The MIT-BIH Arrhythmia Database contains 48 half-hour excerpts of two-channel ambulatory ECG recordings, obtained from 47 subjects studied by the BIH Arrhythmia Laboratory between 1975 and 1979. Twenty-three recordings were chosen at random from a set of 4000 24-hour ambulatory ECG recordings collected from a mixed population of inpatients (about 60%) and outpatients (about 40%) at Boston's Beth Israel Hospital; the remaining 25 recordings were selected from the same set to include less common but clinically significant arrhythmias that would not be well-represented in a small random sample.
28 PAPERS • 5 BENCHMARKS
This dataset is a BIDS compatible version of the Siena Scalp EEG Database. It reorganizes the file structure to comply with the BIDS specification. To this effect:
1 PAPER • NO BENCHMARKS YET
Click to add a brief description of the dataset (Markdown and LaTeX enabled).
This is an improved machine-learning-ready glaucoma dataset using a balanced subset of standardized fundus images from the Rotterdam EyePACS AIROGS [1] set. This dataset is split into training, validation, and test folders which contain 4000 (~84%), 385 (~8%), and 385 (~8%) fundus images in each class respectively. Each training set has a folder for each class: referable glaucoma (RG) and non-referable glaucoma (NRG).
0 PAPER • NO BENCHMARKS YET
This dataset is a BIDS-compatible version of the CHB-MIT Scalp EEG Database. It reorganizes the file structure to comply with the BIDS specification. To this effect:
Overview The Surgical Instruments Recognition Dataset is a groundbreaking collection of high-resolution images (1280x960 pixels) specifically designed for the recognition and categorization of surgical instruments. This dataset captures the intricate details and complexity of surgical tools, particularly when arranged in scenarios reminiscent of an operating room.
We introduce a new AI-ready computational pathology dataset containing restained and co-registered digitized images from eight head-and-neck squamous cell carcinoma patients. Specifically, the same tumor sections were stained with the expensive multiplex immunofluorescence (mIF) assay first and then restained with cheaper multiplex immunohistochemistry (mIHC). This is a first public dataset that demonstrates the equivalence of these two staining methods which in turn allows several use cases; due to the equivalence, our cheaper mIHC staining protocol can offset the need for expensive mIF staining/scanning which requires highly skilled lab technicians. As opposed to subjective and error-prone immune cell annotations from individual pathologists (disagreement > 50%) to drive SOTA deep learning approaches, this dataset provides objective immune and tumor cell annotations via mIF/mIHC restaining for more reproducible and accurate characterization of tumor immune microenvironment (e.g. for
A large paroxysmal atrial fibrillation long-term electrocardiogram monitoring database Abstract Atrial fibrillation (AF) is the most common sustained heart arrhythmia in adults. Holter monitoring, a long-term 2-lead electrocardiogram (ECG), is a key tool available to cardiologists for AF diagnosis. Machine learning (ML) and deep learning (DL) models have shown great capacity to automatically detect AF in ECG and their use as medical decision support tool is growing. Training these models rely on a few open and annotated databases. We present a new Holter monitoring database from patients with paroxysmal AF with 167 records from 152 patients, acquired from an outpatient cardiology clinic from 2006 to 2017 in Belgium. AF episodes were manually annotated and reviewed by an expert cardiologist and a specialist cardiac nurse. Records last from 19 hours up to 95 hours, divided into 24-hour files. In total, it represents 24 million seconds of annotated Holter monitoring, sampled at 200 Hz. Th
Our primary objective in creating this dataset is to support researchers in the advancement of algorithms for keypoints detection and the pretraining of large models on retinal images using a self-supervised approach. The keypoints in the dataset have been carefully annotated by students from our lab, ensuring meticulous accuracy.
The CheXmask Database presents a comprehensive, uniformly annotated collection of chest radiographs, constructed from five public databases: ChestX-ray8, Chexpert, MIMIC-CXR-JPG, Padchest and VinDr-CXR. The database aggregates 657,566 anatomical segmentation masks derived from images which have been processed using the HybridGNet model to ensure consistent, high-quality segmentation. To confirm the quality of the segmentations, we include in this database individual Reverse Classification Accuracy (RCA) scores for each of the segmentation masks. This dataset is intended to catalyze further innovation and refinement in the field of semantic chest X-ray analysis, offering a significant resource for researchers in the medical imaging domain.
