Multi-center breast ultrasound image segmentation aims to leverage limited labeled data from a single center to enhance model discriminability across unlabeled data from other centers. However, differences in equipment parameters, disease severity, and imaging conditions collectively contribute to significant cross-domain shifts in multi-center data. In a spirit of the golden mean, we argue that constructing an intermediate domain between the source and target domains can effectively improve model generalization. Therefore, we propose a Cross-domain Few-label Generalization (CFG) framework for multi-center breast ultrasound image segmentation. Specifically, we design the Intermediate Domain Generator (IDG) to generate intermediate domain samples that contain features from both the source and target domains bidirectionally, enabling the model to explicitly learn universal semantic representations. Additionally, we apply Swin Masked Autoencoder (MAE) to mask and reconstruct ultrasound images, simulating speckle noise encountered during clinical ultrasound acquisition, thereby increasing the diversity of intermediate domain samples. Furthermore, we integrate the Kolmogorov-Arnold Network (KAN) with UNet to construct KAN-UNet, integrating learnable spline functions directly onto the edges, enabling effective multi-scale perception of breast cancer lesion features. Experimental results show that even with limited labeled data from the source domain (BUSI-WHU), the CFG framework achieves a Kappa value of 77.17%, surpassing ten state-of-the-art methods and outperforming the second-best method by 0.78% across four multi-center ultrasound datasets (BUSI-WHU, BUSI, Dataset-B, and Dataset-C) collected from different medical centers.

With the advancement of capsule endoscopy technology, the treatment of gastrointestinal (GI) tract diseases has entered a new era. Capsule robots enable the diagnosis and treatment of lesions in a painless and minimally invasive manner. Research on highly controllable Drug Delivery Systems (DDSs) using capsule endoscopy is significant for treating GI tract diseases. Despite the variety and complexity of DDS designs, most systems lack the capability for multi-target drug delivery and simultaneous carriage of multiple drugs. This paper proposes a dual-drug-chamber drug delivery capsule robot (DDCR) that utilizes a single Internal Permanent Magnet (IPM) for both drug delivery and propulsion. The design of the dual-drug-chamber primarily aims to carry one or two drugs simultaneously for treating one or multiple target sites. The proposed DDCR uses a balloon mechanism for drug containment. An external magnetic drive system activates a needle attached to a piston, which punctures the balloon and, thereby, releases the medication. This mechanism ensures rapid and effective coverage of lesions by the drugs. Based on both theoretical and experimental results regarding balloon drug loading and the control distance of the external permanent magnet (EPM) control distance, it was established that a drug load of 0.3 ml per chamber was most suitable for the design, and the feasibility of the dosing method was demonstrated. The size (29mm in length and ~13mm in diameter) of the DDCR was also found to be suitable for biological experiments, including multi-target drug delivery. By continuously adjusting the distance between the DDCR and the EPM in porcine small intestine samples, the optimal driving distance and drug delivery distance were found to be 80mm and 140mm.

Breast cancer is one of the most prevalent diseases for women worldwide. Early and accurate ultrasound image segmentation plays a crucial role in reducing mortality. Although deep learning methods have demonstrated remarkable segmentation potential, they still struggle with challenges in ultrasound images, including blurred boundaries and speckle noise. To generate accurate ultrasound image segmentation, this paper proposes the Edge-Aware Multi-Scale Group-Mix Attention Network (EMGANet), which generates accurate segmentation by integrating deep and edge features. The Multi-Scale Group Mix Attention block effectively aggregates both sparse global and local features, ensuring the extraction of valuable information. The subsequent Edge Feature Enhancement block then focuses on cancer boundaries, enhancing the segmentation accuracy. Therefore, EMGANet effectively tackles unclear boundaries and noise in ultrasound images. We conduct experiments on two public datasets (Dataset-B, BUSI) and one private dataset which contains 927 samples from Renmin Hospital of Wuhan University (BUSI-WHU). EMGANet demonstrates superior segmentation performance, achieving an overall accuracy (OA) of 98.56%, a mean IoU (mIoU) of 90.32%, and an ASSD of 6.1 pixels on the BUSI-WHU dataset. Additionally, EMGANet performs well on two public datasets, with a mIoU of 88.2% and an ASSD of 9.2 pixels on Dataset-B, and a mIoU of 81.37% and an ASSD of 18.27 pixels on the BUSI dataset. EMGANet achieves a state-of-the-art segmentation performance of about 2% in mIoU across three datasets. In summary, the proposed EMGANet significantly improves breast cancer segmentation through Edge-Aware and Group-Mix Attention mechanisms, showing great potential for clinical applications.

Pathology image matching is crucial for assisting pathologists in the comprehensive diagnosis of cancerous areas. However, variations in image rotation and staining caused by inherent slide imaging techniques increase the burden on pathologists, complicating the examination of cancer across different pathology slides. To address this challenge, we introduce multi-scale ring rotation-invariant matching (MRRM), which improves image matching efficiency using ring topology, assisting pathologists in robustly aligning biomarker information across various pathology images. Specifically, by employing multi-scale rings as convolution kernels, we accurately locate keypoints from the differencing of the ring pyramid, which not only enhances the likelihood of successful pathology image matching but also supports our feature descriptor in achieving advantageous performance in rotation-invariance. Experiments show that with manually annotated golden landmarks as the standard in 81 cases, exhibiting significantly superior matching accuracy (130.93 $\,\mu \mathrm{m}$) and a success rate of 93.83% compared to other methods, particularly in cases with rotated pathology images. This meets the routine diagnostic requirements of pathologists for cancer diagnosis.

Matching whole slide histopathology images to provide comprehensive information on homologous tissues is beneficial for cancer diagnosis. However, the challenge arises with the Giga-pixel whole slide images (WSIs) when aiming for high-accuracy matching. Learning-based methods are difficult to generalize well with large-size WSIs, necessitating the integration of traditional matching methods to enhance accuracy as the size increases. In this paper, we propose a multi-size guiding matching method applicable high-accuracy requirements. Specifically, we design learning multiscale texture to train deep descriptors, called TDescNet, that trains 64 × 64 × 256 and 256 × 256 × 128 size convolution layer as C64 and C256 descriptors to overcome staining variation and low visibility challenges. Furthermore, we develop the 3D-ring descriptor using sparse keypoints to support the description of large-size WSIs. Finally, we employ C64, C256, and 3D-ring descriptors to progressively guide refined local matching, utilizing geometric consistency to identify correct matching results. Experiments show that when matching WSIs of size 4096 × 4096 pixels, our average matching error is 123.48 μm and the success rate is 93.02 % in 43 cases. Notably, our method achieves an average improvement of 65.52 μm in matching accuracy compared to recent state-of-the-art methods, with enhancements ranging from 36.27 μm to 131.66 μm. Therefore, we achieve high-fidelity whole-slice image matching, and overcome staining variation and low visibility challenges, enabling assistance in comprehensive cancer diagnosis through matched WSIs.