Cell-competition algorithm: a new segmentation algorithm for multiple objects with irregular boundaries in ultrasound images

BUSIS: A Benchmark for Breast Ultrasound Image Segmentation

Breast ultrasound (BUS) image segmentation is challenging and critical for BUS computer-aided diagnosis (CAD) systems. Many BUS segmentation approaches have been studied in the last two decades, but the performances of most approaches have been assessed using relatively small private datasets with different quantitative metrics, which results in a discrepancy in performance comparison. Therefore, there is a pressing need for building a benchmark to compare existing methods using a public dataset objectively, to determine the performance of the best breast tumor segmentation algorithm available today, and to investigate what segmentation strategies are valuable in clinical practice and theoretical study. In this work, a benchmark for B-mode breast ultrasound image segmentation is presented. In the benchmark, (1) we collected 562 breast ultrasound images and proposed standardized procedures to obtain accurate annotations using four radiologists; (2) we extensively compared the performance of 16 state-of-the-art segmentation methods and demonstrated that most deep learning-based approaches achieved high dice similarity coefficient values (DSC ≥ 0.90) and outperformed conventional approaches; (3) we proposed the losses-based approach to evaluate the sensitivity of semi-automatic segmentation to user interactions; and (4) the successful segmentation strategies and possible future improvements were discussed in details.

A Multi-Task Learning Framework for Automated Segmentation and Classification of Breast Tumors From Ultrasound Images

Breast cancer is one of the most fatal diseases leading to the death of several women across the world. But early diagnosis of breast cancer can help to reduce the mortality rate. So an efficient multi-task learning approach is proposed in this work for the automatic segmentation and classification of breast tumors from ultrasound images. The proposed learning approach consists of an encoder, decoder, and bridge blocks for segmentation and a dense branch for the classification of tumors. For efficient classification, multi-scale features from different levels of the network are used. Experimental results show that the proposed approach is able to enhance the accuracy and recall of segmentation by 1.08%, 4.13%, and classification by 1.16%, 2.34%, respectively than the methods available in the literature.

Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images

Tumor classification and segmentation are two important tasks for computer-aided diagnosis (CAD) using 3D automated breast ultrasound (ABUS) images. However, they are challenging due to the significant shape variation of breast tumors and the fuzzy nature of ultrasound images (e.g., low contrast and signal to noise ratio). Considering the correlation between tumor classification and segmentation, we argue that learning these two tasks jointly is able to improve the outcomes of both tasks. In this paper, we propose a novel multi-task learning framework for joint segmentation and classification of tumors in ABUS images. The proposed framework consists of two sub-networks: an encoder-decoder network for segmentation and a light-weight multi-scale network for classification. To account for the fuzzy boundaries of tumors in ABUS images, our framework uses an iterative training strategy to refine feature maps with the help of probability maps obtained from previous iterations. Experimental results based on a clinical dataset of 170 3D ABUS volumes collected from 107 patients indicate that the proposed multi-task framework improves tumor segmentation and classification over the single-task learning counterparts.

Automatic Identification of Human Blastocyst Components via Texture

Choosing the most viable embryo during human in vitro fertilization (IVF) is a prime factor in maximizing pregnancy rate. Embryologists visually inspect morphological structures of blastocysts under microscopes to gauge their health. Such grading introduces subjectivity amongst embryologists and adds to the difficulty of quality control during IVF. In this paper, we introduce an algorithm for automatic segmentation of two main components of human blastocysts named: Trophectoderm (TE) and inner cell mass (ICM). We utilize texture information along with biological and physical characteristics of day-5 human embryos (blastocysts) to identify TE or ICM regions according to their intrinsic properties. Both these regions are highly textured and very similar in the quality of their texture, and they often look connected to each other when imaged. These attributes make their automatic identification and separation from each other a difficult task even for an expert embryologist. By automatically identifying TE and ICM regions, we offer the opportunity to perform more detailed assessment of blastocysts. This could help in analyzing, in a quantitative way, various visual/geometrical characteristics of these regions that when combined with the pregnancy outcome can determine the predictive values of such attributes. Our work aids future research in understanding why certain embryos have higher pregnancy success rates. This paper is tested on a set of 211 blastocyst images. We report an accuracy of 86.6% for identification of TE and 91.3% for ICM.

