BAGNet: Bidirectional Aware Guidance Network for Malignant Breast lesions Segmentation

EH-former: Regional easy-hard-aware transformer for breast lesion segmentation in ultrasound images

Breast cancer is one of the leading cancer that affects woman all around the world. Nowadays ultra sound imaging technique is used to diagnose various cancer because of its non-ionizing, on-invasive, and cheap cost. Breast lesion region in ultrasound images are classified depending upon the contour, shape, size and textural features of the segmented region. Seed point is the initial step in segmentation of lesion regions and if that point is located outside the lesion region, it leads to wrong segmentation which results in misclassification of the lesion regions. To avoid this, most of the time the seed point is located manually. In order to avoid this manual intervention, we are proposing a novel method in locating the seed point and also segmenting the breast lesion region automatically. In this method, the image is processed with tan function for effective distinguishing of breast lesion and normal region. Then using the trained neural network, the seed point is automatically located inside the lesion region and from the seed point the region of the lesion is grown and segmented automatically. Most of the past works on automatic segmentation of lesion had concentrated only in single lesion region, but using this proposed method, we were able to automatically segment multiple lesion regions in the image. Outcome of the proposed method is to detect automatically and dynamically separate the lesion region in the range between 90% to 97.5% of images.

Breast lesion segmentation in ultrasound images is of great importance since it can help us to characterize and localize lesion regions. However, low-quality imaging, blurred boundary, and variable lesion shapes bring challenges to accurate segmentation. In recent years, many U-Net variants have been proposed and successfully applied to breast lesion segmentation. However, these methods suffer from two limitations: (1) Ignoring the ability to capture rich global context information, and (2) Introducing extra complex operations. To alleviate these challenges, we propose a multiscale nonlocal feature extraction network (MNFE-Net) for accurately segmenting breast lesions. The core idea includes three points: (1) Parallel Encoder models long-range dependencies, (2) Multiscale Feature Module refines local features without introducing extra complex operations, and (3) Global Feature Guidance Module extracts global semantic information. MNFE-Net mainly has the following advantages: (1) The method has excellent performance for segmentation of malignant breast lesions, (2) The Parallel Encoder increases network parameters without significantly decreasing inference speed, and (3) The method is easy to understand and execute. Extensive experiment results with six state-of-the-art (SOTA) methods on three public breast ultrasound datasets demonstrate the superior segmentation performance of our proposed MNFE-Net.

Pyramid boundary attention network for breast lesion segmentation in ultrasound images

Medical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance. The purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical. SEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently.

Semantic segmentation of breast lesion using deep learning

Accurate lesion segmentation is critical for cancer diagnosis and treatment. Convolutional neural networks (CNNs) are widely used for medical image segmentation but struggle to capture long-range dependencies. Transformers mitigate this limitation but come with high computational costs. Mamba, a state-space model (SSM), efficiently models long-range dependencies but lacks precision in fine details. To address these challenges, this study aimed to develop a novel segmentation approach that combines the strengths of CNNs, Transformers, and Mamba, enhancing both global context understanding and local feature extraction in medical image segmentation. We propose AttmNet, a U-shaped network designed for medical image segmentation, which incorporates a novel structure called MAM (Multiscale-Convolution, Self-Attention, and Mamba). The MAM block integrates multi-layer convolution for multi-scale feature learning with an Att-Mamba component that combines self-attention and Mamba to effectively capture global context while preserving fine details. We evaluated AttmNet on four public datasets for breast, skin, and lung lesion segmentation. AttmNet outperformed state-of-the-art methods in terms of intersection over union (IoU) and Dice similarity coefficients. On the breast ultrasound (BUS) dataset, AttmNet achieved a 3.38% improvement in IoU and a 4.54% increase in Dice over the next best method. On the breast ultrasound images (BUSI) dataset, AttmNet's IoU and Dice coefficients were 1.17% and 3.21% higher than the closest competitor, respectively. In the PH2 Dermoscopy Image dataset, AttmNet surpassed the next best model by 0.25% in both IoU and Dice. On the larger coronavirus disease 2019 (COVID-19) Lung dataset, AttmNet maintained strong performance, achieving higher IoU and Dice scores than the next best models, SegMamba and TransUNet. AttmNet is a powerful and efficient tool for medical image segmentation, addressing the limitations of existing methods through its advanced design. The MAM block significantly enhances segmentation accuracy while maintaining computational efficiency, making AttmNet highly suitable for clinical applications. The code is available at https://github.com/hyb2840/AttmNet.

With magnetic resonance imaging (MRI), the segmentation of breast lesions is helpful for early diagnosis. Since it is subjective and time-consuming for physicians to delineate the lesions, automatic segmentation is in active demand. However, the low contrast and small size of the lesions will cause difficulties in existing segmentation methods. In this paper, we propose a three-stream interactive neural network (TSINet) for the efficient segmentation of MRI breast lesions. TSINet uses three streams for extracting boundary information, location information and predicting lesion masks, respectively. The boundary extraction stream enhances the representation of boundary pixels based on gate convolution. The internal location stream that works based on the attention mechanism identifies the location of the lesions. The lesion segmentation stream fuse the boundary and location information to accurately segment the lesion. We collect MRI data from 248 breast patients at the Second Hospital of Dalian Medical University to evaluate TSINet. The results demonstrate that the TSINet can delineate lesion boundaries close to that drawn by physicians, and outperform state-of-the-art methods.

