A cost-sensitive extension of AdaBoost with markov random field priors for automated segmentation of breast tumors in ultrasonic images

Takemura, Akihiro; Shimizu, A.; Hamamoto, Kazuhiko

doi:10.1007/s11548-010-0411-1

Cited by 15 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tumor segmentation can be regarded as pixel-level binary classification task. Traditional classifiers such as SVM [11]- [13], adaboost [14] and K-means [15], [16] are used to learn the statistical characteristics of tumor regions. Daoud et al [17] proposed an accurate and automatic algorithm to segment breast ultrasound images by combining image boundary and region information.…”

Section: Related Workmentioning

confidence: 99%

“…Takemura et al proposed a novel cost-sensitive AdaBoost model which introduced the Markov random field (MRF) priors for breast tumor segmentation. The proposed method can improve the segmentation performance by avoiding irregular shape, isolated points and holes [14]. Sadek et al [16] used normalized cuts approach to segment ultrasound images into regions of interest where they can possibly finds the lesion, and then K-means classifier is applied to decide finally the location of the lesion.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Label-Distribution Learning-Embedded Active Contour Model for Breast Tumor Segmentation

Meng

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Tumor segmentation is the foundation of breast ultrasound image analysis. However, intensity inhomogeneity occurred in ultrasound images results in the ambiguous segmentation. In order to tackle the challenge, this paper proposed label-distribution learning embedded active contour model for the breast tumor segmentation. Considering that reasonable exploitation of label ambiguity may help to improve performance, a deep pixel-wise label distribution learning model is first proposed to learn an ambiguous label map. The learned map is independent on the intensity variation, which is robust to the intensity inhomogeneity. After that, a novel label distribution learning embedded active contour model is proposed. The new energy function is developed by introducing the new label distribution fitting energy into the active contour model framework. The proposed new fitting energy can enforce the label of pixels to be similar to the learned distribution map, which improves the robustness to the intensity inhomogeneity. To demonstrate the effectiveness of the proposed method, we conduct the experiment on the breast ultrasound images database which consists of 135 benign cases and 51 malignant cases. Our experimental results demonstrated that the proposed method outperforms the state of the art.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Label-Distribution Learning-Embedded Active Contour Model for Breast Tumor Segmentation

Meng

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Methods based on active contour models can obtain tumor contours by minimizing the sum of internal and external energies 16 ; however, these techniques are generally semiautomatic segmentation methods, which require initial contours to be set manually. Markov random field‐based methods can provide a strong exploitation of pixel correlations, 17 but its iteration process is complex and time‐consuming. A previous work 18 tried to speed up multi‐atlas segmentation by implementing corrective learning in a multi‐scale analysis way, but time consumed deformable registration still is required.…”

Section: Introductionmentioning

confidence: 99%

An attention‐supervised full‐resolution residual network for the segmentation of breast ultrasound images

Shi

Hou

et al. 2020

Medical Physics

View full text Add to dashboard Cite

Purpose Breast cancer is the most common cancer among women worldwide. Medical ultrasound imaging is one of the widely applied breast imaging methods for breast tumors. Automatic breast ultrasound (BUS) image segmentation can measure the size of tumors objectively. However, various ultrasound artifacts hinder segmentation. We proposed an attention‐supervised full‐resolution residual network (ASFRRN) to segment tumors from BUS images. Methods In the proposed method, Global Attention Upsample (GAU) and deep supervision were introduced into a full‐resolution residual network (FRRN), where GAU learns to merge features at different levels with attention for deep supervision. Two datasets were employed for evaluation. One (Dataset A) consisted of 163 BUS images with tumors (53 malignant and 110 benign) from UDIAT Centre Diagnostic, and the other (Dataset B) included 980 BUS images with tumors (595 malignant and 385 benign) from the Sun Yat‐sen University Cancer Center. The tumors from both datasets were manually segmented by medical doctors. For evaluation, the Dice coefficient (Dice), Jaccard similarity coefficient (JSC), and F1 score were calculated. Results For Dataset A, the proposed method achieved higher Dice (84.3 ± 10.0%), JSC (75.2 ± 10.7%), and F1 score (84.3 ± 10.0%) than the previous best method: FRRN. For Dataset B, the proposed method also achieved higher Dice (90.7 ± 13.0%), JSC (83.7 ± 14.8%), and F1 score (90.7 ± 13.0%) than the previous best methods: DeepLabv3 and dual attention network (DANet). For Dataset A + B, the proposed method achieved higher Dice (90.5 ± 13.1%), JSC (83.3 ± 14.8%), and F1 score (90.5 ± 13.1%) than the previous best method: DeepLabv3. Additionally, the parameter number of ASFRRN was only 10.6 M, which is less than those of DANet (71.4 M) and DeepLabv3 (41.3 M). Conclusions We proposed ASFRRN, which combined with FRRN, attention mechanism, and deep supervision to segment tumors from BUS images. It achieved high segmentation accuracy with a reduced parameter number.

