Showing papers by "Heng-Da Cheng published in 2018"

New Neutrosophic Approach to Image Segmentation

Abstract: Neutrosophic set (NS), a part of neutrosophy theory, studies the origin, nature and scope of neutralities, as well as their interactions with different ideational spectra. NS is a formal framework that has been recently proposed. However, NS needs to be specified from a technical point of view for a given application or field. We apply NS, after defining some concepts and operations, for image segmentation. The image is transformed into the NS domain, which is described using three membership sets: T, I and F. The entropy in NS is defined and employed to evaluate the indeterminacy. Two operations, @a-mean and @b-enhancement operations are proposed to reduce the set indeterminacy. Finally, the proposed method is employed to perform image segmentation using a @c-means clustering. We have conducted experiments on a variety of images. The experimental results demonstrate that the proposed approach can segment the images automatically and effectively. Especially, it can segment the ''clean'' images and the images having noise with different noise levels.

Unified Approach to Pavement Crack and Sealed Crack Detection Using Preclassification Based on Transfer Learning

Abstract: This work focuses on solving two challenging problems in pavement crack detection: (1) noises caused by complicated pavement textures and intensity inhomogeneity cannot be removed effective...

A Benchmark for Breast Ultrasound Image Segmentation (BUSIS)

Abstract: Breast ultrasound (BUS) image segmentation is challenging and critical for BUS Computer-Aided Diagnosis (CAD) systems. Many BUS segmentation approaches have been proposed in the last two decades, but the performances of most approaches have been assessed using relatively small private datasets with different quantitative metrics, which result in discrepancy in performance comparison.

Medical Knowledge Constrained Semantic Breast Ultrasound Image Segmentation

Abstract: Computer-aided diagnosis (CAD) can help doctors in diagnosing breast cancer. Breast ultrasound (BUS) imaging is harmless, effective, portable, and is the most popular modality for breast cancer detection/diagnosis. Many researchers work on improving the performance of CAD systems. However, there are two main shortcomings: (1) Most of the existing methods are based on prerequisites that there is one and only one tumor in the image. (2) The results depend on the datasets, i.e., an algorithm using different datasets may obtain different performances. It implies that the performance of traditional methods is dataset-dependent. In this paper, we propose an effective approach: (1) using information extended images to train a fully convolutional network (FCN) to semantically segment BUS image into 3 categories: mammary layer, tumor, and background; and (2) applying layer structure information - the breast cancers are located inside the mammary layer - to the conditional random field (CRF) for conducting breast cancer segmentation and making the segmentation result more accurate. The proposed method is evaluated utilizing BUS images of 325 cases, and the result is the best comparing with that of the existing methods by achieving true positive rate 92.80%, false positive rate 9%, and Intersection over Union 82.11%. The proposed approach has solved the above mentioned two shortcomings of the existing methods.

BUSIS: A Benchmark for Breast Ultrasound Image Segmentation.

Abstract: Breast ultrasound (BUS) image segmentation is challenging and critical for BUS Comput-er-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, prepared a software tool, and involved four radiologists in obtaining accurate annotations through standardized procedures; 2) we extensively compared the performance of sixteen state-of-the-art segmentation methods and discussed their advantages and disadvantages; 3) we proposed a set of valuable quantitative metrics to evaluate both semi-automatic and fully automatic segmentation approaches; and 4) the successful segmentation strategies and possible future improvements are discussed in details.

Efficient Dense-Dilation Network for Pavement Cracks Detection with Large Input Image Size

Abstract: Window-sliding/region-proposal based methods have been the popular approaches for object detection with deep convolutional neural networks. However, these methods are very inefficient when the input image size is large, such as pavement images $(2000\times 4000-\mathbf{pixel})$ used for cracking detection. In this paper, we propose a solution to this problem by introducing a fully convolutional dense-dilation network and the corresponding training strategy. The network is trained with small image blocks, then works on full-size images, which only needs to forward once for the process. In the first phase, it trains a classification network which classifies a small image block as crack, sealed crack or background. In the second phase, the fully convolutional layer is employed to convert the classification network into a detection network that is insensitive to the input size. At last, via introducing the equivalent dense-dilation design, it transfers both the low-level and middle-level knowledge from the classification network to facilitate the end-to-end network refining and improve the crack localization accuracy. The proposed approach is validated on 600 pavement images $(2000\times 4000-\mathbf{pixel})$ obtained by industry equipment and it achieves state-of-the-art performance comparing with that of the recently published works in efficiency and accuracy.

Computer-Aided Knee Joint Magnetic Resonance Image Segmentation - A Survey.

