for artery tracking in ultrasound images

Ultrasound guided regional anesthesia (UGRA) has emerged as a powerful technique for pain management in the operating theatre. It uses ultrasound imaging to visualize anatomical structures, the needle insertion and the delivery of the anesthetic around the targeted nerve block. Detection of the nerves is a difficult task, however, due to the poor quality of the ultrasound images. Recent developments in pattern recognition and machine learning have heightened the need for computer aided systems in many applications. This type of system can improve UGRA practice. In many imaging situations nerves are not salient in images. Generally, practitioners rely on the arteries as key anatomical structures to confirm the positions of the nerves, making artery tracking an important aspect for UGRA procedure. However, artery tracking in a noisy environment is a challenging problem, due to the instability of the features. This paper proposes a new method for real-time artery tracking in ultrasound images. It is based on shape information to correct tracker location errors. A new objective function is proposed, which defines an artery as an elliptical shape, enabling its robust fitting in a noisy environment. This approach is incorporated in two well-known tracking algorithms, and shows a systematic improvement over the original trackers. Evaluations were performed on 71 videos of different axillary nerve blocks. The results obtained demonstrated the validity of the proposed method.

[Ultrasonography of supra-aortic trunks]

Ultrasound is a resource that family doctors have first-hand and that we use more and more frequently, to the point of becoming part of our physical examination. It is an easily accessible, affordable, versatile and non-invasive diagnostic technique that uses ultrasound to define the anatomical structures of our body without radiation and is performed in real time, allowing a dynamic exploration. Despite all the above, vascular ultrasound and, specifically, the supra-aortic trunks ultrasound is not as widespread in our setting, despite its important role in the field of cardiovascular prevention, which is essential in primary care. For this reason, this article aims to carry out a brief-and-clear description of the technique with the aim of extending its use in daily practice.

Reliable Thyroid Carcinoma Detection with Real-Time Intelligent Analysis of Ultrasound Images

Thyroid carcinoma is one of the most common endocrine diseases globally, and the incidence has been on the rise in recent years. Ultrasound imaging is the primary clinical method for early thyroid nodule diagnosis. Regions of interest (ROIs) of nodules in ultrasound images are difficult to detect because of their irregular shape nand vague margins. Accurate real-time thyroid nodule detection can provide ROIs for subsequent nodule diagnosis automatically, avoid variabilities between the subjective interpretations and inter-observer effectively and alleviate the workloads of medical practitioners. The aim of this study was to present a reliable, real-time detection method based on the Faster R-CNN (region-based convolutional network) framework for accurate and fast detection of thyroid nodules in ultrasound images. Our study proposed a faster and more accurate thyroid nodule detection method based on the Faster R-CNN framework by adding three strategies: feature pyramid, spatial remapping and anchor-box redesign. Specifically, the network takes raw ultrasound images as inputs and generates boxes with positions and the possibilities that these boxes contain thyroid nodules. The proposed method could locate and detect target nodules accurately with a mean average precision of 92.79% with more than 9000 patient images. In addition, the detection rate has accelerated to >16 frames per second, four times faster than that of the initial network. Therefore, it can meet the requirements of clinical application. The performance of the fivefold cross-validation was also accurate and robust. The proposed automatic thyroid nodule detection method yields better performance in accuracy and detection speed, which indicates the potential value of our method in assisting clinical ultrasound image interpretation.

Evaluation of left ventricular diastolic function of patients with coronary heart disease by ultrasound images on bilateral filtering image noise reduction algorithm combined with electrocardiogram

OBJECTIVE

To explore the evaluation of left ventricular diastolic function (LVDF) in patients with coronary heart disease (CHD) using ultrasound images (UI) combined with electrocardiogram (ECG) on bilateral filtering image noise reduction algorithm (BFINRA).

METHODS

A BFINRA was constructed, and 60 subjects who were investigated were divided into a control group (CG) from June 2019 to November 2019 in Taizhou People's Hospital, a myocardial infarction group (MIG), and an angina pectoris group (APG). The patient's LVDF was examined by two-dimensional electrophoresis (2DE) and real-time three-dimensional echocardiography (RT-3DE) combined with ECG. The results showed BFINRA could improve UI quality.

