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.
2,863
datasets available to search
ShareScore release 0.9.0
Dataset results
2,863 results for “Challenge”
Distributional employment challenges and opportunities of decarbonizing the US power system
<p>This dataset presents the results in the manuscript entitled "Distributional employment challenges and opportunities of decarbonizing the US power system". The Low Carbon Transition Employment Distribution (LoCaTED) model used to generate the results can be found on GitHub (<a href="https://github.com/judyjwxie/LoCaTED">https://github.com/judyjwxie/LoCaTED</a>). The suite of data files is based on the ReEDS 2022 Standard Scenarios and our employment calculation variations. Each file shows the job creation in the number of jobs disaggregated into the year, US state, technology, and economic sector (defined by the JEDI model). </p>
DCASE 2023 Challenge Task 2 Additional Training Dataset
<p><strong>Description</strong></p> <p>This dataset is the "additional training dataset" for the <a href="https://dcase.community/challenge2023/task-first-shot-unsupervised-anomalous-sound-detection-for-machine-condition-monitoring">DCASE 2023 Challenge Task 2 "First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring"</a>.</p> <p>The data consists of the normal/anomalous operating sounds of seven types of real/toy machines. Each recording is a single-channel audio that includes both a machine's operating sound and environmental noise. The duration of recordings varies from 6 to 18 sec, depending on the machine type. The following seven types of real/toy machines are used:</p> <ul> <li>Vacuum</li> <li>ToyTank</li> <li>ToyNscale</li> <li>ToyDrone</li> <li>bandsaw</li> <li>grinder</li> <li>shaker</li> </ul> <p> </p> <p><strong>Overview of the task</strong></p> <p><strong>Anomalous sound detection (ASD) is the task of identifying whether the sound emitted from a target machine is normal or anomalous. </strong>Automatic detection of mechanical failure is an essential technology in the fourth industrial revolution, which involves artificial-intelligence-based factory automation. Prompt detection of machine anomalies by observing sounds is useful for monitoring the condition of machines. </p> <p>This task is the follow-up from DCASE 2020 Task 2 to DCASE 2022 Task 2. The task this year is to develop an ASD system that meets the following four requirements.</p> <p> </p> <p><strong>1. Train a model using only normal sound (unsupervised learning scenario)</strong></p> <p>Because anomalies rarely occur and are highly diverse in real-world factories, it can be difficult to collect exhaustive patterns of anomalous sounds. Therefore, the system must detect unknown types of anomalous sounds that are not provided in the training data. This is the same requirement as in the previous tasks.</p> <p><strong>2. Detect anomalies regardless of domain shifts (domain generalization task) </strong></p> <p>In real-world cases, the operational states of a machine or the environmental noise can change to cause domain shifts. Domain-generalization techniques can be useful for handling domain shifts that occur frequently or are hard-to-notice. In this task, the system is required to use domain-generalization techniques for handling these domain shifts. This requirement is the same as in DCASE 2022 Task 2.</p> <p><strong>3. Train a model for a completely new machine type</strong></p> <p>For a completely new machine type, hyperparameters of the trained model cannot be tuned. Therefore, the system should have the ability to train models without additional hyperparameter tuning.</p> <p><strong>4. Train a model using only one machine from its machine type</strong></p> <p>While sounds from multiple machines of the same machine type can be used to enhance detection performance, it is often the case that sound data from only one machine are available for a machine type. In such a case, the system should be able to train models using only one machine from a machine type.</p> <p> </p> <p>The last two requirements are newly introduced in DCASE 2023 Task2 as the "first-shot problem".</p> <p> </p> <p><strong>Definition</strong></p> <p>We first define key terms in this task: "machine type," "section," "source domain," "target domain," and "attributes.".</p> <ul> <li>"Machine type" indicates the type of machine, which in the development dataset is one of seven: fan, gearbox, bearing, slide rail, valve, ToyCar, and ToyTrain.</li> <li>A section is defined as a subset of the dataset for calculating performance metrics.</li> <li>The source domain is the domain under which most of the training data and some of the test data were recorded, and the target domain is a different set of domains under which some of the training data and some of the test data were recorded. There are differences between the source and target domains in terms of operating speed, machine load, viscosity, heating temperature, type of environmental noise, signal-to-noise ratio, etc.</li> <li>Attributes are parameters that define states of machines or types of noise.</li> </ul> <p> </p> <p><strong>Dataset</strong></p> <p>This dataset consists of seven machine types. For each machine type, one section is provided, and the section is a complete set of training and test data. For each section, this dataset provides (i) 990 clips of normal sounds in the source domain for training, (ii) ten clips of normal sounds in the target domain for training. The source/target domain of each sample is provided. Additionally, the attributes of each sample in the training and test data are provided in the file names and attribute csv files.</p> <p> </p> <p><strong>File names and attribute csv files</strong></p> <p>File names and attribute csv files provide reference labels for each clip. The given reference labels for each training/test clip include machine type, section index, normal/anomaly information, and attributes regarding the condition other than normal/anomaly. The machine type is given by the directory name. The section index is given by their respective file names. For the datasets other than the evaluation dataset, the normal/anomaly information and the attributes are given by their respective file names. Attribute csv files are for easy access to attributes that cause domain shifts. In these files, the file names, name of parameters that cause domain shifts (domain shift parameter, dp), and the value or type of these parameters (domain shift value, dv) are listed. Each row takes the following format:</p> <p> [filename (string)], [d1p (string)], [d1v (int | float | string)], [d2p], [d2v]...