4 PAPERS • NO BENCHMARKS YET
Estimating camera motion in deformable scenes poses a complex and open research challenge. Most existing non-rigid structure from motion techniques assume to observe also static scene parts besides deforming scene parts in order to establish an anchoring reference. However, this assumption does not hold true in certain relevant application cases such as endoscopies. To tackle this issue with a common benchmark, we introduce the Drunkard’s Dataset, a challenging collection of synthetic data targeting visual navigation and reconstruction in deformable environments. This dataset is the first large set of exploratory camera trajectories with ground truth inside 3D scenes where every surface exhibits non-rigid deformations over time. Simulations in realistic 3D buildings lets us obtain a vast amount of data and ground truth labels, including camera poses, RGB images and depth, optical flow and normal maps at high resolution and quality.
1 PAPER • 1 BENCHMARK
Recent accelerations in multi-modal applications have been made possible with the plethora of image and text data available online. However, the scarcity of similar data in the medical field, specifically in histopathology, has halted similar progress. To enable similar representation learning for histopathology, we turn to YouTube, an untapped resource of videos, offering 1,087 hours of valuable educational histopathology videos from expert clinicians. From YouTube, we curate Quilt: a large-scale vision-language dataset consisting of 768,826 image and text pairs. Quilt was automatically curated using a mixture of models, including large language models), handcrafted algorithms, human knowledge databases, and automatic speech recognition. In comparison, the most comprehensive datasets curated for histopathology amass only around 200K samples. We combine Quilt with datasets, from other sources, including Twitter, research papers, and the internet in general, to create an even larger dat
This is a machine-learning-ready glaucoma dataset using a balanced subset of standardized fundus images from the Rotterdam EyePACS AIROGS train set. This dataset is split into training, validation, and test folders which contain 2500, 270, and 500 fundus images in each class respectively. Each training set has a folder for each class: referable glaucoma (RG) and non-referable glaucoma (NRG).
ARCADE: Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs Dataset Phase 2 consist of two folders with 300 images in each of them as well as annotations.
5 PAPERS • 2 BENCHMARKS
This dataset is a collection of fluorescent images from mice in order to test an automatic cell counting tool that we developed. 62 images viewed from 2 or 3 different fields of views are shown. In brief, the dataset was derived from brain sections of a model for HIV-induced brain injury (HIVgp120tg), which expresses soluble gp120 envelope protein in astrocytes under the control of a modified GFAP promoter. The mice were in a mixed C57BL/6.129/SJL genetic background, and two genotypes of 9 month old male mice were selected: wild type controls (Resting, n = 3) and transgenic littermates (HIVgp120tg, Activated, n = 3). No randomization was performed. HIVgp120tg mice show among other hallmarks of human HIV neuropathology an increase in microglia numbers which indicates activation of the cells compared to non-transgenic littermate controls.
A dataset of 100K synthetic images of skin lesions, ground-truth (GT) segmentations of lesions and healthy skin, GT segmentations of seven body parts (head, torso, hips, legs, feet, arms and hands), and GT binary masks of non-skin regions in the texture maps of 215 scans from the 3DBodyTex.v1 dataset [2], [3] created using the framework described in [1]. The dataset is primarily intended to enable the development of skin lesion analysis methods. Synthetic image creation consisted of two main steps. First, skin lesions from the Fitzpatrick 17k dataset were blended onto skin regions of high-resolution three-dimensional human scans from the 3DBodyTex dataset [2], [3]. Second, two-dimensional renders of the modified scans were generated.
PMC-VQA is a large-scale medical visual question-answering dataset that contains 227k VQA pairs of 149k images that cover various modalities or diseases. The question-answer pairs are generated from PMC-OA.
28 PAPERS • 3 BENCHMARKS
Standardized Multi-Channel Dataset for Glaucoma (SMDG-19) is a collection and standardization of 19 public datasets, comprised of full-fundus glaucoma images, associated image metadata like, optic disc segmentation, optic cup segmentation, blood vessel segmentation, and any provided per-instance text metadata like sex and age. This dataset is the largest public repository of fundus images with glaucoma.