RESULTS

Clinical data indicated there were no substantial differences in age, gender, and fasting blood glucose of all subjects. 2DE examination results showed the left ventricular end-diastolic volume (LVEDV), left ventricular end-systolic volume (LVESV), and early diastolic mitral blood flow velocity / early diastolic mitral annulus velocity (E/E') of MIG were much higher than CG (P<0.05), while the left ventricular ejection fraction (LVEF), E / late diastolic mitral blood flow velocity (E/A) and E' peak value were sharply decreased (P<0.05);LVESV and E/E' of APG were increased dramatically (P<0.05), while E peak, E/A and E' peak were decreased greatly. RT-3DE examination results indicated LVEDV and LVESV of MIG were considerably higher than CG (P<0.05), while LVEF and macrophage resistance factor (MRF) were enormously decreased (P<0.05);LVEDV and LVESV of APG were greatly increased (P<0.05). However, LVEF and MRF were not changed significantly (P>0.05). LVEDV had a remarkable difference (P<0.05), but LVESV and LVEF had no obvious differences (P>0.05). The electrocardiogram results illustrated the increase in QT dispersion (QTd) of MIG and APG was statistically significant (P<0.05) compared with CG, while the negative increase of P-wave terminal force in lead V1 (PTFV1) also had a statistical significance (P<0.05). Correlation analysis revealed that MRF and PTFV1 had positive correlation, while MRF and QTd showed a negative correlation.

CONCLUSION

The combination of UI and ECG could better assess LVDF in CHD patients.

An ensemble of deep neural networks for kidney ultrasound image classification

BACKGROUND AND OBJECTIVE

Chronic kidney disease is a worldwide health issue which includes not only kidney failure but also complications of reduced kidney functionality. Cyst formation, nephrolithiasis or kidney stone, and renal cell carcinoma or kidney tumor are the common kidney disorders which affects the functionality of kidneys. These disorders are typically asymptomatic, therefore early and automatic diagnosis of kidney disorders are required to avoid serious complications.

METHODS

This paper proposes an automatic classification of B-mode kidney ultrasound images based on the ensemble of deep neural networks (DNNs) using transfer learning. The ultrasound images are usually affected by speckle noise and quality selection in the ultrasound image is based on perception-based image quality evaluator score. Three variant datasets are given to the pre-trained DNN models for feature extraction followed by support vector machine for classification. The ensembling of different pre-trained DNNs like ResNet-101, ShuffleNet, and MobileNet-v2 are combined and final predictions are done by using the majority voting technique. By combining the predictions from multiple DNNs the ensemble model shows better classification performance than the individual models. The presented method proved its superiority when compared to the conventional and DNN based classification methods. The developed ensemble model classifies the kidney ultrasound images into four classes, namely, normal, cyst, stone, and tumor.

RESULTS

To highlight effectiveness of the proposed approach, the ensemble based approach is compared with the existing state-of-the-art methods and tested in the variants of ultrasound images like in quality and noisy conditions. The presented method resulted in maximum classification accuracy of 96.54% in testing with quality images and 95.58% in testing with noisy images. The performance of the presented approach is evaluated based on accuracy, sensitivity, and selectivity.

CONCLUSIONS

From the experimental analysis, it is clear that the ensemble of DNNs classifies the majority of images correctly and results in maximum classification accuracy as compared to the existing methods. This automatic classification approach is a supporting tool for the radiologists and nephrologists for precise diagnosis of kidney diseases.

