The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However, low-rank pruning struggles to match the performance of semi-structured pruning, often doubling perplexity at similar densities. In this paper, we propose Pivoting Factorization (PIFA), a novel lossless meta low-rank representation that unsupervisedly learns a compact form of any low-rank representation, effectively eliminating redundant information. PIFA identifies pivot rows (linearly independent rows) and expresses non-pivot rows as linear combinations, achieving 24.2% additional memory savings and 24.6% faster inference over low-rank layers at rank = 50% of dimension. To mitigate the performance degradation caused by low-rank pruning, we introduce a novel, retraining-free reconstruction method that minimizes error accumulation (M). MPIFA, combining M and PIFA into an end-to-end framework, significantly outperforms existing low-rank pruning methods, and achieves performance comparable to semi-structured pruning, while surpassing it in GPU efficiency and compatibility. Our code is available at https://github.com/biomedical-cybernetics/pivoting-factorization.

The growing demands on GPU memory posed by the increasing number of neural network parameters call for training approaches that are more memory-efficient. Previous memory reduction training techniques, such as Low-Rank Adaptation (LoRA) and ReLoRA, face challenges, with LoRA being constrained by its low-rank structure, particularly during intensive tasks like pre-training, and ReLoRA suffering from saddle point issues. In this paper, we propose Sparse Spectral Training (SST) to optimize memory usage for pre-training. SST updates all singular values and selectively updates singular vectors through a multinomial sampling method weighted by the magnitude of the singular values. Furthermore, SST employs singular value decomposition to initialize and periodically reinitialize low-rank parameters, reducing distortion relative to full-rank training compared to other low-rank methods. Through comprehensive testing on both Euclidean and hyperbolic neural networks across various tasks, SST demonstrates its ability to outperform existing memory reduction training methods and is comparable to full-rank training in various cases. On LLaMA-1.3B, with only 18.7% of the parameters trainable compared to full-rank training (using a rank equivalent to 6% of the embedding dimension), SST reduces the perplexity gap between other low-rank methods and full-rank training by 97.4%. This result highlights SST as an effective parameter-efficient technique for model pre-training.

This study aims to enlarge our current knowledge on the application of brain-inspired network science principles for training artificial neural networks (ANNs) with sparse connectivity. Dynamic sparse training (DST) emulates the synaptic turnover of real brain networks, reducing the computational demands of training and inference in ANNs. However, existing DST methods face difficulties in maintaining peak performance at high connectivity sparsity levels. The Cannistraci-Hebb training (CHT) is a brain-inspired method that is used in DST for growing synaptic connectivity in sparse neural networks. CHT leverages a gradient-free, topology-driven link regrowth mechanism, which has been shown to achieve ultra-sparse (1\% connectivity or lower) advantage across various tasks compared to fully connected networks. Yet, CHT suffers two main drawbacks: (i) its time complexity is $\mathcal{O}(N\cdot d^3)$- N node network size, d node degree - hence it can be efficiently applied only to ultra-sparse networks. (ii) it rigidly selects top link prediction scores, which is inappropriate for the early training epochs, when the network topology presents many unreliable connections. Here, we design the first brain-inspired network model - termed bipartite receptive field (BRF) - to initialize the connectivity of sparse artificial neural networks. Then, we propose a matrix multiplication GPU-friendly approximation of the CH link predictor, which reduces the computational complexity to $\mathcal{O}(N^3)$, enabling a fast implementation of link prediction in large-scale models. Moreover, we introduce the Cannistraci-Hebb training soft rule (CHTs), which adopts a flexible strategy for sampling connections in both link removal and regrowth, balancing the exploration and exploitation of network topology. Additionally, we propose a sigmoid-based gradual density decay strategy, leading to an advanced framework referred to as CHTss. Empirical results show that BRF offers performance advantages over previous network science models. Using 1\% of connections, CHTs outperforms fully connected networks in MLP architectures on visual classification tasks, compressing some networks to less than 30\% of the nodes. Using 5\% of the connections, CHTss outperforms fully connected networks in two Transformer-based machine translation tasks. Finally, with only 30\% of the connections, both CHTs and CHTss achieve superior performance over other dynamic sparse training methods, and perform on par with—or even surpass—their fully connected counterparts in language modeling across various sparsity levels within the LLaMA model family. The code is available at: https://github.com/biomedical-cybernetics/Cannistraci-Hebb-Training-Soft-Rule-.