show abstract

“…Many automatic BUS image segmentation methods have been proposed. 7,8,10,11,14,15,18,[30][31][32] Automatic segmentation methods can reduce intra-and interoperator variance. In general, these techniques have two steps: (a) region of interest (ROI) detection, for instance, using machine learning techniques and (b) ROI segmentation, that is, extracting the tumor contour from the ROI determined in Step 1.…”

Section: Introductionmentioning

confidence: 99%

“…Many techniques have been developed for US image segmentation. An extensive review of US image segmentation methods was performed by Noble and Boukerroui, 6 and a systematic review of BUS image segmentation and classification methods was conducted by Cheng et al 17 BUS image segmentation techniques include histogram thresholding, 7 region growing, 7,8,14 model-based (active contour models or snakes, 8,9 level set, 10,28,29,32 Markov random fields 11,30 ), graph-based, 12,13 neural network, 7,31 and watershed. 15,16 Table 1 summarizes some selected BUS image segmentation methods in the following aspects: number of cases (images), accuracy, level of automation, and time efficiency.…”

Section: Introductionmentioning

confidence: 99%

Semi-automatic Breast Ultrasound Image Segmentation Based on Mean Shift and Graph Cuts

Zhou

et al. 2014

Ultrason Imaging

View full text Add to dashboard Cite

Computerized tumor segmentation on breast ultrasound (BUS) images remains a challenging task. In this paper, we proposed a new method for semi-automatic tumor segmentation on BUS images using Gaussian filtering, histogram equalization, mean shift, and graph cuts. The only interaction required was to select two diagonal points to determine a region of interest (ROI) on an input image. The ROI image was shrunken by a factor of 2 using bicubic interpolation to reduce computation time. The shrunken image was smoothed by a Gaussian filter and then contrast-enhanced by histogram equalization. Next, the enhanced image was filtered by pyramid mean shift to improve homogeneity. The object and background seeds for graph cuts were automatically generated on the filtered image. Using these seeds, the filtered image was then segmented by graph cuts into a binary image containing the object and background. Finally, the binary image was expanded by a factor of 2 using bicubic interpolation, and the expanded image was processed by morphological opening and closing to refine the tumor contour. The method was implemented with OpenCV 2.4.3 and Visual Studio 2010 and tested for 38 BUS images with benign tumors and 31 BUS images with malignant tumors from different ultrasound scanners. Experimental results showed that our method had a true positive rate (TP) of 91.7%, a false positive (FP) rate of 11.9%, and a similarity (SI) rate of 85.6%. The mean run time on Intel Core 2.66 GHz CPU and 4 GB RAM was 0.49 ± 0.36 s. The experimental results indicate that the proposed method may be useful in BUS image segmentation.

show abstract

A cost-sensitive extension of AdaBoost with markov random field priors for automated segmentation of breast tumors in ultrasonic images

Abstract: A cost-sensitive extension of AdaBoost based on MRF priors provides an efficient and accurate means for the segmentation of tumors in breast ultrasound images.

Cited by 15 publications

References 14 publications

Label-Distribution Learning-Embedded Active Contour Model for Breast Tumor Segmentation

Label-Distribution Learning-Embedded Active Contour Model for Breast Tumor Segmentation

An attention‐supervised full‐resolution residual network for the segmentation of breast ultrasound images

Semi-automatic Breast Ultrasound Image Segmentation Based on Mean Shift and Graph Cuts

Contact Info

Product

Resources

About