An instance segmentation dataset of yeast cells in microstructures. The dataset includes 493 densely annotated microscopy images. For more information see the paper "An Instance Segmentation Dataset of Yeast Cells in Microstructures".
Purpose Medical imaging has become increasingly important in diagnosing and treating oncological patients, particularly in radiotherapy. Recent advances in synthetic computed tomography (sCT) generation have increased interest in public challenges to provide data and evaluation metrics for comparing different approaches openly. This paper describes a dataset of brain and pelvis computed tomography (CT) images with rigidly registered cone-beam CT (CBCT) and magnetic resonance imaging (MRI) images to facilitate the development and evaluation of sCT generation for radiotherapy planning.
SkinCon is a skin disease dataset densely annotated by dermatologists. SkinCon includes 3230 images from the Fitzpatrick 17k skin disease (Fitzpatrick Skin Tone) dataset densely labelled with 48 clinical concepts, 22 of which have at least 50 images representing the concept. The concepts used were chosen by two dermatologists considering the clinical descriptor terms used to describe skin lesions. Examples include "plaque", "scale", and "erosion".
2 PAPERS • NO BENCHMARKS YET
The Fraunhofer Portugal AICOS EDoF Dataset was produced within the TAMI project and is composed of images of microscopic fields of view (FOV) of Liquid-based Cervical Cytology (LBC) samples. A total of 15 LBC samples were supplied by the Pathology Services from Hospital Fernando Fonseca and the Portuguese Oncology Institute of Porto. For each LBC sample, a set of images were obtained using a version of µSmartScope [1,2] prototype adapted to the cervical cytology use case [3,4].
Cancer in the region of the head and neck (HaN) is one of the most prominent cancers, for which radiotherapy represents an important treatment modality that aims to deliver a high radiation dose to the targeted cancerous cells while sparing the nearby healthy organs-at-risk (OARs). A precise three-dimensional spatial description, i.e. segmentation, of the target volumes as well as OARs is required for optimal radiation dose distribution calculation, which is primarily performed using computed tomography (CT) images. However, the HaN region contains many OARs that are poorly visible in CT, but better visible in magnetic resonance (MR) images. Although attempts have been made towards the segmentation of OARs from MR images, so far there has been no evaluation of the impact the combined analysis of CT and MR images has on the segmentation of OARs in the HaN region. The Head and Neck Organ-at-Risk Multi-Modal Segmentation Challenge aims to promote the development of new and application of
5 PAPERS • NO BENCHMARKS YET
VISEM-Tracking is a dataset consisting of 20 video recordings of 30s of spermatozoa with manually annotated bounding-box coordinates and a set of sperm characteristics analyzed by experts in the domain. It is an extension of the previously published VISEM dataset. In addition to the annotated data, unlabeled video clips are provided for easy-to-use access and analysis of the data.
EBHI-Seg is a dataset containing 5,170 images of six types of tumor differentiation stages and the corresponding ground truth images. The dataset can provide researchers with new segmentation algorithms for medical diagnosis of colorectal cancer.
Facial Skeletal Angles (Glabella and Maxilla Angle and Length and Width of Piriformis)
This dataset is obtained during an ICON project (2017-2018) in collaboration with KU Leuven (ESAT-STADIUS), UZ Leuven, UCB, Byteflies and Pilipili. The goal of this project was to design a system using Behind the ear (bhE) EEG electrodes for monitoring the patient in a home environment. This way, a nice balance can be found between sufficient accuracy of seizure detection algorithms (because EEG is used) and wearability (bhe EEG is relatively subtle, similar to a hear-aid device). The dataset acquired in the hospital during presurgical evaluation. During such presurgical evaluation, neurologists try to see if a specific part of the brain is causing the seizures, and if so, if that part of the brain can be removed during surgery. During the presurgical evaluation, patients are monitored using the vEEG for multiple days (typically a week). Patients are however restricted to move within their room because of the wiring and video analysis. In this dataset, following data is available per p
CheXlocalize is a radiologist-annotated segmentation dataset on chest X-rays. The dataset consists of two types of radiologist annotations for the localization of 10 pathologies: pixel-level segmentations and most-representative points. Annotations were drawn on images from the CheXpert validation and test sets. The dataset also consists of two separate sets of radiologist annotations: (1) ground-truth pixel-level segmentations on the validation and test sets, drawn by two board-certified radiologists, and (2) benchmark pixel-level segmentations and most-representative points on the test set, drawn by a separate group of three board-certified radiologists.