</p> <p> </p> <p><strong>Recording procedure</strong></p> <p>Normal/anomalous operating sounds of machines and its related equipment are recorded. Anomalous sounds were collected by deliberately damaging target machines. For simplifying the task, we use only the first channel of multi-channel recordings; all recordings are regarded as single-channel recordings of a fixed microphone. We mixed a target machine sound with environmental noise, and only noisy recordings are provided as training/test data. The environmental noise samples were recorded in several real factory environments. We will publish papers on the dataset to explain the details of the recording procedure by the submission deadline.</p> <p> </p> <p><strong>Directory structure</strong></p> <p>- /dev_data </p> <p> - /raw<br> - /Vacuum<br> - /train (only normal clips) <br> - /section_00_source_train_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_source_train_normal_0989_<attribute>.wav <br> - /section_00_target_train_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_target_train_normal_0009_<attribute>.wav <br> - /test <br> - /section_00_source_test_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_source_test_normal_0049_<attribute>.wav <br> - /section_00_source_test_anomaly_0000_<attribute>.wav <br> - ... <br> - /section_00_source_test_anomaly_0049_<attribute>.wav <br> - /section_00_target_test_normal_0000_<attribute>.wav<br> - ... <br> - /section_00_target_test_normal_0049_<attribute>.wav <br> - /section_00_target_test_anomaly_0000_<attribute>.wav <br> - ... <br> - /section_00_target_test_anomaly_0049_<attribute>.wav <br> - attributes_00.csv (attribute csv for section 00)<br> - /ToyTank (The other machine types have the same directory structure as Vacuum.) <br> - /ToyNscale<br> - /ToyDrone<br> - /bandsaw<br> - /grinder<br> - /shaker</p> <p> </p> <p><strong>Baseline system</strong></p> <p>The baseline system is available on the Github repository <a href="https://github.com/nttcslab/dase2023_task2_baseline_ae">dcase2023_task2_baseline_ae</a>.The baseline systems provide a simple entry-level approach that gives a reasonable performance in the dataset of Task 2. They are good starting points, especially for entry-level researchers who want to get familiar with the anomalous-sound-detection task.</p> <p> </p> <p><strong>Condition of use</strong></p> <p>This dataset was created jointly by <strong>Hitachi, Ltd. </strong>and <strong>NTT Corporation</strong> and is available under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license.</p> <p> </p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite all the following papers. We will publish a paper on the description of the DCASE 2023 Task 2, so pleasure make sure to cite the paper, too.</p> <ul> <li>Noboru Harada, Daisuke Niizumi, Yasunori Ohishi, Daiki Takeuchi, and Masahiro Yasuda. <em>First-shot anomaly detection for machine condition monitoring: A domain generalization baseline. In arXiv e-prints: 2303.00455</em>, 2023. [<a href="https://arxiv.org/pdf/2303.00455.pdf">URL</a>]</li> <li>Kota Dohi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yuki Nikaido, and Yohei Kawaguchi. <em>MIMII DG: sound dataset for malfunctioning industrial machine investigation and inspection for domain generalization task.</em> In Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022), 31-35. Nancy, France, November 2022, . [<a href="https://arxiv.org/pdf/2205.13879.pdf">URL</a>]</li> <li>Noboru Harada, Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Masahiro Yasuda, and Shoichiro Saito. <em>ToyADMOS2: another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions.</em> In Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021), 1–5. Barcelona, Spain, November 2021. [<a href="https://dcase.community/documents/workshop2021/proceedings/DCASE2021Workshop_Harada_6.pdf">URL</a>]</li> </ul> <p> </p> <p><strong>Contact</strong></p> <p>If there is any problem, please contact us:</p> <ul> <li>Kota Dohi, <a href="mailto:kota.dohi.gr@hitachi.com">kota.dohi.gr@hitachi.com</a></li> <li>Keisuke Imoto, <a href="mailto:keisuke.imoto@ieee.org">keisuke.imoto@ieee.org</a></li> <li>Noboru Harada, <a href="mailto:noboru@ieee.org">noboru@ieee.org</a></li> <li>Daisuke Niizumi, <a href="mailto:daisuke.niizumi.dt@hco.ntt.co.jp">daisuke.niizumi.dt@hco.ntt.co.jp</a></li> <li>Yohei Kawaguchi, <a href="mailto:yohei.kawaguchi.xk@hitachi.com">yohei.kawaguchi.xk@hitachi.com</a></li> </ul>
Deep learning models challenge the prevailing assumption that face-like effects for objects of expertise support domain-general mechanisms
<p>The question of whether perceptual expertise is mediated by general-expert or domain-specific processing mechanisms has been debated for decades. Because humans are experts in face recognition, face-like neural and cognitive effects for objects of expertise were considered to support for the general-expertise hypothesis. Conversely, stronger effects for faces than objects of expertise were considered to support the domain-specific hypothesis. However, the effects of domain, experience, and level of categorization, are confounded in human studies, which may lead to erroneous inferences. To overcome these limitations, we used computational models of perceptual expertise and tested different domains (objects, faces, birds) and levels of categorization (basic, sub-ordinate, individual) in isolation, matched for amount of experience. Like humans, the models generated a larger inversion effect for faces than for objects. Importantly, a face-like inversion effect was found for individual-based categorization of non-faces (birds) but only in a network specialized for that domain. Thus, contrary to prevalent assumptions, face-like effects in objects of expertise may originate from domain-specific rather than domain-general processing mechanisms. More generally, we show how deep learning algorithms can be used to isolate the effects of factors that are inherently confounded in the natural environment of biological organisms.</p>
Dataset of "Challenging Point Scanning across Electron Microscopy and Optical Imaging using Computational Imaging"
