Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
238
datasets available to search
ShareScore release 0.9.0
Dataset results
238 results for “Radiomics”
WAW-TACE: A Hepatocellular Carcinoma Multiphase CT Dataset with Segmentations, Radiomics Features, and Clinical Data
<p>The WAW-TACE dataset contains multiphase abdominal CT images from N=233 treatment-naive patients with HCC treated with TACE in monotherapy, annotated with N=377 hand-crafted liver tumor masks, automated segmentations of multiple internal organs, extracted radiomics features, and corresponding extensive clinical data.</p> <p> </p>
AI-derived annotations for the NLST and NSCLC-Radiomics computed tomography imaging collections
<p>Public imaging datasets are critical for the development and evaluation of automated tools in cancer imaging. Unfortunately, many of the available datasets do not provide annotations of tumors or organs-at-risk, crucial for the assessment of these tools. This is due to the fact that annotation of medical images is time consuming and requires domain expertise. It has been demonstrated that artificial intelligence (AI) based annotation tools can achieve acceptable performance and thus can be used to automate the annotation of large datasets. As part of the effort to enrich the public data available within NCI Imaging Data Commons (IDC) (<a href="https://imaging.datacommons.cancer.gov/">https://imaging.datacommons.cancer.gov/</a>) [1], we introduce this dataset that consists of such AI-generated annotations for two publicly available medical imaging collections of Computed Tomography (CT) images of the chest. For detailed information concerning this dataset, please refer to our publication <a href="https://www.nature.com/articles/s41597-023-02864-y">here</a> [2]. </p> <p>We use publicly available pre-trained AI tools to enhance CT lung cancer collections that are unlabeled or partially labeled. The first tool is the nnU-Net deep learning framework [3] for volumetric segmentation of organs, where we use a pretrained model (Task D18 using the SegTHOR dataset) for labeling volumetric regions in the image corresponding to the heart, trachea, aorta and esophagus. These are the major organs-at-risk for radiation therapy for lung cancer. We further enhance these annotations by computing 3D shape radiomics features using the pyradiomics package [4]. The second tool is a pretrained model for per-slice automatic labeling of anatomic landmarks and imaged body part regions in axial CT volumes [5].</p> <p>We focus on enhancing two publicly available collections, the Non-small Cell Lung Cancer Radiomics (NSCLC-Radiomics collection) [6,7], and the National Lung Screening Trial (NLST collection) [8,9]. The CT data for these collections are available both in The Cancer Imaging Archive (TCIA) [10] and in NCI Imaging Data Commons (IDC). Further, the NSLSC-Radiomics collection includes expert-generated manual annotations of several chest organs, allowing us to quantify performance of the AI tools in that subset of data.</p> <p>IDC is relying on the DICOM standard to achieve FAIR [10] sharing of data and interoperability. Generated annotations are saved as DICOM Segmentation objects (volumetric segmentations of regions of interest) created using the <em>dcmqi</em> [12], and DICOM Structured Report (SR) objects (per-slice annotations of the body part imaged, anatomical landmarks and radiomics features) created using <em>dcmqi </em>and <em>highdicom</em> [13]. 3D shape radiomics features and corresponding DICOM SR objects are also provided for the manual segmentations available in the NSCLC-Radiomics collection. </p> <p>The dataset is available in IDC, and is accompanied by our publication <a href="https://www.nature.com/articles/s41597-023-02864-y">here</a> [2]. This pre-print details how the data were generated, and how the resulting DICOM objects can be interpreted and used in tools. Additionally, for further information about how to interact with and explore the dataset, please refer to our <a href="https://github.com/ImagingDataCommons/nnU-Net-BPR-annotations/">repository</a> and accompanying <a href="https://github.com/ImagingDataCommons/nnU-Net-BPR-annotations/blob/main/usage_notebooks/scientific_data_paper_usage_notes.ipynb">Google Colaboratory notebook</a>. </p> <p>The annotations are organized as follows. For NSCLC-Radiomics, three nnU-Net models were evaluated ('2d-tta', '3d_lowres-tta' and '3d_fullres-tta'). Within each folder, the PatientID and the StudyInstanceUID are subdirectories, and within this the DICOM Segmentation object and the DICOM SR for the 3D shape features are stored. A separate directory for the DICOM SR body part regression regions ('sr_regions') and landmarks ('sr_landmarks') are also provided with the same folder structure as above. Lastly, the DICOM SR for the existing manual annotations are provided in the 'sr_gt' directory. For NSCLC-Radiomics, each patient has a single StudyInstanceUID. The DICOM Segmentation and SR objects are named according to the SeriesInstanceUID of the original CT files. </p> <ul> <li>nsclc <ul> <li>2d-tta <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_SEG.dcm</li> <li>ReferencedSeriesInstanceUID_features_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>3d_lowres-tta <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_SEG.dcm</li> <li>ReferencedSeriesInstanceUID_features_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>3d_fullres-tta <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_SEG.dcm</li> <li>ReferencedSeriesInstanceUID_features_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>sr_regions <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_regions_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>sr_landmarks <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_landmarks_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>sr_gt <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_features_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> </ul> </li> </ul> <p>For NLST, the '3d_fullres-tta' model was evaluated. The data is organized the same as above, where within each folder the PatientID and the StudyInstanceUID are subdirectories. For the NLST collection, it is possible that some patients have more than one StudyInstanceUID subdirectory. A separate directory for the DICOM SR body par regions ('sr_regions') and landmarks ('sr_landmarks') are also provided. The DICOM Segmentation and SR objects are named according to the SeriesInstanceUID of the original CT files. </p> <ul> <li>nlst <ul> <li>3d_fullres-tta <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_SEG.dcm</li> <li>ReferencedSeriesInstanceUID_features_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>sr_regions <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_regions_SR.dcm</li> </ul> </li> </ul> </li> </ul> </li> <li>sr_landmarks <ul> <li>PatientID <ul> <li>StudyInstanceUID <ul> <li>ReferencedSeriesInstanceUID_landmarks_SR.dcm </li> </ul> </li> </ul> </li> </ul> </li> </ul> </li> </ul> <p>The query used for NSCLC-Radiomics is <a href="https://github.com/ImagingDataCommons/ai_medima_misc/blob/main/common/queries/NSCLC_Radiomics_query.txt">here</a>, and a list of corresponding SeriesInstanceUIDs (along with PatientIDs and StudyInstanceUIDs) is <a href="https://github.com/ImagingDataCommons/ai_medima_misc/blob/main/common/queries/zenodo_nsclc_radiomics_series_analyzed.csv">here</a>. The query used for NLST is <a href="https://github.com/ImagingDataCommons/ai_medima_misc/blob/main/common/queries/NLST_query.txt">here</a>, and a list of corresponding SeriesInstanceUIDs (along with PatientIDs and StudyInstanceUIDs) is <a href="https://github.com/ImagingDataCommons/ai_medima_misc/blob/main/common/queries/zenodo_nlst_series_analyzed.csv">here</a>. The two csv files that describe the series analyzed, <em>nsclc_series_analyzed.csv</em> and <em>nlst_series_analyzed.csv</em>, are also available as uploads to this repository. </p> <p><em>Version updates: </em></p> <p><em>Version 2: For the regions SR and landmarks SR, changed to use a distinct TrackingUniqueIdentifier for each MeasurementGroup. Also instead of using TargetRegion, changed to use FindingSite. Additionally for the landmarks SR, the TopographicalModifier was made a child of FindingSite instead of a sibling.</em></p> <p><em>Version 3: Added the two csv files that describe which series were analyzed </em></p> <p><em>Version 4: Modified the landmarks SR as the TopographicalModifier for the Kidney landmark (bottom) does not describe the landmark correctly. The Kidney landmark is the "first slice where both kidneys can be seen well." Instead, removed the use of the TopographicalModifier for that landmark. For the features SR, modified the units code for the Flatness and Elongation, as we incorrectly used mm units instead of no units. </em></p>
Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment
<p>We uploaded the raw data related to extracted features of the manuscript "Granata V, Fusco R, De Muzio F, Brunese MC, Setola SV, Ottaiano A, Cardone C, Avallone A, Patrone R, Pradella S, Miele V, Tatangelo F, Cutolo C, Maggialetti N, Caruso D, Izzo F, Petrillo A. Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment. Radiol Med. 2023 Nov;128(11):1310-1332. doi: 10.1007/s11547-023-01710-w. Epub 2023 Sep 11. PMID: 37697033."</p>
Benchmarking eliminative radiomic feature selection for head and neck lymph node classification - Supplemental data