Segmentation of the Common Carotid Intima-Media Complex in Ultrasound Images Using 2-D Continuous Max-Flow and Stacked Sparse Auto-encoder

The intima-media thickness (IMT) of a common carotid artery in an ultrasound image is considered an important indicator of the onset of atherosclerosis. However, it is challenging to segment the intima-media complex (IMC) directly in ultrasound images. This study proposes a fully automatic method to segment the IMC on longitudinal B-mode ultrasound images. Our method consists of two stages: (i) extraction of the region of interest with a continuous max-flow algorithm and region-of-interest reconstruction using a stacked sparse auto-encoder model, and (ii) IMC segmentation using a trained random forest classifier. The proposed method has been tested on three databases from three different imaging centres, comprising a total of 228 ultrasound images of the common carotid artery. On the three databases, our method yields mean absolute errors of 0.028 ± 0.016 mm, 0.579 ± 0.288 pixel and 0.582 ± 0.341 pixel; polyline distance (PD) measures of 0.026 ± 0.017 mm, 0.657 ± 0.275 pixel and 0.731 ± 0:282 pixel; Hausdorff distance measures of 0.249 ± 0.101 mm, 4.760 ± 1.085 pixels and 5.825 ± 2.059 pixels; and correlation coefficients of 95.19%, 93.79%, and 98.96%, respectively. These results indicate that the proposed method performs well in segmentation of the IMC and measurement of the IMT.

Nodule Localization in Thyroid Ultrasound Images with a Joint-Training Convolutional Neural Network

The accurate localization of nodules in ultrasound images can convey crucial information to support a reliable diagnosis. However, this is usually challenging due to low contrast and image artifacts, especially in thyroid ultrasound images where nodules are relatively small in most cases. To address these problems, in this paper, we propose a joint-training convolutional neural network (CNN) for thyroid nodule localization in ultrasound images. Considering the advantage of the faster region-based CNN (Faster R-CNN) in detecting natural targets, we adopt it as the basic framework. To boost the representative power and noise suppression capability of the network, the attention mechanism module is embedded for adaptive feature refinement along the channel and spatial dimensions. Furthermore, in the training process, we annotate the training set in a novel way, called joint-training annotation, by exploiting the fake foreground (FFG) area around the nodule as a spatial prior constraint to improve the sensitivity to small nodules. Ablation experiments are conducted to verify the effectiveness of our proposed method. The experimental results show that our method outperforms others by a mean average precision (mAP) of 0.93 and achieves an intersection over union (IoU) of 0.9, indicating that the localization results agree well with the ground truth. Furthermore, extended experiments on breast nodule datasets are also conducted to verify the generalizability of the proposed approach. Above all, the proposed algorithm is of considerable significance for accurate thyroid nodule localization in ultrasound images and can be generalized to other types of nodules, thereby providing trustworthy assistance for clinical diagnosis.

Segmentation of finger tendon and synovial sheath in ultrasound image using deep convolutional neural network

BACKGROUND

Trigger finger is a common hand disease, which is caused by a mismatch in diameter between the tendon and the pulley. Ultrasound images are typically used to diagnose this disease, which are also used to guide surgical treatment. However, background noise and unclear tissue boundaries in the images increase the difficulty of the process. To overcome these problems, a computer-aided tool for the identification of finger tissue is needed.

RESULTS

Two datasets were used for evaluation: one comprised different cases of individual images and another consisting of eight groups of continuous images. Regarding result similarity and contour smoothness, our proposed deeply supervised dilated fully convolutional DenseNet (D2FC-DN) is better than ATASM (the state-of-art segmentation method) and representative CNN methods. As a practical application, our proposed method can be used to build a tendon and synovial sheath model that can be used in a training system for ultrasound-guided trigger finger surgery.

CONCLUSION

We proposed a D2FC-DN for finger tendon and synovial sheath segmentation in ultrasound images. The segmentation results were remarkably accurate for two datasets. It can be applied to assist the diagnosis of trigger finger by highlighting the tissues and generate models for surgical training systems in the future.

METHODS

We propose a novel finger tendon segmentation method for use with ultrasound images that can also be used for synovial sheath segmentation that yields a more complete description for analysis. In this study, a hybrid of effective convolutional neural network techniques are applied, resulting in a deeply supervised dilated fully convolutional DenseNet (D2FC-DN), which displayed excellent segmentation performance on the tendon and synovial sheath.

Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks

It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys automatically. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images. These features are used as input to learn kidney boundary distance maps using a boundary distance regression network and the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixelwise classification network in an end-to-end learning fashion. We also adopted a data-augmentation method based on kidney shape registration to generate enriched training data from a small number of US images with manually segmented kidney labels. Experimental results have demonstrated that our method could automatically segment the kidney with promising performance, significantly better than deep learning-based pixel classification networks.

