A large-scale cloze-style biomedical MRC dataset. Care was taken to reduce noise, compared to the previous BIOREAD dataset of Pappas et al. (2018).
8 PAPERS • 1 BENCHMARK
The Breast Cancer Histopathological Image Classification (BreakHis) is composed of 9,109 microscopic images of breast tumor tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X). It contains 2,480 benign and 5,429 malignant samples (700X460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format). This database has been built in collaboration with the P&D Laboratory - Pathological Anatomy and Cytopathology, Parana, Brazil.
8 PAPERS • 5 BENCHMARKS
CHAOS challenge aims the segmentation of abdominal organs (liver, kidneys and spleen) from CT and MRI data. ONsite section of the CHAOS was held in The IEEE International Symposium on Biomedical Imaging (ISBI) on April 11, 2019, Venice, ITALY. Online submissions are still welcome!
8 PAPERS • NO BENCHMARKS YET
The MedNLI dataset consists of the sentence pairs developed by Physicians from the Past Medical History section of MIMIC-III clinical notes annotated for Definitely True, Maybe True and Definitely False. The dataset contains 11,232 training, 1,395 development and 1,422 test instances. This provides a natural language inference task (NLI) grounded in the medical history of patients.
8 PAPERS • 2 BENCHMARKS
TMED is a clinically-motivated benchmark dataset for computer vision and machine learning from limited labeled data.
Prediction of Finger Flexion IV Brain-Computer Interface Data Competition The goal of this dataset is to predict the flexion of individual fingers from signals recorded from the surface of the brain (electrocorticography (ECoG)). This data set contains brain signals from three subjects, as well as the time courses of the flexion of each of five fingers. The task in this competition is to use the provided flexion information in order to predict finger flexion for a provided test set. The performance of the classifier will be evaluated by calculating the average correlation coefficient r between actual and predicted finger flexion.
7 PAPERS • 1 BENCHMARK
This dataset contains 1200 images (1000 WLI images and 200 FICE images) with fine-grained segmentation annotations. The training set consists of 1000 images, and the test set consists of 200 images. All polyps are classified into neoplastic or non-neoplastic classes denoted by red and green colors, respectively. This dataset is a part of a bigger dataset called NeoPolyp.
Chinese Medical Named Entity Recognition, a dataset first released in CHIP20204, is used for CMeEE task. Given a pre-defined schema, the task is to identify and extract entities from the given sentence and classify them into nine categories: disease, clinical manifestations, drugs, medical equipment, medical procedures, body, medical examinations, microorganisms, and department.
Under a close collaboration with an expert radiologist team of the Hospital Universitario San Cecilio, the COVIDGR-1.0 dataset of patients' anonymized X-ray images has been built. 852 images have been collected following a strict labeling protocol. They are categorized into 426 positive cases and 426 negative cases. Positive images correspond to patients who have been tested positive for COVID-19 using RT-PCR within a time span of at most 24h between the X-ray image and the test. Every image has been taken using the same type of equipment and with the same format: only the posterior-anterior view is considered.
7 PAPERS • NO BENCHMARKS YET
The Diabetic Foot Ulcers dataset (DFUC2021) is a dataset for analysis of pathology, focusing on infection and ischaemia. The final release of DFUC2021 consists of 15,683 DFU patches, with 5,955 training, 5,734 for testing and 3,994 unlabeled DFU patches. The ground truth labels are four classes, i.e. control, infection, ischaemia and both conditions.
The ISIC 2018 dataset was published by the International Skin Imaging Collaboration (ISIC) as a large-scale dataset of dermoscopy images. The Task 3 dataset is the challenge on lesion classification. It includes 2594 images. The task is to classify the dermoscopic images into one of the following categories: melanoma, melanocytic nevus, basal cell carcinoma, actinic keratosis / Bowen’s disease, benign keratosis, dermatofibroma, and vascular lesion.
The 2021 Kidney and Kidney Tumor Segmentation challenge (abbreviated KiTS21) is a competition in which teams compete to develop the best system for automatic semantic segmentation of renal tumors and surrounding anatomy.
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.
English subset of the SLAKE dataset, comprising 642 images and more than 7,000 question–answer pairs.
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.
