A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning: Dataset (5/6)

This dataset contains a collection of ultrafast ultrasound acquisitions from nine volunteers and the CIRS 054G phantom. For a comprehensive understanding of the dataset, please refer to the paper: Viñals, R.; Thiran, J.-P. A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning. J. Imaging 2023, 9, 256. https://doi.org/10.3390/jimaging9120256. Please cite the original paper when using this dataset.Due to data size restriction, the dataset has been divided into six subdatasets, each one published into a separate entry in Zenodo. This repository contains subdataset 5.StructureIn Vivo DataNumber of Acquisitions: 20,000Volunteers: Nine volunteersFile Structure: Each volunteer's data is compressed in a separate zip file.Note: For volunteer 1, due to a higher number of acquisitions, data for this volunteer is distributed across multiple zip files, each containing acquisitions from different body regions.Regions :Abdomen: 6599 acquisitionsNeck: 3294 acquisitionsBreast: 3291 acquisitionsLower limbs: 2616 acquisitionsUpper limbs: 2110 acquisitionsBack: 2090 acquisitionsFile Naming Convention: Incremental IDs from acquisition_00000 to acquisition_19999. In Vitro DataNumber of Acquisitions: 32 from CIRS model 054G phantomFile Structure: The in vitro data is compressed in the cirs-phantom.zip file.File Naming Convention: Incremental IDs from invitro_00000 to invitro_00031.CSV FilesTwo CSV files are provided:invivo_dataset.csv :Contains a list of all in vivo acquisitions.Columns: id, path, volunteer id, body region.invitro_dataset.csv :Contains a list of all in vitro acquisitions.Columns: id, pathZenodo dataset splits and filesThe dataset has been divided into six subdatasets, each one published in a separate entry on Zenodo. The following table indicates, for each file or compressed folder, the Zenodo dataset split where it has been uploaded along with its size. Each dataset split is named "A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning: Dataset (ii/6)", where ii represents the split number. This repository contains the 5th split.File nameSizeZenodo subdataset numberinvivo_dataset.csv995.9 kB1invitro_dataset.csv1.1 kB1cirs-phantom.zip418.2 MB1volunteer-1-lowerLimbs.zip29.7 GB1volunteer-1-carotids.zip8.8 GB1volunteer-1-back.zip7.1 GB1volunteer-1-abdomen.zip34.0 GB2volunteer-1-breast.zip15.7 GB2volunteer-1-upperLimbs.zip25.0 GB3volunteer-2.zip26.5 GB4volunteer-3.zip20.3 GB3volunteer-4.zip24.1 GB5volunteer-5.zip6.5 GB5volunteer-6.zip11.5 GB5volunteer-7.zip11.1 GB6volunteer-8.zip21.2 GB6volunteer-9.zip23.2 GB4Normalized RF ImagesBeamforming:Depth from 1 mm to 55 mmWidth spanning the probe apertureGrid: 𝜆/8 × 𝜆/8Resulting images shape: 1483 × 1189Two beamformed RF images from each acquisition:Input image: single unfocused acquisition obtained from a single plane wave (PW) steered at 0° (acquisition-xxxx-1PW)Target image: coherently compounded image from 87 PWs acquisitions steered at different angles (acquisition-xxxx-87PWs)Normalization:The two RF images have been normalizedTo display the images:Perform the envelop detection (to obtain the IQ images)Log-compress (to obtain the B-mode images)File Format: Saved in npy format, loadable using Python and numpy.load(file).Training and Validation Split in the paperFor the volunteer-based split used in the paper:Training set: volunteers 1, 2, 3, 6, 7, 9Validation set: volunteer 4Test set: volunteers 5, 8Images analyzed in the paperCarotid acquisition (from volunteer 5): acquisition_12397Back acquisition (from volunteer 8): acquisition_19764In vitro acquisition: invitro-00030LicenseThis dataset is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).Please cite the original paper when using this dataset :Viñals, R.; Thiran, J.-P. A KL Divergence-Based Loss for In Vivo Ultrafast Ultrasound Image Enhancement with Deep Learning. J. Imaging 2023, 9, 256. DOI: 10.3390/jimaging9120256ContactFor inquiries or issues related to this dataset, please contact:Name: Roser ViñalsEmail: [email protected]