Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance

ACL-DUNet: A tumor segmentation method based on multiple attention and densely connected breast ultrasound images

Breast cancer is the most common cancer in women. Breast masses are one of the distinctive signs for diagnosing breast cancer, and ultrasound is widely used for screening as a non-invasive and effective method for breast examination. In this study, we used the Mendeley and BUSI datasets, comprising 250 images (100 benign, 150 malignant) and 780 images (133 normal, 487 benign, 210 malignant), respectively. The datasets were split into 80% for training and 20% for validation. The accurate measurement and characterization of different breast tumors play a crucial role in guiding clinical decision-making. The area and shape of the different breast tumors detected are critical for clinicians to make accurate diagnostic decisions. In this study, a deep learning method for mass segmentation in breast ultrasound images is proposed, which uses densely connected U-net with attention gates (AGs) as well as channel attention modules and scale attention modules for accurate breast tumor segmentation.The densely connected network is employed in the encoding stage to enhance the network's feature extraction capabilities. Three attention modules are integrated in the decoding stage to better capture the most relevant features. After validation on the Mendeley and BUSI datasets, the experimental results demonstrate that our method achieves a Dice Similarity Coefficient (DSC) of 0.8764 and 0.8313, respectively, outperforming other deep learning approaches. The source code is located at github.com/zhanghaoCV/plos-one.

Switchable ROS Scavenger/Generator for MRI-Guided Anti-Inflammation and Anti-Tumor Therapy with Enhanced Therapeutic Efficacy and Reduced Side Effects

Photosensitizer in photodynamic therapy (PDT)  accumulates in both tumor and adjacent normal tissue due to low selective biodistribution, results in undesirable side effect with limited clinic application. Herein, an intelligent nanoplatform is reported that selectively acts as reactive oxygen species (ROS) scavenger in normal tissue but as ROS generator in tumor microenvironment (TME) to differentially control ROS level in tumor and surrounding normal tissue during PDT. By down-regulating the produced ROS with dampened cytokine wave in normal tissue after PDT, the nanoplatform reduces the inflammatory response of normal tissue in PDT, minimizing the side effect and tumor metastasis in PDT. Alternatively, the nanoplatform switches from ROS scavenger to generator through the glutathione (GSH) responsive degradation in TME, which effectively improves the PDT efficacy with reduced GSH level and amplified oxidative stress in tumor. Simultaneously, the released Mn ions provide real-time and in situ signal change of magnetic resonance imaging (MRI) to monitor the reversal process of catalysis activity and achieve accurate tumor diagnosis. This TME-responsive ROS scavenger/generator with activable MRI contrast may provide a new dimension for design of next-generation PDT agents with precise diagnosis, high therapeutic efficacy, and low side effect.

Fully multi-target segmentation for breast ultrasound image based on fully convolutional network

Ultrasound image segmentation plays an important role in computer-aided diagnosis of breast cancer. Existing approaches focused on extracting the tumor tissue to characterize the tumor class. However, other tissues are also helpful for providing the references. In this paper, a multi-target semantic segmentation approach is proposed based on the fully convolutional network for segmenting the breast ultrasound image into different target tissue regions. For handling the uncertain affiliation of pixels in blurry boundaries, the certain outputs of pixel characteristics in AlexNet are transformed into the fuzzy decision expression. For improving the image detail representation, the AlexNet network structure of fully convolutional network is optimized with fully connected skip structure. In addition, the output of net model is optimized with fully connected conditional random field to improve the characterization of spatial consistency and pixels' correlation of the image. Moreover, a data training optimization method is developed for improving the efficiency of network training. In the experiment, 325 ultrasound images and four error metrics are utilized for validating the segmentation performance. Comparing with existing methods, experimental results show that the proposed approach is effective for handling the breast ultrasound images accurately and reliably. Graphical abstract.

Two-stage ultrasound image segmentation using U-Net and test time augmentation

PURPOSE

Detecting breast lesions using ultrasound imaging is an important application of computer-aided diagnosis systems. Several automatic methods have been proposed for breast lesion detection and segmentation; however, due to the ultrasound artefacts, and to the complexity of lesion shapes and locations, lesion or tumor segmentation from ultrasound breast images is still an open problem. In this paper, we propose using a lesion detection stage prior to the segmentation stage in order to improve the accuracy of the segmentation.