Abstract: Osteoarthritis (OA) is one of the major health issues among the elderly population MRI is the most popular technology to observe and evaluate the progress of OA course However, the extreme labor cost of MRI analysis makes the process inefficient and expensive Also, due to human error and subjective nature, the inter- and intra-observer variability is rather high Computer-aided knee MRI segmentation is currently an active research field because it can alleviate doctors and radiologists from the time consuming and tedious job, and improve the diagnosis performance which has immense potential for both clinic and scientific research In the past decades, researchers have investigated automatic/semi-automatic knee MRI segmentation methods extensively However, to the best of our knowledge, there is no comprehensive survey paper in this field yet In this survey paper, we classify the existing methods by their principles and discuss the current research status and point out the future research trend in-depth

A Hybrid Framework for Tumor Saliency Estimation

Abstract: Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality. Most tumor segmentation approaches achieve good performance on BUS images collected in controlled settings; however, the performance degrades greatly with BUS images from different sources. Tumor saliency estimation (TSE) has attracted increasing attention to solve the problem by modeling radiologists' attention mechanism. In this paper, we propose a novel hybrid framework for TSE, which integrates both high-level domain-knowledge and robust low-level saliency assumptions and can overcome drawbacks caused by direct mapping in traditional TSE approaches. The new framework integrated the Neutro-Connectedness (NC) map, the adaptive-center, the correlation and the layer structure-based weighted map. The experimental results demonstrate that the proposed approach outperforms state-of-the-art TSE methods.

A Benchmark for Breast Ultrasound Image Segmentation (BUSIS)

Abstract: Breast ultrasound (BUS) image segmentation is challenging and critical for BUS Computer-Aided Diagnosis (CAD) systems. Many BUS segmentation approaches have been proposed in the last two decades, but the performances of most approaches have been assessed using relatively small private datasets with differ-ent quantitative metrics, which result in discrepancy in performance comparison. Therefore, there is a pressing need for building a benchmark to compare existing methods using a public dataset objectively, and 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, we will publish a B-mode BUS image segmentation benchmark (BUSIS) with 562 images and compare the performance of five state-of-the-art BUS segmentation methods quantitatively.

Abstaining Classification When Error Costs are Unequal and Unknown.

Abstract: Abstaining classificaiton aims to reject to classify the easily misclassified examples, so it is an effective approach to increase the clasificaiton reliability and reduce the misclassification risk in the cost-sensitive applications. In such applications, different types of errors (false positive or false negative) usaully have unequal costs. And the error costs, which depend on specific applications, are usually unknown. However, current abstaining classification methods either do not distinguish the error types, or they need the cost information of misclassification and rejection, which are realized in the framework of cost-sensitive learning. In this paper, we propose a bounded-abstention method with two constraints of reject rates (BA2), which performs abstaining classification when error costs are unequal and unknown. BA2 aims to obtain the optimal area under the ROC curve (AUC) by constraining the reject rates of the positive and negative classes respectively. Specifically, we construct the receiver operating characteristic (ROC) curve, and stepwise search the optimal reject thresholds from both ends of the curve, untill the two constraints are satisfied. Experimental results show that BA2 obtains higher AUC and lower total cost than the state-of-the-art abstaining classification methods. Meanwhile, BA2 achieves controllable reject rates of the positive and negative classes.

A Novel Imbalanced Classification Method based on Decision Tree and Bagging

Abstract: Imbalanced classification is a challenging problem in the field of big data research and applications. Complex data distributions, such as small disjuncts and overlapping classes, make traditional methods unable to easily recognize the minority class and thus, lead to low sensitivity. The misclassification costs of the minority class are usually higher than that of the majority class. To deal with imbalanced datasets, typical algorithmic-level methods either introduce cost information or simply rebalance class distribution without considering the distribution of the minority class. In this paper, we propose an optimization embedded bagging (OEBag) approach to increase the sensitivity by learning the complex distributions in the minority class more precisely. By learning these base classifiers, OEBag selectively learns the minority examples that are misclassified easily by referring to examples in out-of-bag. OEBag is implemented by using two specialized under-sampling bagging methods. Nineteen real datasets with diverse levels of classification difficulties are utilized in this paper. Experimental results demonstrate that OEBag performs significantly better in sensitivity and has a great overall performance in terms of AUC (area under ROC curve) and G-mean when compared with several state-of-the-art methods.

A Hybrid Framework for Tumor Saliency Estimation

Abstract: Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality. Most tumor segmentation approaches achieve good performance on BUS images collected in controlled settings; however, the performance degrades greatly with BUS images from different sources. Tumor saliency estimation (TSE) has attracted increasing attention to solving the problem by modeling radiologists' attention mechanism. In this paper, we propose a novel hybrid framework for TSE, which integrates both high-level domain-knowledge and robust low-level saliency assumptions and can overcome drawbacks caused by direct mapping in traditional TSE approaches. The new framework integrated the Neutro-Connectedness (NC) map, the adaptive-center, the correlation and the layer structure-based weighted map. The experimental results demonstrate that the proposed approach outperforms state-of-the-art TSE methods.