Evaluating the performance of convolutional neural networks with direct acyclic graph architectures in automatic segmentation of breast lesion in US images

Background

Outlining lesion contours in Ultra Sound (US) breast images is an important step in breast cancer diagnosis. Malignant lesions infiltrate the surrounding tissue, generating irregular contours, with spiculation and angulated margins, whereas benign lesions produce contours with a smooth outline and elliptical shape. In breast imaging, the majority of the existing publications in the literature focus on using Convolutional Neural Networks (CNNs) for segmentation and classification of lesions in mammographic images. In this study our main objective is to assess the ability of CNNs in detecting contour irregularities in breast lesions in US images.

Methods

In this study we compare the performance of two CNNs with Direct Acyclic Graph (DAG) architecture and one CNN with a series architecture for breast lesion segmentation in US images. DAG and series architectures are both feedforward networks. The difference is that a DAG architecture could have more than one path between the first layer and end layer, whereas a series architecture has only one path from the beginning layer to the end layer. The CNN architectures were evaluated with two datasets.

Results

With the more complex DAG architecture, the following mean values were obtained for the metrics used to evaluate the segmented contours: global accuracy: 0.956; IOU: 0.876; F measure: 68.77%; Dice coefficient: 0.892.

Conclusion

The CNN DAG architecture shows the best metric values used for quantitatively evaluating the segmented contours compared with the gold-standard contours. The segmented contours obtained with this architecture also have more details and irregularities, like the gold-standard contours.

Computer-aided diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data by integrating texture image features and deep transfer learning image features

INTRODUCTION

Anatomic characteristics of kidneys derived from ultrasound images are potential biomarkers of children with congenital abnormalities of the kidney and urinary tract (CAKUT), but current methods are limited by the lack of automated processes that accurately classify diseased and normal kidneys.

OBJECTIVE

The objective of the study was to evaluate the diagnostic performance of deep transfer learning techniques to classify kidneys of normal children and those with CAKUT.

STUDY DESIGN

A transfer learning method was developed to extract features of kidneys from ultrasound images obtained during routine clinical care of 50 children with CAKUT and 50 controls. To classify diseased and normal kidneys, support vector machine classifiers were built on the extracted features using (1) transfer learning imaging features from a pretrained deep learning model, (2) conventional imaging features, and (3) their combination. These classifiers were compared, and their diagnosis performance was measured using area under the receiver operating characteristic curve (AUC), accuracy, specificity, and sensitivity.

RESULTS

The AUC for classifiers built on the combination features were 0.92, 0.88, and 0.92 for discriminating the left, right, and bilateral abnormal kidney scans from controls with classification rates of 84%, 81%, and 87%; specificity of 84%, 74%, and 88%; and sensitivity of 85%, 88%, and 86%, respectively. These classifiers performed better than classifiers built on either the transfer learning features or the conventional features alone (p < 0.001).

DISCUSSION

The present study validated transfer learning techniques for imaging feature extraction of ultrasound images to build classifiers for distinguishing children with CAKUT from controls. The experiments have demonstrated that the classifiers built on the transfer learning features and conventional image features could distinguish abnormal kidney images from controls with AUCs greater than 0.88, indicating that classification of ultrasound kidney scans has a great potential to aid kidney disease diagnosis. A limitation of the present study is the moderate number of patients that contributed data to the transfer learning approach.

CONCLUSIONS

The combination of transfer learning and conventional imaging features yielded the best classification performance for distinguishing children with CAKUT from controls based on ultrasound images of kidneys.

Adaptive median binary patterns for fully automatic nerves tracking in ultrasound images

BACKGROUND AND OBJECTIVE

In the last decade, Ultrasound-Guided Regional Anesthesia (UGRA) gained importance in surgical procedures and pain management, due to its ability to perform target delivery of local anesthetics under direct sonographic visualization. However, practicing UGRA can be challenging, since it requires high skilled and experienced operator. Among the difficult task that the operator can face, is the tracking of the nerve structure in ultrasound images. Tracking task in US images is very challenging due to the noise and other artifacts.