METHODS

We used a breast ultrasound imaging dataset which contained 163 images of the breast with either benign lesions or malignant tumors. First, we used a U-Net to detect the lesions and then used another U-Net to segment the detected region. We could show when the lesion is precisely detected, the segmentation performance substantially improves; however, if the detection stage is not precise enough, the segmentation stage also fails. Therefore, we developed a test-time augmentation technique to assess the detection stage performance.

RESULTS

By using the proposed two-stage approach, we could improve the average Dice score by 1.8% overall. The improvement was substantially more for images wherein the original Dice score was less than 70%, where average Dice score was improved by 14.5%.

CONCLUSIONS

The proposed two-stage technique shows promising results for segmentation of breast US images and has a much smaller chance of failure.

Initialization of active contours for segmentation of breast cancer via fusion of ultrasound, Doppler, and elasticity images

Active contours (snakes) are an efficient method for segmentation of ultrasound (US) images of breast cancer. However, the method produces inaccurate results if the seeds are initialized improperly (far from the true boundaries and close to the false boundaries). Therefore, we propose a novel initialization method based on the fusion of a conventional US image with elasticity and Doppler images. The proposed fusion method (FM) has been tested against four state-of-the-art initialization methods on 90 ultrasound images from a database collected by the Thammasat University Hospital of Thailand. The ground truth was hand-drawn by three leading radiologists of the hospital. The reference methods are: center of divergence (CoD), force field segmentation (FFS), Poisson Inverse Gradient Vector Flow (PIG), and quasi-automated initialization (QAI). A variety of numerical tests proves the advantages of the FM. For the raw US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-26.7%, QAI-42.2%. The percentage of correctly segmented tumors is FM-84.4%, CoD-0%, FFS-0%, PIG-16.67%, QAI-22.44%. For reduced field of view US images, the percentage of correctly initialized contours is: FM-94.2%, CoD-0%, FFS-0%, PIG-65.6%, QAI-67.8%. The correctly segmented tumors are FM-88.9%, CoD-0%, FFS-0%, PIG-48.9%, QAI-44.5%. The accuracy, in terms of the average Hausdorff distance, is respectively 2.29 pixels, 33.81, 34.71, 7.7, and 8.4, whereas in terms of the Jaccard index, it is 0.9, 0.18, 0.19, 0.63, and 0.48.

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.

An Automatic Localization Algorithm for Ultrasound Breast Tumors Based on Human Visual Mechanism

Human visual mechanisms (HVMs) can quickly localize the most salient object in natural images, but it is ineffective at localizing tumors in ultrasound breast images. In this paper, we research the characteristics of tumors, develop a classic HVM and propose a novel auto-localization method. Comparing to surrounding areas, tumors have higher global and local contrast. In this method, intensity, blackness ratio and superpixel contrast features are combined to compute a saliency map, in which a Winner Take All algorithm is used to localize the most salient region, which is represented by a circle. The results show that the proposed method can successfully avoid the interference caused by background areas of low echo and high intensity. The method has been tested on 400 ultrasound breast images, among which 376 images succeed in localization. This means this method has a high accuracy of 94.00%, indicating its good performance in real-life applications.

A contrast enhancement method for improving the segmentation of breast lesions on ultrasonography

PURPOSE

This paper presents an adaptive contrast enhancement method based on sigmoidal mapping function (SACE) used for improving the computerized segmentation of breast lesions on ultrasound.

METHODS

First, from the original ultrasound image an intensity variation map is obtained, which is used to generate local sigmoidal mapping functions related to distinct contextual regions. Then, a bilinear interpolation scheme is used to transform every original pixel to a new gray level value. Also, four contrast enhancement techniques widely used in breast ultrasound enhancement are implemented: histogram equalization (HEQ), contrast limited adaptive histogram equalization (CLAHE), fuzzy enhancement (FEN), and sigmoid based enhancement (SEN). In addition, these contrast enhancement techniques are considered in a computerized lesion segmentation scheme based on watershed transformation. The performance comparison among techniques is assessed in terms of both the quality of contrast enhancement and the segmentation accuracy. The former is quantified by the measure, where the greater the value, the better the contrast enhancement, whereas the latter is calculated by the Jaccard index, which should tend towards unity to indicate adequate segmentation.

