Ultrasound image segmentation: a survey

Evaluation of an improved tool for non-invasive prediction of neonatal respiratory morbidity based on fully automated fetal lung ultrasound analysis

The objective of this study was to evaluate the performance of a new version of quantusFLM®, a software tool for prediction of neonatal respiratory morbidity (NRM) by ultrasound, which incorporates a fully automated fetal lung delineation based on Deep Learning techniques. A set of 790 fetal lung ultrasound images obtained at 24 + 0–38 + 6 weeks’ gestation was evaluated. Perinatal outcomes and the occurrence of NRM were recorded. quantusFLM® version 3.0 was applied to all images to automatically delineate the fetal lung and predict NRM risk. The test was compared with the same technology but using a manual delineation of the fetal lung, and with a scenario where only gestational age was available. The software predicted NRM with a sensitivity, specificity, and positive and negative predictive value of 71.0%, 94.7%, 67.9%, and 95.4%, respectively, with an accuracy of 91.5%. The accuracy for predicting NRM obtained with the same texture analysis but using a manual delineation of the lung was 90.3%, and using only gestational age was 75.6%. To sum up, automated and non-invasive software predicted NRM with a performance similar to that reported for tests based on amniotic fluid analysis and much greater than that of gestational age alone.

A dataset of laryngeal endoscopic images with comparative study on convolution neural network-based semantic segmentation

PURPOSE

Automated segmentation of anatomical structures in medical image analysis is a prerequisite for autonomous diagnosis as well as various computer- and robot-aided interventions. Recent methods based on deep convolutional neural networks (CNN) have outperformed former heuristic methods. However, those methods were primarily evaluated on rigid, real-world environments. In this study, existing segmentation methods were evaluated for their use on a new dataset of transoral endoscopic exploration.

METHODS

Four machine learning-based methods SegNet, UNet, ENet and ErfNet were trained with supervision on a novel 7-class dataset of the human larynx. The dataset contains 536 manually segmented images from two patients during laser incisions. The Intersection-over-Union (IoU) evaluation metric was used to measure the accuracy of each method. Data augmentation and network ensembling were employed to increase segmentation accuracy. Stochastic inference was used to show uncertainties of the individual models. Patient-to-patient transfer was investigated using patient-specific fine-tuning.

RESULTS

In this study, a weighted average ensemble network of UNet and ErfNet was best suited for the segmentation of laryngeal soft tissue with a mean IoU of 84.7%. The highest efficiency was achieved by ENet with a mean inference time of 9.22 ms per image. It is shown that 10 additional images from a new patient are sufficient for patient-specific fine-tuning.

CONCLUSION

CNN-based methods for semantic segmentation are applicable to endoscopic images of laryngeal soft tissue. The segmentation can be used for active constraints or to monitor morphological changes and autonomously detect pathologies. Further improvements could be achieved by using a larger dataset or training the models in a self-supervised manner on additional unlabeled data.

Automatic tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model

PURPOSE

Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images.

METHODS

A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570 BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method.

RESULTS

Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170 BUS images show that the proposed method had a Dice Similarity coefficient of 88.97 ± 10.01%, a Hausdorff distance (HD) of 35.54 ± 29.70 pixels, and a mean absolute deviation (MAD) of 7.67 ± 6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results.

CONCLUSIONS

The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications.

MITT: Medical Image Tracking Toolbox

Over the years, medical image tracking has gained considerable attention from both medical and research communities due to its widespread utility in a multitude of clinical applications, from functional assessment during diagnosis and therapy planning to structure tracking or image fusion during image-guided interventions. Despite the ever-increasing number of image tracking methods available, most still consist of independent implementations with specific target applications, lacking the versatility to deal with distinct end-goals without the need for methodological tailoring and/or exhaustive tuning of numerous parameters. With this in mind, we have developed the medical image tracking toolbox (MITT)-a software package designed to ease customization of image tracking solutions in the medical field. While its workflow principles make it suitable to work with 2-D or 3-D image sequences, its modules offer versatility to set up computationally efficient tracking solutions, even for users with limited programming skills. MITT is implemented in both C/C++ and MATLAB, including several variants of an object-based image tracking algorithm and allowing to track multiple types of objects (i.e., contours, multi-contours, surfaces, and multi-surfaces) with several customization features. In this paper, the toolbox is presented, its features discussed, and illustrative examples of its usage in the cardiology field provided, demonstrating its versatility, simplicity, and time efficiency.

Diagnostic ultrasound assessment of temporomandibular joints: a systematic review and meta-analysis

OBJECTIVES:

The purpose of this systematic review was to determine the diagnostic capability of ultrasound to assess TMJ alterations as disc displacement (DD), joint effusion (JE) and condylar changes (CC) using 3D imaging modalities as reference standard.

METHODS:

Studies were gathered by searching several electronic databases and partial grey literature up to January eighth, 2018 without restrictions of language and time. The risk of bias was evaluated using the second version of Quality Assessment Tool for Diagnostic of Accuracy Studies-2 (QUADAS-2). The grading of Recommendation, Assessment, Development and Evaluation (GRADEpro system) instrument was applied to assess the level of evidence across the studies.

RESULTS:

After applying the eligibility criteria, 28 studies were identified and synthesized. All studies were methodologically acceptable presenting low applicability concerns, although none of them fulfilled all QUADAS-2 criteria. The quantitative analysis included 22 studies, 2829 joints in total. The quality of the evidence evaluated by GRADE system suggested moderate confidence in estimating the outcomes.

CONCLUSION:

This systematic review demonstrated the ultrasound has acceptable capability to screen for DD and JE in TMD patients. For screening of condylar changes, ultrasound needs further studies using CT or CBCT as reference standard to support its use. More advanced imaging such as MRI can thereafter be used to confirm the diagnosis if deemed necessary.