<p>Dataset containing the jupyter notebook with codes for the simulation of the structured illumination patterns used for image reconstruction (the simulation parameters have been optimized to make sure that the patterns were almost identical to the experimental ones), the reconstruction algorithms. Moreover, there are three experimental dataset saved as txxt file, where each line contains the six biases applied to the electron modulator and the intensity measured by the single pixel detector that we used.</p>
DCASE 2023 Challenge Task 2 Development Dataset
<p><strong>Description</strong></p> <p>This dataset is the "development dataset" for the <a href="https://dcase.community/challenge2023/task-first-shot-unsupervised-anomalous-sound-detection-for-machine-condition-monitoring">DCASE 2023 Challenge Task 2 "First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring"</a>.</p> <p>The data consists of the normal/anomalous operating sounds of seven types of real/toy machines. Each recording is a single-channel 10-second audio that includes both a machine's operating sound and environmental noise. The following seven types of real/toy machines are used in this task:</p> <ul> <li>ToyCar</li> <li>ToyTrain</li> <li>Fan</li> <li>Gearbox</li> <li>Bearing</li> <li>Slide rail</li> <li>Valve</li> </ul> <p> </p> <p><strong>Overview of the task</strong></p> <p><strong>Anomalous sound detection (ASD) is the task of identifying whether the sound emitted from a target machine is normal or anomalous. </strong>Automatic detection of mechanical failure is an essential technology in the fourth industrial revolution, which involves artificial-intelligence-based factory automation. Prompt detection of machine anomalies by observing sounds is useful for monitoring the condition of machines. </p> <p>This task is the follow-up from DCASE 2020 Task 2 to DCASE 2022 Task 2. The task this year is to develop an ASD system that meets the following four requirements.</p> <p> </p> <p><strong>1. Train a model using only normal sound (unsupervised learning scenario)</strong></p> <p>Because anomalies rarely occur and are highly diverse in real-world factories, it can be difficult to collect exhaustive patterns of anomalous sounds. Therefore, the system must detect unknown types of anomalous sounds that are not provided in the training data. This is the same requirement as in the previous tasks.</p> <p><strong>2. Detect anomalies regardless of domain shifts (domain generalization task) </strong></p> <p>In real-world cases, the operational states of a machine or the environmental noise can change to cause domain shifts. Domain-generalization techniques can be useful for handling domain shifts that occur frequently or are hard-to-notice. In this task, the system is required to use domain-generalization techniques for handling these domain shifts. This requirement is the same as in DCASE 2022 Task 2.</p> <p><strong>3. Train a model for a completely new machine type</strong></p> <p>For a completely new machine type, hyperparameters of the trained model cannot be tuned. Therefore, the system should have the ability to train models without additional hyperparameter tuning.</p> <p><strong>4. Train a model using only one machine from its machine type</strong></p> <p>While sounds from multiple machines of the same machine type can be used to enhance detection performance, it is often the case that sound data from only one machine are available for a machine type. In such a case, the system should be able to train models using only one machine from a machine type.</p> <p> </p> <p>The last two requirements are newly introduced in DCASE 2023 Task2 as the "first-shot problem".</p> <p> </p> <p><strong>Definition</strong></p> <p>We first define key terms in this task: "machine type," "section," "source domain," "target domain," and "attributes.".</p> <ul> <li>"Machine type" indicates the type of machine, which in the development dataset is one of seven: fan, gearbox, bearing, slide rail, valve, ToyCar, and ToyTrain.</li> <li>A section is defined as a subset of the dataset for calculating performance metrics.</li> <li>The source domain is the domain under which most of the training data and some of the test data were recorded, and the target domain is a different set of domains under which some of the training data and some of the test data were recorded. There are differences between the source and target domains in terms of operating speed, machine load, viscosity, heating temperature, type of environmental noise, signal-to-noise ratio, etc.</li> <li>Attributes are parameters that define states of machines or types of noise.</li> </ul> <p> </p> <p><strong>Dataset</strong></p> <p>This dataset consists of seven machine types. For each machine type, one section is provided, and the section is a complete set of training and test data. For each section, this dataset provides (i) 990 clips of normal sounds in the source domain for training, (ii) ten clips of normal sounds in the target domain for training, and (iii) 100 clips each of normal and anomalous sounds for the test. The source/target domain of each sample is provided. Additionally, the attributes of each sample in the training and test data are provided in the file names and attribute csv files.</p> <p> </p> <p><strong>File names and attribute csv files</strong></p> <p>File names and attribute csv files provide reference labels for each clip. The given reference labels for each training/test clip include machine type, section index, normal/anomaly information, and attributes regarding the condition other than normal/anomaly. The machine type is given by the directory name. The section index is given by their respective file names. For the datasets other than the evaluation dataset, the normal/anomaly information and the attributes are given by their respective file names. Attribute csv files are for easy access to attributes that cause domain shifts. In these files, the file names, name of parameters that cause domain shifts (domain shift parameter, dp), and the value or type of these parameters (domain shift value, dv) are listed. Each row takes the following format:</p> <p> [filename (string)], [d1p (string)], [d1v (int | float | string)], [d2p], [d2v]...</p> <p> </p> <p><strong>Recording procedure</strong></p> <p>Normal/anomalous operating sounds of machines and its related equipment are recorded. Anomalous sounds were collected by deliberately damaging target machines. For simplifying the task, we use only the first channel of multi-channel recordings; all recordings are regarded as single-channel recordings of a fixed microphone. We mixed a target machine sound with environmental noise, and only noisy recordings are provided as training/test data. The environmental noise samples were recorded in several real factory environments. We will publish papers on the dataset to explain the details of the recording procedure by the submission deadline.