RESULTS

The experiments consider a data set with 500 breast ultrasound images. The results show that SACE outperforms its counterparts, where the median values for the measure are: SACE: 139.4, SEN: 68.2, HEQ: 64.1, CLAHE: 62.8, and FEN: 7.9. Considering the segmentation performance results, the SACE method presents the largest accuracy, where the median values for the Jaccard index are: SACE: 0.81, FEN: 0.80, CLAHE: 0.79, HEQ: 77, and SEN: 0.63.

CONCLUSION

The SACE method performs well due to the combination of three elements: (1) the intensity variation map reduces intensity variations that could distort the real response of the mapping function, (2) the sigmoidal mapping function enhances the gray level range where the transition between lesion and background is found, and (3) the adaptive enhancing scheme for coping with local contrasts. Hence, the SACE approach is appropriate for enhancing contrast before computerized lesion segmentation.

New Fully Automated Method for Segmentation of Breast Lesions on Ultrasound Based on Texture Analysis

The study described here explored a fully automatic segmentation approach based on texture analysis for breast lesions on ultrasound images. The proposed method involves two main stages: (i) In lesion region detection, the original gray-scale image is transformed into a texture domain based on log-Gabor filters. Local texture patterns are then extracted from overlapping lattices that are further classified by a linear discriminant analysis classifier to distinguish between the "normal tissue" and "breast lesion" classes. Next, an incremental method based on the average radial derivative function reveals the region with the highest probability of being a lesion. (ii) In lesion delineation, using the detected region and the pre-processed ultrasound image, an iterative thresholding procedure based on the average radial derivative function is performed to determine the final lesion contour. The experiments are carried out on a data set of 544 breast ultrasound images (including cysts, benign solid masses and malignant lesions) acquired with three distinct ultrasound machines. In terms of the area under the receiver operating characteristic curve, the one-way analysis of variance test (α=0.05) indicates that the proposed approach significantly outperforms two published fully automatic methods (p<0.001), for which the areas under the curve are 0.91, 0.82 and 0.63, respectively. Hence, these results suggest that the log-Gabor domain improves the discrimination power of texture features to accurately segment breast lesions. In addition, the proposed approach can potentially be used for automated computer diagnosis purposes to assist physicians in detection and classification of breast masses.

A novel breast ultrasound image segmentation algorithm based on neutrosophic similarity score and level set

Breast ultrasound (BUS) image segmentation is a challenging task due to the speckle noise, poor quality of the ultrasound images and size and location of the breast lesions. In this paper, we propose a new BUS image segmentation algorithm based on neutrosophic similarity score (NSS) and level set algorithm. At first, the input BUS image is transferred to the NS domain via three membership subsets T, I and F, and then, a similarity score NSS is defined and employed to measure the belonging degree to the true tumor region. Finally, the level set method is used to segment the tumor from the background tissue region in the NSS image. Experiments have been conducted on a variety of clinical BUS images. Several measurements are used to evaluate and compare the proposed method's performance. The experimental results demonstrate that the proposed method is able to segment the BUS images effectively and accurately.

Feature Based Active Contour Method for Automatic Detection of Breast Lesions Using Ultrasound Images

Breast cancer has been increasing over the past three decades. Early detection of breast cancer is crucial for an effective treatment. Mammography is used for early detection and screening. Especially for young women, mammography procedures may not be very comfortable. Ultrasound has been one of the most powerful techniques for imaging organs and soft tissue structure in the human body. It has been used for breast cancer detection because of its non-invasive, sensitive to dense breast, low positive rate and cheap cost. But due to the nature of ultrasound image, the image suffers from poor quality caused by speckle noise. These make the automatic segmentation and classification of interested lesion difficult. One of the frequently used segmentation method is active contour. If this initial contour of active contour method is selected outside the region of interest, final segmentation and classification would be definitely incorrect. So, mostly the initial contour is manually selected in order to avoid incorrect segmentation and classification. Here implementing a method which was able to locate the initial contour automatically within the multiple lesion regions by using the wavelet soft threshold speckle reduction method, statistical features of the lesion regions and neural network and also we are able to automatically segment the lesion regions properly. This will help the radiologist to identify the lesion boundary automatically.