Clinical diagnosis of the eye is performed over multifarious data modalities including scalar clinical labels, vectorized biomarkers, two-dimensional fundus images, and three-dimensional Optical Coherence Tomography (OCT) scans. While the clinical labels, fundus images and OCT scans are instrumental measurements, the vectorized biomarkers are interpreted attributes from the other measurements. Clinical practitioners use all these data modalities for diagnosing and treating eye diseases like Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). Enabling usage of machine learning algorithms within the ophthalmic medical domain requires research into the relationships and interactions between these relevant data modalities. Existing datasets are limited in that: (i) they view the problem as disease prediction without assessing biomarkers, and (ii) they do not consider the explicit relationship among all four data modalities over the treatment period. In this paper, we introduce the O
The MIMIC PERform Testing dataset contains the following physiological signals recorded from 200 critically-ill patients during routine clinical care:
1 PAPER • 2 BENCHMARKS
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.
OVQA contains 19,020 medical visual question and answer pairs generated from 2,001 medical images collected from 2,212 EMRs in Orthopedics.
3 PAPERS • 1 BENCHMARK
Abstract The Norwegian Endurance Athlete ECG Database contains 12-lead ECG recordings from 28 elite athletes from various sports in Norway. All recordings are 10 seconds resting ECGs recorded with a General Electric (GE) MAC VUE 360 electrocardiograph. All ECGs are interpreted with both the GE Marquette SL12 algorithm (version 23 (v243)) and one cardiologist with training in interpretation of athlete's ECG. The data was collected at the University of Oslo in February and March 2020.
The SUN-SEG dataset is a high-quality per-frame annotated VPS dataset, which includes 158,690 frames from the famous SUN dataset. It extends the labels with diverse types, i.e., object mask, boundary, scribble, polygon, and visual attribute. It also introduces the pathological information from the original SUN dataset, including pathological classification labels, location information, and shape information.
13 PAPERS • 1 BENCHMARK
Accurate lesion segmentation is critical in stroke rehabilitation research for the quantification of lesion burden and accurate image processing. Current automated lesion segmentation methods for T1-weighted (T1w) MRIs, commonly used in rehabilitation research, lack accuracy and reliability. Manual segmentation remains the gold standard, but it is time-consuming, subjective, and requires significant neuroanatomical expertise. However, many methods developed with ATLAS v1.2 report low accuracy, are not publicly accessible or are improperly validated, limiting their utility to the field. Here we present ATLAS v2.0 (N=1271), a larger dataset of T1w stroke MRIs and manually segmented lesion masks that includes training (public. n=655), test (masks hidden, n=300), and generalizability (completely hidden, n=316) data. Algorithm development using this larger sample should lead to more robust solutions, and the hidden test and generalizability datasets allow for unbiased performance evaluation
6 PAPERS • 1 BENCHMARK
An experimental and synthetic (simulated) OA raw signals and reconstructed image domain datasets rendered with different experimental parameters and tomographic acquisition geometries.
RadQA is a radiology question answering dataset with 3074 questions posed against radiology reports and annotated with their corresponding answer spans (resulting in a total of 6148 question-answer evidence pairs) by physicians. The questions are manually created using the clinical referral section of the reports that take into account the actual information needs of ordering physicians and eliminate bias from seeing the answer context (and, further, organically create unanswerable questions). The answer spans are marked within the Findings and Impressions sections of a report. The dataset aims to satisfy the complex clinical requirements by including complete (yet concise) answer phrases (which are not just entities) that can span multiple lines.