</p> <p> </p> <p><strong>Directory structure</strong></p> <p>- /dev_data </p> <p> - /raw<br> - /fan<br> - /train (only normal clips) <br> - /section_00_source_train_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_source_train_normal_0989_<attribute>.wav <br> - /section_00_target_train_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_target_train_normal_0009_<attribute>.wav <br> - /test <br> - /section_00_source_test_normal_0000_<attribute>.wav <br> - ... <br> - /section_00_source_test_normal_0049_<attribute>.wav <br> - /section_00_source_test_anomaly_0000_<attribute>.wav <br> - ... <br> - /section_00_source_test_anomaly_0049_<attribute>.wav <br> - /section_00_target_test_normal_0000_<attribute>.wav<br> - ... <br> - /section_00_target_test_normal_0049_<attribute>.wav <br> - /section_00_target_test_anomaly_0000_<attribute>.wav <br> - ... <br> - /section_00_target_test_anomaly_0049_<attribute>.wav <br> - attributes_00.csv (attribute csv for section 00)<br> - /gearbox (The other machine types have the same directory structure as fan.) <br> - /bearing<br> - /slider (`slider` means "slide rail")<br> - /ToyCar <br> - /ToyTrain <br> - /valve </p> <p> </p> <p><strong>Baseline system</strong></p> <p>The baseline system is available on the Github repository <a href="https://github.com/nttcslab/dase2023_task2_baseline_ae">dcase2023_task2_baseline_ae</a>.The baseline systems provide a simple entry-level approach that gives a reasonable performance in the dataset of Task 2. They are good starting points, especially for entry-level researchers who want to get familiar with the anomalous-sound-detection task.</p> <p> </p> <p><strong>Condition of use</strong></p> <p>This dataset was created jointly by <strong>Hitachi, Ltd. </strong>and <strong>NTT Corporation</strong> and is available under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license.</p> <p> </p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite all the following papers. We will publish a paper on the description of the DCASE 2023 Task 2, so pleasure make sure to cite the paper, too.</p> <ul> <li>Noboru Harada, Daisuke Niizumi, Yasunori Ohishi, Daiki Takeuchi, and Masahiro Yasuda. <em>First-shot anomaly detection for machine condition monitoring: A domain generalization baseline. In arXiv e-prints: 2303.00455</em>, 2023. [<a href="https://arxiv.org/pdf/2303.00455.pdf">URL</a>]</li> <li>Kota Dohi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yuki Nikaido, and Yohei Kawaguchi. <em>MIMII DG: sound dataset for malfunctioning industrial machine investigation and inspection for domain generalization task.</em> In Proceedings of the 7th Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022), 31-35. Nancy, France, November 2022, . [<a href="https://arxiv.org/pdf/2205.13879.pdf">URL</a>]</li> <li>Noboru Harada, Daisuke Niizumi, Daiki Takeuchi, Yasunori Ohishi, Masahiro Yasuda, and Shoichiro Saito. <em>ToyADMOS2: another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions.</em> In Proceedings of the 6th Detection and Classification of Acoustic Scenes and Events 2021 Workshop (DCASE2021), 1–5. Barcelona, Spain, November 2021. [<a href="https://dcase.community/documents/workshop2021/proceedings/DCASE2021Workshop_Harada_6.pdf">URL</a>]</li> </ul> <p> </p> <p><strong>Contact</strong></p> <p>If there is any problem, please contact us:</p> <ul> <li>Kota Dohi, <a href="mailto:kota.dohi.gr@hitachi.com">kota.dohi.gr@hitachi.com</a></li> <li>Keisuke Imoto, <a href="mailto:keisuke.imoto@ieee.org">keisuke.imoto@ieee.org</a></li> <li>Noboru Harada, <a href="mailto:noboru@ieee.org">noboru@ieee.org</a></li> <li>Daisuke Niizumi, <a href="mailto:daisuke.niizumi.dt@hco.ntt.co.jp">daisuke.niizumi.dt@hco.ntt.co.jp</a></li> <li>Yohei Kawaguchi, <a href="mailto:yohei.kawaguchi.xk@hitachi.com">yohei.kawaguchi.xk@hitachi.com</a></li> </ul>
Dataset TrainBatch1 for the MICCAI-2022-Challenge: Airway Tree Modeling (ATM'22)
<p>Dataset for the MICCAI-2022-Challenge: Airway Tree Modeling (ATM'22)</p> <p>This is the TrainBatch1. </p> <p>We provide the casename correspondence information in the TrainBatch1_CaseInfo.csv file. It is convinient for researchers to locate the original cases in LIDC-IDRI with our provided full airway annotation for other research purposes.</p> <p>If you use this dataset in your research, you must cite the papers in the <strong>References </strong>below !!!</p>
Supplementary data for a systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challenges
<p>The Microsoft Excel files containing the supplementary data and diagrams for the paper:</p> <p><strong>A systematic literature review on source code similarity measurement and clone detection: techniques, applications, and challenges</strong></p> <p>The article is under review in the Journal of Systems and Software.</p> <p>In this version, the literature search has been performed between April and May 2023, and studies published until that date has been mentioned in the attached Excel files.</p> <p>This version (v3.4.0) corresponds to the third revision (R3) of the manuscript.</p> <p> </p>
SynthRAD2023 Grand Challenge validation dataset: synthetizing computed tomography for radiotherapy
<p><strong>Version 1.1</strong>, updated on 2023-06-04 --> the task2_val.zip has been modified with a new cbct file for patient 2BA078.<br> <br> The dataset can be downloaded from <a href="https://doi.org/10.5281/zenodo.7260705">https://doi.org/</a><a href="https://doi.org/10.5281/zenodo.7868169">10.5281/zenodo.7868169</a> and a detailed description is offered at <a href="https://doi.org/10.5281/zenodo.7260704">https://doi.org/10.5281/zenodo.7260704</a> in the "synthRAD2023_dataset_description.pdf".</p> <p>The<strong> </strong>input of the<strong> validation datasets</strong> for Task1 is in Task1_val.zip, while for Task2 in Task2_val.zip. After unzipping, each Task is organized according to the following folder structure:</p> <p>Task1_val.zip/</p> <p>├── Task1</p> <p> ├── brain</p> <p> ├── 1Bxxxx</p> <p> ├── mr.nii.gz</p> <p> └── mask.nii.gz</p> <p> ├── ...</p> <p>└── overview</p> <p> ├── 1_brain_val.xlsx</p> <p> ├── 1Bxxxx_val.png</p> <p> └── ... </p> <p> └── pelvis</p> <p> ├── 1Pxxxx</p> <p> ├── mr.nii.gz</p> <p> ├── mask.nii.gz</p> <p> ├── ...</p> <p>└── overview</p> <p> ├── 1_pelvis_val.xlsx</p> <p> ├── 1Pxxxx_val.png</p> <p> └── ....