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 with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

This paper performs a comprehensive study on the deep-learning-based computer-aided diagnosis (CADx) for the differential diagnosis of benign and malignant nodules/lesions by avoiding the potential errors caused by inaccurate image processing results (e.g., boundary segmentation), as well as the classification bias resulting from a less robust feature set, as involved in most conventional CADx algorithms. Specifically, the stacked denoising auto-encoder (SDAE) is exploited on the two CADx applications for the differentiation of breast ultrasound lesions and lung CT nodules. The SDAE architecture is well equipped with the automatic feature exploration mechanism and noise tolerance advantage, and hence may be suitable to deal with the intrinsically noisy property of medical image data from various imaging modalities. To show the outperformance of SDAE-based CADx over the conventional scheme, two latest conventional CADx algorithms are implemented for comparison. 10 times of 10-fold cross-validations are conducted to illustrate the efficacy of the SDAE-based CADx algorithm. The experimental results show the significant performance boost by the SDAE-based CADx algorithm over the two conventional methods, suggesting that deep learning techniques can potentially change the design paradigm of the CADx systems without the need of explicit design and selection of problem-oriented features.

Automatic Segmentation of the Corpus Callosum Using a Cell-Competition Algorithm: Diffusion Tensor Imaging-Based Evaluation of Callosal Atrophy and Tissue Alterations in Patients With Systemic Lupus Erythematosus

OBJECTIVE

Patients with neuropsychiatric systemic lupus erythematosus (NPSLE) may exhibit corpus callosal atrophy and tissue alterations. Measuring the callosal volume and tissue integrity using diffusion tensor imaging (DTI) could help to differentiate patients with NPSLE from patients without NPSLE. Hence, this study aimed to use an automatic cell-competition algorithm to segment the corpus callosum and to investigate the effects of central nervous system (CNS) involvement on the callosal volume and tissue integrity in patients with SLE.

METHODS

Twenty-two SLE patients with (N = 10, NPSLE) and without (N = 12, non-NPSLE) CNS involvement and 22 control subjects were enrolled in this study. For volumetric measurement, a cell-competition algorithm was used to automatically delineate corpus callosal boundaries based on a midsagittal fractional anisotropy (FA) map. After obtaining corpus callosal boundaries for all subjects, the volume, FA, and mean diffusivity (MD) of the corpus callosum were calculated. A post hoc Tamhane's T2 analysis was performed to statistically compare differences among NPSLE, non-NPSLE, and control subjects. A receiver operating characteristic curve analysis was also performed to compare the performance of the volume, FA, and MD of the corpus callosum in differentiating NPSLE from other subjects.

RESULTS

Patients with NPSLE had significant decreases in volume and FA but an increase in MD in the corpus callosum compared with control subjects, whereas no significant difference was noted between patients without NPSLE and control subjects. The FA was found to have better performance in differentiating NPSLE from other subjects.

CONCLUSIONS

A cell-competition algorithm could be used to automatically evaluate callosal atrophy and tissue alterations. Assessments of the corpus callosal volume and tissue integrity helped to demonstrate the effects of CNS involvement in patients with SLE.

Automated image analysis of lung branching morphogenesis from microscopic images of fetal rat explants

Background. Regulating mechanisms of branching morphogenesis of fetal lung rat explants have been an essential tool for molecular research. This work presents a new methodology to accurately quantify the epithelial, outer contour, and peripheral airway buds of lung explants during cellular development from microscopic images. Methods. The outer contour was defined using an adaptive and multiscale threshold algorithm whose level was automatically calculated based on an entropy maximization criterion. The inner lung epithelium was defined by a clustering procedure that groups small image regions according to the minimum description length principle and local statistical properties. Finally, the number of peripheral buds was counted as the skeleton branched ends from a skeletonized image of the lung inner epithelia. Results. The time for lung branching morphometric analysis was reduced in 98% in contrast to the manual method. Best results were obtained in the first two days of cellular development, with lesser standard deviations. Nonsignificant differences were found between the automatic and manual results in all culture days. Conclusions. The proposed method introduces a series of advantages related to its intuitive use and accuracy, making the technique suitable to images with different lighting characteristics and allowing a reliable comparison between different researchers.

