Scientific DataPub Date : 2026-08-24DOI: 10.1038/s41597-026-07801-3
Nora R Aasen, Sybil A Herrera-Foessel, Silius M Vandeskog, Therése Bengtsson, Mulatu G Dida, Isak Drozdik, Sigridur Dalmannsdottir, Egill Gautason, Jaroslaw S Grodek, Hrannar S Hilmarsson, Merja Högnäsbacka, Ortrud Jäck, Janne Kaseva, Antti Laine, Alex Lenkoski, Morten Lillemo, Min Lin, Anne Marthe Lundby, Shirin Mohammadi, Per J Møllerhagen, Markku Niskanen, Rodomiro Ortiz, Maxie Skalshøi, Anna G Þórðardóttir, Maria Thorkildsen
{"title":"A multi-environment dataset consisting of official field trials for three major crops in the Nordic countries.","authors":"Nora R Aasen, Sybil A Herrera-Foessel, Silius M Vandeskog, Therése Bengtsson, Mulatu G Dida, Isak Drozdik, Sigridur Dalmannsdottir, Egill Gautason, Jaroslaw S Grodek, Hrannar S Hilmarsson, Merja Högnäsbacka, Ortrud Jäck, Janne Kaseva, Antti Laine, Alex Lenkoski, Morten Lillemo, Min Lin, Anne Marthe Lundby, Shirin Mohammadi, Per J Møllerhagen, Markku Niskanen, Rodomiro Ortiz, Maxie Skalshøi, Anna G Þórðardóttir, Maria Thorkildsen","doi":"10.1038/s41597-026-07801-3","DOIUrl":"10.1038/s41597-026-07801-3","url":null,"abstract":"<p><p>Climate change will substantially impact agriculture, requiring the development of new crop cultivars adapted for resilience to future stresses. Developing a new crop cultivar is a decades-long process. Therefore climate change considerations must already be incorporated into breeding programs. National breeding programs have typically involved field trials in a single country, which has functioned satisfactorily during periods of stable climate variability. However, it is widely acknowledged that when field trial information across borders is made available, it can significantly aid plant breeding programs. This paper presents a pan-Nordic multi-environment dataset that consolidates national trial data and data from VCU (Value for Cultivation and Use) trials for spring barley, red clover, and potato, during 1970-2024. The dataset harmonizes information on yield across diverse environments, enabling comparative analyses and cross-regional assessments. By providing a unified resource for the Nordic region, this dataset supports the development of more resilient crop varieties and facilitates data-driven breeding strategies under changing climatic conditions.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13503912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148814027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-19DOI: 10.1038/s41597-026-07935-4
Anne-Marie Galow, Frieder Hadlich, Nares Trakooljul, Christina Walz, Andreas Hoeflich, Julia Brenmoehl
{"title":"Effects of genotype and exercise on hepatic gene expression in phenotype-selected marathon mice.","authors":"Anne-Marie Galow, Frieder Hadlich, Nares Trakooljul, Christina Walz, Andreas Hoeflich, Julia Brenmoehl","doi":"10.1038/s41597-026-07935-4","DOIUrl":"10.1038/s41597-026-07935-4","url":null,"abstract":"<p><p>Experimental evolution through selection experiments is a vital tool for exploring the special features of polygenic traits. Here, we provide liver transcriptome data from a paternally selected marathon mouse model (DUhTP), characterized by exceptional running performance, and unselected controls (DUC), both descended from the same polygenic background. To study training responses, both lines were either challenged by three weeks of high-speed treadmill training or remained sedentary. For each condition, eight animals were used for liver tissue isolation and next-generation sequencing. Raw sequencing files were submitted to the ArrayExpress collection under accession number E-MTAB-12071. High data quality was confirmed by appropriate mean read lengths, high mean quality scores, and low duplication rates after adapter trimming. With an average of 16.9 million reads per sample mapping to 19,930 genes, the dataset enables comprehensive gene expression analyses. A multiQC report for the dataset, together with a sample-by-gene count matrix, is available on Figshare. The provided data offer a valuable resource for research in polygenic traits associated with physical activity.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13490605/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-18DOI: 10.1038/s41597-026-07388-9
Matthias Aengenheyster, Christopher David Roberts, Razvan Aguridan, Matthew Griffith, Robin Hogan, Balthasar Reuter, Malcolm J Roberts, Domokos Sarmany, Retish Senan, Timothy N Stockdale, Sebastien Villaume, Fabian Wachsmann