A new nonparametric statistical approach to detect lumen and Media-Adventitia borders in intravascular ultrasound frames

Intravascular ultrasound (IVUS) imaging is widely known as a powerful interventional imaging modality for diagnosing atherosclerosis, and for treatment planning. In this regard, the detection of lumen and media-adventitia (MA) borders is considered to be a vital process. However, the manual detection of these two borders by the physician is cumbersome due to the large number of frames in a sequence. In addition, no approved universal automatic method has been presented so far due to the great diversity in the appearance of the coronary artery in the images acquired by different IVUS systems. To this end, the present study aimed to provide a new border search theory on the radial profile, based upon the nonparametric statistical approach, and to develop a generic and fully automatic three-step process for extracting the lumen and MA borders in IVUS frames based on the proposed theory. Thereafter, the proposed theory and three-step process were evaluated on synthetic images, as well as on a test set of standard publicly available images, respectively. The results showed that our three-step process could segment the borders with ≥0.82 and with ≥0.75 Jaccard measure (JM) to manual borders in IVUS frames acquired by the 20 MHz and 40 MHz probes, respectively. Based on the results, the lumen and MA borders can be extracted automatically, and the border extraction process can be implemented in parallel for a polar image due to the capability of the present proposed method to estimate the borders for each angle independently.

Ultrasound Image Segmentation: A Deeply Supervised Network With Attention to Boundaries

OBJECTIVE

Segmentation of anatomical structures in ultrasound images requires vast radiological knowledge and experience. Moreover, the manual segmentation often results in subjective variations, therefore, an automatic segmentation is desirable. We aim to develop a fully convolutional neural network (FCNN) with attentional deep supervision for the automatic and accurate segmentation of the ultrasound images.

METHOD

FCNN/CNNs are used to infer high-level context using low-level image features. In this paper, a sub-problem specific deep supervision of the FCNN is performed. The attention of fine resolution layers is steered to learn object boundary definitions using auxiliary losses, whereas coarse resolution layers are trained to discriminate object regions from the background. Furthermore, a customized scheme for downweighting the auxiliary losses and a trainable fusion layer are introduced. This produces an accurate segmentation and helps in dealing with the broken boundaries, usually found in the ultrasound images.

RESULTS

The proposed network is first tested for blood vessel segmentation in liver images. It results in F1 score, mean intersection over union, and dice index of 0.83, 0.83, and 0.79, respectively. The best values observed among the existing approaches are produced by U-net as 0.74, 0.81, and 0.75, respectively. The proposed network also results in dice index value of 0.91 in the lumen segmentation experiments on MICCAI 2011 IVUS challenge dataset, which is near to the provided reference value of 0.93. Furthermore, the improvements similar to vessel segmentation experiments are also observed in the experiment performed to segment lesions.

CONCLUSION

Deep supervision of the network based on the input-output characteristics of the layers results in improvement in overall segmentation accuracy.

SIGNIFICANCE

Sub-problem specific deep supervision for ultrasound image segmentation is the main contribution of this paper. Currently the network is trained and tested for fixed size inputs. It requires image resizing and limits the performance in small size images.

Microbubble-Mediated Delivery for Cancer Therapy

Despite an overall improvement in survival rates for cancer, certain resistant forms of the disease still impose a significant burden on patients and healthcare systems. Standard chemotherapy in these cases is often ineffective and/or gives rise to severe side effects. Targeted delivery of chemotherapeutics could improve both tumour response and patient experience. Hence, there is an urgent need to develop effective methods for this. Ultrasound is an established technique in both diagnosis and therapy. Its use in conjunction with microbubbles is being actively researched for the targeted delivery of small-molecule drugs. In this review, we cover the methods by which ultrasound and microbubbles can be used to overcome tumour barriers to cancer therapy.

3D Ultrasound for Orthopedic Interventions

Ultrasound is a real-time, non-radiation-based imaging modality with an ability to acquire two-dimensional (2D) and three-dimensional (3D) data. Due to these capabilities, research has been carried out in order to incorporate it as an intraoperative imaging modality for various orthopedic surgery procedures. However, high levels of noise, different imaging artifacts, and bone surfaces appearing blurred with several mm in thickness have prohibited the widespread use of ultrasound as a standard of care imaging modality in orthopedics. In this chapter, we provided a detailed overview of numerous applications of 3D ultrasound in the domain of orthopedic surgery. Specifically, we discuss the advantages and disadvantages of methods proposed for segmentation and enhancement of bone ultrasound data and the successful application of these methods in clinical domain. Finally, a number of challenges are identified which need to be overcome in order for ultrasound to become a preferred imaging modality in orthopedics.

A Dynamic Graph Cuts Method with Integrated Multiple Feature Maps for Segmenting Kidneys in 2D Ultrasound Images

RATIONALE AND OBJECTIVES

Automatic segmentation of kidneys in ultrasound (US) images remains a challenging task because of high speckle noise, low contrast, and large appearance variations of kidneys in US images. Because texture features may improve the US image segmentation performance, we propose a novel graph cuts method to segment kidney in US images by integrating image intensity information and texture feature maps.

MATERIALS AND METHODS

We develop a new graph cuts-based method to segment kidney US images by integrating original image intensity information and texture feature maps extracted using Gabor filters. To handle large appearance variation within kidney images and improve computational efficiency, we build a graph of image pixels close to kidney boundary instead of building a graph of the whole image. To make the kidney segmentation robust to weak boundaries, we adopt localized regional information to measure similarity between image pixels for computing edge weights to build the graph of image pixels. The localized graph is dynamically updated and the graph cuts-based segmentation iteratively progresses until convergence. Our method has been evaluated based on kidney US images of 85 subjects. The imaging data of 20 randomly selected subjects were used as training data to tune parameters of the image segmentation method, and the remaining data were used as testing data for validation.

RESULTS

Experiment results demonstrated that the proposed method obtained promising segmentation results for bilateral kidneys (average Dice index = 0.9446, average mean distance = 2.2551, average specificity = 0.9971, average accuracy = 0.9919), better than other methods under comparison (P < .05, paired Wilcoxon rank sum tests).

CONCLUSIONS

The proposed method achieved promising performance for segmenting kidneys in two-dimensional US images, better than segmentation methods built on any single channel of image information. This method will facilitate extraction of kidney characteristics that may predict important clinical outcomes such as progression of chronic kidney disease.