<p>Supplementary files for the publication "Benchmarking eliminative radiomic feature selection for head and neck lymph node classification"</p>
Dataset related to article: QUALITY ASSESSMENT OF THE MRI-RADIOMICS STUDIES FOR MGMT PROMOTER METHYLATION PREDICTION IN GLIOMA: A SYSTEMATIC REVIEW AND META-ANALYSIS
<p><strong><span>This table contains the raw data used to generate the heatmap illustrated in Fig 2. Each row of the table shows the distribution of the scores achieved by the studies for a domain. Colors from red to green denote progressive increase from minimum to maximum score obtainable for each domain.</span></strong></p>
Representative snapshots of imaging sequences used in transcan_IDH-mutant_LGG_radiomics analysis
Open the record for dataset details and reuse information.
VISION Invited lecture - Radiomics and radiogenomics in cancer
<p>Recording and presentation of the invited lecture that took place online on 8 February 2023 - <strong>Carolina de la Pinta, MD. - Radiomics and radiogenomics in cancer</strong>.</p> <p>Radiomics and radiogenomics are very young research fields. These tools have great potential for clinical use in the context of personalized medicine. Their utility has been demonstrated in early diagnosis, differential diagnosis, treatment selection and patient prognosis. Undoubtedly show tremendous potential for improving our knowledge and developing new clinical tools, based on the application of computer techniques and data processing.</p>
Rating results obtained during a review of original articles on radiomics and machine learning for outcome prediction based on PET
<p>This upload provides Open Data associated with the publication "Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET)" by Rogasch JMM <em>et al.</em> (2023).</p> <p>The upload contains the item-by-item results of rating for all criteria and all 100 original articles. PubMed IDs are also included.</p> <p>Furthermore, a description of all variable names and how the rating categories were encoded in the data tables can be found in the PDF file "ML_prediction_Dictionary_2023_08_27.pdf".</p>
Head-Neck-Radiomics-HN1 data processed with Pyradiomics ready to use for data analysis
<p>We downloaded <a href="https://wiki.cancerimagingarchive.net/display/Public/Head-Neck-Radiomics-HN1">Head-Neck-Radiomics-HN1, </a>align CT and segmentation images and use PyRadiomics to extract all kind of features for data analysis.</p> <p>CSV contains all the features. Some of them are settings information, setting information should be remove before any data analysis. By using feature extraction algorithm or... by checking values, all the settings have the same values in the columns. Each row is a patient.</p> <p> </p> <p> </p>
Impact of Image Processing Settings for Radiomic Features in Alzheimer's Disease Using 18F-FDG and 11C-PIB PET Scans
<p>Radiomics is an established method for calculating features for computer-aided diagnosis and has been vastly applied to oncological studies. This study aimed to assess the impact of image processing in radiomic features in neuroimaging. Fifteen Alzheimer's disease subjects and 18 healthy individuals underwent [18F]-2-fluoro-2-deoxy-D-glucose (FDG) and 11C-labelled Pittsburgh Compound B (PIB) PET scans. T1-MRI scans were used for cerebellar and grey matter (GM), and white matter (WM) tissue delineation. PET images were registered to MRI (MR space) and transformed to MNI space. All images were normalized to cerebellar uptake (SUVR). All possible combinations of the following settings were considered to extract feature values: (1)tracer: FDG or PIB; (2)space: MR or MNI space; (3)discretization: fixed bin number (BN) of 64, fixed bin sizes (BS) of 0.05 or 0.25; and (4)volume of interest (VOI): GM, WM, or BRAIN (GM+WM). Features that correlated (>0.9) to traditional metrics (average VOI SUVR and volume) in any configuration were removed. Correlation of feature values between configurations, redundancy, and harmonization of feature values were tested. Image processing settings highly affect radiomic feature values and should be carefully taken into consideration during study design and should be properly reported.</p><p> </p><p>The enclosed datasets refer to the work developed at the University Medical Center Groningen and consists of extracted feature values used in the publication.</p>
Radiomics and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to detect breast malignant Lesions
<p>We uploade the dataset of the manuscript "Radiomics and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to detect breast malignant Lesions" by Current Oncology.</p> <p> </p>
Conventional, Functional and Radiomics Assessment for Intrahepatic Cholangiocarcinoma.