{"title":"Multi-decadal high-resolution historical simulations with the ECMWF global atmosphere model.","authors":"Matthias Aengenheyster, Christopher David Roberts, Razvan Aguridan, Matthew Griffith, Robin Hogan, Balthasar Reuter, Malcolm J Roberts, Domokos Sarmany, Retish Senan, Timothy N Stockdale, Sebastien Villaume, Fabian Wachsmann","doi":"10.1038/s41597-026-07388-9","DOIUrl":"10.1038/s41597-026-07388-9","url":null,"abstract":"<p><p>This paper describes an ensemble of global atmosphere reference simulations covering the period 1980 to 2023 produced with the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecasting System (IFS). The resulting dataset consists of 6-hourly three-dimensional global outputs from higher- and lower-resolution configurations of the IFS, which have average horizontal grid spacings of ~9 km (one ensemble member) and ~28 km (ten ensemble members), respectively. The atmosphere is constrained by high-resolution satellite-based estimates of daily mean sea surface temperature and sea ice concentration and time-evolving external climate forcings, including observed greenhouse gas and estimated aerosol concentrations. These data were produced as part of the European Eddy-Rich Earth System Models (EERIE) project and will serve as a reference for corresponding ocean-atmosphere coupled simulations and idealised sensitivity experiments. We have made this dataset publicly available and expect it to be a valuable resource for scientific research and other applications that extend beyond the lifetime of the EERIE project.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13498584/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-17DOI: 10.1038/s41597-026-07809-9
D V Kostulin, P D Shaposhnikov, A Kh Ekizyan, I G Shevchenko, D G Shaposhnikov, I V Shcherban, V N Kiroy
{"title":"EEG-based brain-computer interface (BCI) dataset for directional word recognition.","authors":"D V Kostulin, P D Shaposhnikov, A Kh Ekizyan, I G Shevchenko, D G Shaposhnikov, I V Shcherban, V N Kiroy","doi":"10.1038/s41597-026-07809-9","DOIUrl":"https://doi.org/10.1038/s41597-026-07809-9","url":null,"abstract":"<p><p>We present an EEG dataset recorded from 22 neurologically healthy volunteers (12 native Russian speakers and 10 native Spanish speakers) during overt and covert articulation of six spatial-direction words. Monopolar EEG signals were acquired from 38 electrodes positioned according to the international 10-10 system using a Neurovisor-BMM-52 (NVX) amplifier at 500 Hz. In a subset of participants, electromyography (EMG) was simultaneously recorded from the masseter muscle and laryngeal region to exploratorily characterize articulatory muscle activation. Exploratory spectral and coherence analyses, together with classification using standard machine learning methods (Random Forest, SVM, LDA), confirm the presence of condition-specific neural activity distinguishable by standard classifiers (best accuracy 78 ± 4%). The dataset is intended to support the development and benchmarking of algorithms for inner speech recognition in brain-computer interface applications.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13482365/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-17DOI: 10.1038/s41597-026-07799-8
Benyue Su, Baoqian Wang, Zhixin Ge, Yu Li, Yuting Li, Xin Li, Qingfeng Tang, Min Sheng
{"title":"GaitIntent: A Kinematic Dataset Focusing on Steady-State to Transitional Locomotion for Lower-Limb Motion Rehabilitation.","authors":"Benyue Su, Baoqian Wang, Zhixin Ge, Yu Li, Yuting Li, Xin Li, Qingfeng Tang, Min Sheng","doi":"10.1038/s41597-026-07799-8","DOIUrl":"https://doi.org/10.1038/s41597-026-07799-8","url":null,"abstract":"<p><p>Motion intent recognition (MIR), the real-time interpretation of user movement, is crucial for advanced motion rehabilitation. MIR enables responsive control of prostheses and exoskeletons, enhancing mobility for lower-limb impaired individuals. Most existing datasets prioritize steady-state locomotion, often overlooking complex transitional movements critical in daily activities, which limits anticipatory control development. We introduce GaitIntent, a novel kinematic dataset. Inspired by gait symmetry, it uses sound limb kinematics for predictive MIR for the affected side-an approach less comprehensively covered. We collected multi-node Inertial Measurement Units (IMUs) data from the thigh, shank, and foot of 11 subjects' sound limbs performing 13 daily activities, emphasizing eight distinct transitional movements. GaitIntent provides a valuable resource for developing low-latency, robust algorithms for wearable rehabilitation and human-centric control systems.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13482561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-17DOI: 10.1038/s41597-026-07727-w
Lihao Zheng, Mohamad Iqbal Hakim Mohd Azhan, Shairul Izan Ramlee, Erneeza Mohd Hata, Dzarifah Zulperi, Kumar Gaurav, Sanu Arora, Muhammad Asyraf Md Hatta
