Lesion segmentation in breast ultrasound images using the optimized marked watershed method

Curated benchmark dataset for ultrasound based breast lesion analysis

A new detailed dataset of breast ultrasound scans (BrEaST) containing images of benign and malignant lesions as well as normal tissue examples, is presented. The dataset consists of 256 breast scans collected from 256 patients. Each scan was manually annotated and labeled by a radiologist experienced in breast ultrasound examination. In particular, each tumor was identified in the image using a freehand annotation and labeled according to BIRADS features and lexicon. The histopathological classification of the tumor was also provided for patients who underwent a biopsy. The BrEaST dataset is the first breast ultrasound dataset containing patient-level labels, image-level annotations, and tumor-level labels with all cases confirmed by follow-up care or core needle biopsy result. To enable research into breast disease detection, tumor segmentation and classification, the BrEaST dataset is made publicly available with the CC-BY 4.0 license.

Accurate segmentation of breast tumor in ultrasound images through joint training and refined segmentation

Objective. This paper proposes an automatic breast tumor segmentation method for two-dimensional (2D) ultrasound images, which is significantly more accurate, robust, and adaptable than common deep learning models on small datasets. Approach. A generalized joint training and refined segmentation framework (JR) was established, involving a joint training module (J module ) and a refined segmentation module (R module ). In J module , two segmentation networks are trained simultaneously, under the guidance of the proposed Jocor for Segmentation (JFS) algorithm. In R module , the output of J module is refined by the proposed area first (AF) algorithm, and marked watershed (MW) algorithm. The AF mainly reduces false positives, which arise easily from the inherent features of breast ultrasound images, in the light of the area, distance, average radical derivative (ARD) and radical gradient index (RGI) of candidate contours. Meanwhile, the MW avoids over-segmentation, and refines segmentation results. To verify its performance, the JR framework was evaluated on three breast ultrasound image datasets. Image dataset A contains 1036 images from local hospitals. Image datasets B and C are two public datasets, containing 562 images and 163 images, respectively. The evaluation was followed by related ablation experiments. Main results. The JR outperformed the other state-of-the-art (SOTA) methods on the three image datasets, especially on image dataset B. Compared with the SOTA methods, the JR improved true positive ratio (TPR) and Jaccard index (JI) by 1.5% and 3.2%, respectively, and reduces (false positive ratio) FPR by 3.7% on image dataset B. The results of the ablation experiments show that each component of the JR matters, and contributes to the segmentation accuracy, particularly in the reduction of false positives. Significance. This study successfully combines traditional segmentation methods with deep learning models. The proposed method can segment small-scale breast ultrasound image datasets efficiently and effectively, with excellent generalization performance.

Graphical Image Region Extraction with K-Means Clustering and Watershed

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

Fus2Net: a novel Convolutional Neural Network for classification of benign and malignant breast tumor in ultrasound images

BACKGROUND

The rapid development of artificial intelligence technology has improved the capability of automatic breast cancer diagnosis, compared to traditional machine learning methods. Convolutional Neural Network (CNN) can automatically select high efficiency features, which helps to improve the level of computer-aided diagnosis (CAD). It can improve the performance of distinguishing benign and malignant breast ultrasound (BUS) tumor images, making rapid breast tumor screening possible.

RESULTS

The classification model was evaluated with a different dataset of 100 BUS tumor images (50 benign cases and 50 malignant cases), which was not used in network training. Evaluation indicators include accuracy, sensitivity, specificity, and area under curve (AUC) value. The results in the Fus2Net model had an accuracy of 92%, the sensitivity reached 95.65%, the specificity reached 88.89%, and the AUC value reached 0.97 for classifying BUS tumor images.

CONCLUSIONS

The experiment compared the existing CNN-categorized architecture, and the Fus2Net architecture we customed has more advantages in a comprehensive performance. The obtained results demonstrated that the Fus2Net classification method we proposed can better assist radiologists in the diagnosis of benign and malignant BUS tumor images.

METHODS

The existing public datasets are small and the amount of data suffer from the balance issue. In this paper, we provide a relatively larger dataset with a total of 1052 ultrasound images, including 696 benign images and 356 malignant images, which were collected from a local hospital. We proposed a novel CNN named Fus2Net for the benign and malignant classification of BUS tumor images and it contains two self-designed feature extraction modules. To evaluate how the classifier generalizes on the experimental dataset, we employed the training set (646 benign cases and 306 malignant cases) for tenfold cross-validation. Meanwhile, to solve the balance of the dataset, the training data were augmented before being fed into the Fus2Net. In the experiment, we used hyperparameter fine-tuning and regularization technology to make the Fus2Net convergence.