Many complex networks have partially observed or evolving connectivity, making link prediction a fundamental task. Topological link prediction infers missing links using only network topology, with applications in social, biological, and technological systems. The Cannistraci-Hebb (CH) theory provides a topological formulation of Hebbian learning, grounded on two pillars: (1) the **minimization of external links** within local communities, and (2) the **path-based definition of local communities** that capture homophilic (similarity-driven) interactions via paths of length 2 and synergetic (diversity-driven) interactions via paths of length 3. Building on this, we introduce the Cannistraci-Hebb Adaptive (CHA) network automata, an adaptive learning machine that automatically selects the optimal CH rule and path length to model each network. CHA unifies theoretical interpretability and data-driven adaptivity, bridging physics-inspired network science and machine intelligence. Across 1,269 networks from 14 domains, CHA consistently surpasses state-of-the-art methods—including SPM, SBM, graph embedding methods, and message-passing graph neural networks—while revealing the mechanistic principles governing link formation. Our code is available at https://github.com/biomedical-cybernetics/Cannistraci_Hebb_network_automata.

Sparse training (ST) aims to ameliorate deep learning by replacing fully connected artificial neural networks (ANNs) with sparse or ultra-sparse ones, such as brain networks are, therefore it might benefit to borrow brain-inspired learning paradigms from complex network intelligence theory. Here, we launch the ultra-sparse advantage challenge, whose goal is to offer evidence on the extent to which ultra-sparse (around 1\% connection retained) topologies can achieve any leaning advantage against fully connected. Epitopological learning is a field of network science and complex network intelligence that studies how to implement learning on complex networks by changing the shape of their connectivity structure (epitopological plasticity). One way to implement Epitopological (epi- means new) Learning is via link prediction: predicting the likelihood of non-observed links to appear in the network. Cannistraci-Hebb learning theory inspired the CH3-L3 network automata rule for link prediction which is effective for general-purpose link prediction. Here, starting from CH3-L3 we propose Epitopological Sparse Meta-deep Learning (ESML) to apply Epitopological Learning to sparse training. In empirical experiments, we find that ESML learns ANNs with ultra-sparse hyperbolic (epi-)topology in which emerges a community layer organization that is meta-deep (meaning that each layer also has an internal depth due to power-law node hierarchy). Furthermore, we discover that ESML can in many cases automatically sparse the neurons during training (arriving even to 30\% neurons left in hidden layers), this process of node dynamic removal is called percolation. Starting from this network science evidence, we design Cannistraci-Hebb training (CHT), a 4-step training methodology that puts ESML at its heart. We conduct experiments on 7 datasets and 5 network structures comparing CHT to dynamic sparse training SOTA algorithms and the fully connected counterparts. The results indicate that, with a mere 1\% of links retained during training, CHT surpasses fully connected networks on VGG16, GoogLeNet, ResNet50, and ResNet152. This key finding is an evidence for ultra-sparse advantage and signs a milestone in deep learning. CHT acts akin to a gradient-free oracle that adopts CH3-L3-based epitopological learning to guide the placement of new links in the ultra-sparse network topology to facilitate sparse-weight gradient learning, and this in turn reduces the convergence time of ultra-sparse training. Finally, CHT offers the first examples of parsimony dynamic sparse training because, in many datasets, it can retain network performance by percolating and significantly reducing the node network size. Our code is available at: https://github.com/biomedical-cybernetics/Cannistraci-Hebb-training

With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) **Relative Importance and Activations (RIA)**, a new pruning metric that jointly considers the weight and activations efficiently on LLMs, and 2) **Channel Permutation**, a new approach to maximally preserves important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

