Image segmentation and registration of carp brain tissue slices oriented to brain atlas construction.

Soybean (Glycine max L.) performs an important position as a main resource of protein in Indonesia. Its quality and productivity can be assessed based on the characteristics of its seed. Accordingly, the identification process through the observation of soybean seed traits is a crucial step in plant breeding and quality assurance. Manual approaches rely on manual observation, which is subjective, prone to human error and time-consuming. With the improvement of artificial intelligence, automated seed identification has appeared as a potential solution. However, progress is constrained by the lack of open and standardized image datasets, especially for locally bred varieties in developing countries. To address this gap, we propose an open image dataset of Indonesian soybean seeds from three widely cultivated and plant-bred varieties: Anjasmoro, Grobogan, and DEGA-1. The dataset consists of high-resolution seed images captured with an Epson L360 flatbed scanner, with the optical resolution fixed at 800 dots per inch, yielding images of 6800 × 9359 pixels. All raw images are saved in JPG format. No manually segmentation masks are released in this version, instead of using Deeplab V3+ with MobileNet as backbone to enable the automated seed image segmentation. The curated dataset is intended to support a broad range of applications, including computer vision tasks such as image classification and segmentation, as well as research in plant breeding, seed quality assessment, and agricultural informatics. By providing a standardized and publicly accessible resource, this dataset contributes to the advancement of interdisciplinary studies at the intersection of agriculture and artificial intelligence.

This dataset presents the first open-access collection of near-infrared hyperspectral imaging (NIR-HSI) data for the optical identification of textiles, with a focus on supporting research in sensor-based textile sorting and recycling. The dataset comprises hyperspectral images, RGB photographs, and detailed metadata, including fibre composition and colour, for 71 post-industrial textile samples, collected in Finland. Over 11 million spectra are included in the hyperspectral images, with more than 6 million annotated, providing a robust foundation for machine learning and data analysis. In addition, we provide a single representative NIR spectra and RGB value for each sample in order to accommodate classic spectroscopic analysis. Used garments were sourced from a partner company specializing in end-of-life textile management, with ground truth information on fibre composition obtained from suppliers. Small pieces of each garment were measured using Specim SWIR 3 hyperspectral camera and photographed with high-resolution mobile phone camera (Samsung Galaxy A52). The dataset is organized into folders containing raw and processed data, including ENVI-format hyperspectral images, RGB images, as well as CSV files with mean spectra, mean RGB values, and sample metadata. An example Python script is provided to facilitate data access and processing. Potential reuse scenarios include classification of textiles by material or colour, prediction of natural fibre content, image segmentation, algorithm development for spectral classification, and use as a reference spectral library. The dataset's comprehensive structure and open availability address the limitations of previous research, which often relied on small or non-public datasets, and is intended to accelerate advances in optical identification technologies for textile recycling.

• Dual-feature compensation framework to improve medical image segmentation of challenging lesions. • Addresses the loss of detailed global features caused by downsampling. • Uses SSL residual maps to provide additional pixel-level feature representations. • Applies patch-based cross-attention to integrate SSL residual maps, targeting likely lesion regions. Automated lesion segmentation of medical images has made tremendous improvements in recent years due to deep learning advancements. However, accurately capturing fine-grained global and regional feature representations remains a challenge. Many existing methods achieve suboptimal performance in complex lesion segmentation due to information loss during typical downsampling operations and insufficient capture of either regional or global features. To address these issues, we propose the Global and Regional Compensation Segmentation Framework (GRCSF), which introduces two key innovations: the Global Compensation Unit (GCU) and the Region Compensation Unit (RCU). The proposed GCU addresses resolution loss in the U-shaped backbone by preserving global contextual features and fine-grained details during multiscale downsampling. Meanwhile, the RCU introduces a self-supervised learning (SSL) residual map generated by Masked Autoencoders (MAE), obtained as pixel-wise differences between reconstructed and original images, to highlight regions with potential lesions. These SSL residual maps guide precise lesion localization and segmentation through a patch-based cross-attention mechanism that integrates regional spatial and pixel-level features. Additionally, the RCU incorporates patch-level importance scoring to enhance feature fusion by leveraging global spatial information from the backbone. Experiments on three publicly available medical image segmentation datasets, including brain stroke lesion, lung tumor and coronary artery calcification datasets, demonstrate that our GRCSF outperforms state-of-the-art methods, confirming its effectiveness across diverse lesion types and its potential as a generalizable lesion segmentation solution.