{"title":"Whole-Genome Variants Resource of 144 Oryza rufipogon Accessions.","authors":"Lihao Zheng, Mohamad Iqbal Hakim Mohd Azhan, Shairul Izan Ramlee, Erneeza Mohd Hata, Dzarifah Zulperi, Kumar Gaurav, Sanu Arora, Muhammad Asyraf Md Hatta","doi":"10.1038/s41597-026-07727-w","DOIUrl":"https://doi.org/10.1038/s41597-026-07727-w","url":null,"abstract":"<p><p>The global food security crisis highlights the urgent need to improve rice yield and quality. Oryza rufipogon, the wild progenitor of cultivated rice, offers valuable genetic diversity, yet its genome remains underexplored. We conducted whole-genome resequencing (WGS) of 144 O. rufipogon accessions from 13 countries, generating ~400 GB of data using the Illumina NovaSeq 6000 platform. After quality control, 97.58% of reads aligned to the reference genome, achieving 87.97% coverage with 12.47× average depth. We identified a total of 6,183,832 SNPs and 748,493 InDels across 12 chromosomes. Chromosome 1 exhibited the most variants (715,636 SNPs and 91,276 InDels), while chromosome 9 had the fewest (384,000 SNPs and 44,817 InDels). Mutation rates were 67 SNPs and 559 InDels per million base pairs. Notably, 40.75% of SNPs and 46.09% of InDels were found upstream of genes, with 19.13% and 22.26% located downstream, respectively. A transition-to-transversion ratio (Ti/Tv) of 2.72 confirmed the data's reliability. Our findings offer a comprehensive genomic variation resource for O. rufipogon, supporting future genetic research and rice breeding efforts.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13483050/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios.","authors":"Zeyi Liu, Shuang Liu, Jihai Min, Zhaoheng Zhang, Jun Cen, Pengyu Han, Songqiao Hu, Zihan Meng, Xiao He, Donghua Zhou","doi":"10.1038/s41597-026-07796-x","DOIUrl":"https://doi.org/10.1038/s41597-026-07796-x","url":null,"abstract":"<p><p>With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex and dynamic industrial sites has become a key bottleneck for deploying predictive maintenance and autonomous inspection. Most public datasets remain limited by simulated data sources, single-modality sensing, or the absence of fine-grained object-level annotations, which prevents robust scene understanding and multimodal safety reasoning for industrial foundation models. To address these limitations, InspecSafe-V1 is released as the first multimodal benchmark dataset for industrial inspection safety assessment that is collected from routine operations of real inspection robots in real-world environments. InspecSafe-V1 covers five representative industrial scenarios, including tunnels, power facilities, sintering equipment, oil and gas petrochemical plants, and coal conveyor trestles. The dataset is constructed from 41 wheeled and rail-mounted inspection robots operating at 2,239 valid inspection sites, yielding 5,013 inspection instances. For each instance, pixel-level segmentation annotations are provided for key objects in visible-spectrum images. In addition, a semantic scene description and a corresponding safety level label are provided according to practical inspection tasks. Seven synchronized sensing modalities are further included, including infrared video, audio, depth point clouds, radar point clouds, gas measurements, temperature, and humidity, to support multimodal anomaly recognition, cross-modal fusion, and comprehensive safety assessment in industrial environments.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13482562/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A High-Quality Haplotype-Resolved Reference Genome for Drakensberger Cattle (Bos taurus indicus/taurus) Achieved Through Trio-Binned Long-Read Sequencing.","authors":"Ntanganedzeni Mapholi, Thendo Tshilate, Rae Smith, Nompilo Hlongwane, Lucky Tendani Nesengani","doi":"10.1038/s41597-026-07794-z","DOIUrl":"https://doi.org/10.1038/s41597-026-07794-z","url":null,"abstract":"<p><p>Drakensberger cattle is indigenous to South Africa and represent a unique genetic resource which is known for its quality beef production and adapted to the harsh climatic conditions. Despite its significance within the beef industry, no high-quality chromosomal level genome has been reported for this breed, limiting genomic selection and conservation efforts. Although there is a bovine genome reference, we need a breed specific reference to identify breed-unique alleles and structural variants that might not be explained by a distant reference. To address this, we generated a haplotype resolved assembly for Drakensberger cattle using a trio-binning where we employed PacBio HiFi reads for sire and dam, a combination of PacBio HiFi reads, Oxford Nanopore Technologies reads and Omni-C reads for the offspring. The assembled diploid genome size is 2.89 Gb with a scaffold N50 of 111 Mb and contig N50 of 61 Mb. The consensus accuracy was exceptionally high (QV = 70.23) and a genome completeness of 97.5%, as analysed by the Benchmarking Universal Single-Copy Orthologs (BUSCO). The k-mer profiling suggested one of the strong haplotype separation for livestock with the paternity assembly containing 97.1% and maternity with 99.0%, combined diploid genome recovered 99.46% of all the statistically solid read k-mers. We identified 14 telomeric ends across 13 scaffolds. The final genome encompassed a total of 22,854 protein-coding genes. This is the first high-quality, haplotype resolved genome assembly of the Drakensberger breed. This assembly high accuracy, contiguity and completeness place the genome among the highest-quality cattle genomes produced to date. This genomic resource is essential in designing programs to studies for breed evolution, adaptation, genomic selection and for conservation of the South African indigenous resources.