METHODS

In this paper, we introduce a new and robust tracking technique by using Adaptive Median Binary Pattern(AMBP) as texture feature for tracking algorithms (particle filter, mean-shift and Kanade-Lucas-Tomasi(KLT)). Moreover, we propose to incorporate Kalman filter as prediction and correction steps for the tracking algorithms, in order to enhance the accuracy, computational cost and handle target disappearance.

RESULTS

The proposed method have been applied on real data and evaluated in different situations. The obtained results show that tracking with AMBP features outperforms other descriptors and achieved best performance with 95% accuracy.

CONCLUSIONS

This paper presents the first fully automatic nerve tracking method in Ultrasound images. AMBP features outperforms other descriptors in all situations such as noisy and filtered images.

Enhanced Wiener filter for ultrasound image restoration

BACKGROUND AND OBJECTIVE

Speckle phenomenon strongly affects UltraSound (US) images. In the last years, several efforts have been done in order to provide an effective denoising methodology. Although good results have been achieved in terms of noise reduction effectiveness, most of the proposed approaches are not characterized by low computational burden and require the supervision of an external operator for tuning the input parameters.

METHODS

Within this manuscript, a novel approach is investigated, based on Wiener filter. Working in the frequency domain, it is characterized by high computational efficiency. With respect to classical Wiener filter, the proposed Enhanced Wiener filter is able to locally adapt itself by tuning its kernel in order to combine edges and details preservation with effective noise reduction. This characteristic is achieved by implementing a Local Gaussian Markov Random Field for modeling the image. Due to its intrinsic characteristics, the computational burden of the algorithm is sensibly low compared to other widely adopted filters and the parameter tuning effort is minimal, being well suited for quasi real time applications.

RESULTS

The approach has been tested on both simulated and real datasets, showing interesting performances compared to other state of art methods.

CONCLUSIONS

A novel denoising method for UltraSound images is proposed. The approach is able to combine low computational burden with interesting denoising performances and details preservation.

Automatic segmentation of tumors in B-Mode breast ultrasound images using information gain based neutrosophic clustering

BACKGROUND

Since breast ultrasound images are of low contrast, contain inherent noise and shadowing effect due to its imaging process, segmentation of breast tumors depicting ultrasound image is a challenging task. Thus, a robust breast ultrasound image segmentation technique is inevitable.

OBJECTIVE

To develop an automatic lesion segmentation technique for breast ultrasound images.

METHODS

First, the technique automatically detects the suspicious tumor region of interest and discards the unwanted complex background regions. Next, based on the concept of information gain, the technique applies an existing neutrosophic clustering method to the detected region to segment the desired tumor area. The proposed technique computes information gain values from the local neighbourhood of each pixel, which is further used to update the membership values and the cluster centers for the neutrosophic clustering process. Integrating the concept of entropy and neutrosophic logic features into the technique enabled to generate better segmentation results.

RESULTS

Results of proposed method were compared both qualitatively and quantitatively with fuzzy c-means, neutrosophic c-means and neutrosophic ℓ-means clustering methods. It was observed that the proposed method outperformed the other three methods and yielded the best Mean (TP: 94.72, FP: 5.85, SI: 93.75, HD: 8.2, AMED: 2.4) and Standard deviation (TP: 3.2, FP: 3.7, SI: 3.8, HD: 2.6, AMED: 1.3) values for different quality metrics on the current set of breast ultrasound images.

CONCLUSION

Study demonstrated that the proposed technique is robust to the shadowing effect and produces more accurate segmentation of the tumor region, which is very similar to that visually segmented by Radiologist.

Ultrasound Image Despeckling Based on Statistical Similarity

Ultrasound images are affected by the speckle phenomenon, a multiplicative noise that degrades image quality. Several methods for denoising have been proposed in recent years, based on different approaches. The so-called non-local mean is considered the state-of-the-art method; the idea is to find similar patches across the image and exploit them to regularize the image. The method proposed here is in the non-local family, although instead of partitioning the target image in patches, it works pixelwise. The similarity between pixels is evaluated by analyzing their statistical behavior, in particular, by measuring the Kolmogorov-Smirnov distance between their distributions. To make this possible, a stack of acquired images is required. The proposed method has been tested on both simulated and real data sets and compared with other widely adopted techniques. Performance is interesting, with quality parameters and visual inspection confirming such findings.