</p> <p>Task2_val.zip/</p> <p>├──Task2</p> <p> ├── brain</p> <p> ├── 2Bxxxx</p> <p> ├── cbct.nii.gz</p> <p> └── mask.nii.gz</p> <p> ├── ...</p> <p>└── overview</p> <p> ├── 2_brain_val.xlsx</p> <p> ├── 2Bxxxx_val.png</p> <p> └── ... </p> <p> └── pelvis</p> <p> ├── 2Pxxxx</p> <p> ├── cbct.nii.gz</p> <p> ├── mask.nii.gz</p> <p>├── ...</p> <p>└── overview</p> <p> ├── 2_pelvis_val.xlsx</p> <p> ├── 2Pxxxx_val.png</p> <p> └── ....</p> <p>Each patient folder has a unique name that contains information about the task, anatomy, center and a patient ID. The naming follows the convention below:</p> <p>[Task] [Anatomy] [Center] [PatientID]</p> <p>1 B A 001</p> <p>In each patient folder, two files can be found: </p> <ul> <li> <p>mr.nii.gz or cbct.nii.gz (depending on the task): CBCT/MR image</p> </li> <li> <p>mask.nii.gz: image containing a binary mask of the dilated patient outline </p> </li> </ul> <p>For each task and anatomy, an overview folder is provided which contains the following files:</p> <ul> <li> <p>[task]_[anatomy]_val.xlsx: This file contains information about the image acquisition protocol for each patient.</p> </li> <li> <p>[task][anatomy][center][PatientID]_val.png: For each patient a png showing axial, coronal and sagittal slices of CBCT/MR, CT, mask and the difference between CBCT/MR and CT is provided. These images are meant to provide a quick visual overview of the data.</p> </li> </ul> <p><strong>DATASET DESCRIPTION</strong></p> <p>This challenge dataset contains imaging data of patients who underwent radiotherapy in the brain or pelvis region. Overall, the population is predominantly adult and no gender restrictions were considered during data collection. For Task 1, the inclusion criteria were the acquisition of a CT and MRI during treatment planning while for task 2, acquisitions of a CT and CBCT, used for patient positioning, were required. Datasets for task 1 and 2 do not necessarily contain the same patients, given the different image acquisitions for the different tasks.</p> <p>Data was collected at 3 Dutch university medical centers:</p> <ul> <li> <p>Radboud University Medical Center;</p> </li> <li> <p>University Medical Center Utrecht;</p> </li> <li> <p>University Medical Center Groningen.</p> </li> </ul> <p>For anonymization purposes, from here on, institution names are substituted with A, B and C, without specifying which institute each letter refers to.</p> <p>The following number of patients is available in the validation set.</p> <p><strong>Validation</strong></p> <table> <tbody> <tr> <td> </td> <td> <p><strong>Brain</strong></p> </td> <td> <p><strong>Pelvis</strong></p> </td> </tr> <tr> <td> </td> <td> <p><strong>Center A</strong></p> </td> <td> <p><strong>Center B</strong></p> </td> <td> <p><strong>Center C</strong></p> </td> <td> <p><strong>Total</strong></p> </td> <td> <p><strong>Center A</strong></p> </td> <td> <p><strong>Center B</strong></p> </td> <td> <p><strong>Center C</strong></p> </td> <td> <p><strong>Tota</strong>l</p> </td> </tr> <tr> <td> <p><strong>Task 1</strong></p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>30</p> </td> <td> <p>20</p> </td> <td> <p>0</p> </td> <td> <p>10</p> </td> <td> <p>30</p> </td> </tr> <tr> <td> <p><strong>Task 2</strong></p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>30</p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>10</p> </td> <td> <p>30</p> </td> </tr> </tbody> </table> <p>In total, for all tasks and anatomies combined, 120 image pairs are available in this dataset. <strong>This repository only contains the validation data. </strong>The training data is provided at: h<a href="https://doi.org/10.5281/zenodo.7260704">ttps://doi.org/10.5281/zenodo.7260704</a>.</p> <p>All images were acquired with the clinically used scanners and imaging protocols of the respective centers and reflect typical images found in clinical routine. As a result, imaging protocols and scanner can vary between patients. A detailed description of the imaging protocol for each image, can be found in spreadsheets that are part of the dataset release (see dataset structure).</p> <p>Data was acquired with the following scanners:</p> <ul> <li> <p>Center A:</p> <ul> <li> <p>MRI: Philips Ingenia 1.5T/3.0T</p> </li> <li> <p>CT: Philips Brilliance Big Bore or Siemens Biograph20 PET-CT</p> </li> <li> <p>CBCT: Elekta XVI</p> </li> </ul> </li> <li> <p>Center B:</p> <ul> <li> <p>MRI: Siemens MAGNETOM Aera 1.5T or MAGNETOM Avanto_fit 1.5T</p> </li> <li> <p>CT: Siemens SOMATOM Definition AS</p> </li> <li> <p>CBCT: IBA Proteus+ or Elekta XVI</p> </li> </ul> </li> <li> <p>Center C:</p> <ul> <li> <p>MRI: Siemens Avanto fit 1.5T or Siemens MAGNETOM Vida fit 3.0T</p> </li> <li> <p>CT: Philips Brilliance Big Bore</p> </li> <li> <p>CBCT: Elekta XVI</p> </li> </ul> </li> </ul> <p>For task 1, MRIs were acquired with a T1-weighted gradient echo or an inversion prepared - turbo field echo (TFE) sequence and collected along with the corresponding planning CTs for all subjects. The exact acquisition parameters vary between patients and centers. For centers B and C, selected MRIs were acquired with Gadolinium contrast, while the selected MRIs of center A were acquired without contrast.</p> <p>For task 2, the CBCTs used for image-guided radiotherapy ensuring accurate patient position were selected for all subjects along with the corresponding planning CT.</p> <p>The following pre-processing steps were performed on the data:</p> <ul> <li> <p>Conversion from dicom to compressed nifti (nii.gz)</p> </li> <li> <p>Rigid registration between CT and MR/CBCT</p> </li> <li> <p>Anonymization (face removal, only for brain patients)</p> </li> <li> <p>Patient outline segmentation (provided as a binary mask)</p> </li> <li> <p>Crop MR/CBCT, CT and mask to remove background and reduce file sizes</p> </li> </ul> <p>The code used to preprocess the images can be found at: <a href="https://github.com/SynthRAD2023/">https://github.com/SynthRAD2023/</a>. Detailed information about the dataset are provided in SynthRAD2023_dataset_description.pdf published here along with the data and will also be submitted to Medical Physics.</p> <p><strong>ETHICAL APPROVAL</strong></p> <p>Each institution received ethical approval from their internal review board/Medical Ethical committee:</p> <ul> <li> <p>UMC Utrecht approved not-WMO on 4/03/2022 with number 22/474 entitled: “Synthetizing computed tomography for radiotherapy Grand Challenge (SynthRAD)”.</p> </li> <li> <p>UMC Groningen approved not-WMO on 20/07/2022 with number 202200310 entitled: “Synthesizing computed tomography for radiotherapy - Grand Challenge”.</p> </li> <li> <p>Radboud UMC declared the study not-WMO on 17/10/2022 with number 2022-15950 entitled “Synthetizing computed tomography for radiotherapy Grand Challenge”.</p> </li> </ul> <p><strong>CHALLENGE DESIGN</strong></p> <p>The overall challenge design can be found at <a href="https://doi.org/10.5281/zenodo.7746019">https://doi.org/10.5281/zenodo.7746019</a>.</p>
