Find research datasets worth reusing

restrictedcc-by-4.0May 2024View details →

Segmented LGE-MRI dataset

Segmented dataset own data from Moscow Regional Scientific Research Clinical Institute. MF Vladimirsky and from cDEMRIS dataset (https://figshare.com/articles/dataset/CDEMRIS_fibrosis_scar_challenge_data_2012/4214532/5)

restrictedcc-by-4.0May 2024View details →

DSCA: A Digital Subtraction Angiography Sequence Dataset for Cerebral Artery Segmentation

These datasets are released for academic research purpose only. <table> <tbody> <tr> <td>Folders</td> <td>Formats</td> <td>Train/Test</td> <td>Number</td> </tr> <tr> <td>imagesTr</td> <td>nii.gz</td> <td>Train</td> <td>180</td> </tr> <tr> <td>imagesTr_s</td> <td>dcm/sequence</td> <td>Train</td> <td>180</td> </tr> <tr> <td>imagesTs</td> <td>nii.gz</td> <td>Test</td> <td>44</td> </tr> <tr> <td>imagesTs_s</td> <td>dcm/sequence</td> <td>Test</td> <td>44</td> </tr> <tr> <td>labelsTr</td> <td>nii.gz</td> <td>Train</td> <td>180</td> </tr> <tr> <td>labelsTs</td> <td>nii.gz</td> <td>Test</td> <td>44</td> </tr> </tbody> </table>

restrictedcc-by-4.0Oct 2024View details →

Dataset for research paper titled "Seafloor Spreading Characteristics of Slow-Spreading Segment in the Central Indian Ridge"

This dataset contains the following data: (1) Bathymetry data of Segment 3-2 in middle-part of Central Indian Ridge (GMT grid file). (2) Magnetic anomaly data (processed line data) acquired by sea-surface magnetometer (.dat file). (3) Re-sampled magnetic anomaly data for estimation of half-spreading rate (.dat file).

openother-ncMar 2023View details →

Large-scale annotation dataset for cell/tissue segmentation in H&E-stained images : anti-MIST1 (plasma cells)

LICENSE This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC-BY-NC-SA 4.0) For non-commercial use, please use the dataset under CC-BY-NC-SA. If you would like to use the dataset for commercial purposes, please contact us (ishum-prm@m.u-tokyo.ac.jp). A Tar.gz file contains the following files: - HE image file: {antigen}_{celltype}_{slideID}_{posx}_{posy}_HE.png - Mask image file: {antigen}_{celltype}_{slideID}_{posx}_{posy}_mask.png Each image file is 984x984 px. posX and posY are the leftmost position in WSI coordinate. Mask files store binary segmentation mask (background : 0, target : 1)   A csv file contains the following information: antigen : Antibodies for this antigen were used to create the segmentation mask. filename: filename of image or mask file. train_val_test : train, validation, or test sample in the paper.   Citation If you use this dataset for your research, please cite our paper. Daisuke Komura, Takumi Onoyama, Koki Shinbo, Hiroto Odaka, Minako Hayakawa, Mieko Ochi, Ranny Rahaningrum Herdiantoputri, Haruya Endo, Hiroto Katoh, Tohru Ikeda, Tetsuo Ushiku, Shumpei Ishikawa, Restaining-based annotation for cancer histology segmentation to overcome annotation-related limitations among pathologists, Patterns, Volume 4, Issue 2, 2023, 100688, https://doi.org/10.1016/j.patter.2023.100688.

opencc-by-4.0Dec 2022View details →

Additional dataset for 'Principles of RNA recruitment to viral ribonucleoprotein condensates in a segmented dsRNA virus'

Additional dataset - RNA FISH data set for Figure 6b

restrictedcc-by-4.0Apr 2024View details →

A comprehensive dataset of magnetic resonance enterography images with bowel segment annotations