Quantization of large language models (LLMs) faces significant challenges, particularly due to the presence of outlier activations that impede efficient low-bit representation. Traditional approaches predominantly address Normal Outliers, which are activations across all tokens with relatively large magnitudes. However, these methods struggle with smoothing Massive Outliers that display significantly larger values, which leads to significant performance degradation in low-bit quantization. In this paper, we introduce DuQuant, a novel approach that utilizes rotation and permutation transformations to more effectively mitigate both massive and normal outliers. First, DuQuant starts by constructing the rotation matrix, using specific outlier dimensions as prior knowledge, to redistribute outliers to adjacent channels by block-wise rotation. Second, We further employ a zigzag permutation to balance the distribution of outliers across blocks, thereby reducing block-wise variance. A subsequent rotation further smooths the activation landscape, enhancing model performance. DuQuant simplifies the quantization process and excels in managing outliers, outperforming the state-of-the-art baselines across various sizes and types of LLMs on multiple tasks, even with 4-bit weight-activation quantization. Our code is available at https://github.com/Hsu1023/DuQuant.

Many practical applications suffer from the problem of imbalanced classification. The minority class has poor classification performance; on the other hand, its misclassification cost is high. One reason for classification difficulty is the intrinsic complicated distribution characteristics (CDCs) in imbalanced data itself. Classical oversampling method SMOTE generates synthetic minority class examples between neighbors, which is parameter dependent. Furthermore, due to blindness of neighbor selection, SMOTE suffers from overgeneralization in the minority class. To solve such problems, we propose an oversampling method, called extended natural neighbors based SMOTE (ExNN-SMOTE). In ExNN-SMOTE, neighbors are determined adaptively by capturing data distribution characteristics. Extensive experiments over synthetic and real datasets demonstrate the effectiveness of ExNN-SMOTE dealing with CDCs and the superiority of ExNN-SMOTE over other SMOTE-related methods.

Imbalanced classification exists commonly in practical applications, and it has always been a challenging issue. Traditional classification methods have poor performance on imbalanced data, especially, on the minority class. However, the minority class is usually of our interest, and its misclassification cost is higher. The critical factor is the intrinsic complicated distribution characteristics in imbalanced data itself. Resampling ensemble learning achieves promising results and is a research focus recently. However, some resampling ensembles do not consider complicated distribution characteristics, thus limiting the performance improvement. In this paper, a generalized optimization embedded framework (GOEF) is proposed based on undersampling bagging. The GOEF aims to pay more attention to the learning of local regions to handle the complicated distribution characteristics. Specifically, the GOEF utilizes out-of-bag data to explore heterogeneous local areas and chooses misclassified examples to optimize base classifiers. The optimization can focus on a single class or both classes. Extensive experiments over synthetic and real datasets demonstrate that GOEF with the minority class optimization performs the best in terms of AUC, G-mean, and sensitivity, compared with five resampling ensemble methods.

Convolutional neural networks (CNNs) are widely used in medical image analysis, especially for breast ultrasound (BUS) image segmentation. Automatically encoding deep features is one of the most important reasons leading to the success of deep convolutional neural networks. There are a lot of studies on obtaining better convolutional features; how-ever, they do not discuss the higher-order information in the features. In this research, we propose a novel convolutional operator, a shape-adaptive convolutional operator, which can select pixels for calculating convolution rather than in the Euclidean space. The proposed operator is combined with the original convolutional operator to extract higher-order convolutional features. We conduct extensive experiments to evaluate the performance of the proposed operator for image segmentation using three datasets: two public BUS image datasets and one multi-category BUS image dataset. The proposed approach achieves state-of-the-art performance.

Recently, deep learning-based algorithms have brought impressive results in deblurring tasks. However, as an image prior proved important in image restoration tasks, self-similarity was not exploited in motion deblurring. To tackle this problem, we propose an Attention Self-Similarity Capture (ASSC) module, which takes full advantage of self-similarity by capturing long-range feature dependencies. Besides, to achieve a trade-off between performance and efficiency, we design an Enhanced Spatial Attention (ESA) module, which can dynamically adapt to the spatially-varying motion blur. We employ patch-hierarchical architecture composed of the two modules mentioned above with parameter-free feature flow between different levels. Moreover, we build two large-scale datasets, GOPRO-Supplement and SONY-Extension, to expand the public GOPRO dataset’s scene and resolution. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on both the public GOPRO dataset and our datasets.