MR to Ultrasound Registration for Prostate Challenge - Dataset
<p>Multimodal image registration between pre-operative and intra-operative imaging enables the fusion of clinically important information during many surgical and interventional tasks. The registration of magnetic resonance imaging (MRI) and transrectal ultrasound (TRUS) images assists prostate biopsy and focal therapy, arguably having transformed prostate cancer patient care to a less invasive and more localized diagnostic, monitoring and treatment pathway. Though, even with great progress having been made by the community in the past two decades, challenges remain in this application. First, paired MRI and TRUS data from a sizable patient cohort are not routinely stored in clinical practice, and publicly-accessible data is scarce and low-quality. Second, annotating anatomical and pathological landmarks on both images - critical in representing corresponding locations for validation - requires expert domain knowledge and experience from multiple disciplines including urology, radiology and pathology.</p> <p>In addition to its prevalence-warranted clinical importance, this is also a unique application that saw a wide range of registration algorithms proposed and housed intriguing debates such as rigid-versus-nonrigid and FLE-versus-TRE. Both feature- and intensity-based classical methods and unsupervised or segmentation-driven learning methods have been innovated with some most technically interesting approaches in the field such as biomechanical regularisation and statistical motion modelling.</p> <p>The mu-Reg challenge aims to provide well-curated, yet real-world clinical data, with more than a hundred paired MR and TRUS images, annotated carefully by researchers and clinicians with more than 15 years of experience working with this application. The outcome of the challenge includes one of the first multimodal imaging data, facilitated with expert annotations for validation, for benchmarking advancement in registration methodology, as well as for future research in managing the most common non-skin cancer in men.</p> <p>---</p> <p><strong>The training and validation data may be used within the research remit of this challenge and in further research-related publications. The training and validation data are not to be used commercially. However, if the desired use is unclear, the organizers ask that those accessing the data refrain from further use or distribution outside of this challenge.</strong></p> <p>---</p> <p>Challenge information is accessible at: https://muregpro.github.io/</p>
RMLStreamer with Reference Conditions in the KGCW Challenge 2023
<p>This repository contains all necessary data to reproduce the participation of RMLStreamer with reference conditions in the <a href="https://doi.org/10.5281/zenodo.7689310">KGCW 2023 Challenge</a>, as well as the reported results.</p> <p>For more information we refer to the related paper:</p> <p><em>E. de Vleeschauwer, G.Haesendonck, D. Van Assche. B. De Meester, RMLStreamer with Reference Conditions in the<br> KGCW Challenge 2023, in: Proceedings of the 4rd International Workshop on Knowledge Graph Construction (KGCW 2023) co-located with 20th Extended Semantic Web Conference (ESWC 2023), 2023</em></p> <p> </p> <p> </p> <p> </p>
Helsinki Tomography Challenge 2022 (HTC2022) open tomographic dataset
<p>This dataset was primarily designed for the Helsinki Tomography Challenge 2022 (HTC2022), but it can be used for generic algorithm research and development in 2D CT reconstruction.</p><p>The dataset contains 2D tomographic measurements, i.e., sinograms and the affiliated metadata containing measurement geometry and other specifications. The sinograms have already been pre-processed with background and flat-field corrections, and compensated for a slightly misaligned center of rotation in the cone-beam computed tomography scanner. The log-transforms from intensity measurements to attenuation data have also been already computed. The data has been stored as MATLAB structs and saved in .mat file format.</p><p>The purpose of HTC2022 was to develop algorithms for limited angle tomography. The challenge data consists of tomographic measurements of two sets of plastic phantoms with a diameter of 7 cm and with holes of differing shapes cut into them. The first set is the teaching data, containing five training phantoms. The second set consists of 21 test phantoms used in the challenge to test algorithm performance. The test phantom data was released after the competition period ended.</p><p>The training phantoms were designed to facilitate algorithm development and benchmarking for the challenge itself. Four of the training phantoms contain holes. These are labeled ta, tb, tc, and td. A fifth training phantom is a solid disc with no holes. We encourage subsampling these datasets to create limited data sinograms and comparing the reconstruction results to the ground truth obtainable from the full-data sinograms. Note that the phantoms are not all identically centered.<br><br>The teaching data includes the following files for each phantom:</p><ul><li>The sinogram and all associated metadata (.MAT).</li><li>A pre-computed FBP reconstruction of the phantom (.MAT and .PNG).</li><li>A segmentation of the FBP reconstruction created with the procedure described below (.MAT and .PNG).</li></ul><p>Also included in the teaching dataset is a MATLAB example script for how to work with the CT data.</p><p>The challenge test data is arranged into seven different difficulty levels, labeled 1-7, with each level containing three different phantoms, labeled A-C. As the difficulty level increases, the number of holes increases and their shapes become increasingly complex. Furthermore, the view angle is reduced as the difficulty level increases, starting with a 90 degree field of view at level 1, and reducing by 10 degrees at each increasing level of difficulty. The view-angles in the challenge data will not all begin from 0 degrees.