Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different models. In this paper, we introduce the IMed-361M benchmark dataset, a significant advancement in general IMIS research. First, we collect and standardize over 6.4 million medical images and their corresponding ground truth masks from multiple data sources. Then, leveraging the strong object recognition capabilities of a vision foundational model, we automatically generated dense interactive masks for each image and ensured their quality through rigorous quality control and granularity management. Unlike previous datasets, which are limited by specific modalities or sparse annotations, IMed-361M spans 14 modalities and 204 segmentation targets, totaling 361 million masks—an average of 56 masks per image. Finally, we developed an IMIS baseline network on this dataset that supports high-quality mask generation through interactive inputs, including clicks, bounding boxes, text prompts, and their combinations. We evaluate its performance on medical image segmentation tasks from multiple perspectives, demonstrating superior accuracy and scalability compared to existing interactive segmentation models. To facilitate research on foundational models in medical computer vision, we release the IMed-361M and model at https://github.com/uni-medical/IMIS-Bench.

Medical image segmentation based on neural networks is pivotal in promoting digital health equity. The attention mechanism increasingly serves as a key component in modern neural networks, as it enables the network to focus on regions of interest, thus improving the segmentation accuracy in medical images. However, current attention mechanisms confront an accuracy-complexity trade-off paradox: accuracy gains demand higher computational costs, while reducing complexity sacrifices model accuracy. Such a contradiction inherently restricts the real-world deployment of attention mechanisms in resource-limited settings, thus exacerbating healthcare disparities. To overcome this dilemma, we propose a parameter-free Neighborhood Self-Dissimilarity Attention (NSDA), inspired by radiologists' diagnostic patterns of prioritizing regions exhibiting substantial differences during clinical image interpretation. Unlike pairwise-similarity-based self-attention mechanisms, NSDA constructs a size-adaptive local dissimilarity measure that quantifies element-neighborhood differences. By assigning higher attention weights to regions with larger feature differences, NSDA directs the neural network to focus on high-discrepancy regions, thus improving segmentation accuracy without adding trainable parameters directly related to computational complexity. The experimental results demonstrate the effectiveness and generalization of our method. This study presents a parameter-free attention paradigm, designed with clinical prior knowledge, to improve neural network performance for medical image analysis and contribute to digital health equity in low-resource settings. The code is available at [https://github.com/ChenJunren-Lab/Neighborhood-Self-Dissimilarity-Attention](https://github.com/ChenJunren-Lab/Neighborhood-Self-Dissimilarity-Attention).

Existing volumetric medical image segmentation models are typically task-specific, excelling at specific targets but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this article, we introduce segment anything model (SAM)-Med3D, a vision foundation model (VFM) for general-purpose segmentation on volumetric medical images. Given only a few 3-D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and preprocess a large-scale 3-D medical image segmentation dataset, SA-Med3D-140K, from 70 public datasets and 8K licensed private cases from hospitals. This dataset includes 22K 3-D images and 143K corresponding masks. SAM-Med3D, a promptable segmentation model characterized by its fully learnable 3-D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation demonstrates the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pretrained model. Our approach illustrates that substantial medical resources can be harnessed to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at: https://github.com/uni-medical/SAM-Med3D.

Accurate automatic segmentation of medical images has long faced challenges such as significant lesion scale variations and blurred boundaries. This study proposes a Boundary-Adaptive Transformer (BAformer) specifically designed for 2D medical image segmentation. BAformer employs a hierarchical architecture that focuses on boundary-related features across varying resolutions. Additionally, we introduce a Dense Feed-forward Network (DenseFFN) to reuse features, enabling each layer to accumulate information from previous layers. Finally, we extend the benefits of the dense network to the decoder, balancing parameter efficiency and performance. Extensive experiments demonstrate that BAformer achieves state-of-the-art performance on several challenging medical segmentation tasks. Furthermore, BAformer can seamlessly integrate with existing segmentation networks, demonstrating its versatility and effectiveness.

In this paper, we are interested in exploring the problem of full-resolution image segmentation, with the focus placed on learning full-resolution representations for biomedicine images. We divide the original resolution image into patches of different sizes in different stages and then extracte local features from large to small patches using efficient and flexible components in modern convolutional neural networks (CNN). Meanwhile, a multilayer perceptron (MLP) block intended for modeling long-range dependencies between patches is designed to compensate for the inherent inductive bias caused by convolution operations. In addition, we perform multi-scale fusion and receive representation information from parallel paths at each stage, resulting in a rich full-resolution representation. We evaluate the proposed method on different biomedical image segmentation tasks and it achieves a competitive performance compared to the latest deep learning segmentation methods. It is hoped that this method will serve as a useful alternative to biomedical image segmentation and provide an improved idea for the research based on full-resolution representation.