Fully convolutional network is a powerful tool for per-pixel semantic segmentation/detection. However, it is problematic when coping with crack detection using partially accurate ground truths (GTs): the network may easily converge to the status that treats all the pixels as background (BG) and still achieves a very good loss, named “All Black” phenomenon, due to the unavailability of accurate GTs and the data imbalance. To tackle this problem, we propose crack-patch-only (CPO) supervised generative adversarial learning for end-to-end training, which forces the network to always produce crack-GT images while reserves both crack and BG-image translation abilities by feeding a larger-size crack image into an asymmetric U-shape generator to overcome the “All Black” issue. The proposed approach is validated using four crack datasets; and achieves state-of-the-art performance comparing with that of the recently published works in efficiency and accuracy.

Tongue crack segmentation is an essential component of computer-aided diagnosis applied in Traditional Chinese Medicine (TCM). However, existing methods are inadequate when dealing with the vague boundary of the foreground and the variation of tongue images. To this end, we propose a P-shaped neural network architecture based on the lightweight encoder-decoder structure: the encoder transforms pixel position information into channel information by aggregating adjacent pixel values; the decoder restores the image size and obtains the refined pixel-level extraction results by integrating the information of the corresponding layer in the encoder. To further improve the utilization of network parameters and the model's generalization ability, we design three novel sub-modules: (1) the phantom module utilizes cheap operations to generate feature maps, speeding up the calculation; (2) the dual-input module increases the original input information to enhance the model's foreground understanding; (3) the dual attention gate module strengthens the information fusion of high-level and low-level feature maps, retaining good boundary information while capturing detail information. Additionally, we propose a pre-training method based on cropped patch images, which makes the model sensitive to details of the foreground before formal training. We demonstrate the model's effectiveness on our constructed dataset, achieving 60.6% IoU accuracy, and the segmentation of a 513 × 513$image takes 390 ms on CPU. And our dataset is available at https://github.com/pengjianqiang/FDU-TC.

Deep learning approaches have achieved impressive results in breast ultrasound (BUS) image segmentation. However, these methods did not solve uncertainty and noise in BUS images well. Meanwhile, they did not involve the context information of BUS images, either. To address this issue, we present a novel deep learning structure for BUS image semantic segmentation by analyzing the uncertainty using a pyramid fuzzy block and generating a novel feature based on connectedness. There are three major contributions in this paper: (1) the structure of pyramid fuzzy block; (2) a novel membership function based on multi-convolution layers; and (3) a novel context feature based on connectedness. The proposed methods are applied to two datasets: a BUS image benchmark with two categories (background and tumor) and a five-category BUS image dataset with fat layer, mammary layer, muscle layer, background, and tumor. The proposed method achieves the best results on both datasets compared with eight state-of-the-art deep learning-based approaches.

Breast cancer investigation is of great significance, and developing tumor detection methodologies is a critical need. However, it is challenging for breast cancer detection using breast ultrasound (BUS) images due to the complicated breast structure and poor quality of the images. This paper proposes a novel tumor saliency estimation (TSE) model guided by enriched breast anatomy knowledge to localize the tumor. First, the breast anatomy layers are generated by a deep neural network. Then we refine the layers by integrating a non-semantic breast anatomy model to solve the problems of incomplete mammary layers. Meanwhile, a new background map generation method weighted by the semantic probability and spatial distance is proposed to improve the performance. The experiment demonstrates that the proposed method with the new background map outperforms four state-of-the-art TSE models with an increasing 10% of Fmeasure on the public BUS dataset.

With the popularity of smart phones and mobile Internet services, crowdsourcing has become a popular business model by which the tasks are published at some crowdsourcing platforms, while the registered members can download the tasks and earn money after finishing the tasks in a distributive manner. This kind of self-service labor crowdsourcing platforms based on mobile Internet provides enterprises with various business inspections and information collection services. During the entire process, how to determine the prices for different tasks is one of key issues of crowdsourcing business. In this paper, we propose three pricing models for crowdsourcing based on geographical information, and then take the Chinese MCM problem B of 2017 as a case study, to give an evaluation on the reasonability and the effectiveness of the proposed pricing models for crowdsourced photography.