Inflammatory bowel disease (IBD) is a kind of recurrent bowel disease and usually requires magnetic resonance enterography (MRE) examinations for diagnosis and monitoring. However, radiologists’ recognition of bowel segments from MRE images is challenging and time-consuming. Deep learning-based medical image segmentation has shown the potential to reduce manual efforts and provide automated tools to assist in the management of disease, but it requires a large-scale fine-annotated dataset for training. To address this gap, we collected MRE data from 114 IBD patients. The bowel images per patient were contoured and annotated as ten segments (stomach, duodenum, small intestine, appendix, cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum), with fine pixel-level annotations labeled by experienced radiologists. Further, we validated the efficiency of several state-of-the-art segmentation methods on this dataset. This work established a high quality, publicly available whole bowel segment MR dataset with benchmark results and laid a groundwork for IBD’s AI research.

restrictedNov 2021View details →

A study of generalization and compatibility performance of 3D U‑Net segmentation on multiple heterogeneous liver CT datasets

Background: Most existing algorithms have been focused on the segmentation from several public Liver CT datasets scanned regularly (no pneumoperitoneum and horizontal supine position). This study primarily segmented datasets with unconventional liver shapes and intensities deduced by contrast phases, irregular scanning conditions, different scanning objects of pigs and patients with large pathological tumors, which formed the multiple heterogeneity of datasets used in this study. Methods: The multiple heterogeneous datasets used in this paper includes: (1) One public contrast-enhanced CT dataset and one public non-contrast CT dataset; (2) A contrast-enhanced dataset that has abnormal liver shape with very long left liver lobes and large-sized liver tumors with abnormal presets deduced by microvascular invasion; (3) One artificial pneumoperitoneum dataset under the pneumoperitoneum and three scanning profiles (horizontal/ left/right recumbent position); (4) Two porcine datasets of Bama type and domestic type that contains pneumoperitoneum cases but with large anatomy discrepancy with humans. The study aimed to investigate the segmentation performances of 3D U-Net in: (1) generalization ability between multiple heterogeneous datasets by cross-testing experiments; (2) the compatibility when hybrid training all datasets in different sampling and encoder layer sharing schema. We further investigated the compatibility of encoder level by setting separate level for each dataset (i.e., dataset-wise convolutions) while sharing the decoder. Results: Model trained on different datasets has different segmentation performance. The prediction accuracy between LiTS dataset and Zhujiang dataset was about 0.955 and 0.958 which shows their good generalization ability due to that they were all contrast-enhanced clinical patient datasets scanned regularly. For the datasets scanned under pneumoperitoneum, their corresponding datasets scanned without pneumoperitoneum showed good generalization ability. Dataset-wise convolution module in high-level can improve the dataset unbalance problem. The experimental results will facilitate researchers making solutions when segmenting those special datasets. Conclusions: (1) Regularly scanned datasets is well generalized to irregularly ones. (2) The hybrid training is beneficial but the dataset imbalance problem always exits due to the multi-domain homogeneity. The higher levels encoded more domain specific information than lower levels and thus were less compatible in terms of our datasets.

restrictedFeb 2022View details →

An unenhanced abdominal CT dataset for kidney and kidney stone segmentation

260 unenhanced abdominal CT scans from 2018 to 2020 were collected from the First Affiliated Hospital of Guangzhou Medical University. After data desensitization and data cleaning, the clean NIfTI image of abdominal CT scans was annotated based on clinical requirements and image segmentation needs. Two labels (“kidney” and “kidney stone”) were considered for masking and labeling. The 3D Slicer tool was used to mask the CT scans. The data annotations process comprised three stages. Data annotation was performed under the guidance of a professional urologist.  Each CT scan contains an original raw image and a masked image for kidney and kidney stone. Please note that the whole dataset is split into 5 parts for easy download.

restrictedcc-by-4.0Jul 2022View details →

Validation dataset and reference code for Carotid Vessel Wall Segmentation and Atherosclerosis Diagnosis Challenge, MICCAI 2022.