Speckle noise removal applied to ultrasound image of carotid artery based on total least squares model

An ultrasonic image speckle noise removal method by using total least squares model is proposed and applied onto images of cardiovascular structures such as the carotid artery. On the basis of the least squares principle, the related principle of minimum square method is applied to cardiac ultrasound image speckle noise removal process to establish the model of total least squares, orthogonal projection transformation processing is utilized for the output of the model, and the denoising processing for the cardiac ultrasound image speckle noise is realized. Experimental results show that the improved algorithm can greatly improve the resolution of the image, and meet the needs of clinical medical diagnosis and treatment of the cardiovascular system for the head and neck. Furthermore, the success in imaging of carotid arteries has strong implications in neurological complications such as stroke.

Influence of ultrasound speckle tracking strategies for motion and strain estimation

Speckle Tracking is one of the most prominent techniques used to estimate the regional movement of the heart based on ultrasound acquisitions. Many different approaches have been proposed, proving their suitability to obtain quantitative and qualitative information regarding myocardial deformation, motion and function assessment. New proposals to improve the basic algorithm usually focus on one of these three steps: (1) the similarity measure between images and the speckle model; (2) the transformation model, i.e. the type of motion considered between images; (3) the optimization strategies, such as the use of different optimization techniques in the transformation step or the inclusion of structural information. While many contributions have shown their good performance independently, it is not always clear how they perform when integrated in a whole pipeline. Every step will have a degree of influence over the following and hence over the final result. Thus, a Speckle Tracking pipeline must be analyzed as a whole when developing novel methods, since improvements in a particular step might be undermined by the choices taken in further steps. This work presents two main contributions: (1) We provide a complete analysis of the influence of the different steps in a Speckle Tracking pipeline over the motion and strain estimation accuracy. (2) The study proposes a methodology for the analysis of Speckle Tracking systems specifically designed to provide an easy and systematic way to include other strategies. We close the analysis with some conclusions and recommendations that can be used as an orientation of the degree of influence of the models for speckle, the transformation models, interpolation schemes and optimization strategies over the estimation of motion features. They can be further use to evaluate and design new strategy into a Speckle Tracking system.

Evaluation of statin therapy on endothelial function in hypercholesterolemic rabbits by automatic measurement of arterial wall movement using ultrasound images

The aim of this study was to evaluate arterial endothelial function, assessed as acetylcholine-mediated dilation (AMD), in a hypercholesterolemic atherosclerotic rabbit model to investigate the effects of atorvastatin in the atherosclerotic process, using a new computerized analysis model and ultrasound images. Twenty-seven rabbits were fed a high-cholesterol (2%) diet for 6 wk and then divided into three groups for an additional 9 wk: Group A received regular chow food, group B received a 2% cholesterol-rich diet plus atorvastatin drug, and group C received regular chow food plus atorvastatin. Ultrasound examinations of endothelial function of the rabbit abdominal aorta artery were performed immediately after the 6 weeks (0 wk) and then 3, 6 and 9 wk after that. For off-line analysis, a computerized analysis method for evaluating instantaneous changes in the wall of the rabbit abdominal aorta was used. As parameters of improvement resulting from treatment, endothelium-dependent acetylcholine-induced dilation and endothelium-independent nitroglycerin-induced dilation were evaluated in treated rabbits. Differences among groups were tested using analysis of variance. On histopathology, intima-media thickness decreased after treatment in all groups. There were no significant differences in arterial diameter and blood velocity changes among treated rabbits at 0, 3, 6 and 9 wk of treatment in all groups, except in end-diastolic velocity, radial strain percentage, pulse index and resistance index in group C. In group A, AMD did not significantly improve after 3, 6 and 9 wk, as compared with 0 wk. Atorvastatin treatment significantly increased AMD (18%) at 3 wk in group B, compared with week 0. AMD significantly increased after 3 (26%), 6 (124%) and 9 (182%) wk in group C, compared with 0 wk. It is concluded that the new automatic method enables accurate and repeated evaluation of endothelial function during the progression and regression of atherosclerosis. Also, the results obtained in this study indicate that short-term administration of atorvastatin can improve endothelial function in cholesterol-fed rabbits.