7 PAPERS • 1 BENCHMARK
There has been a rapidly growing interest in Automatic Symptom Detection (ASD) and Automatic Diagnosis (AD) systems in the machine learning research literature, aiming to assist doctors in telemedicine services. These systems are designed to interact with patients, collect evidence about their symptoms and relevant antecedents, and possibly make predictions about the underlying diseases. Doctors would review the interactions, including the evidence and the predictions, collect if necessary additional information from patients, before deciding on next steps. Despite recent progress in this area, an important piece of doctors' interactions with patients is missing in the design of these systems, namely the differential diagnosis. Its absence is largely due to the lack of datasets that include such information for models to train on. In this work, we present a large-scale synthetic dataset of roughly 1.3 million patients that includes a differential diagnosis, along with the ground truth
8 PAPERS • NO BENCHMARKS YET
The MS-CXR dataset provides 1162 image–sentence pairs of bounding boxes and corresponding phrases, collected across eight different cardiopulmonary radiological findings, with an approximately equal number of pairs for each finding. This dataset complements the existing MIMIC-CXR v.2 dataset and comprises: 1. Reviewed and edited bounding boxes and phrases (1026 pairs of bounding box/sentence); and 2. Manual bounding box labels from scratch (136 pairs of bounding box/sentence).e
23 PAPERS • NO BENCHMARKS YET
The Endomapper dataset is the first collection of complete endoscopy sequences acquired during regular medical practice, including slow and careful screening explorations, making secondary use of medical data. Its original purpose is to facilitate the development and evaluation of VSLAM (Visual Simultaneous Localization and Mapping) methods in real endoscopy data. The first release of the dataset is composed of 50 sequences with a total of more than 13 hours of video. It is also the first endoscopic dataset that includes both the computed geometric and photometric endoscope calibration as well as the original calibration videos. Meta-data and annotations associated to the dataset varies from anatomical landmark and description of the procedure labeling, tools segmentation masks, COLMAP 3D reconstructions, simulated sequences with groundtruth and meta-data related to special cases, such as sequences from the same patient. This information will improve the research in endoscopic VSLAM, a
12 PAPERS • NO BENCHMARKS YET
This dataset includes sharp-blur pairs of Leishmania image, which is a protozoan parasite microscopy image dataset of Leishmania, obtained from the preserved slides stained with Giemsa. The paired blur-sharp images are acquired by employing a bright-field microscope (Olympus IX53) with 100× magnification oil immersion objectives.We first capture the sharp images as ground truth, then acquire its corresponding out-of-focus images. The extent and nature of defocusing are random along the optical axis, where the degree of out-of-focus is inconsistent from image-to-image. This dataset includes 764 in-focus and 764 corresponding out-of-focus images, where each image is composed of 2304 × 1728 pixels in 24-bit JPG format.
The evaluation of human epidermal growth factor receptor 2 (HER2) expression is essential to formulate a precise treatment for breast cancer. The routine evaluation of HER2 is conducted with immunohistochemical techniques (IHC), which is very expensive. Therefore, we propose a breast cancer immunohistochemical (BCI) benchmark attempting to synthesize IHC data directly with the paired hematoxylin and eosin (HE) stained images. The dataset contains 4870 registered image pairs, covering a variety of HER2 expression levels (0, 1+, 2+, 3+).
10 PAPERS • 1 BENCHMARK
Onchocerciasis is causing blindness in over half a million people in the world today. Drug development for the disease is crippled as there is no way of measuring effectiveness of the drug without an invasive procedure. Drug efficacy measurement through assessment of viability of onchocerca worms requires the patients to undergo nodulectomy which is invasive, expensive, time-consuming, skill-dependent, infrastructure dependent and lengthy process.
4D-OR includes a total of 6734 scenes, recorded by six calibrated RGB-D Kinect sensors 1 mounted to the ceiling of the OR, with one frame-per-second, providing synchronized RGB and depth images. We provide fused point cloud sequences of entire scenes, automatically annotated human 6D poses and 3D bounding boxes for OR objects. Furthermore, we provide SSG annotations for each step of the surgery together with the clinical roles of all the humans in the scenes, e.g., nurse, head surgeon, anesthesiologist.
8 PAPERS • 1 BENCHMARK
Set of landmark annotations for JSRT, Montgomery, Shenzhen and a subset of Padchest datasets
The LIMUC dataset is the largest publicly available labeled ulcerative colitis dataset that compromises 11276 images from 564 patients and 1043 colonoscopy procedures. Three experienced gastroenterologists were involved in the annotation process, and all images are labeled according to the Mayo endoscopic score (MES).
4 PAPERS • 1 BENCHMARK