Validation dataset and reference code for Carotid Vessel Wall Segmentation and Atherosclerosis Diagnosis Challenge, MICCAI 2022.  Please refer to our website: https://vessel-wall-segmentation-2022.grand-challenge.org/.

restrictedApr 2022View details →

A semantic segmentation dataset consisting of soil-root images with multiple growth stages.

A semantic segmentation dataset consisting of soil-root images with multiple growth stages. <blockquote> Last Update: 2022.08.10 </blockquote>

restrictedcc-by-4.0Apr 2024View details →

Self-Supervised Learning Cell Image Dataset of Master Thesis "Enhancing Cell Instance Segmentation in 3D Microscopy using Self-Supervised ViTs"

This is the self-supervised learning cell image dataset of master thesis "Enhancing Cell Instance Segmentation in 3D Microscopy using Self-Supervised ViTs". We gather images from datasets such as the LIVECell dataset, the EVICAN dataset, as well as datasets available on Image Data Resource (https://idr.openmicroscopy.org/) and the Broad Bioimage Benchmark Collection (https://bbbc.broadinstitute.org/). Only images with sizes larger than 512x512 are collected. For datasets containing more than 1000 images, we randomly select 1000 images. Otherwise, we retain all images in the dataset.    After download, please put all compressed folders of subdatasets in the "image" folder under the root directory.

restrictedcc-by-4.0Jul 2021View details →

ROSE: Retinal OCT-Angiography segmentation dataset

Retinal OCT-Angiography Vessel Segmentation Dataset (ROSE) is now open source. It includes two subsets: ROSE-1 and ROSE-2.  <ul> <li>ROSE-1 subset consists of a total of 117 OCTA images from 39 subjects (26 with disease  and the rest are healthy control) and was split into 90 images for training and 27 images for testing. Each subject has en face angiograms of superficial (SVC), deep (DVC), and the inner retinal vascular plexus that includes both SVC and DVC (SVC+DVC) respectively. All the OCTA scans were captured by the RTVue XR Avanti SD-OCT system (Optovue, USA) equipped with AngioVue software, with image resolution of 304 × 304 pixels. The scan area was 3×3 mm2 area centred at the fovea. The manual annotations of these vascular network were graded  by image experts and clinicians, and the consensus of them was then used as the groundtruth. Two different types of vessel annotations are available: centerline-level and pixel-level annotation. </li> <li>ROSE-2 subset contains a total of 112 OCT-A images of 112 eyes acquired by Heidelberg OCT2 system with Spectralis software (Heidelberg Engineering, Heidelberg, Germany) and was split into 90 images for training and 22 images for testing. All the images in this dataset are the en face angiograms of SVC within a 3×3 mm2 area centred at the fovea, and each image was resized into a grayscale image with 840 × 840 pixels. All the visible retinal vessels were manually traced using an in-house program written in Matlab (Mathworks R2018, Natwick) by an experienced clinical ophthalmologist. </li> </ul> code: <a href="https://github.com/iMED-Lab/OCTA-Net-OCTA-Vessel-Segmentation-Network">iMED-Lab/OCTA-Net-OCTA-Vessel-Segmentation-Network (github.com)</a> ROSE-O is a retinal structure detection dataset of OCTA images, with precise manual annotations of RV, RVJ and the FAZ. It contains 117 images which were captured using the Optovue Avanti RTVue XR with AngioVue software (Optovue, Fremont, USA): the images have a resolution of 304×304 pixels. The SVC, DVC and IVC angiograms of each participant were obtained by the device.  code: <a href="https://github.com/iMED-Lab/VAFF-Net">https://github.com/iMED-Lab/VAFF-Net</a>

