123 machine learning datasets
123 dataset results
MediConfusion is a challenging medical Visual Question Answering (VQA) benchmark dataset, that probes the failure modes of medical Multimodal Large Language Models (MLLMs) from a vision perspective. We reveal that state-of-the-art models are easily confused by image pairs that are otherwise visually dissimilar and clearly distinct for medical experts. <br /> Our benchmark consists of 176 confusing pairs. A confusing pair is a set of two images that share the same question and corresponding answer options, but the correct answer is different for the images. <br /> We evaluate models based on their ability to answer <i>both</i> questions correctly within a confusing pair, which we call <b>set accuracy</b>. This metric indicates how well models can tell the two images apart, as a model that selects the same answer option for both images for all pairs will receive 0% set accuracy. We also report <b>confusion</b>, a metric that describes the proportion of confusing pairs where the model ha
The dataset SCARED-C is introduced in the context of assessing robustness in endoscopic depth prediction models. It is part of the EndoDepth benchmark, which is designed to evaluate the performance of monocular depth prediction models specifically for endoscopic scenarios. The dataset features 16 different types of image corruptions, each with five levels of severity, encompassing challenges like lens distortion, resolution alterations, specular reflection, and color changes that are typical in endoscopic imaging. The ground truth is on the original testing set of SCARED.
Prediction of a speaker's height is of interest in fields such as voice forensics, surveillance, and automatic speaker profiling. HeightCeleb is an extension of Voxceleb that includes height information for all 1251 speakers. The height data was extracted automatically from publicly available sources. The purpose of this dataset is to enable the research community to leverage freely available speaker embedding extractors, pre-trained on VoxCeleb, to develop more accurate speaker height estimators.
The datasets used and analysed from the glucose clamp study are available in this Excel file. They include pseudonymised information on the participants, somatometric data, biomarkers of lipid metabolism and parameters of insulin-glucose homeostasis, i.e. concentrations of insulin, glucose and c-peptide as well as data from glucose-clamp experiments, HOMA, SPINA Carb parameters (SPINA-GBeta and SPINA-GR), Matsuda index, insulinogenic index, disposition index and McAuley index.
The datasets used and analysed from the glucose clamp study are available in this DIF file. They include pseudonymised information on the participants, somatometric data, biomarkers of lipid metabolism and parameters of insulin-glucose homeostasis, i.e. concentrations of insulin, glucose and c-peptide as well as data from glucose-clamp experiments, HOMA, SPINA Carb parameters (SPINA-GBeta and SPINA-GR), Matsuda index, insulinogenic index, disposition index and McAuley index.
Rethinking Abdominal Organ Segmentation (RAOS) in the clinical scenario: A robustness evaluation benchmark with challenging cases.
The Liver-US dataset is a comprehensive collection of high-quality ultrasound images of the liver, including both normal and abnormal cases. This dataset is designed to facilitate research in medical image classification, with a focus on liver-related conditions. It includes a diverse range of ultrasound images acquired from multiple clinical settings, providing a robust foundation for developing and validating machine learning models in medical image analysis. Detailed Dataset Description
Wearanize+ includes overnight sleep data from 130 participants (one night each) using three different wearable devices: Zmax headband, Empatica E4 wristband, and ActivPAL leg patch, alongside full-scale PSG recorded with SomnoScreen Plus and Mentalab Explore Pro. It also includes questionnaires, such as PSQI, MADRE, and PHQ-9, providing information on participants’ sleep, dreams, and overall health. (The link to access the dataset will be added soon).
This dataset contains pre-processed versions of datasets introduced in prior works. Additionally, it also contains new data that are pertinent to the paper.
ATC-GRAPH is the most extensive ATC benchmark dataset. All drugs in the benchmarks are linked to their Mol files instead of the SMILES sequences utilized in earlier benchmarks. This shift allows for more precise and detailed modeling and learning. In terms of scale, ATC-GRAPH surpasses Chen-2012 and ATC-SMILES by 36.78% and 16.85%, respectively. Significantly, ATC-GRAPH was curated through a cross-validation process involving multiple resources such as KEGG, PubChem, ChEMBL, ChemSpider, and ChemicalBook. This results in ATC-GRAPH being distinguished by its timeliness and comprehensive coverage across all five levels and drug genres.