Segmentation of medical ultrasound images is one of the most important functional components of medical ultrasonic instruments for computed aided diagnosis, such as breast lesion early detection and measurement. However, the segmentation of breast lesions from ultrasound images is still a challenging task due to the variance in shape of the lesions and interference from speckle noise. In this paper, a novel approach using tight frames of grouping bandlet(TFGB) and improved stochastic neighbor embedding algorithm(ISNE) is adopted for the segmentation of breast lesions. Novelty in this paper includes that grouplet transform is successively applied and adapted for image segmentation for the first time whereas all of previous works were focused on image inpainting, texture synthesis and image denoising. Moreover, an effective stopping criterion is proposed to improve the dimension reduction technique-stochastic neighbor embedding (SNE) in this paper. Applications to clinical ultrasound images with fibroadenoma and fibrocystic breast lesions contaminated by speckle noise are performed, respectively. Experimental results show that compared with the state-of-the-art approach to the segmentation of breast lesions in ultrasound images, the proposed approach demonstrates robustness to speckle noise and superior performance on the effectiveness.

Breast UltraSound (BUS) imaging is a commonly used diagnostic tool in the field of counter fighting breast diseases, especially for early detection and diagnosis of breast cancer. Due to the inherent characteristics of ultrasound images such as blurry boundaries and diverse tumor morphologies, it is challenging for doctors to manually segment breast tumors. In recent years, the Convolutional Neural Network (CNN) technology has been widely applied to automatically segment BUS images. However, due to the inherent limitations of CNNs in capturing global contextual information, it is difficult to capture the full context. To address this issue, the paper proposes a novel BGRD-TransUNet model for breast lesion segmentation, based on TransUNet. The proposed model, first, replaces the original ResNet50 backbone network of TransUNet with DenseNet121 for initial feature extraction. Next, newly designed Residual Multi-Scale Feature Modules (RMSFMs) are employed to extract features from various layers of DenseNet121, thus capturing richer features within specific layers. Thirdly, a Boundary Guidance (BG) network is added to enhance the contour information of BUS images. Additionally, newly designed Boundary Attentional Feature Fusion Modules (BAFFMs) are used to integrate edge information and features extracted through RMSFMs. Finally, newly designed Parallel Channel and Spatial Attention Modules (PCSAMs) are used to refine feature extraction using channel and spatial attention. An extensive experimental testing performed on two public datasets demonstrates that the proposed BGRD-TransUNet model outperforms all state-of-the-art medical image segmentation models, participating in the experiments, according to all evaluation metrics used (except for few separate cases), including the two most important and widely used metrics in the field of medical image segmentation, namely the Intersection over Union (IoU) and Dice Similarity Coefficient (DSC). More specifically, on the BUSI dataset and dataset B, BGRD-TransUNet achieves IoU values of 76.77% and 86.61%, and DSC values of 85.08% and 92.47%, respectively, which are higher by 7.27 and 3.64, and 5.81 and 2.54 percentage points, than the corresponding values achieved by the baseline (TransUNet).

Unsupervised domain adaption (UDA), which aims to enhance the segmentation performance of deep models on unlabeled data, has recently drawn much attention. In this paper, we propose a novel UDA method (namely DLaST) for medical image segmentation via disentanglement learning and self-training. Disentanglement learning factorizes an image into domain-invariant anatomy and domain-specific modality components. To make the best of disentanglement learning, we propose a novel shape constraint to boost the adaptation performance. The self-training strategy further adaptively improves the segmentation performance of the model for the target domain through adversarial learning and pseudo label, which implicitly facilitates feature alignment in the anatomy space. Experimental results demonstrate that the proposed method outperforms the state-of-the-art UDA methods for medical image segmentation on three public datasets, i.e., a cardiac dataset, an abdominal dataset and a brain dataset. The code will be released soon.

An efficient neural network based method for medical image segmentation

Ultrasound video-based breast lesion segmentation provides valuable assistance in early breast lesion detection and discrimination. However, this field faces two key challenges: the first is how to simultaneously utilize both intra-frame and inter-frame lesion cues to accurately segment breast lesions, and the second is that the availability of breast ultrasound video datasets is quite limited. In this paper, we propose a novel Spatial-Temporal Progressive Fusion Network (STPFNet) for video-based breast lesion segmentation problem. The proposed STPFNet comprises three main components. First, we propose to adopt a unified network architecture to capture spatial dependencies within each ultrasound frame and temporal correlations between different frames together for feature representation of ultrasound video. Second, we propose a new fusion module called Multi-Granularity Feature Fusion (MGFF) to fuse the extracted information with different granularities for lesion segmentation. MGFF can help improve the issue of lesion boundary blurring. Third, we propose to take the segmentation result of the previous frame as prior knowledge to suppress the noisy background and learn a more robust representation. To further promote the research in this field, we construct a new ultrasound video breast lesion segmentation dataset, called UVBLS200, comprising 200 videos (80 benign and 120 malignant lesions). Experiments on the proposed dataset demonstrate that the proposed STPFNet achieves a better breast lesion detection performance than state-of-the-art methods.

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it popular among researchers. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the Dice coefficient, specificity, sensitivity, and F1 score values obtained were 0.93, 0.99, 0.94, and 0.94, respectively. In addition, McNemar’s statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperformed all other models, resulting in improved breast lesion segmentation.

Automated Segmentation of Ultrasonic Breast Lesions Using Statistical Texture Classification and Active Contour Based on Probability Distance