Anatomical Structure Segmentation in Ultrasound Volumes Using Cross Frame Belief Propagating Iterative Random Walks

Ultrasound (US) is widely used as a low-cost alternative to computed tomography or magnetic resonance and primarily for preliminary imaging. Since speckle intensity in US images is inherently stochastic, readers are often challenged in their ability to identify the pathological regions in a volume of a large number of images. This paper introduces a generalized approach for volumetric segmentation of structures in US images and volumes. We employ an iterative random walks (IRW) solver, a random forest learning model, and a gradient vector flow (GVF) based interframe belief propagation technique for achieving cross-frame volumetric segmentation. At the start, a weak estimate of the tissue structure is obtained using estimates of parameters of a statistical mechanics model of US tissue interaction. Ensemble learning of these parameters further using a random forest is used to initialize the segmentation pipeline. IRW is used for correcting the contour in various steps of the algorithm. Subsequently, a GVF-based interframe belief propagation is applied to adjacent frames based on the initialization of contour using information in the current frame to segment the complete volume by frame-wise processing. We have experimentally evaluated our approach using two different datasets. Intravascular ultrasound (IVUS) segmentation was evaluated using 10 pullbacks acquired at 20 MHz and thyroid US segmentation is evaluated on 16 volumes acquired at [Formula: see text] MHz. Our approach obtains a Jaccard score of [Formula: see text] for IVUS segmentation and [Formula: see text] for thyroid segmentation while processing each frame in [Formula: see text] for the IVUS and in [Formula: see text] for thyroid segmentation without the need of any computing accelerators such as GPUs.

Error analysis of speed of sound reconstruction in ultrasound limited angle transmission tomography

We have investigated limited angle transmission tomography to estimate speed of sound (SOS) distributions for breast cancer detection. That requires both accurate delineations of major tissues, in this case by segmentation of prior B-mode images, and calibration of the relative positions of the opposed transducers. Experimental sensitivity evaluation of the reconstructions with respect to segmentation and calibration errors is difficult with our current system. Therefore, parametric studies of SOS errors in our bent-ray reconstructions were simulated. They included mis-segmentation of an object of interest or a nearby object, and miscalibration of relative transducer positions in 3D. Close correspondence of reconstruction accuracy was verified in the simplest case, a cylindrical object in homogeneous background with induced segmentation and calibration inaccuracies. Simulated mis-segmentation in object size and lateral location produced maximum SOS errors of 6.3% within 10 mm diameter change and 9.1% within 5 mm shift, respectively. Modest errors in assumed transducer separation produced the maximum SOS error from miscalibrations (57.3% within 5 mm shift), still, correction of this type of error can easily be achieved in the clinic. This study should aid in designing adequate transducer mounts and calibration procedures, and in specification of B-mode image quality and segmentation algorithms for limited angle transmission tomography relying on ray tracing algorithms.

A Methodology for Non-Invasive 3-D Surveillance of Arteriovenous Fistulae Using Freehand Ultrasound

OBJECTIVE

Surveillance techniques for arteriovenous fistulae are required to maintain functional vascular access, with two-dimensional duplex ultrasound the most widely used imaging modality. This paper presents a surveillance method for an arteriovenous fistula using a freehand three-dimensional (3-D) ultrasound system. A patient-case study highlights the applicability in a clinical environment.

METHODS

The freehand ultrasound system uses optical tracking to determine the vascular probe location, and as the probe is swept down a patient's arm, each B-mode slice is spatially arranged to be post-processed as a volume. The volume is segmented to obtain the 3-D vasculature for high detail analysis.

RESULTS

The results follow a patient with stenosis, undergoing surgery to have a stent placement. A surveillance scan was taken pre-surgery, postsurgery, and at a two-month follow-up. Vasculature changes are quantified using detailed analysis, and the benefits of using 3-D imaging are shown through 3-D printing and visualization.

CONCLUSION AND SIGNIFICANCE

Non-invasive 3-D surveillance of arteriovenous fistulae is possible, and a patient-specific geometry was created using ultrasound and optical tracking. Access to this non-invasive 3-D surveillance technique will enable future studies to determine patient-specific remodeling behavior, in terms of geometry and hemodynamics over time.

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.

Automated Techniques for the Interpretation of Fetal Abnormalities: A Review

Ultrasound (US) image segmentation methods, focusing on techniques developed for fetal biometric parameters and nuchal translucency, are briefly reviewed. Ultrasound medical images can easily identify the fetus using segmentation techniques and calculate fetal parameters. It can timely find the fetal abnormality so that necessary action can be taken by the pregnant woman. Firstly, a detailed literature has been offered on fetal biometric parameters and nuchal translucency to highlight the investigation approaches with a degree of validation in diverse clinical domains. Then, a categorization of the bibliographic assessment of recent research effort in the segmentation field of ultrasound 2D fetal images has been presented. The fetal images of high-risk pregnant women have been taken into the routine and continuous monitoring of fetal parameters. These parameters are used for detection of fetal weight, fetal growth, gestational age, and any possible abnormality detection.

Machine learning for medical ultrasound: status, methods, and future opportunities

Ultrasound (US) imaging is the most commonly performed cross-sectional diagnostic imaging modality in the practice of medicine. It is low-cost, non-ionizing, portable, and capable of real-time image acquisition and display. US is a rapidly evolving technology with significant challenges and opportunities. Challenges include high inter- and intra-operator variability and limited image quality control. Tremendous opportunities have arisen in the last decade as a result of exponential growth in available computational power coupled with progressive miniaturization of US devices. As US devices become smaller, enhanced computational capability can contribute significantly to decreasing variability through advanced image processing. In this paper, we review leading machine learning (ML) approaches and research directions in US, with an emphasis on recent ML advances. We also present our outlook on future opportunities for ML techniques to further improve clinical workflow and US-based disease diagnosis and characterization.

Thermal Device Design for a Carbon Nanotube Terahertz Camera

Terahertz (THz) wave detectors are increasingly expected to serve as key components of powerful nondestructive and noncontact inspection tools in a large variety of fields. In contrast to conventional THz detectors based on rigid solid materials, we previously developed an uncooled and bendable THz camera based on the THz-induced photothermoelectric effect of carbon nanotube (CNT) array devices and demonstrated omnidirectional THz imaging of three-dimensional curved samples. Although this development opened a pathway to flexible THz electronics, the physical parameters that determine the performance of the CNT THz camera have not been fully investigated. As a result, the thermal device design has not been optimized in terms of the camera sensitivity and spatial resolution. In this work, we studied the underlying mechanism of the THz-induced photothermoelectric effect of the CNT camera and found physical factors related to the detector performance. Through simulation and experiments, we observed that the detection sensitivity and response time strongly depend on the CNT channel width and film thickness. We further identified that the irradiated wave penetration into the CNT film through the electrode materials deteriorates the detection area, which is directly linked to the camera spatial resolution. By utilizing the improved CNT device design fabricated based on these findings, we eliminated undesired signals generated via thermal diffusion and THz wave penetration and achieved higher-sensitivity THz detection and higher imaging resolution compared to our previously reported THz camera. The presented technologies are expected to contribute to future flexible THz imaging applications and will also be applicable to other types of photothermoelectric devices.