Quantum-enhanced gold rush Optimizer for multi-threshold segmentation of lupus nephritis pathological images

The present study investigated structural and metabolic changes in the two brain regions of the limbic system, right hippocampus and anterior cingulate cortex (ACC), implicated in the pathophysiology of major depressive disorder (MDD). Three-dimensional-T1-weighted magnetic resonance imaging (MRI) and single-voxel invivo magnetic resonance spectroscopy (MRS) were performed on a 3.0 T MRI in patients with MDD (n = 64) and healthy controls (HC, n = 47). The severity of depression was assessed using clinical scales (Hamilton Depression Rating Score [HDRS] and Montgomery-Åsberg Depression Rating Score [MDRS]). The automated volumetric segmentation of the T1-weighted MR images was performed using Freesurfer 7.2.0. The tissue-corrected concentration of neurochemicals was quantified using Osprey software. The relationship between hippocampal and ACC metabolite levels was examined with their volumes. Additionally, the levels of neurochemicals and volumes were correlated with the severity of depression. After adjusting for multiple comparisons using the false discovery rate (FDR), the concentration of total NAA (t-NAA, N-acetyl aspartate+ N-acetyl-aspartyl-glutamate [NAAG]), myoinositol (mI), total choline (tCho) and total creatine (tCr) were significantly reduced (pFDR < 0.05) in the hippocampus of the MDD patients. The ACC in MDD patients showed significantly higher levels of tNAA and tCr (pFDR < 0.05). Further, the volume of ACC was significantly increased in patients with MDD. Although hippocampal volume was not different between the two groups, a weak positive correlation was observed between the tCho levels and the volumes of the hippocampus and mid-ACC. Hippocampal glutamate + glutamine (Glx) levels showed a weak negative correlation with the MDRS score, whereas ACC tCho showed a negative correlation with the HDRS score. Our observations suggested that the pathophysiology of MDD is not only associated with hippocampal neurodegeneration but may also involve glial proliferation, leading to increased ACC volume. These changes might alter neurotransmission in the limbic system, contributing to the pathophysiology of depression.

Segmentation and analysis of OCTA images of coronary heart disease patients based on a multi-dimensional collaborative feature fusion network

MSFP-Net: a multi-scale and multi-frequency enhanced 3D network with learnable priors for coronary artery segmentation in CCTA images

EATE-Net: Edge-aware fusion and texture enhancement for fine-grained prostate zonal segmentation in transrectal ultrasound images

A robust and efficient CNN-transformer network for crack segmentation of high resolution images

Non-invasive MRI biomarkers for assessment of neoadjuvant chemotherapy response in osteosarcoma: Current techniques and clinical perspectives.

Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring precise and temporally consistent mask propagation in dynamic scenes. SAM 2 attempts to address this by training a model on massive image and video data from scratch to learn complex spatiotemporal associations, resulting in huge training costs that hinder research and practical deployment. In this paper, we introduce SAM-I2V++, a training-efficient image-to-video upgradation method for cultivating a promptable video segmentation (PVS) model. Our approach strategically upgrades the pre-trained SAM to support PVS, significantly reducing training complexity and resource requirements. To achieve this, we introduce three key innovations: (i) an image-to-video feature extraction upgrader built upon SAM's static image encoder to enable spatiotemporal video perception, (ii) a memory selective associator that retrieves the most relevant past frames via similarity-driven selection and uses multiscale-enhanced cross-attention to associate selected memory features with the current frame, and (iii) a memory-as-prompt mechanism leveraging object memory to ensure temporally consistent mask propagation in dynamic scenes. Comprehensive experiments demonstrate that our method achieves 93% of SAM 2's performance while using only 0.2% of its training cost. Our work presents a resource-efficient pathway to PVS, lowering barriers for further research in PVS model design and enabling broader applications and advancements in the field.

TD2-LTS: Transformer based group-channel interaction for medical image segmentation

Mix-contrastive learning with multi-way fusion for high-efficiency semi-supervised medical image segmentation

Joint parallel modeling with direction-wise convolution and deformable transformer for 3D medical image segmentation

Hawk-Net: Medical image segmentation and classification using multi-scale convolutional self-attention-based image processor with DK-CNN-Mamba-xAttention Fusion Network

Aegis: A domain generalization framework for medical image segmentation by mitigating feature misalignment

LBMS-SAM: Segment anything model guided SEM image segmentation for lithium battery materials.

Domain divergence minimization for unsupervised domain adaptation cross-modality medical image segmentation

Uncertainty-weighted feature alignment and information interaction network for multi-scale medical image segmentation