restrictedcc-by-4.0Sep 2024View details →

BaMBo: An Annotated Bone Marrow Biopsy Dataset for Segmentation Task

Bone marrow examination has become increasingly important for the diagnosis and treatment of hematologic and other illnesses. The present methods for analyzing bone marrow biopsy samples involve subjective and inaccurate assessments by visual estimation by pathologists. Thus, there is a need to develop automated tools to assist in the analysis of bone marrow samples. However, there is a lack of publicly available standardized and high-quality datasets that can aid in the research and development of automated tools that can provide consistent and objective measurements. In this paper, we present a comprehensive Bone Marrow Biopsy (BaMBo) dataset consisting 185 semantic-segmented bone marrow biopsy images, specifically designed for the automated calculation of bone marrow cellularity. Our dataset comprises high-resolution, generalized images of bone marrow biopsies, each annotated with precise semantic segmentation of different haematological components. These components are divided into 4 classes: Bony trabeculae, adipocytes, cellular region and BG. The annotations were performed with the help of two experienced hematopathologists that were supported by state-of-the-art DL models and image processing techniques.

restrictedcc-by-4.0Sep 2024View details →

BoMBR: An Annotated Bone Marrow Biopsy Dataset for Segmentation of Reticulin Fibers

Bone marrow reticulin fibrosis is associated with varied benign as well as malignant hematological conditions. The assessment of reticulin fibrosis is important in the diagnosis, prognostication and management of such disorders. The current methods for quantification of reticulin fibrosis are inefficient and prone to errors. Therefore, there is a need for automated tools for accurate and consistent quantification of reticulin. However, the lack of standardized datasets has hindered the development of such tools. In this study, we present a comprehensive dataset that comprises of 201 Bone Marrow Biopsy images for Reticulin (BoMBR) quantification. These images were meticulously annotated for semantic segmentation, with the focus on performing reticulin fiber quantification. This annotation was done by two trained hematopathologists who were aided by DL models and image processing techniques that generated a rough automated annotation for them to start with. This ensured precise delineation of the reticulin fibers alongside other cellular components such as bony trabeculae, fat, and cells. This is the first publicly available dataset in this domain with the aim to catalyze advancements the development of computational models for improved reticulin quantification.

restrictedJul 2021View details →

OCTA image dataset with pixel-level mask annotation for FAZ segmentation

This dataset is publish by the research "A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image" Detail: This dataset is the pixel-level mask annotation for FAZ segmentation. 1,101 3 × 3 mm2 sOCTA images chosen from gradable and best OCTA images randomly in subset sOCTA-3x3-10k, and 1,143 6 × 6 mm2dOCTA images were annotated by an experienced ophthalmologist. GitHub: <a href="https://github.com/shanzha09/COIPS">https://github.com/shanzha09/COIPS</a> These datasets are public available, if you use the dataset or our system in your research, please cite our paper: <code>A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image</code>. arXiv:<a href="https://arxiv.org/abs/2107.10476v1">https://arxiv.org/abs/2107.10476v1</a>

restrictedAug 2020View details →

CADA Test Dataset addon for task 2 (segmentation): Aneurysm seed points

Test data addon for the <a href="https://cada.grand-challenge.org/">CADA challenge</a>(s). This dataset contains the seeds pointing to the true aneurysms to segment. See https://cada.grand-challenge.org/Copyright/ for license info on the data. See README.md for detailed info.

restrictedNov 2023View details →

Dataset and code for "FK-means: Automatic Atrial Fibrosis Segmentation using Fractal-guided K-means Clustering with Voronoi-Clipping Feature Extraction of Anatomical Structures": FKmeans for fibrosis segmentation