Inverse Problem of Ultrasound Beamforming With Sparsity Constraints and Regularization

Ultrasound (US) beamforming is the process of reconstructing an image from acquired echo traces on several transducer elements. Typical beamforming approaches, such as delay-and-sum, perform simple projection operations, while techniques using statistical information also exist, e.g., adaptive, phase coherence, delay-multiply-and-sum, and sparse coding approaches. Inspired by the feasibility and success of inverse problem (IP) formulations in several image reconstruction problems, such as computed tomography, we herein devise an IP approach for US beamforming. We define a linear forward model for the synthesis of the beamformed image, and solve its IP thanks to several intuitive and physics-based constraints and regularization terms proposed. These reflect the prior knowledge about the spectra of carrier signal and spatial coherence of modulated signal. These constraints admit effective formulation through sparse representations. Our proposed method was evaluated for plane-wave imaging (PWI) that transmits unfocused waves, enabling high frame rates with large field of view at the expense of much lower image quality with conventional beamforming techniques. Results are evaluated in numerical simulations, as well as tissue-mimicking phantoms and in vivo data provided by PWI challenge in medical US. The best results achieved by our proposed techniques are 0.39-mm full-width at half-maximum for spatial resolution and 16.3-dB contrast-to-noise ratio, using a single plane-wave transmit.

Receiver-Operating Characteristic Analysis of Eigen-Based Clutter Filters for Ultrasound Color Flow Imaging

The eigen-based filter has theoretically established itself as a potent solution in ultrasound color flow imaging (CFI) for combating against clutter arising from moving tissues. Yet, it remains poorly understood on how much gain in flow detection sensitivity and specificity can be delivered by this adaptive clutter filter. Here, we investigated the receiver operating characteristic (ROC) of the eigen-based clutter filter to statistically evaluate its efficacy. Our investigation was conducted using a new vascular phantom testbed that incorporated both intrinsic tissue motion (vessel pulsation: 7.58 cm/s peak velocity) and extrinsic tissue motion (vibration: 5-Hz frequency, 2.98 cm/s peak velocity), as well as pulsatile flow (pulse rate: 60 beats/min; systolic flow rate: 6.5 mL/s). The eigen-filter (single-ensemble formulation) was applied to CFI raw data sets obtained from the phantom's short-axis view (slow-time ensemble size: 12; pulse repetition frequency: 2 kHz; and ultrasound frequency: 5 MHz), and post-filter Doppler power was compared between flow and tissue regions. Results show that, in the presence of vessel pulsation and tissue vibration, the eigen-filter yielded a high true positive rate in depicting flow pixels in CFI frames (0.945 and 0.917, respectively, during peak systole and end diastole at 60° beam-flow angle), while maintaining a low false alarm rate (0.10) in rendering tissue pixels. Also, the eigen-filter posed ROC curves whose area under curve was higher than those for the polynomial regression filter (statistically significant; t-test p values were less than 0.05). These findings serve well to substantiate the merit of using eigen-filters to enhance the vascular visualization capability of CFI.

A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.

Patient-specific model-based segmentation of brain tumors in 3D intraoperative ultrasound images

PURPOSE

Intraoperative ultrasound (iUS) imaging is commonly used to support brain tumor operation. The tumor segmentation in the iUS images is a difficult task and still under improvement because of the low signal-to-noise ratio. The success of automatic methods is also limited due to the high noise sensibility. Therefore, an alternative brain tumor segmentation method in 3D-iUS data using a tumor model obtained from magnetic resonance (MR) data for local MR-iUS registration is presented in this paper. The aim is to enhance the visualization of the brain tumor contours in iUS.

METHODS

A multistep approach is proposed. First, a region of interest (ROI) based on the specific patient tumor model is defined. Second, hyperechogenic structures, mainly tumor tissues, are extracted from the ROI of both modalities by using automatic thresholding techniques. Third, the registration is performed over the extracted binary sub-volumes using a similarity measure based on gradient values, and rigid and affine transformations. Finally, the tumor model is aligned with the 3D-iUS data, and its contours are represented.

RESULTS

Experiments were successfully conducted on a dataset of 33 patients. The method was evaluated by comparing the tumor segmentation with expert manual delineations using two binary metrics: contour mean distance and Dice index. The proposed segmentation method using local and binary registration was compared with two grayscale-based approaches. The outcomes showed that our approach reached better results in terms of computational time and accuracy than the comparative methods.

CONCLUSION

The proposed approach requires limited interaction and reduced computation time, making it relevant for intraoperative use. Experimental results and evaluations were performed offline. The developed tool could be useful for brain tumor resection supporting neurosurgeons to improve tumor border visualization in the iUS volumes.

Image Segmentation Based on Statistical Confidence Intervals

Image segmentation is defined as a partition realized to an image into homogeneous regions to modify it into something that is more meaningful and softer to examine. Although several segmentation approaches have been proposed recently, in this paper, we develop a new image segmentation method based on the statistical confidence interval tool along with the well-known Otsu algorithm. According to our numerical experiments, our method has a dissimilar performance in comparison to the standard Otsu algorithm to specially process images with speckle noise perturbation. Actually, the effect of the speckle noise entropy is almost filtered out by our algorithm. Furthermore, our approach is validated by employing some image samples.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

Fast left ventricle tracking using localized anatomical affine optical flow

In daily clinical cardiology practice, left ventricle (LV) global and regional function assessment is crucial for disease diagnosis, therapy selection, and patient follow-up. Currently, this is still a time-consuming task, spending valuable human resources. In this work, a novel fast methodology for automatic LV tracking is proposed based on localized anatomically constrained affine optical flow. This novel method can be combined to previously proposed segmentation frameworks or manually delineated surfaces at an initial frame to obtain fully delineated datasets and, thus, assess both global and regional myocardial function. Its feasibility and accuracy were investigated in 3 distinct public databases, namely in realistically simulated 3D ultrasound, clinical 3D echocardiography, and clinical cine cardiac magnetic resonance images. The method showed accurate tracking results in all databases, proving its applicability and accuracy for myocardial function assessment. Moreover, when combined to previous state-of-the-art segmentation frameworks, it outperformed previous tracking strategies in both 3D ultrasound and cardiac magnetic resonance data, automatically computing relevant cardiac indices with smaller biases and narrower limits of agreement compared to reference indices. Simultaneously, the proposed localized tracking method showed to be suitable for online processing, even for 3D motion assessment. Importantly, although here evaluated for LV tracking only, this novel methodology is applicable for tracking of other target structures with minimal adaptations.