An effective approach of lesion segmentation within the breast ultrasound image based on the cellular automata principle

In this paper, a novel lesion segmentation within breast ultrasound (BUS) image based on the cellular automata principle is proposed. Its energy transition function is formulated based on global image information difference and local image information difference using different energy transfer strategies. First, an energy decrease strategy is used for modeling the spatial relation information of pixels. For modeling global image information difference, a seed information comparison function is developed using an energy preserve strategy. Then, a texture information comparison function is proposed for considering local image difference in different regions, which is helpful for handling blurry boundaries. Moreover, two neighborhood systems (von Neumann and Moore neighborhood systems) are integrated as the evolution environment, and a similarity-based criterion is used for suppressing noise and reducing computation complexity. The proposed method was applied to 205 clinical BUS images for studying its characteristic and functionality, and several overlapping area error metrics and statistical evaluation methods are utilized for evaluating its performance. The experimental results demonstrate that the proposed method can handle BUS images with blurry boundaries and low contrast well and can segment breast lesions accurately and effectively.

Breast ultrasound image classification based on multiple-instance learning

Breast ultrasound (BUS) image segmentation is a very difficult task due to poor image quality and speckle noise. In this paper, local features extracted from roughly segmented regions of interest (ROIs) are used to describe breast tumors. The roughly segmented ROI is viewed as a bag. And subregions of the ROI are considered as the instances of the bag. Multiple-instance learning (MIL) method is more suitable for classifying breast tumors using BUS images. However, due to the complexity of BUS images, traditional MIL method is not applicable. In this paper, a novel MIL method is proposed for solving such task. First, a self-organizing map is used to map the instance space to the concept space. Then, we use the distribution of the instances of each bag in the concept space to construct the bag feature vector. Finally, a support vector machine is employed for classifying the tumors. The experimental results show that the proposed method can achieve better performance: the accuracy is 0.9107 and the area under receiver operator characteristic curve is 0.96 (p < 0.005).

Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound

In this paper, we investigated the behavior of 22 co-occurrence statistics combined to six gray-scale quantization levels to classify breast lesions on ultrasound (BUS) images. The database of 436 BUS images used in this investigation was formed by 217 carcinoma and 219 benign lesions images. The region delimited by a minimum bounding rectangle around the lesion was employed to calculate the gray-level co-occurrence matrix (GLCM). Next, 22 co-occurrence statistics were computed regarding six quantization levels (8, 16, 32, 64, 128, and 256), four orientations (0° , 45° , 90° , and 135°), and ten distances (1, 2,...,10 pixels). Also, to reduce feature space dimensionality, texture descriptors of the same distance were averaged over all orientations, which is a common practice in the literature. Thereafter, the feature space was ranked using mutual information technique with minimal-redundancy-maximal-relevance (mRMR) criterion. Fisher linear discriminant analysis (FLDA) was applied to assess the discrimination power of texture features, by adding the first m-ranked features to the classification procedure iteratively until all of them were considered. The area under ROC curve (AUC) was used as figure of merit to measure the performance of the classifier. It was observed that averaging texture descriptors of a same distance impacts negatively the classification performance, since the best AUC of 0.81 was achieved with 32 gray levels and 109 features. On the other hand, regarding the single texture features (i.e., without averaging procedure), the quantization level does not impact the discrimination power, since AUC = 0.87 was obtained for the six quantization levels. Moreover, the number of features was reduced (between 17 and 24 features). The texture descriptors that contributed notably to distinguish breast lesions were contrast and correlation computed from GLCMs with orientation of 90° and distance more than five pixels.

Segmentation of ultrasonic breast tumors based on homogeneous patch

PURPOSE

Accurately segmenting breast tumors in ultrasound (US) images is a difficult problem due to their specular nature and appearance of sonographic tumors. The current paper presents a variant of the normalized cut (NCut) algorithm based on homogeneous patches (HP-NCut) for the segmentation of ultrasonic breast tumors.

METHODS

A novel boundary-detection function is defined by combining texture and intensity information to find the fuzzy boundaries in US images. Subsequently, based on the precalculated boundary map, an adaptive neighborhood according to image location referred to as a homogeneous patch (HP) is proposed. HPs are guaranteed to spread within the same tissue region; thus, the statistics of primary features within the HPs is more reliable in distinguishing the different tissues and benefits subsequent segmentation. Finally, the fuzzy distribution of textons within HPs is used as final image features, and the segmentation is obtained using the NCut framework.