</p><p>The test data includes the following files for each phantom:</p><ul><li>The full sinogram and all associated metadata (.MAT).</li><li>The limited angle sinogram and all associated metadata, used to test the algorithms submitted to the challenge (.MAT).</li><li>A pre-computed FBP reconstruction of the phantom using the full data (.MAT and .PNG).</li><li>A pre-computed FBP reconstruction of the phantom using the limited angle data. These are of poor quality, and serve mainly as a demonstration of how FBP fails with limited angle data (.MAT and .PNG).</li><li>A segmentation of the FBP reconstruction using the full data, created with the procedure described below. This was used as the ground truth reference in the challenge (.MAT and .PNG).</li><li>A segmentation of the FBP reconstruction using the limited angle data, created with the procedure described below. These are of poor quality, and serve mainly as a demonstration of how FBP fails with limited angle data (.MAT and .PNG).</li><li>A photograph of the phantom, rotated and resized to match the ground truth segmentation (.PNG).</li></ul><p>Also included in the test dataset is a collage in .PNG format, showing all the ground truth segmentation images and the photographs of the phantoms together.</p><p>As the orientation of CT reconstructions can depend on the tools used, we have included the example reconstructions for each of the phantoms to demonstrate how the reconstructions obtained from the sinograms and the specified geometry should be oriented. The reconstructions have been computed using the filtered back-projection algorithm (FBP) provided by the ASTRA Toolbox.</p><p>We have also included segmentation examples of the reconstructions to demonstrate the desired format for the final competition entries. The segmentation images for obtained by the following steps:<br>1) Set all negative pixel values in the reconstruction to zero.<br>2) Determine a threshold level using Otsu's method.<br>3) Globally threshold the image using the threshold level.<br>4) Perform a morphological closing on the image using a disc with a radius of 3 pixels.</p><p>The competitors were not obliged to follow the above procedure, and were encouraged to explore various segmentation techniques for the limited angle reconstructions.</p><p>For getting started with the data, we recommend the following MATLAB toolboxes:</p><p>HelTomo - Helsinki Tomography Toolbox<br>https://github.com/Diagonalizable/HelTomo/<br><br>The ASTRA Toolbox<br>https://www.astra-toolbox.com/<br><br>Spot – A Linear-Operator Toolbox<br>https://www.cs.ubc.ca/labs/scl/spot/<br><br>Using the above toolboxes for the Challenge was by no means compulsory: the metadata for each dataset contains a full specification of the measurement geometry, and the competitors were free to use any and all computational tools they want to in computing the reconstructions and segmentations.</p><p>All measurements were conducted at the Industrial Mathematics Computed Tomography Laboratory at the University of Helsinki.</p>
Challenges and Limitations in the Design and Implementation of Fair and Equitable Machine Learning Algorithms in Healthcare
<p>We provide the programs in Python, a CSV file with references, images used in the article and a text corpus generated with Python.</p>
Don't mention it: challenges to using software mentions to investigate citation and discoverability - Data and Notebooks
<p>This deposit contains the data and Jupyter notebooks used for sampling and annotation analysis of our submission to the PeerJ Computer Science special issue <em>Software Citation, Indexing, and Discoverability </em>(<a href="https://peerj.com/collections/84-software">https://peerj.com/collections/84-software</a>):</p> <blockquote> <p>Stephan Druskat, Neil P. Chue Hong, Sammie Buzzard, Olexandr Konovalov, and Patrick Kornek. Don’t mention it: challenges to using software mentions to investigate citation and discoverability.</p> </blockquote> <p>See the README in this deposit.</p> <p>The contents of this deposit can also be browsed at <a href="https://github.com/softwaresaved/habeas-corpus/tree/main/replication-package">https://github.com/softwaresaved/habeas-corpus/tree/main/replication-package</a>.</p>
Combining Solid-State NMR with Structural and Biophysical Techniques to Design Challenging Protein-Drug Conjugates
<p>Solid-state NMR spectra (DARR and NCA) of rehydrated freeze-dried free TTR and TTR in the presence of Tafamidis and Taf-PTX</p> <p>Reference citation: Combining Solid-State NMR with Structural and Biophysical Techniques to Design Challenging Protein-Drug Conjugates. Angew Chem Int Ed Engl. 2023 Jun 5:e202303202. doi: 10.1002/anie.202303202. PMID: 37276329.</p>
Fast Calorimeter Simulation Challenge 2022 - Dataset 1
<p>This is dataset 1 of the “Fast Calorimeter Simulation Challenge 2022”. It is based on the ATLAS GEANT4 open datasets that were published <a href="http://opendata-qa.cern.ch/record/15012">here</a>. There are four files, two for photons and two for charged pions. Each dataset contains the voxelised shower information obtained from single particles produced at the calorimeter surface in the η range (0.2-0.25) and simulated in the ATLAS detector. Each file contains "incident_energies" of shape (num_showers, 1) and "showers" of shape (num_showers, num_voxels). There are 15 incident energies from 256 MeV up to 4 TeV produced in powers of two. 10k events are available in each sample with the exception of those at higher energies that have a lower statistics. These samples were used to train the corresponding two GANs presented in the AtlFast3 paper <a href="https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PAPERS/SIMU-2018-04/">SIMU-2018-04</a> and in the FastCaloGAN note <a href="https://atlas.web.cern.ch/Atlas/GROUPS/PHYSICS/PUBNOTES/ATL-SOFT-PUB-2020-006/">ATL-SOFT-PUB-2020-006</a>. The number of radial and angular bins varies from layer to layer and is also different for photons and pions, resulting in 368 voxels for photons and 533 for pions.</p> <p>dataset_1_photons_1.hdf5 and dataset_1_pions_1.hdf5 should be used for training, dataset_1_photons_2.hdf5 and dataset_1_pions_2.hdf5 for evaluation.</p> <p>More details, in particular helper scripts to parse the data and calculate and visualize basic high-level physics features, are available at <a href="https://calochallenge.github.io/homepage/">https://calochallenge.github.io/homepage/</a></p>