Focal Liver Lesions: Computer-aided Diagnosis by Using Contrast-enhanced US Cine Recordings

Purpose To assess the performance of computer-aided diagnosis (CAD) systems and to determine the dominant ultrasonographic (US) features when classifying benign versus malignant focal liver lesions (FLLs) by using contrast material-enhanced US cine clips. Materials and Methods One hundred six US data sets in all subjects enrolled by three centers from a multicenter trial that included 54 malignant, 51 benign, and one indeterminate FLL were retrospectively analyzed. The 105 benign or malignant lesions were confirmed at histologic examination, contrast-enhanced computed tomography (CT), dynamic contrast-enhanced magnetic resonance (MR) imaging, and/or 6 or more months of clinical follow-up. Data sets included 3-minute cine clips that were automatically corrected for in-plane motion and automatically filtered out frames acquired off plane. B-mode and contrast-specific features were automatically extracted on a pixel-by-pixel basis and analyzed by using an artificial neural network (ANN) and a support vector machine (SVM). Areas under the receiver operating characteristic curve (AUCs) for CAD were compared with those for one experienced and one inexperienced blinded reader. A third observer graded cine quality to assess its effects on CAD performance. Results CAD, the inexperienced observer, and the experienced observer were able to analyze 95, 100, and 102 cine clips, respectively. The AUCs for the SVM, ANN, and experienced and inexperienced observers were 0.883 (95% confidence interval [CI]: 0.793, 0.940), 0.829 (95% CI: 0.724, 0.901), 0.843 (95% CI: 0.756, 0.903), and 0.702 (95% CI: 0.586, 0.782), respectively; only the difference between SVM and the inexperienced observer was statistically significant. Accuracy improved from 71.3% (67 of 94; 95% CI: 60.6%, 79.8%) to 87.7% (57 of 65; 95% CI: 78.5%, 93.8%) and from 80.9% (76 of 94; 95% CI: 72.3%, 88.3%) to 90.3% (65 of 72; 95% CI: 80.6%, 95.8%) when CAD was in agreement with the inexperienced reader and when it was in agreement with the experienced reader, respectively. B-mode heterogeneity and contrast material washout were the most discriminating features selected by CAD for all iterations. CAD selected time-based time-intensity curve (TIC) features 99.0% (207 of 209) of the time to classify FLLs, versus 1.0% (two of 209) of the time for intensity-based features. None of the 15 video-quality criteria had a statistically significant effect on CAD accuracy-all P values were greater than the Holm-Sidak α-level correction for multiple comparisons. Conclusion CAD systems classified benign and malignant FLLs with an accuracy similar to that of an expert reader. CAD improved the accuracy of both readers. Time-based features of TIC were more discriminating than intensity-based features. ^© RSNA, 2017 Online supplemental material is available for this article.

Automatic identification of blood vessel cross-section for central venous catheter placement using a cascading classifier

This paper presents a system that is able to automatically identify, segment, and track the cross-section of the internal jugular vein (IJV) and the common carotid artery (CCA) in an ultrasound image feed during a central venous catheter (CVC) placement procedure. The goal is to provide assistance to the practitioner in order to decrease the probability of complications stemming from inadvertent punctures of the CCA during the procedure. In the system, a modified Star algorithm is implemented to segment and track the blood vessel throughout an ultrasound video feed. A novel algorithm based on a cascading classifier is used to identify the location of the IJV and the CCA for two main tasks: (1) selecting the initial seed point at the start of tracking and (2) validating the segmentation results at each subsequent frame. The classifier uses shape features (vessel area, ellipse fitting error, vessel depth, vessel eccentricity) and pixel-based features (pixel intensity and the histogram of oriented gradients descriptor) to differentiate between vessel and non-vessel structures and also differentiate between the IJV and the CCA. Evaluated on a database of 800 ultrasound images containing the cross-section of both vessels, the cascading classifier was able to identify the IJV and the CCA in 92.25% and 85.13% of the images respectively without any initialization from the user at a maximum processing rate of 40.65 frames per second. This allows identification to be conducted in real-time with existing ultrasound machines.

A random walk-based segmentation framework for 3D ultrasound images of the prostate

PURPOSE

Accurate segmentation of the prostate on ultrasound images has many applications in prostate cancer diagnosis and therapy. Transrectal ultrasound (TRUS) has been routinely used to guide prostate biopsy. This manuscript proposes a semiautomatic segmentation method for the prostate on three-dimensional (3D) TRUS images.

METHODS

The proposed segmentation method uses a context-classification-based random walk algorithm. Because context information reflects patient-specific characteristics and prostate changes in the adjacent slices, and classification information reflects population-based prior knowledge, we combine the context and classification information at the same time in order to define the applicable population and patient-specific knowledge so as to more accurately determine the seed points for the random walk algorithm. The method is initialized with the user drawing the prostate and non-prostate circles on the mid-gland slice and then automatically segments the prostate on other slices. To achieve reliable classification, we use a new adaptive k-means algorithm to cluster the training data and train multiple decision-tree classifiers. According to the patient-specific characteristics, the most suitable classifier is selected and combined with the context information in order to locate the seed points. By providing accuracy locations of the seed points, the random walk algorithm improves segmentation performance.

RESULTS

We evaluate the proposed segmentation approach on a set of 3D TRUS volumes of prostate patients. The experimental results show that our method achieved a Dice similarity coefficient of 91.0% ± 1.6% as compared to manual segmentation by clinically experienced radiologist.

CONCLUSIONS

The random walk-based segmentation framework, which combines patient-specific characteristics and population information, is effective for segmenting the prostate on ultrasound images. The segmentation method can have various applications in ultrasound-guided prostate procedures.