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.

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.

Intensity inhomogeneity correction for the breast sonogram: constrained fuzzy cell-based bipartitioning and polynomial surface modeling

PURPOSE

To develop an intensity inhomogeneity algorithm for breast sonograms in order to assist visual identification and automatic delineation of lesion boundaries.

METHODS

The proposed algorithm was composed of two essential ideas. One was decomposing the region of interest (ROI) into foreground and background regions by a cell-based segmentation algorithm, called constrained fuzzy cell-based bipartition-EM (CFCB-EM) algorithm. The CFCB-EM algorithm deformed the contour in a fuzzy cell-based deformation fashion with the cell structures derived by the fuzzy cell competition (FCC) algorithm as the deformation unit and the boundary estimated by the normalized cut (NC) algorithm as the reference contour. The other was modeling the intensity inhomogeneity in an ROI as a spatially variant normal distribution with a constant variance and spatially variant means, which formed a polynomial surface of order n. The proposed algorithm was formulated as a nested EM algorithm comprising the outer-layer EM algorithm, i.e., the intensity inhomogeneity correction-EM (IIC-EM) algorithm, and the inner-layer EM algorithm, i.e., the CFCB-EM algorithm. The E step of the IIC-EM algorithm was to provide a reasonably good bipartition separating the ROI into foreground and background regions, which included three major component algorithms, namely, the FCC, the NC, and the CFCB-EM. The M step of the IIC-EM algorithm was to estimate and correct the intensity inhomogeneity field by least-squared fitting the intensity inhomogeneity to an nth order polynomial surface. Forty-nine breast sonograms with intensity inhomogeneity, each from a different subject, were randomly selected for performance analysis. Three assessments were carried out to evaluate the effectiveness of the proposed algorithm.

RESULTS

Based on the visual evaluation of two experienced radiologists, in the first assessment, 46 out of 49 breast lesions were considered to have better contrasts on the inhomogeneity-corrected images by both radiologists. The interrater reliability for the radiologists was found to be kappa = 0.479 (p = 0.001). In the second assessment, the mean gradients of the low-gradient boundary points before and after correction of the intensity inhomogeneity were compared by the paired t-test, yielding a p-value of 0.000, which suggested the proposed intensity inhomogeneity algorithm may enhance the mean gradient of the low-gradient boundary points. By using the paired t-test, the third assessment further showed that the Chan and Vese level set method could derive a much better lesion boundary on the inhomogeneity-corrected image than on the original image (p = 0.000).

CONCLUSIONS

The proposed intensity inhomogeneity correction algorithm could not only augment the visibility of lesion boundary but also improve the segmentation result on a breast sonogram.

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

Because of its complicated structure, low signal/noise ratio, low contrast and blurry boundaries, fully automated segmentation of a breast ultrasound (BUS) image is a difficult task. In this paper, a novel segmentation method for BUS images without human intervention is proposed. Unlike most published approaches, the proposed method handles the segmentation problem by using a two-step strategy: ROI generation and ROI segmentation. First, a well-trained texture classifier categorizes the tissues into different classes, and the background knowledge rules are used for selecting the regions of interest (ROIs) from them. Second, a novel probability distance-based active contour model is applied for segmenting the ROIs and finding the accurate positions of the breast tumors. The active contour model combines both global statistical information and local edge information, using a level set approach. The proposed segmentation method was performed on 103 BUS images (48 benign and 55 malignant). To validate the performance, the results were compared with the corresponding tumor regions marked by an experienced radiologist. Three error metrics, true-positive ratio (TP), false-negative ratio (FN) and false-positive ratio (FP) were used for measuring the performance of the proposed method. The final results (TP = 91.31%, FN = 8.69% and FP = 7.26%) demonstrate that the proposed method can segment BUS images efficiently, quickly and automatically.