<p>I uploaded the images of the manuscript "Conventional, Functional and Radiomics Assessment for Intrahepatic Cholangiocarcinoma".</p>
TotalSegmentator-CT-Segmentations: TotalSegmentator segmentations and radiomics features for NCI Imaging Data Commons CT images
<p>This dataset contributes volumetric segmentations of the anatomic regions in a subset of CT images available from NCI Imaging Data Commons [1] (<a href="https://imaging.datacommons.cancer.gov/">https://imaging.datacommons.cancer.gov/</a>) automatically generated using the TotalSegmentation model v1.5.6 [2]. The initial release includes segmentations for the majority of the CT scans included in the National Lung Screening Trial (NLST) collection [3], [4] already available in IDC. Direct link to open this analysis result dataset in IDC (available after release of IDC v18): <a href="https://portal.imaging.datacommons.cancer.gov/explore/filters/?analysis_results_id=TotalSegmentator-CT-Segmentations">https://portal.imaging.datacommons.cancer.gov/explore/filters/?analysis_results_id=TotalSegmentator-CT-Segmentations</a>. </p> <p>Specifically, for each of the CT series analyzed, we include segmentations as generated by TotalSegmentator, converted into DICOM Segmentation object format using dcmqi v1.3.0 [5], and first order and shape features for each of the segmented regions, as produced by pyradiomics v3.0.1 [6]. Radiomics features were converted to DICOM Structured Reporting documents following template TID1500 using dcmqi. TotalSegmentator analysis on the NLST cohort was executed using Terra platform [7]. Implementation of the workflow that was used for performing the analysis is available at <a href="https://github.com/ImagingDataCommons/CloudSegmentator">https://github.com/ImagingDataCommons/CloudSegmentator</a> [8].</p> <p>Due to the large size of the files, they are stored in the cloud buckets maintained by IDC, and the attached files are the manifests that can be used to download the actual files.</p> <p>If you use the files referenced in the attached manifests, we ask you to cite this dataset and the preprint describing how it was generated [9].</p> <h3>Download instructions</h3> <p>Each of the manifests include instructions in the header on how to download the included files.</p> <p>To download the TotalSegmentator segmentations (in DICOM SEG format) and pyradiomics measurements (in DICOM SR format) files using <code>.s5cmd</code> manifests:</p> <ol> <li>install <a href="https://github.com/imagingdatacommons/idc-index" target="_blank" rel="noopener">idc-index</a> package: <code>pip install --upgrade idc-index</code></li> <li>download the files referenced by manifests included in this dataset by passing the <code>.s5cmd</code> manifest file. E.g., <code>idc download totalsegmentator_ct_segmentations_aws.s5cmd</code></li> </ol> <p>Other files included in the record are:</p> <ol> <li>firstorder and shape radiomics features extracted using pyradiomics, and organized one file per segmented structure (see README file in the zip file for details on how those are organized) <ol> <li>pyradiomics_features_csv.zip: saved in CSV format</li> <li>pyradiomics_features_parquet.zip: saved in Parquet format</li> </ol> </li> </ol> <h3>Support</h3> <p>If you have any questions about this dataset, or if you experience any issues, please reach out to Imaging Data Commons support via <a href="mailto:support@canceridc.dev">support@canceridc.dev</a> or (preferred) IDC Forum at <a href="https://discourse.canceridc.dev" target="_blank" rel="noopener">https://discourse.canceridc.dev</a>.</p>
Radiomics in hepatic metastasis by colorectal cancer