Medical image segmentation based on level set and isoperimetric constraint

Level set based methods are being increasingly used in image segmentation. In these methods, various shape constraints can be incorporated into the energy functionals to obtain the desired shapes of the contours represented by their zero level sets of functions. Motivated by the isoperimetric inequality in differential geometry, we propose a segmentation method in which the isoperimetric constrain is integrated into a level set framework to penalize the ratio of its squared perimeter to its enclosed area of an active contour. The new model can ensure the compactness of segmenting objects and complete missing or/and blurred parts of their boundaries simultaneously. The isoperimetric shape constraint is free of explicit expressions of shapes and scale-invariant. As a result, the proposed method can handle various objects with different scales and does not need to estimate parameters of shapes. Our method can segment lesions with blurred or/and partially missing boundaries in ultrasound, Computed Tomography (CT) and Magnetic Resonance (MR) images efficiently. Quantitative evaluation also confirms that the proposed method can provide more accurate segmentation than two well-known level set methods. Therefore, our proposed method shows potential of accurate segmentation of lesions for applying in diagnoses and surgical planning.

Virtual and Augmented Reality Systems for Renal Interventions: A Systematic Review

PURPOSE

Many virtual and augmented reality systems have been proposed to support renal interventions. This paper reviews such systems employed in the treatment of renal cell carcinoma and renal stones.

METHODS

A systematic literature search was performed. Inclusion criteria were virtual and augmented reality systems for radical or partial nephrectomy and renal stone treatment, excluding systems solely developed or evaluated for training purposes.

RESULTS

In total, 52 research papers were identified and analyzed. Most of the identified literature (87%) deals with systems for renal cell carcinoma treatment. About 44% of the systems have already been employed in clinical practice, but only 20% in studies with ten or more patients. Main challenges remaining for future research include the consideration of organ movement and deformation, human factor issues, and the conduction of large clinical studies.

CONCLUSION

Augmented and virtual reality systems have the potential to improve safety and outcomes of renal interventions. In the last ten years, many technical advances have led to more sophisticated systems, which are already applied in clinical practice. Further research is required to cope with current limitations of virtual and augmented reality assistance in clinical environments.

Three-Dimensional Model-Based Segmentation in Echocardiography Using High Temporal Tissue and Blood Flow Information

Accurate 3-D surface segmentation is a challenging task in echocardiography because of the relatively low image quality. We introduce a new method for 3-D segmentation of the endocardium involving temporal decorrelation of echo signals originating from tissue and blood using radiofrequency (RF) signals acquired in 3-D Doppler mode. Temporal features were extracted in 3-D Doppler mode, where a sequence of RF lines is recorded for each image line. Each set of RF lines is highly correlated because of the high pulse repetition frequency. However, for high blood flow, the RF signals will decorrelate over time in contrast to the endocardium, which will remain relatively highly correlated over time. These decorrelation features permit differentiation between myocardial tissue and blood flow. We describe an implementation of a 3-D segmentation model in which temporal information is used as external constraint. The model was validated in a phantom and in vivo in healthy volunteers (n = 5). The phantom study revealed that the model successfully segmented the artificial blood lumen even for low flow velocity and illustrated the sensitivity of the segmentations to flow rate. In healthy volunteers, high Dice similarity indices indicate that 3-D segmentation of the endocardial border in vivo is feasible.

An adaptive Fuzzy C-means method utilizing neighboring information for breast tumor segmentation in ultrasound images

PURPOSE

Ultrasound (US) imaging has been widely used in breast tumor diagnosis and treatment intervention. Automatic delineation of the tumor is a crucial first step, especially for the computer-aided diagnosis (CAD) and US-guided breast procedure. However, the intrinsic properties of US images such as low contrast and blurry boundaries pose challenges to the automatic segmentation of the breast tumor. Therefore, the purpose of this study is to propose a segmentation algorithm that can contour the breast tumor in US images.

METHODS

To utilize the neighbor information of each pixel, a Hausdorff distance based fuzzy c-means (FCM) method was adopted. The size of the neighbor region was adaptively updated by comparing the mutual information between them. The objective function of the clustering process was updated by a combination of Euclid distance and the adaptively calculated Hausdorff distance. Segmentation results were evaluated by comparing with three experts' manual segmentations. The results were also compared with a kernel-induced distance based FCM with spatial constraints, the method without adaptive region selection, and conventional FCM.

RESULTS

Results from segmenting 30 patient images showed the adaptive method had a value of sensitivity, specificity, Jaccard similarity, and Dice coefficient of 93.60 ± 5.33%, 97.83 ± 2.17%, 86.38 ± 5.80%, and 92.58 ± 3.68%, respectively. The region-based metrics of average symmetric surface distance (ASSD), root mean square symmetric distance (RMSD), and maximum symmetric surface distance (MSSD) were 0.03 ± 0.04 mm, 0.04 ± 0.03 mm, and 1.18 ± 1.01 mm, respectively. All the metrics except sensitivity were better than that of the non-adaptive algorithm and the conventional FCM. Only three region-based metrics were better than that of the kernel-induced distance based FCM with spatial constraints.

CONCLUSION

Inclusion of the pixel neighbor information adaptively in segmenting US images improved the segmentation performance. The results demonstrate the potential application of the method in breast tumor CAD and other US-guided procedures.

Ultrasound imaging and segmentation of bone surfaces: A review

Due to its real-time, non-radiation based three-dimensional (3D) imaging capabilities, ultrasound (US) has been incorporated into various orthopedic procedures. However, imaging artifacts, low signal-to-noise ratio (SNR) and bone boundaries appearing several mm in thickness make the analysis of US data difficult. This paper provides a review about the state-of-the-art bone segmentation and enhancement methods developed for two-dimensional (2D) and 3D US data. First, an overview for the appearance of bone surface response in B-mode data is presented. Then, classification of the proposed techniques in terms of the image information being used is provided. Specifically, the focus is given on segmentation and enhancement of B-mode US data. The review is concluded by discussing future directions of research and additional challenges which need to be overcome in order to make this imaging modality more successful in orthopedics.

