Precipitation - BES rain gauge network
收藏Tree (DSD)
The dataset provides information of the Tree by the Drainage Services Department.
空间数据共享平台 收录
钢城区施工许可数据信息
钢城区施工许可数据信息
山东公共数据开放网 收录
黄河流域30米分辨率数字高程模型(DEM)数据
本数据以SRTM30米分辨率DEM数据为数据源,进行数据拼接、重采样等影像处理,再利用黄河流域区域边界裁剪,生成空间分辨率为30m的黄河流域区域DEM数据产品。该数据可为黄河流域区域科学研究提供基础地理数据支持。
国家冰川冻土沙漠科学数据中心 收录
IVLLab/MultiDialog
该数据集包含手动注释的元数据,将音频文件与转录、情感和其他属性链接起来。数据集支持多种任务,包括多模态对话生成、自动语音识别和文本到语音转换。数据集的语言为英语,并提供了一个黄金情感对话子集,用于研究对话中的情感动态。数据集的结构包括音频文件、对话ID、话语ID、来源、音频特征、转录文本、情感标签和原始路径等信息。
hugging_face 收录
didsr/tsynth
--- license: cc0-1.0 task_categories: - image-classification - image-segmentation tags: - medical pretty_name: T-SYNTH size_categories: - 1K<n<10K --- # T-SYNTH <!-- Provide a quick summary of the dataset. --> T-SYNTH is a synthetic digital breast tomosynthesis (DBT) dataset with four breast fibroglandular density distributions imaged using Monte Carlo x-ray simulations with the publicly available [Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE)](https://github.com/DIDSR/VICTRE) toolkit. ## Dataset Details The dataset has the following characteristics: * Breast density: dense, heterogeneously dense, scattered, fatty * Mass radius (mm): 5.00, 7.00, 9.00 * Mass density: 1.0, 1.06, 1.1 (ratio of mass radiodensity to that of fibroglandular tissue) ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> - **Curated by:** [Christopher Wiedeman](https://www.linkedin.com/in/christopher-wiedeman-a0b01014b), [Anastasiia Sarmakeeva](https://www.linkedin.com/in/anastasiia-sarmakeeva/), [Elena Sizikova](https://esizikova.github.io/), [Daniil Filienko](https://www.linkedin.com/in/daniil-filienko-800160215/), [Miguel Lago](https://www.linkedin.com/in/milaan/), [Jana Gut Delfino](https://www.linkedin.com/in/janadelfino/), [Aldo Badano](https://www.linkedin.com/in/aldobadano/) - **License:** Creative Commons 1.0 Universal License (CC0) ## Data Acquisition Details **Imaging Modality:** Paired 2D digital mammography (DM) and 3D digital breast tomosynthesis (DBT) images. The DBT images are projected into C-VIEW via the method of (Klein, 2023). **Manufacturer and Model:** Replica of the Siemens detector based on MC-GPU (Badal and Badano, 2009). **Demographics:** All breast phantoms are synthetic and do not represent real human subjects. **Cohort Description:** 9,000 synthetic digital breast tomosynthesis (DBT) samples, distributed across four breast density categories: | Breast Density | Fatty | Scattered | Hetero | Dense | **Total** | | --------- | --------- | --------- | ------- | ------- | --------- | | **Les.-free / Les.-present** | 1350/1350 | 1350/1350 | 900/900 | 900/900 | 4500/4500 | **Annotation Protocols:** Lesion masks and bounding boxes were generated automatically from the phantom. **Data Format and Structure:** Image files are in .raw format. ### Dataset Sources <!-- Provide the basic links for the dataset. --> - **Code:** [https://github.com/DIDSR/tsynth-release](https://github.com/DIDSR/tsynth-release) ## Intended Use <!-- Address questions around how the dataset is intended to be used. --> T-SYNTH is intended to facilitate testing of AI with pre-computed synthetic digital breast tomosynthesis (DBT) data, complementing the M-SYNTH synthetic mammography dataset. ## Ethical Considerations This work is using synthetically generated data and does not include any real patient-identifiable information. Publication of synthetic data aims to promote transparency, reproducibility, and fairness in medical AI research. We recommend avoiding training models only on synthetic data without appropriate validation. ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> Directory layout: ``` T-SYNTH/data/ ├── cview ├── embed_metadata ├── pretrained_models ├── results └── volumes_subset ``` Descriptions: * **`cview/`** -- contains T-SYNTH C-VIEW images. * **`embed_metadata/`** -- Configuration files needed to reproduce experiments. * **`pretrained_models/`** -- Pretrained models for ```DBT```, ```DM``` and ```diffusion``` experiments to reproduce results from the paper. Note to reproduce you need files from **`embed_metadata/`**. * **`results/`** -- Output data and plots used in the paper (see [T-SYNTH repository](https://github.com/DIDSR/tsynth-release/tree/main/code/notebooks)). Description for each experiment could be found [here](https://github.com/DIDSR/tsynth-release/blob/main/code/README.md#experiment-configuration-map). * **`volumes_subset/`** -- example of volumetric data. The full data set will be released later due to volume. The data is organized by lesion size, breast density and lesion density. Folder names follow the convention: ```output_cview_det_Victre/device_data_VICTREPhantoms_spic_[LESION_DENSITY]/[BREAST_DENSITY]/2/[LESION_SIZE]/SIM.zip```. Example path in `volumes_subset`: ``` device_data_VICTREPhantoms_spic_1.1/fatty/2/5.0/SIM/D2_5.0_fatty.1/1/ ├── reconstruction1.loc # Lesion coordinates ├── reconstruction1.mhd # Metadata (raw format) ├── reconstruction1.raw # Raw image data └── reconstruction1_mask.h5 # Pixel-level segmentation masks for lesions and tissues ``` ## How to use it The description how to use it could be found [here](https://github.com/DIDSR/tsynth-release/blob/main/code/README.md). ## Citation ``` @article{t-synth, title={T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Images}, author={Christopher Wiedeman, Anastasiia Sarmakeeva, Elena Sizikova, Daniil Filienko, Miguel Lago, Jana G. Delfino, Aldo Badano}, journal={}, volume={}, pages={}, year={2025} } ``` ## Related Links 1. [Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE)](https://cdrh-rst.fda.gov/victre-silico-breast-imaging-pipeline). 2. [M-SYNTH: A Dataset for the Comparative Evaluation of Mammography AI](https://cdrh-rst.fda.gov/m-synth-dataset-comparative-evaluation-mammography-ai). 6. A. Kim*, N. Saharkhiz*, E. Sizikova*, M. Lago, B. Sahiner, J. G. Delfino, A. Badano. [S-SYNTH: Knowledge-Based, Synthetic Generation of Skin Images](https://github.com/DIDSR/ssynth-release). MICCAI 2024. 4. [FDA Catalog of Regulatory Science Tools to Help Assess New Medical Devices](https://www.fda.gov/medical-devices/science-and-research-medical-devices/catalog-regulatory-science-tools-help-assess-new-medical-devices).
hugging_face 收录