<p>We uploaded the images of the manuscript Granata V, Fusco R, Barretta ML, Picone C, Avallone A, Belli A, Patrone R, Ferrante M, Cozzi D, Grassi R, Grassi R, Izzo F, Petrillo A. Radiomics in hepatic metastasis by colorectal cancer. Infect Agent Cancer. 2021 Jun 2;16(1):39. doi: 10.1186/s13027-021-00379-y. PMID: 34078424; PMCID: PMC8173908.</p>
Raw Data for the article: Brain magnetic resonance imaging radiomics features associated with hepatic encephalopathy in adult cirrhotic patients
<p><strong>Purpose: </strong>Hepatic encephalopathy (HE) is a potential complication of cirrhosis. Magnetic resonance imaging (MRI) may demonstrate hyperintense T1 signal in the globi pallidi. The purpose of this study was to evaluate the performance of MRI-based radiomic features for diagnosing and grading chronic HE in adult patients affected by cirrhosis.</p> <p><strong>Methods: </strong>Adult patients with and without cirrhosis underwent brain MRI with identical imaging protocol on a 3T scanner. Patients without history of chronic liver disease were the control population. HE grading was based on underlying liver disease, severity of clinical manifestation, and number of encephalopathic episodes. Texture analysis was performed on axial T1-weighted images on bilateral lentiform nuclei at the level of the foramina of Monro. Diagnostic performance of texture analysis for the diagnosis and grading of HE was assessed by calculating the area under the receiver operating characteristics (AUROC) with 95% confidence interval (CI).</p> <p><strong>Results: </strong>The final study population consisted of 124 patients, 70 cirrhotic patients, and 54 non-cirrhotic controls. Thirty-eight patients had history of HE with 22 having an HE grade > 1. The radiomic features predicted the presence of HE with an AUROC of 0.82 (95% CI: 0.73, 0.90; P < .0001; 82% sensitivity, 66% specificity). Radiomic features predicted grade 1 HE (AUROC 0.75; 95% CI: 0.61, 0.89; P < .0001; 94% sensitivity, 60% specificity) and grade ≥ 2 HE (AUROC 0.82; 95% CI: 0.71, 0.93; P < .0001, 95% sensitivity, 57% specificity).</p> <p><strong>Conclusion: </strong>In cirrhotic patients, MR radiomic is effective in predicting the presence of chronic HE and in grading its severity.</p>
Quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis and healthy controls
<p>This dataset provides access to radiomic features of brain MR susceptibility-based images (QSM). Specifically, a cohort of 151 subjects, mixed of patients with multiple sclerosis (121) and healthy controls (30) was analysed, studying the Normal Appearing White Matter (NAWM) and NAWM tracts (e.g. corticospinal tract and optic radiation). Robustness analysis of those imaging descriptors can be found in Fiscone et al., <em>Assessing robustness of quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis. </em></p> <p>In the .zip folder, instructions about the organization of the dataset can be found. Together with the data, the code used to assess the reliability of those features is available. </p>
18F-FDG PET Radiomics of Diffuse Large B-cell Lymphoma
ClinicalTrials.gov study NCT04317313. IPD Sharing: NO. Countries: 1. Publications: 1.
Investigation of Hemodynamics and Radiomics Based on High Resolution Magnetic Resonance Imaging for Predicting the Outcomes of Intracranial Dissecting Aneurysm
ClinicalTrials.gov study NCT07335029. IPD Sharing: NO. Countries: 1. Publications: 2.
Predicting Pathological Complete Response in Esophageal Squamous Cell Carcinoma Using a Multimodal Model Integrating Clinical, Radiomics, and Deep Learning Features
ClinicalTrials.gov study NCT07181850. IPD Sharing: NO. Countries: 1. Publications: 4.
Deep Learning Radiomics Model for Predicting Post-cystectomy Outcome in Muscle Invasive Bladder Cancer
ClinicalTrials.gov study NCT06092450. IPD Sharing: NO. Countries: 1. Publications: 1.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.