Real-Time Nonlocal Means-Based Despeckling

In this paper, we propose a multiscale nonlocal means-based despeckling method for medical ultrasound. The multiscale approach leads to large computational savings and improves despeckling results over single-scale iterative approaches. We present two variants of the method. The first, denoted multiscale nonlocal means (MNLM), yields uniform robust filtering of speckle both in structured and homogeneous regions. The second, denoted unnormalized MNLM (UMNLM), is more conservative in regions of structure assuring minimal disruption of salient image details. Due to the popularity of anisotropic diffusion-based methods in the despeckling literature, we review the connection between anisotropic diffusion and iterative variants of NLM. These iterative variants in turn relate to our multiscale variant. As part of our evaluation, we conduct a simulation study making use of ground truth phantoms generated from clinical B-mode ultrasound images. We evaluate our method against a set of popular methods from the despeckling literature on both fine and coarse speckle noise. In terms of computational efficiency, our method outperforms the other considered methods. Quantitatively on simulations and on a tissue-mimicking phantom, our method is found to be competitive with the state-of-the-art. On clinical B-mode images, our method is found to effectively smooth speckle while preserving low-contrast and highly localized salient image detail.

Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification

We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM). Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

An automatic segmentation method of a parameter-adaptive PCNN for medical images

PURPOSE

Since pre-processing and initial segmentation steps in medical images directly affect the final segmentation results of the regions of interesting, an automatic segmentation method of a parameter-adaptive pulse-coupled neural network is proposed to integrate the above-mentioned two segmentation steps into one. This method has a low computational complexity for different kinds of medical images and has a high segmentation precision.

METHODS

The method comprises four steps. Firstly, an optimal histogram threshold is used to determine the parameter [Formula: see text] for different kinds of images. Secondly, we acquire the parameter [Formula: see text] according to a simplified pulse-coupled neural network (SPCNN). Thirdly, we redefine the parameter V of the SPCNN model by sub-intensity distribution range of firing pixels. Fourthly, we add an offset [Formula: see text] to improve initial segmentation precision.

RESULTS

Compared with the state-of-the-art algorithms, the new method achieves a comparable performance by the experimental results from ultrasound images of the gallbladder and gallstones, magnetic resonance images of the left ventricle, and mammogram images of the left and the right breast, presenting the overall metric UM of 0.9845, CM of 0.8142, TM of 0.0726.

CONCLUSION

The algorithm has a great potential to achieve the pre-processing and initial segmentation steps in various medical images. This is a premise for assisting physicians to detect and diagnose clinical cases.

A Novel Segmentation Approach Combining Region- and Edge-Based Information for Ultrasound Images

Ultrasound imaging has become one of the most popular medical imaging modalities with numerous diagnostic applications. However, ultrasound (US) image segmentation, which is the essential process for further analysis, is a challenging task due to the poor image quality. In this paper, we propose a new segmentation scheme to combine both region- and edge-based information into the robust graph-based (RGB) segmentation method. The only interaction required is to select two diagonal points to determine a region of interest (ROI) on the original image. The ROI image is smoothed by a bilateral filter and then contrast-enhanced by histogram equalization. Then, the enhanced image is filtered by pyramid mean shift to improve homogeneity. With the optimization of particle swarm optimization (PSO) algorithm, the RGB segmentation method is performed to segment the filtered image. The segmentation results of our method have been compared with the corresponding results obtained by three existing approaches, and four metrics have been used to measure the segmentation performance. The experimental results show that the method achieves the best overall performance and gets the lowest ARE (10.77%), the second highest TPVF (85.34%), and the second lowest FPVF (4.48%).

Computer-aided diagnosis of malignant or benign thyroid nodes based on ultrasound images

The objective of this study is to evaluate the diagnostic value of combination of artificial neural networks (ANN) and support vector machine (SVM)-based CAD systems in differentiating malignant from benign thyroid nodes with gray-scale ultrasound images. Two morphological and 65 texture features extracted from regions of interest in 610 2D-ultrasound thyroid node images from 543 patients (207 malignant, 403 benign) were used to develop the ANN and SVM models. Tenfold cross validation evaluated their performance; the best models showed accuracy of 99% for ANN and 100% for SVM. From 50 thyroid node ultrasound images from 45 prospectively enrolled patients, the ANN model showed sensitivity, specificity, positive and negative predictive values, Youden index, and accuracy of 88.24, 90.91, 83.33, 93.75, 79.14, and 90.00%, respectively, the SVM model 76.47, 90.91, 81.25, 88.24, 67.38, and 86.00%, respectively, and in combination 100.00, 87.88, 80.95, 100.00, 87.88, and 92.00%, respectively. Both ANN and SVM had high value in classifying thyroid nodes. In combination, the sensitivity increased but specificity decreased. This combination might provide a second opinion for radiologists dealing with difficult to diagnose thyroid node ultrasound images.

Linear and nonlinear characterization of microbubbles and tissue using the Nakagami statistical model

The goal of this work is to exploit the statistical signatures for discrimination between biological tissues and contrast microbubbles in order to develop new strategies for contrast imaging and tissue characterization. For this purpose, the efficiency of the Nakagami statistical model, for describing the ultrasonic echoes of both contrast microbubbles and tissues, was investigated. Experimental measurements have been performed using a linear array probe connected to an open research platform. A commercially available in vitro phantom was used to mimic biological tissue in which SonoVue contrast microbubbles were flowing. Experimental ultrasound echoes have been filtered around the transmitted frequency (fundamental at 2.5MHz) and around twice the transmitted frequency (at 5MHz) for 2nd harmonic analysis, and a logarithmic compression was applied. The signals have been analyzed in order to evaluate the Nakagami parameter m, the scaling parameter Ω and the probability density function at both frequencies. Parametric images based on the Nakagami parameters map (Nakagami-mode images) were reconstructed and compared to B-mode images. Contrary to the B-mode image which is influenced by the system settings and user operations, the Nakagami parametric image is only based on the backscattered statistics of the ultrasonic signals in a local phantom. Such an imaging principle allows the Nakagami image to quantify the local scatterer concentrations in the phantom and to extract the backscattering information from the regions of the weakest echoes that may be lost in the conventional B-mode image. Results show that the tissue and microbubbles characterization is more sensitive in the 2nd harmonic mode when a logarithmic transform is used. These results would be useful for improving the ultrasound image quality and contrast detection in nonlinear mode.