Daily Activity Recordings for Artificial Intelligence (DARai, pronounced "Dahr-ree") is a multimodal, hierarchically annotated dataset constructed to understand human activities in real-world settings. DARai consists of continuous scripted and unscripted recordings of 50 participants in 10 different environments, totaling over 200 hours of data from 20 sensors including multiple camera views, depth and radar sensors, wearable inertial measurement units (IMUs), electromyography (EMG), insole pressure sensors, biomonitor sensors, and gaze tracker. To capture the complexity in human activities, DARai is annotated at three levels of hierarchy: (i) high-level activities (L1) that are independent tasks, (ii) lower-level actions (L2) that are patterns shared between activities, and (iii) fine-grained procedures (L3) that detail the exact execution steps for actions. The dataset annotations and recordings are designed so that 22.7% of L2 actions are shared between L1 activities and 14.2% of L3
The medaka (Oryzias latipes) and the zebrafish (Danio rerio) are used as a model organism for a variety of subjects in biomedical research. The presented work aims to study the potential of automated ventricular dimension estimation through heart segmentation in medaka. For more on this, it's time for a closer look on our paper and the supplementary materials.
The RSNA Pulmonary Embolism CT (RSPECT) Dataset is composed of CT pulmonary angiogram images and annotations related to pulmonary embolism. It's part of the 2020 RSNA Pulmonary Embolism Detection Challenge which invited researchers to develop machine-learning algorithms to detect and characterize instances of pulmonary embolism (PE) on chest CT studies. The competition, conducted in collaboration with the Society of Thoracic Radiology (STR), involved creating the largest publicly available annotated PE dataset, comprised of more than 12,000 CT studies. Imaging data was contributed by five international research centers and labeled with detailed clinical annotations by a group of more than 80 expert thoracic radiologists. For the first time in an RSNA data challenge, the rules required competitors to submit and run their code in a standard shared environment, producing simpler, more readily usable models.
We've made available several genome-wide datasets, which can be used for training microRNA (miRNA) classifiers. The hairpin sequences available are from the genomes of: Homo sapiens, Arabidopsis thaliana, Anopheles gambiae, Caenorhabditis elegans and Drosophila melanogaster. Hairpin.s are small RNA sequences that naturaly folds into a hairpin-structure. However, not all hairpins have clear function (they are not miRNAs).
InfiniteRep is a synthetic, open-source dataset for fitness and physical therapy (PT) applications. It includes 1k videos of diverse avatars performing multiple repetitions of common exercises. It includes significant variation in the environment, lighting conditions, avatar demographics, and movement trajectories. From cadence to kinematic trajectory, each rep is done slightly differently -- just like real humans. InfiniteRep videos are accompanied by a rich set of pixel-perfect labels and annotations, including frame-specific repetition counts.
FHRMA is an open-source project for Fetal Heart Rate Morphological Analysis containing Matlab source code and datasets. As a sub-project, it includes a deep learning method and dataset for automatic identification of the maternal heart rate (MHR) and, more generally, false signals (FSs) on fetal heart rate (FHR) recordings. The challenge concerns particularly the FHR signal recorded with Doppler sensors, on which MHR interference and other FSs are particularly common, but the dataset also includes FHR recorded with scalp-ECG. The training and validation dataset contained 1030 expert-annotated periods (mean duration: 36 min) from 635 recordings. Labels consist of annotating each time sample as either 1: False signal; 0: True signal, or -1: do not know or irrelevant.
Datasets at https://zenodo.org/record/8105485 for Motion Robust CMR Reconstruction Code in https://github.com/syedmurtazaarshad/motion-robust-CMR
Human activity recognition and clinical biomechanics are challenging problems in physical telerehabilitation medicine. However, most publicly available datasets on human body movements cannot be used to study both problems in an out-of-the-lab movement acquisition setting. The objective of the VIDIMU dataset is to pave the way towards affordable patient tracking solutions for remote daily life activities recognition and kinematic analysis.
Introduction: The scientific publishing landscape is expanding rapidly, creating challenges for researchers to stay up-to-date with the evolution of the literature. Natural Language Processing (NLP) has emerged as a potent approach to automating knowledge extraction from this vast amount of publications and preprints. Tasks such as Named-Entity Recognition (NER) and Named-Entity Linking (NEL), in conjunction with context-dependent semantic interpretation, offer promising and complementary approaches to extracting structured information and revealing key concepts. Results: We present the SourceData-NLP dataset produced through the routine curation of papers during the publication process. A unique feature of this dataset is its emphasis on the annotation of bioentities in figure legends. We annotate eight classes of biomedical entities (small molecules, gene products, subcellular components, cell lines, cell types, tissues, organisms, and diseases), their role in the experimental de
Dataset for the DREAMING - Diminished Reality for Emerging Applications in Medicine through Inpainting Challenge!