Assessment of left atrial (LA) fibrosis from late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) adds to the management of patients with atrial fibrillation (AF). However, accurate assessment of fibrosis in the LA wall remains challenging. Excluding anatomical structures in the LA proximity using clipping techniques can reduce misclassification of LA fibrosis. A novel FK-means approach for combined automatic clipping and automatic fibrosis segmentation was developed. This approach combines a feature-based Voronoi diagram with a hierarchical 3D K-means fractal-based method. The proposed automatic Voronoi clipping method was applied on LGE MRI data and achieved a Dice score of 0.75, similar as the score obtained by a deep learning method (3D UNet) for clipping (0.74). The automatic fibrosis segmentation method, which utilizes the Voronoi clipping method, achieved a Dice score of 0.76. This outperformed a 3D U-Net method for clipping and fibrosis classification, which had a Dice score of 0.69. Moreover, the proposed automatic fibrosis segmentation method achieved a Dice score of 0.90, using manual clipping of anatomical structures. The findings suggest that the automatic FK-means analysis approach enables reliable LA fibrosis segmentation and that clipping of anatomical structures in the atrial proximity can add to the assessment of atrial fibrosis.

restrictedJan 2022View details →

Dataset related to the article " Automated Left and Right Ventricular Chamber Segmentation in Cardiac Magnetic Resonance Images Using Dense Fully Convolutional Neural Network"

This record contains raw data related to the article " Automated left and right ventricular chamber segmentation in cardiac magnetic resonance images using dense fully convolutional neural network" Background and objective: Segmentation of the left ventricular (LV) myocardium (Myo) and RV endocardium on cine cardiac magnetic resonance (CMR) images represents an essential step for cardiacfunction evaluation and diagnosis. In order to have a common reference for comparing segmentation algorithms, several CMR image datasets were made available, but in general they do not include the most apical and basal slices, and/or gold standard tracing is limited to only one of the two ventricles, thus not fully corresponding to real clinical practice. Our aim was to develop a deep learning (DL) approach for automated segmentation of both RV and LV chambers from short-axis (SAX) CMR images, reporting separately the performance for basal slices, together with the applied criterion of choice. Method: A retrospectively selected database (DB1) of 210 cine sequences (3 pathology groups) was considered: images (GE, 1.5 T) were acquired at Centro Cardiologico Monzino (Milan, Italy), and end-diastolic (ED) and end-systolic frames (ES) were manually segmented (gold standard, GS). Automatic ED and ES RV and LV segmentation were performed with a U-Net inspired architecture, where skip connections were redesigned introducing dense blocks to alleviate the semantic gap between the U-Net encoder and decoder. The proposed architecture was trained including: A) the basal slices where the Myo surrounded the LV for at least the 50% and all the other slice; B) all the slices where the Myo completely surrounded the LV. To evaluate the clinical relevance of the proposed architecture in a practical use case scenario, a graphical user interface was developed to allow clinicians to revise, and correct when needed, the automatic segmentation. Additionally, to assess generalizability, analysis of CMR images obtained in 12 healthy volunteers (DB2) with different equipment (Siemens, 3T) and settings was performed. Results: The proposed architecture outperformed the original U-Net. Comparing the performance on DB1 between the two criteria, no significant differences were measured when considering all slices together, but were present when only basal slices were examined. Automatic and manually-adjusted segmentation performed similarly compared to the GS (bias±95%LoA): LVEDV -1±12 ml, LVESV -1±14 ml, RVEDV 6±12 ml, RVESV 6±14 ml, ED LV mass 6±26 g, ES LV mass 5±26 g). Also, generalizability showed very similar performance, with Dice scores of 0.944 (LV), 0.908 (RV) and 0.852 (Myo) on DB1, and 0.940 (LV), 0.880 (RV), and 0.856 (Myo) on DB2. Conclusions: Our results support the potential of DL methods for accurate LV and RV contours segmentation and the advantages of dense skip connections in alleviating the semantic gap generated when high level features are concatenated with lower level feature. The evaluation on our dataset, considering separately the performance on basal and apical slices, reveals the potential of DL approaches for fast, accurate and reliable automated cardiac segmentation in a real clinical setting.

restrictedOct 2017View details →

River segmentation dataset

This dataset contains 300 images of rivers. Each image is associated with a ground-truth image where the 0 pixels correspond to background pixels and pixels with 1 value correspond to water pixels.