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.

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.

This paper proposes individualized cleaning for diverse imbalanced data sets. Existing techniques for data cleaning have difficulties with rare cases and outliers in minority class, especially, in highly unbalanced data. The drawback leads incomplete and imprecise examples to removal. In order to enhance the robustness and perform thorough data cleaning, we propose a weighted edited nearest neighbor (WENN), which detects and removes noisy examples from both classes intelligently. It considers individual characteristics of each imbalanced data, involving global class imbalance and local distribution. The main idea of the proposed method is to carefully put more focus on the majority class than the minority class during data cleaning. Extensive experiments over synthetic and real data clearly validate the superiority of our approach against other data cleaning methods.

Interactive image segmentation is a popular and challenging task. User interactions, e.g., setting seeds or specifying bounding box, play a critical role in determining the performance of all interactive segmentation approaches. However, most methods focus on improving segmentation performance by integrating higher level information; and to the best of our knowledge, no work has been done to improve the effectiveness of user interactions yet. In this paper, we propose the effective interactive segmentation (EISeg) method based on Neutro-Connectedness, which provides user with objective visual clues for guiding interactions. The experiments demonstrate that the proposed EISeg method guides interaction effectively, and achieves better results with much less user interaction (averagely 2.3 foreground and 1.8 background seeds/image) than state-of-the-art approaches.

Visual saliency estimation based on optimization models is gaining increasing popularity recently. In this paper, we formulate saliency estimation as a quadratic program (QP) problem based on robust hypotheses. First, we propose an adaptive center-based bias hypothesis to replace the most common image center-based center-bias. It calculates the weighted center by utilizing local contrast which is much more robust when the objects are far away from the image center. Second, we model smoothness term on saliency statistics of each color. It forces the pixels with similar colors to have similar saliency statistics. The proposed smoothness term is more robust than the smoothness term based on region dissimilarity when the image has complicated background or low contrast. The primal-dual interior point method is applied to optimize the proposed QP in polynomial time. Extensive experiments demonstrate that the proposed method can outperform 10 state-of-the-art methods on three public benchmark datasets.

Interactive image segmentation is a challenging task and receives increasing attention recently; however, two major drawbacks exist in interactive segmentation approaches. First, the segmentation performance of region of interest (ROI)-based methods is sensitive to the initial ROI: different ROIs may produce results with great difference. Second, most seed-based methods need intense interactions, and are not applicable in many cases. In this paper, we generalize the neutro-connectedness (NC) to be independent of top-down priors of objects and to model image topology with indeterminacy measurement on image regions, propose a novel method for determining object and background regions, which is applied to exclude isolated background regions and enforce label consistency, and put forward a hybrid interactive segmentation method, NC Cut (NC-Cut), which can overcome the above two problems by utilizing both pixelwise appearance information and region-based NC properties. We evaluate the proposed NC-Cut by employing two image data sets (265 images), and demonstrate that the proposed approach outperforms the state-of-the-art interactive image segmentation methods (Grabcut, MILCut, One-Cut, MGCmaxsum, and pPBC).

Transesophageal echocardiography (TEE) is widely used to detect left atrium (LA)/left atrial appendage (LAA) thrombi. In this paper, the local binary pattern variance (LBPV) features are extracted from region of interest (ROI). And the dynamic features are formed by using the information of its neighbor frames in the sequence. The sequence is viewed as a bag, and the ROIs in the sequence are considered as the instances. Multiple-instance learning (MIL) method is employed to solve the LAA thrombi detection. The experimental results show that the proposed method can achieve better performance than that by using other methods.

Tumor detection is the key issue of computer-aided diagnosis (CAD) systems using breast ultrasound (BUS) images. However, accurately and automatically locating the suspicious lesions in BUS images is still a very challenging job. In this paper, we propose a saliency model to describe the radiologists' visual (RV) attention. The main contributions of the paper are: (1) The saliency model is built based on biological hypotheses instead of using inflexible assumptions which are more robust, adaptive and objective. (2) Background based attention cue is also proposed. Before, the background information was either ignored or only used for excluding non-target areas. However, we find that the background information is very useful for establishing the anatomy constrains. The proposed method is evaluated using real breast ultrasound images and the result demonstrates a significantly improved performance comparing with that of the state-of-the-art methods.