Cardiac imaging: working towards fully-automated machine analysis & interpretation

INTRODUCTION

Non-invasive imaging plays a critical role in managing patients with cardiovascular disease. Although subjective visual interpretation remains the clinical mainstay, quantitative analysis facilitates objective, evidence-based management, and advances in clinical research. This has driven developments in computing and software tools aimed at achieving fully automated image processing and quantitative analysis. In parallel, machine learning techniques have been used to rapidly integrate large amounts of clinical and quantitative imaging data to provide highly personalized individual patient-based conclusions. Areas covered: This review summarizes recent advances in automated quantitative imaging in cardiology and describes the latest techniques which incorporate machine learning principles. The review focuses on the cardiac imaging techniques which are in wide clinical use. It also discusses key issues and obstacles for these tools to become utilized in mainstream clinical practice. Expert commentary: Fully-automated processing and high-level computer interpretation of cardiac imaging are becoming a reality. Application of machine learning to the vast amounts of quantitative data generated per scan and integration with clinical data also facilitates a move to more patient-specific interpretation. These developments are unlikely to replace interpreting physicians but will provide them with highly accurate tools to detect disease, risk-stratify, and optimize patient-specific treatment. However, with each technological advance, we move further from human dependence and closer to fully-automated machine interpretation.

Classification of breast lesions using segmented quantitative ultrasound maps of homodyned K distribution parameters

PURPOSE

Statistical modeling of an ultrasound backscattered echo envelope is used for tissue characterization. However, in the presence of complex structures within the analyzed area, estimation of parameters is disturbed and unreliable, e.g., in the case of breast tumor classification. In order to improve the differentiation of breast lesions, the authors proposed a method based on the segmentation of homodyned K distribution parameter maps. Regions within lesions of different scattering properties were extracted and analyzed. In order to improve the classification, the best-performing features were selected from various regions and then combined.

METHODS

A radio-frequency data set consisting of 103 breast lesions was used in the authors' analysis. Maps of homodyned K distribution parameters were created using an algorithm based on signal-to-noise ratio, kurtosis, and skewness of fractional-order envelope moments. A Markov random field model was used to segment parametric maps. Features of different segments were extracted and evaluated based on bootstrapping and the receiver operating characteristic curve. To determine the best-performing feature subset, the authors applied the joint mutual information criterion.

RESULTS

It was found that there were individual features which performed better than the ones commonly used for lesion characterization, like the parameter obtained through averaging of values over the whole lesion. The authors selected and discussed the best-performing features. Properties of different extracted regions were important and improved the distinction between benign and malignant tumors. The best performance was obtained by combining four features with the area under the receiver operating curve of 0.84.

CONCLUSIONS

The study showed that the analysis of internal changes in lesion parametric maps leads to a better classification of breast tumors. The authors recommend combining multiple features for characterization, instead of using only one parameter, especially in the case of heterogeneous lesions.

Segmentation of prostate from ultrasound images using level sets on active band and intensity variation across edges

PURPOSE

In this paper, the authors propose a novel efficient method to segment ultrasound images of the prostate with weak boundaries. Segmentation of the prostate from ultrasound images with weak boundaries widely exists in clinical applications. One of the most typical examples is the diagnosis and treatment of prostate cancer. Accurate segmentation of the prostate boundaries from ultrasound images plays an important role in many prostate-related applications such as the accurate placement of the biopsy needles, the assignment of the appropriate therapy in cancer treatment, and the measurement of the prostate volume.

METHODS

Ultrasound images of the prostate are usually corrupted with intensity inhomogeneities, weak boundaries, and unwanted edges, which make the segmentation of the prostate an inherently difficult task. Regarding to these difficulties, the authors introduce an active band term and an edge descriptor term in the modified level set energy functional. The active band term is to deal with intensity inhomogeneities and the edge descriptor term is to capture the weak boundaries or to rule out unwanted boundaries. The level set function of the proposed model is updated in a band region around the zero level set which the authors call it an active band. The active band restricts the authors' method to utilize the local image information in a banded region around the prostate contour. Compared to traditional level set methods, the average intensities inside∖outside the zero level set are only computed in this banded region. Thus, only pixels in the active band have influence on the evolution of the level set. For weak boundaries, they are hard to be distinguished by human eyes, but in local patches in the band region around prostate boundaries, they are easier to be detected. The authors incorporate an edge descriptor to calculate the total intensity variation in a local patch paralleled to the normal direction of the zero level set, which can detect weak boundaries and avoid unwanted edges in the ultrasound images.

RESULTS

The efficiency of the proposed model is demonstrated by experiments on real 3D volume images and 2D ultrasound images and comparisons with other approaches. Validation results on real 3D TRUS prostate images show that the authors' model can obtain a Dice similarity coefficient (DSC) of 94.03% ± 1.50% and a sensitivity of 93.16% ± 2.30%. Experiments on 100 typical 2D ultrasound images show that the authors' method can obtain a sensitivity of 94.87% ± 1.85% and a DSC of 95.82% ± 2.23%. A reproducibility experiment is done to evaluate the robustness of the proposed model.

CONCLUSIONS

As far as the authors know, prostate segmentation from ultrasound images with weak boundaries and unwanted edges is a difficult task. A novel method using level sets with active band and the intensity variation across edges is proposed in this paper. Extensive experimental results demonstrate that the proposed method is more efficient and accurate.

Plantar fascia segmentation and thickness estimation in ultrasound images

Ultrasound (US) imaging offers significant potential in diagnosis of plantar fascia (PF) injury and monitoring treatment. In particular US imaging has been shown to be reliable in foot and ankle assessment and offers a real-time effective imaging technique that is able to reliably confirm structural changes, such as thickening, and identify changes in the internal echo structure associated with diseased or damaged tissue. Despite the advantages of US imaging, images are difficult to interpret during medical assessment. This is partly due to the size and position of the PF in relation to the adjacent tissues. It is therefore a requirement to devise a system that allows better and easier interpretation of PF ultrasound images during diagnosis. This study proposes an automatic segmentation approach which for the first time extracts ultrasound data to estimate size across three sections of the PF (rearfoot, midfoot and forefoot). This segmentation method uses artificial neural network module (ANN) in order to classify small overlapping patches as belonging or not-belonging to the region of interest (ROI) of the PF tissue. Features ranking and selection techniques were performed as a post-processing step for features extraction to reduce the dimension and number of the extracted features. The trained ANN classifies the image overlapping patches into PF and non-PF tissue, and then it is used to segment the desired PF region. The PF thickness was calculated using two different methods: distance transformation and area-length calculation algorithms. This new approach is capable of accurately segmenting the PF region, differentiating it from surrounding tissues and estimating its thickness.