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13482388/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific DataPub Date : 2026-08-13DOI: 10.1038/s41597-026-08064-8
Xiang Xu, Fei Wang, Weiqi Liu, Haowen Li, Yingyu Wang, Yuan Li, Bing Wang, Mingming Liu, Yang Li
{"title":"An integrated single-cell transcriptomic and microbiome dataset of orbital adipose tissue in thyroid eye disease.","authors":"Xiang Xu, Fei Wang, Weiqi Liu, Haowen Li, Yingyu Wang, Yuan Li, Bing Wang, Mingming Liu, Yang Li","doi":"10.1038/s41597-026-08064-8","DOIUrl":"10.1038/s41597-026-08064-8","url":null,"abstract":"<p><p>Thyroid eye disease (TED), also historically referred to as thyroid-associated ophthalmopathy (TAO) or Graves' orbitopathy (GO), is an autoimmune ophthalmopathy characterized by inflammation and adipogenesis within orbital adipose (OA) tissue. While the contribution of immune cell infiltration and fibroblast activation is recognized, the cellular heterogeneity and the potential role of local microbial dysbiosis in the orbital microenvironment remain poorly defined. Here, we present a multi-omics dataset derived from OA of patients with TED and healthy controls collected at Beijing Tongren Hospital. The dataset comprises single-cell RNA sequencing (scRNA-seq) data generated from human orbital adipose tissue and subcutaneous fat. Following quality control filtering and doublet removal, a total of 61,302 high-quality singlet cells were retained for downstream analyses, capturing the transcriptomic landscape of orbital fibroblasts, immune subsets, and vascular cells. In parallel, 16S rRNA gene sequencing was performed on orbital adipose tissue samples collected from the integrated study cohort, alongside environmental samples for contamination assessment, to characterize the low-biomass orbital microbiome DNA signatures. Raw sequencing reads, quality-controlled gene-expression matrices, and contamination-corrected microbial feature tables are provided. Our dataset provides an opportunity to investigate the crosstalk between host cellular immunity and potential local microbiome signatures, facilitating hypothesis generation regarding host-microbiome crosstalk and the exploration of novel therapeutic targets for TED.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13680605/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149224800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PatchChestCT: A patch-level spatial annotation dataset for nine abnormalities in chest CT.","authors":"Yingtai Li, Hongchun Zhang, Mengwen Xu, Lidan Zhang, Najuan Lei, Yushuang Zhang, Xinli Zhu, Yan Lu, Wei Wei, Shaohua Kevin Zhou","doi":"10.1038/s41597-026-07793-0","DOIUrl":"10.1038/s41597-026-07793-0","url":null,"abstract":"<p><p>The development of generalist artificial intelligence (AI) models for radiology is hindered by a lack of large-scale, three-dimensional (3D) imaging datasets with precise spatial annotations. While numerous datasets provide image-level labels for chest computed tomography (CT), these are insufficient for training models that can accurately localize findings. To address this gap, we present PatchChestCT, a large-scale, publicly available dataset for multi-abnormality localization in non-contrast chest CT. Using CT-RATE as the source cohort, PatchChestCT provides 3D patch-level annotations for nine clinically significant abnormalities across 2,201 physician-reviewed CT studies, with one reconstructed volume labeled per study. We introduce a token-aligned annotation scheme that is efficient, scalable, and naturally integrates with modern deep learning architectures like Transformers. To validate the dataset's utility, we show that models trained with our patch-level labels achieved higher localization performance than weakly supervised baselines trained on image-level labels alone, across multiple architectures. PatchChestCT provides a public resource for training localization-aware models in chest CT.</p>","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"13 1","pages":""},"PeriodicalIF":7.2,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13469086/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148725460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}