The resolution of feature maps is a critical factor for accurate medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation adopt a U-Net-like architecture, which contains an encoder that converts the high-resolution input image into low-resolution feature maps using a sequence of Transformer blocks and a decoder that gradually generates high-resolution representations from low-resolution feature maps. However, the procedure of recovering high-resolution representations from low-resolution representations may harm the spatial precision of the generated segmentation masks. Unlike previous studies, in this study, we utilized the high-resolution network (HRNet) design style by replacing the convolutional layers with Transformer blocks, continuously exchanging feature map information with different resolutions generated by the Transformer blocks. The proposed Transformer-based network is named the high-resolution Swin Transformer network (HRSTNet). Extensive experiments demonstrated that the HRSTNet can achieve performance comparable with that of the state-of-the-art Transformer-based U-Net-like architecture on the 2021 Brain Tumor Segmentation dataset, the Medical Segmentation Decathlon’s liver dataset, and the BTCV multi-organ segmentation dataset.

Registration of optical and synthetic aperture radar (SAR) images is challenging because extracting located identically and unique features on both images are tricky. This paper proposes a novel optical and SAR image registration method based on relative total variation (RTV) and scale-invariant feature transform (SIFT), named RTV-SIFT, to extract feature points on the edges of structures and construct structural edge descriptors to improve the registration accuracy. First, a novel RTV-Harris feature point detection method by combining the RTV and the multiscale Harris algorithm is proposed to extract feature points on both images’ significant structures. This ensures a high repetition rate of the feature points. Second, the feature point descriptors are constructed on enhanced phase congruency edge (EPCE), which combines the Sobel operator and maximum moment of phase congruency (PC) to extract edges from structured images that enhance robustness to nonlinear intensity differences and speckle noise. Finally, after coarse registration, the position and orientation Euclidean distance (POED) between feature points is utilized to achieve fine feature point matching to improve the registration accuracy. The experimental results demonstrate the superiority of the proposed RTV-SIFT method in different scenes and image capture conditions, indicating its robustness and effectiveness in optical and SAR image registration.

Synthetic Aperture Radar (SAR) is an all-weather sensing technology that has proven its effectiveness for ship detection. However, detecting ships accurately with oriented bounding boxes (OBB) on SAR images is challenging due to arbitrary ship orientations and misleading scattering. In this article, we propose a novel anchor-free key-point-based detection method, KeyShip, for detecting orientated SAR ships with high precision. Our approach uses a shape descriptor to model a ship as a combination of three types of key points located at the short-edge centers, long-edge centers, and the target center. These key points are detected separately and clustered based on predicted shape descriptors to construct the final OBB detection results. To address the boundary problem that arises with the shape descriptor representation, we propose a soft training target assignment strategy that facilitates successful shape descriptor training and implicitly learns the shape information of the targets. Our experimental results on three datasets (SSDD, RSDD, and HRSC2016) demonstrate our proposed method’s high performance and robustness.

Accurate coronary artery segmentation is crucial for quantitative analysis of coronary arteries in noninvasive coronary computed tomography angiography (CCTA) images. However, current segmentation algorithms often have unsatisfactory recall due to the small size and complex morphology of coronary arteries, particularly in the distal segments. To address this issue, we introduce a new fully automated method named Ensembled-SAMs, which harnesses the strengths of the Segment Anything Model (SAM) and the no-new-U-Net (nnU-Net). First, noisy bounding box prompts are automatically generated by a vesselness algorithm that highlights the tubular structures in the CCTA images. These noisy prompts are then used to fine-tune the SAM and its two variants separately. The SAM variants introduce a classification head in their mask decoder to alleviate the false positives. In addition, an nnU-Net segmentation network is trained from scratch. Finally, the outputs of the SAMs and the nnU-Net are strategically aggregated to obtain the final segmentation result. Experiments on both a self-built dataset and the public Automated Segmentation of Coronary Arteries (ASOCA) challenge dataset demonstrate that the proposed Ensembled-SAMs outperforms the state-of-the-arts, achieving precise segmentation of coronary arteries, with particular enhancement in delineating small coronary artery segments.

Traditional deep learning models for fruit and vegetable classification are usually implemented via training on an unchanged dataset. However, changing fruit and vegetable categories is a very common occurrence in the context of real agricultural sales. When dealing with changes related to variety, deep learning models need to be retrained on the entire updated dataset. The retraining process is time-consuming and inefficient, and it may even cause the ‘catastrophic forgetting’ problem. In response to this challenge, the Adversarial Domain Adaptation Class Incremental Learning (ADA-CIL) method is introduced. This approach employs adversarial domain adaptation techniques combined with core-set selection strategies to effectively extract and integrate cross-domain features. We utilize the ResNet34 architecture as the backbone for feature extraction due to its deep residual learning framework, which is robust in handling the complexities of large and varied image datasets. It achieves a dynamic balance in learning between new and existing categories, significantly enhancing the model’s generalization capabilities and information retention efficiency. The FruVeg dataset, composed of three sub-datasets, includes over 120,000 color images, covering more than 100 different categories of fruits and vegetables collected from various domains and backgrounds. The experimental results on the FruVeg dataset show that the ADA-CIL method achieves an average accuracy of 96.30%, a forgetting rate of 2.96%, a cumulative accuracy of 96.26%, and a current accuracy of 98.60%. The ADA-CIL method improves the average accuracy by 1.65% and 1.82% compared to iCaRL and BiC, respectively, and it reduces the forgetting rate by 2.69% and 2.76%. These performance metrics demonstrate the ADA-CIL method’s impressive ability to handle incremental category and domain changes, highlighting its capability to effectively maintain the intra-class stability and exhibit exceptional adaptability in dynamic learning environments.