6 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
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
6 PAPERS • NO BENCHMARKS YET
This paper introduces FrenchMedMCQA, the first publicly available Multiple-Choice Question Answering (MCQA) dataset in French for medical domain. It is composed of 3,105 questions taken from real exams of the French medical specialization diploma in pharmacy, mixing single and multiple answers. Each instance of the dataset contains an identifier, a question, five possible answers and their manual correction(s). We also propose first baseline models to automatically process this MCQA task in order to report on the current performances and to highlight the difficulty of the task. A detailed analysis of the results showed that it is necessary to have representations adapted to the medical domain or to the MCQA task: in our case, English specialized models yielded better results than generic French ones, even though FrenchMedMCQA is in French. Corpus, models and tools are available online.
6 PAPERS • 2 BENCHMARKS
A large publicly available retinal fundus image dataset for glaucoma classification called G1020. The dataset is curated by conforming to standard practices in routine ophthalmology and it is expected to serve as standard benchmark dataset for glaucoma detection. This database consists of 1020 high resolution colour fundus images and provides ground truth annotations for glaucoma diagnosis, optic disc and optic cup segmentation, vertical cup-to-disc ratio, size of neuroretinal rim in inferior, superior, nasal and temporal quadrants, and bounding box location for optic disc.
The KUMC dataset for polyp detection and classification was collected from the University of Kansas Medical Center. It contains 80 colonoscopy video sequences which are manually labeled with bounding boxes as well as the polyp classes for the entire dataset.
The MISAW data set is composed of 27 sequences of micro-surgical anastomosis on artificial blood vessels performed by 3 surgeons and 3 engineering students. The dataset contained video, kinematic, and procedural descriptions synchronized at 30Hz. The procedural descriptions contained phases, steps, and activities performed by the participants.
The MedDialog dataset (Chinese) contains conversations (in Chinese) between doctors and patients. It has 1.1 million dialogues and 4 million utterances. The data is continuously growing and more dialogues will be added. The raw dialogues are from haodf.com. All copyrights of the data belong to haodf.com.
Mindboggle is a large publicly available dataset of manually labeled brain MRI. It consists of 101 subjects collected from different sites, with cortical meshes varying from 102K to 185K vertices. Each brain surface contains 25 or 31 manually labeled parcels.
PHM2017 is a new dataset consisting of 7,192 English tweets across six diseases and conditions: Alzheimer’s Disease, heart attack (any severity), Parkinson’s disease, cancer (any type), Depression (any severity), and Stroke. The Twitter search API was used to retrieve the data using the colloquial disease names as search keywords, with the expectation of retrieving a high-recall, low precision dataset. After removing the re-tweets and replies, the tweets were manually annotated. The labels are:
PSI-AVA is a dataset designed for holistic surgical scene understanding. It contains approximately 20.45 hours of the surgical procedure performed by three expert surgeons and annotations for both long-term (Phase and Step recognition) and short-term reasoning (Instrument detection and novel Atomic Action recognition) in robot-assisted radical prostatectomy videos.
The REFLACX dataset contains eye-tracking data for 3,032 readings of chest x-rays by five radiologists. The dictated reports were transcribed and have timestamps synchronized with the eye-tracking data.
Over 1.5K images selected from the public Kaggle DR Detection dataset; Five DR grades (DR0 / DR1 / DR2 / DR3 / DR4), re-labeled by a panel of 45 experienced ophthalmologists; Eight retinal lesion classes, including microaneurysm, intraretinal hemorrhage, hard exudate, cotton-wool spot, vitreous hemorrhage, preretinal hemorrhage, neovascularization and fibrous proliferation; Over 34K expert-labeled pixel-level lesion segments; Multi-task, i.e., lesion segmentation, lesion classification, and DR grading.
The SD-198 dataset contains 198 different diseases from different types of eczema, acne and various cancerous conditions. There are 6,584 images in total. A subset include the classes with more than 20 image samples, namely SD-128."
6 PAPERS • 6 BENCHMARKS
The SKM-TEA dataset pairs raw quantitative knee MRI (qMRI) data, image data, and dense labels of tissues and pathology for end-to-end exploration and evaluation of the MR imaging pipeline. This 1.6TB dataset consists of raw-data measurements of ~25,000 slices (155 patients) of anonymized patient knee MRI scans, the corresponding scanner-generated DICOM images, manual segmentations of four tissues, and bounding box annotations for sixteen clinically relevant pathologies.
VinDr-CXR is an open large-scale dataset of chest X-rays with radiologist’s annotations. It's bult from more than 100,000 raw images in DICOM format that were retrospectively collected from the Hospital 108 and the Hanoi Medical University Hospital, two of the largest hospitals in Vietnam. The published dataset consists of 18,000 postero-anterior (PA) view CXR scans that come with both the localization of critical findings and the classification of common thoracic diseases. These images were annotated by a group of 17 radiologists with at least 8 years of experience for the presence of 22 critical findings (local labels) and 6 diagnoses (global labels); each finding is localized with a bounding box. The local and global labels correspond to the “Findings” and “Impressions” sections, respectively, of a standard radiology report.