Phase-based probabilistic active contour for nerve detection in ultrasound images for regional anesthesia

Ultrasound guided regional anesthesia (UGRA) is steadily growing in popularity, owing to advances in ultrasound imaging technology and the advantages that this technique presents for safety and efficiency. The aim of this work is to assist anaesthetists during the UGRA procedure by automatically detecting the nerve blocks in the ultrasound images. The main disadvantage of ultrasound images is the poor quality of the images, which are also affected by the speckle noise. Moreover, the nerve structure is not salient amid the other tissues, which makes its detection a challenging problem. In this paper we propose a new method to tackle the problem of nerve zone detection in ultrasound images. The method consists in a combination of three approaches: probabilistic, edge phase information and active contours. The gradient vector flow (GVF) is adopted as an edge-based active contour. The phase analysis of the monogenic signal is used to provide reliable edges for the GVF. Then, a learned probabilistic model reduces the false positives and increases the likelihood energy term of the target region. It yields a new external force field that attracts the active contour toward the desired region of interest. The proposed scheme has been applied to sciatic nerve regions. The qualitative and quantitative evaluations show a high accuracy and a significant improvement in performance.

Region and boundary feature estimation on ultrasound images using moment invariants

In ultrasound images, tissues are characterized by their speckle texture. Moment-based techniques have proven their ability to capture texture features. However, in ultrasound images, the speckle size increases with the distance from the probe and in some cases the speckle has a concentric texture arrangement. We propose to use moment invariants with respect to image scale and rotation to capture the texture in such cases. Results on synthetic data show that moment invariants are able to characterize the texture but also that some moment orders are sensitive to regions and, moreover, some are sensitive to the boundaries between two different textures. This behavior seems to be very interesting to be used within some segmentation scheme dealing with a combination of regional and boundary information. In this paper we will try to prove the usability of this complementary information in a min-cut/max-flow graph cut scheme.

Segmentation of ultrasound images of thyroid nodule for assisting fine needle aspiration cytology

The incidence of thyroid nodule is very high and generally increases with the age. Thyroid nodule may presage the emergence of thyroid cancer. Most thyroid nodules are asymptomatic which makes thyroid cancer different from other cancers. The thyroid nodule can be completely cured if detected early. Therefore, it is necessary to correctly classify the thyroid nodule to be benign or malignant. Fine needle aspiration cytology is a recognized early diagnosis method of thyroid nodule. There are still some limitations in the fine needle aspiration cytology, such as the difficulty in location and the insufficient cytology specimen. The accuracy of ultrasound diagnosis of thyroid nodule improves constantly, and it has become the first choice for auxiliary examination of thyroid nodular disease. If we could combine medical imaging technology and fine needle aspiration cytology, the diagnostic rate of thyroid nodule would be improved significantly.

The properties of ultrasound, such as echo, shadow, and reflection, will degrade the image quality, which makes it difficult to recognize the edges for physicians. Image segmentation technique based on graph theory has become a research hotspot at present. Normalized cut (Ncut) is a representative one, whose biggest advantage is not prone to small region segmentation but suitable for segmentation of feature parts of medical image. However, how to solve the normalized cut has become a problem, which needs large memory capacity and heavy calculation of weight matrix. It always generates over segmentation or less segmentation which leads to inaccurate in the segmentation.

The speckle noise produced in the formation process of B ultrasound image of thyroid tumor makes the quality of the image deteriorate. In the light of this characteristic, we combine the anisotropic diffusion model with the normalized cut in this paper. After the enhancement of anisotropic diffusion model, it removes the noise in the B ultrasound image while preserves the important edges and local details. This reduces the amount of computation in constructing the weight matrix of the improved normalized cut and improves the accuracy of the final segmentation results. The feasibility of the method is proved by the experimental results.