RESULTS

The HP-NCut algorithm was evaluated on a large dataset of 100 breast US images (50 benign and 50 malignant). The mean Hausdorff distance measure, the mean minimum Euclidean distance measure and similarity measure achieved 7.1 pixels, 1.58 pixels, and 86.67%, respectively, for benign tumors while those achieved 10.57 pixels, 1.98 pixels, and 84.41%, respectively, for malignant tumors.

CONCLUSIONS

The HP-NCut algorithm provided the improvement in accuracy and robustness compared with state-of-the-art methods. A conclusion that the HP-NCut algorithm is suitable for ultrasonic tumor segmentation problems can be drawn.

Completely automated segmentation approach for breast ultrasound images using multiple-domain features

Lesion segmentation is a challenging task for computer aided diagnosis systems. In this article, we propose a novel and fully automated segmentation approach for breast ultrasound (BUS) images. The major contributions of this work are: an efficient region-of-interest (ROI) generation method is developed and new features to characterize lesion boundaries are proposed. After a ROI is located automatically, two newly proposed lesion features (phase in max-energy orientation and radial distance), combined with a traditional intensity-and-texture feature, are utilized to detect the lesion by a trained artificial neural network. The proposed features are tested on a database of 120 images and the experimental results prove their strong distinguishing ability. Compared with other breast ultrasound segmentation methods, the proposed method improves the TP rate from 84.9% to 92.8%, similarity rate from 79.0% to 83.1% and reduces the FP rate from 14.1% to 12.0%, using the same database. In addition, sensitivity analysis demonstrates the robustness of the proposed method.

The feasibility of hybrid automatic segmentation of axillary lymph nodes from a 3-D sonogram

The use of manual segmentation of lymph nodes, within an ultrasound image, is challenging due to operator dependency and speckle. A group of 23 healthy female volunteers consented to a short imaging session to capture a maximum of three axillary lymph nodes. A feasibility study was completed using both automatic and manual segmentation techniques to analyze a sample of 45, three-dimensional (3-D) nodal volume sets. Level-set segmentation based on geodesic active contours and shape-space learning based on a level-set segmentation approach was used to capture global node shapes. Most of the image feature based segmentation methods failed; however, a more precise automatic segmentation algorithm was obtained using a superimposed shape model. Shape model based segmentation significantly improved the segmentation compared with standard level sets. The best segmentation results were achieved when an experienced sonographer assisted with setting seed surfaces. The initialization of seed surfaces improved the capture of the global shape and lymphatic vessels.

Automatic detection and classification of breast tumors in ultrasonic images using texture and morphological features

Due to severe presence of speckle noise, poor image contrast and irregular lesion shape, it is challenging to build a fully automatic detection and classification system for breast ultrasonic images. In this paper, a novel and effective computer-aided method including generation of a region of interest (ROI), segmentation and classification of breast tumor is proposed without any manual intervention. By incorporating local features of texture and position, a ROI is firstly detected using a self-organizing map neural network. Then a modified Normalized Cut approach considering the weighted neighborhood gray values is proposed to partition the ROI into clusters and get the initial boundary. In addition, a regional-fitting active contour model is used to adjust the few inaccurate initial boundaries for the final segmentation. Finally, three textures and five morphologic features are extracted from each breast tumor; whereby a highly efficient Affinity Propagation clustering is used to fulfill the malignancy and benign classification for an existing database without any training process. The proposed system is validated by 132 cases (67 benignancies and 65 malignancies) with its performance compared to traditional methods such as level set segmentation, artificial neural network classifiers, and so forth. Experiment results show that the proposed system, which needs no training procedure or manual interference, performs best in detection and classification of ultrasonic breast tumors, while having the lowest computation complexity.

Group average difference: a termination criterion for active contour

This paper presents a termination criterion for active contour that does not involve alteration of the energy functional. The criterion is based on the area difference of the contour during evolution. In this criterion, the evolution of the contour terminates when the area difference fluctuates around a constant. The termination criterion is tested using parametric gradient vector flow active contour with contour resampling and normal force selection. The usefulness of the criterion is shown through its trend, speed, accuracy, shape insensitivity, and insensitivity to contour resampling. The metric used in the proposed criterion demonstrated a steadily decreasing trend. For automatic implementation in which different shapes need to be segmented, the proposed criterion demonstrated almost 50% and 60% total time reduction while achieving similar accuracy as compared with the pixel movement-based method in the segmentation of synthetic and real medical images, respectively. Our results also show that the proposed termination criterion is insensitive to shape variation and contour resampling. The criterion also possesses potential to be used for other kinds of snakes.