An automatic segmentation approach for boundary delineation of corpus callosum based on cell competition

The size and shape of corpus callosum are important indicators for assisting diagnosis of many neurological diseases involving morphological changes of corpus callosum. A new automatic segmentation approach was proposed in this paper for boundary delineation of corpus callosum. The basic idea of the proposed approach was to perform segmentation on the red component of color-coded map of diffusion tensor magnetic resonance image (MR-DTI). The boundary of corpus callosum was delineated in two phases. Firstly, a rough boundary surrounding corpus callosum was derived by using a built-in contour function in Matlab. Then, this cell competition algorithm was applied to the area inside the rough boundary derived in the first phase. The proposed segmentation approach has been evaluated and compared to the Chan and Vese level set method by using the MR-DTI images of a healthy volunteer and a systemic lupus erythematorsus (SLE) patient. The implementation results showed that the proposed approach could delineate the boundaries of corpus callosum reasonably well for both cases, whereas the Chan and Vese level set method failed to catch the weak edge for the SLE patient.

Cell-based two-region competition algorithm with a map framework for boundary delineation of a series of 2D ultrasound images

To ensure the delineated boundaries of a series of 2-D images closely following the visually perceivable edges with high boundary coherence between consecutive slices, a cell-based two-region competition algorithm based on a maximum a posteriori (MAP) framework is proposed. It deforms the region boundary in a cell-by-cell fashion through a cell-based two-region competition process. The cell-based deformation is guided by a cell-based MAP framework with a posterior function characterizing the distribution of the cell means in each region, the salience and shape complexity of the region boundary and the boundary coherence of the consecutive slices. The proposed algorithm has been validated using 10 series of breast sonograms, including seven compression series and three freehand series. The compression series contains two carcinoma and five fibroadenoma cases and the freehand series contains two carcinoma and one fibroadenoma cases. The results show that >70% of the derived boundaries fall within the span of the manually delineated boundaries. The robustness of the proposed algorithm to the variation of regions-of-interest is confirmed by the Friedman tests and the p-values of which are 0.517 and 0.352 for the compression and freehand series groups, respectively. The Pearson's correlations between the lesion sizes derived by the proposed algorithm and those defined by the average manually delineated boundaries are all higher than 0.990. The overlapping and difference ratios between the derived boundaries and the average manually delineated boundaries are mostly higher than 0.90 and lower than 0.13, respectively. For both series groups, all assessments conclude that the boundaries derived by the proposed algorithm be comparable to those delineated manually. Moreover, it is shown that the proposed algorithm is superior to the Chan and Vese level set method based on the paired-sample t-tests on the performance indices at a 5% significance level.

A hybrid multi-scale model for thyroid nodule boundary detection on ultrasound images

A hybrid model for thyroid nodule boundary detection on ultrasound images is introduced. The segmentation model combines the advantages of the "á trous" wavelet transform to detect sharp gray-level variations and the efficiency of the Hough transform to discriminate the region of interest within an environment with excessive structural noise. The proposed method comprise three major steps: a wavelet edge detection procedure for speckle reduction and edge map estimation, based on local maxima representation. Subsequently, a multiscale structure model is utilised in order to acquire a contour representation by means of local maxima chaining with similar attributes to form significant structures. Finally, the Hough transform is employed with 'a priori' knowledge related to the nodule's shape in order to distinguish the nodule's contour from adjacent structures. The comparative study between our automatic method and manual delineations demonstrated that the boundaries extracted by the hybrid model are closely correlated with that of the physicians. The proposed hybrid method can be of value to thyroid nodules' shape-based classification and as an educational tool for inexperienced radiologists.