Breast tumor segmentation is an important step of breast ultrasound (BUS) computer-aided diagnosis (CAD) systems. However, because of the poor quality of BUS images, it's a challenging task to develop a robust and accurate segmentation algorithm. Much progress has been made on applying fuzzy connectedness to segment objects from low quality images. However, the fuzzy connectedness method still has difficulty in segmenting objects with weak boundaries. The neutrosophic set theory has been widely applied to image processing, and shows more strengths in modeling uncertainty and indeterminacy. In this paper, two new concepts of neutrosophic subset and neutrosophic connectedness (neutro-connectedness) were defined to generalize the fuzzy subset and fuzzy connectedness. The newly proposed neutro-connectedness models the inherent uncertainty and indeterminacy of the spatial topological properties of the image. The proposed method is applied to a breast ultrasound database with 131 cases, and its performance is evaluated by similarity ratio (SIR), false positive ratio (FPR) and average Hausdroff error (AHE). In comparison with the fuzzy connectedness segmentation method, the proposed method is more accurate and robust in segmenting tumors in BUS images.

To improve the diagnostic accuracy of breast ultrasound classification, a novel computer-aided diagnosis (CAD) system based on B-Mode and color Doppler flow imaging is proposed. Several new features are modeled and extracted from the static images and color Doppler image sequences to study blood flow characteristics. Moreover, we proposed a novel classifier ensemble strategy for obtaining the benefit of mutual compensation of classifiers with different characteristics. Experimental results demonstrate that the proposed CAD system can improve the true-positive and decrease the false positive detection rate, which is useful for reducing the unnecessary biopsy and death rate.

Over-enhancement is the major problem of image contrast enhancement algorithms which could induce the loss of edges, change the important texture, impair the fine details, and make the images look unnatural. Over-enhancement has traditionally been assessed by visual inspection due to the fact that there is no an effective objective criterion for over-enhancement yet. In this paper, we propose a novel approach for the detection of over-enhancement. The main contributions of the paper are as follows. (1) The reasons for generating over-enhancement are investigated and analyzed deeply. (2) An objective criterion for detecting over-enhancement is proposed. The experimental results demonstrate that the proposed approach can locate the over enhanced areas accurately and effectively, and provide a quantitative criterion to assess the over-enhancement levels well. The proposed approach will be useful for dynamically monitoring the quality of the enhanced image, and optimizing the parameter settings of the contrast enhancement algorithms.

Breast ultrasound (BUS) image segmentation is a very challenge task because of the poor image quality. In this paper, we proposed a probability model-based method for the accurate and robust segmentation for low quality medical images. It combines the spatial priori knowledge with the frequency constraints under the maximum a posteriori probability with markov random field (MAP-MRF) segmentation frameworks. The spatial constraints model the global location, object pose and the appearance, and the objective boundary is constrained in the frequency domain via modeling the phase feature and the zero crossing feature of the wavelet coefficients. The proposed method is applied to a breast ultrasound database with 131 cases, and its performance is evaluated by area error metrics and boundary error metrics. In comparing with the state of the art, our method is more accurate and robust in segmenting breast ultrasound images.

Two major problems of ultrasound imaging are low-contrast and speckle noise. Traditionally, before speckle reduction, an enhancement algorithm is employed to improve the quality of the image. However, the noise is enhanced as well. To overcome this drawback, we introduce a novel fuzzy anisotropic diffusion approach for speckle reduction and contrast enhancement. Maximum fuzzy entropy principle is used to map the image from space domain to fuzzy domain. Then, fractional-order partial differential equation is used to remove noise and to preserve edges. Finally, the subpixel operator is utilized as a tuning parameter to achieve the optimal result. We test the proposed method on synthetic and real breast ultrasound (BUS) images. The experimental results demonstrate that the proposed method can preserve the edges and enhance the structural details of the BUS images well while removing speckle noise.