Brain lesion segmentation is crucial for neurological disease research and diagnosis. As different types of lesions exhibit distinct characteristics on different imaging modalities, segmentation methods are typically developed in a task-specific manner, where each segmentation model is tailored to a specific lesion type and modality. However, the use of task-specific models requires predetermination of the lesion type and imaging modality, which complicates their deployment in real-world scenarios. In this work, we propose a universal foundation model for brain lesion segmentation on magnetic resonance imaging (MRI), which can automatically segment different types of brain lesions given input of various MRI modalities. We develop a novel Mixture of Modality Experts (MoME) framework with multiple expert networks attending to different imaging modalities. A hierarchical gating network is proposed to combine the expert predictions and foster expertise collaboration. Moreover, to avoid the degeneration of each expert network, we introduce a curriculum learning strategy during training to preserve the specialisation of each expert. In addition to MoME, to handle the combination of multiple input modalities, we propose MoME+, which uses a soft dispatch network for input modality routing. We evaluated the proposed method on nine brain lesion datasets, encompassing five imaging modalities and eight lesion types. The results show that our model outperforms state-of-the-art universal models for brain lesion segmentation and achieves promising generalisation performance onto unseen datasets.
Remote sensing has now been widely used in various fields, and the research on the automatic land-cover segmentation methods of remote sensing imagery is significant to the development of remote sensing technology. Deep learning methods, which are developing rapidly in the field of semantic segmentation, have been widely applied to remote sensing imagery segmentation. In this work, a novel deep learning network—Dual Encoder with Attention Network (DEANet) is proposed. In this network, a dual-branch encoder structure, whose first branch is used to generate a rough guidance feature map as area attention to help re-encode feature maps in the next branch, is proposed to improve the encoding ability of the network, and an improved pyramid partial decoder (PPD) based on the parallel partial decoder is put forward to make fuller use of the features form the encoder along with the receptive filed block (RFB). In addition, an edge attention module using the transfer learning method is introduced to explicitly advance the segmentation performance in edge areas. Except for structure, a loss function composed with the weighted Cross Entropy (CE) loss and weighted Union subtract Intersection (UsI) loss is designed for training, where UsI loss represents a new region-based aware loss which replaces the IoU loss to adapt to multi-classification tasks. Furthermore, a detailed training strategy for the network is introduced as well. Extensive experiments on three public datasets verify the effectiveness of each proposed module in our framework and demonstrate that our method achieves more excellent performance over some state-of-the-art methods.
Deep learning shows promise in automated brain tumour segmentation, but it depends on costly expert annotations. Recent advances in unsupervised learning offer an alternative by using synthetic data for training. However, the discrepancy between real and synthetic data limits the accuracy of the unsupervised approaches. In this paper, we propose an approach for unsupervised brain tumour segmentation on magnetic resonance (MR) images via a two-stage image synthesis strategy. This approach accounts for the domain gap between real and synthetic data and aims to generate realistic synthetic data for model training. In the first stage, we train a junior segmentation model using synthetic brain tumour images generated by hand-crafted tumour shape and intensity models, and employs a validation set with distribution shift for model selection. The trained junior model is applied to segment unlabelled real tumour images, generating pseudo labels that capture realistic tumour shape, intensity, and texture. In the second stage, realistic synthetic tumour images are generated by mixing brain images with tumour pseudo labels, closing the domain gap between real and synthetic images. The generated synthetic data is then used to train a senior model for final segmentation. In experiments on five brain imaging datasets, the proposed approach, named as SynthTumour, surpasses existing unsupervised methods and demonstrates high performance for both brain tumour segmentation and ischemic stroke lesion segmentation tasks.
Accurate camera–LiDAR fusion relies on precise extrinsic calibration, which fundamentally depends on establishing reliable cross-modal correspondences under potentially large misalignments. Existing learning-based methods typically project LiDAR points into depth maps for feature fusion, which distorts 3D geometry and degrades performance when the extrinsic initialization is far from the ground truth. To address this issue, we propose an extrinsic-aware cross-attention framework that directly aligns image patches and LiDAR point groups in their native domains. The proposed attention mechanism explicitly injects extrinsic parameter hypotheses into the correspondence modeling process, enabling geometry-consistent cross-modal interaction without relying on projected 2D depth maps. Extensive experiments on the KITTI and nuScenes benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in both accuracy and robustness. Under large extrinsic perturbations, our approach achieves accurate calibration in 88% of KITTI cases and 99% of nuScenes cases, substantially surpassing the second-best baseline.