GO Tables from/for: Oligogalactolipid production during cold challenge is conserved in early diverging lineages
<p>Severe cold, defined as a damaging cold beyond acclimation temperatures, has unique responses, but the signaling and evolution of these responses are not well understood. Production of oligogalactolipids, which is triggered by cytosolic acidification in Arabidopsis (<em>Arabidopsis</em> <em>thaliana</em>), contributes to survival in severe cold. Here, we investigated oligogalactolipid production in species from bryophytes to angiosperms. Production of oligogalactolipids differed within each clade, suggesting multiple evolutionary origins of severe cold tolerance. We also observed greater oligogalactolipid production in control samples instead of temperature-challenged samples of some species. Further examination of representative species revealed a tight association between temperature, damage, and oligogalactolipid production that scaled with the cold tolerance of each species. Based on oligogalactolipid production and transcript changes, multiple species share a signal of oligogalactolipid production initially described in Arabidopsis, cytosolic acidification. Together, these data suggest that oligogalactolipid production is a severe cold response that originated from an ancestral damage response that remains in many land plant lineages and that cytosolic acidification is a common signaling mechanism for its activation. </p>
Characteristics and challenges of elderly entrepreneurs from Cyprus. Raw dataset from 37 semi-structured interviews
<p>This dataset delves into the motivations and behaviours of elderly entrepreneurs in Cyprus - individuals who continue to engage in entrepreneurial activities past retirement age. Cypriot entrepreneurs often remain active post-retirement for varied reasons.</p> <p>The dataset includes qualitative data, collected in Cyprus (areas of Nicosia and Limassol), between the second half of 2018 and the first half of 2019. The dataset includes the transcripts in English of 37 semi-structured interviews. </p>
Open Data of the article "Literal vs. default translation. Challenging the constructs with Middle Egyptian translation as an extreme case in point"
<p>The file contains the datasets and the code generated for the analyses presented in the article "Literal vs. default translation. Challenging the constructs with Middle Egyptian translation as an extreme case in point", to be published in <em>Sendebar</em> in 2023.</p> <p> </p> <p>Abstract of the article:</p> <p>This paper presents the results of a study that compares the constructs of literal translation (Schaeffer & Carl, 2014) and default translation (Halverson, 2019) by means of an observational, exploratory study with Middle Egyptian translation as an extreme case in point. Two graduating students of the MA in Egyptology at Universitat Autònoma de Barcelona and three recent graduates of the same MA took part in the study. They translated two excerpts from two Middle Egyptian literary texts into Spanish. InputLog was used to collect translation-process data and derive word-level indicators of cognitive effort (typos per word, word typing speed, and within-word pause) from them. Results showed a clear link between default translations and cognitive effort (low number of typos, low number of respites, and fast writing speed). However, the assumption that deviations from literality cause greater cognitive effort was not observed. Hence, default translation may serve as a more adequate construct to describe the regular way translators perform.</p>
Adult presence does not ameliorate juvenile feeding challenges in a leaf-footed bug
<p>Herbivores often grapple with structural defenses in their host plants, which may pose especially difficult challenges for juveniles due to their underdeveloped feeding morphology. The degree to which juvenile herbivore survival is limited by structural defenses as well as the strategies used to overcome them are not well understood. We hypothesized that juveniles benefit from feeding near adults because adults pierce through physical barriers while feeding, enabling juveniles to access nutrients that they otherwise could not. We tested this feeding facilitation hypothesis in the leaf-footed bug Leptoglossus zonatus (<em>Hemiptera</em>: <em>Coreidae</em>). Bugs were raised with an adult or a juvenile conspecific and fed a diet of pecans with or without shells. As predicted, we found that juveniles suffered greater mortality when fed nuts with shells than when fed nuts without shells. Contrary to our expectations, the presence of an adult feeding on the same nut did not lessen this effect. Therefore, the presence of an adult does not ameliorate the feeding difficulties faced by juvenile <em>L. zonatus</em>, despite evidence for feeding facilitation in related insect species. This study adds to our understanding of how host plant defenses can limit the survival of even highly generalist herbivores.</p>
Immune challenge affects reproductive behaviour in the Guppy (Poecilia reticulata)
<p>Immunocompetence and reproductive success are among the most important determinants of fitness in animals. However, energetic and metabolic constraints create conflict between these two priorities. The trade-off between immunity and reproductive fitness has been the subject of great scientific interest over many decades. While a number of studies exploring the relationship between immune activity and reproductive fitness/behaviour have been conducted using birds and mammals inoculated with bacterial endotoxin (LPS), relatively few have focussed on fish. This presents a conspicuous gap in our understanding of how immune activity affects reproduction in vertebrates more generally. Fish have been experimentally neglected in this area due, in part, to the claim that fish are largely resistant to the immune effects of endotoxins, and thus presumably suffer negligible behavioural effects. While the immune response to endotoxins may differ somewhat between fish and terrestrial vertebrates, the findings here suggest that they are nonetheless susceptible to significant behavioural effects with respect to reproduction. In this study, we show that although immune challenge does not suppress general activity in male guppies, it significantly reduces reproductive effort. As such, it is important to expand the examination of these processes to a greater diversity of vertebrate species, including fish.</p>
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.