ACCOMP: Augmented cell competition algorithm for breast lesion demarcation in sonography

PURPOSE

Fully automatic and high-quality demarcation of sonographical breast lesions remains a far-reaching goal. This article aims to develop an image segmentation algorithm that provides quality delineation of breast lesions in sonography with a simple and friendly semiautomatic scheme.

METHODS

A data-driven image segmentation algorithm, named as augmented cell competition (ACCOMP) algorithm, is developed to delineate breast lesion boundaries in ultrasound images. Inspired by visual perceptual experience and Gestalt principles, the ACCOMP algorithm is constituted of two major processes, i.e., cell competition and cell-based contour grouping. The cell competition process drives cells, i.e., the catchment basins generated by a two-pass watershed transformation, to merge and split into prominent components. A prominent component is defined as a relatively large and homogeneous region circumscribed by a perceivable boundary. Based on the prominent component tessellation, cell-based contour grouping process seeks the best closed subsets of edges in the prominent component structure as the desirable boundary candidates. Finally, five boundary candidates with respect to five devised boundary cost functions are suggested by the ACCOMP algorithm for user selection. To evaluate the efficacy of the ACCOMP algorithm on breast lesions with complicated echogenicity and shapes, 324 breast sonograms, including 199 benign and 125 malignant lesions, are adopted as testing data. The boundaries generated by the ACCOMP algorithm are compared to manual delineations, which were confirmed by four experienced medical doctors. Four assessment metrics, including the modified Williams index, percentage statistic, overlapping ratio, and difference ratio, are employed to see if the ACCOMP-generated boundaries are comparable to manual delineations. A comparative study is also conducted by implementing two pixel-based segmentation algorithms. The same four assessment metrics are employed to evaluate the boundaries generated by two conventional pixel-based algorithms based on the same set of manual delineations.

RESULTS

The ACCOMP-generated boundaries are shown to be comparable to the manual delineations. Particularly, the modified Williams indices of the boundaries generated by the ACCOMP algorithm and the first and second pixel-based algorithms are 1.069 +/- 0.024, 0.935 +/- 0.024, and 0.579 +/- 0.013, respectively. If the modified Williams index is greater than or equal to 1, the average distance between the computer-generated boundaries and manual delineations is deemed to be comparable to that between the manual delineations.

CONCLUSIONS

The boundaries derived by the ACCOMP algorithm are shown to reasonably demarcate sonographic breast lesions, especially for the cases with complicated echogenicity and shapes. It suggests that the ACCOMP-generated boundaries can potentially serve as the basis for further morphological or quantitative analysis.

CAD algorithms for solid breast masses discrimination: evaluation of the accuracy and interobserver variability

For a successful computer-aided diagnosis (CAD) approach, investigating the benefit of the output for radiologist diagnosis is as important as developing the computer algorithm itself. To evaluate the accuracy and the interobserver variability of two newly developed CAD algorithms for breast mass discrimination, eight radiologists with varied experience in breast ultrasonography (US) independently reviewed the lesions according to Breast Imaging Reporting and Data System (BI-RADS)-US. They interpreted the original ultrasound images, provided a final assessment category to indicate the probability of malignancy and then made a further diagnosis using the images processed by the proposed CAD algorithms. The receiver operating characteristic (ROC) curve and Cohen's kappa statistics were employed to evaluate the effect of the CAD algorithms on radiologist diagnoses. By using the proposed CAD approach, the quality of the images was improved and more information was provided to the observers. With the processed images, the areas under the ROC (Az) of each reader (0.86 approximately 0.89) were greater than those with the original ultrasound images (0.81 approximately 0.86) and all the radiologists improved their performance significantly (p < 0.05) except two senior radiologists (p > 0.05). The Az values of the junior radiologists with CAD were comparable to those of the senior radiologists. Cohen's kappa statistics showed that better interobserver agreement was obtained by using the processed images. We conclude that the proposed CAD method is more helpful for the junior radiologists than for the senior ones and it also showed the advantage of decreasing interobserver variability.