The 3DSeg-8 is a collection of several publicly available 3D segmentation datasets from different medical imaging modalities, e.g. magnetic resonance imaging (MRI) and computed tomography (CT), with various scan regions, target organs and pathologies.
5 PAPERS • NO BENCHMARKS YET
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
ARCH is a computational pathology (CP) multiple instance captioning dataset to facilitate dense supervision of CP tasks. Existing CP datasets focus on narrow tasks; ARCH on the other hand contains dense diagnostic and morphological descriptions for a range of stains, tissue types and pathologies.
BRATS 2014 is a brain tumor segmentation dataset.
5 PAPERS • 1 BENCHMARK
Cata7 is the first cataract surgical instrument dataset for semantic segmentation. The dataset consists of seven videos while each video records a complete cataract surgery. All videos are from Beijing Tongren Hospital. Each video is split into a sequence of images, where resolution is 1920×1080 pixels. To reduce redundancy, the videos are downsampled from 30 fps to 1 fps. Also, images without surgical instruments are manually removed. Each image is labeled with precise edges and types of surgical instruments. This dataset contains 2,500 images, which are divided into training and test sets. The training set consists of five video sequences and test set consists of two video sequence.
ChestX-Det is a chest X-Ray dataset with instance-level annotations (boxes and masks). ChestX-Det is a subset of the public dataset NIH ChestX-ray14. It contains ~3500 images of 13 common disease categories labeled by three board-certified radiologists.
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
ISRUC-Sleep is a polysomnographic (PSG) dataset. The data were obtained from human adults, including healthy subjects, and subjects with sleep disorders under the effect of sleep medication. The dataset, which is structured to support different research objectives, comprises three groups of data: (a) data concerning 100 subjects, with one recording session per subject, (b) data gathered from 8 subjects; two recording sessions were performed per subject, which are useful for studies involving changes in the PSG signals over time, (c) data collected from one recording session related to 10 healthy subjects, which are useful for studies involving comparison of healthy subjects with the patients suffering from sleep disorders.
Lesion Boundary Segmentation Dataset is a dataset for lesion segmentation from the ISIC2018 challenge. The dataset contains skin lesions and their corresponding annotations.
The Messidor database has been established to facilitate studies on computer-assisted diagnoses of diabetic retinopathy. The research community is welcome to test its algorithms on this database. In this section, you will find instructions on how to download the database.
The Multi-domain Mobile Video Physiology Dataset (MMPD), comprising 11 hours(1152K frames) of recordings from mobile phones of 33 subjects. The dataset was designed to capture videos with greater representation across skin tone, body motion, and lighting conditions. MMPD is comprehensive with eight descriptive labels and can be used in conjunction with the rPPG-toolbox and PhysBench. MMPD is widely used for rPPG tasks and remote heart rate estimation. To access the dataset, you are supposed to download this data release agreement and request downloading by email.
MyoPS is a dataset for myocardial pathology segmentation combining three-sequence cardiac magnetic resonance (CMR) images, which was first proposed in the MyoPS challenge, in conjunction with MICCAI 2020. The challenge provided 45 paired and pre-aligned CMR images, allowing algorithms to combine the complementary information from the three CMR sequences for pathology segment
The Raider dataset collects fMRI recordings of 1000 voxels from the ventral temporal cortex, for 10 healthy adult participants passively watching the full-length movie “Raiders of the Lost Ark”.
The m2cai16-tool-locations dataset contains spatial tool annotations for 2,532 frames across the first 10 videos in the m2cai16-tool dataset, which includes 15 videos in total. The dataset consists of 3,141 annotations of 7 surgical instrument classes, with an average of 1.2 labels per frame and 7 instrument classes per video.
This brain anatomy segmentation dataset has 1300 2D US scans for training and 329 for testing. A total of 1629 in vivo B-mode US images were obtained from 20 different subjects (age<1 years old) who were treated between 2010 and 2016. The dataset contained subjects with IVH and without (healthy subjects but in risk of developing IVH). The US scans were collected using a Philips US machine with a C8-5 broadband curved array transducer using coronal and sagittal scan planes. For every collected image ventricles and septum pellecudi are manually segmented by an expert ultrasonographer. We split these images randomly into 1300 Training images and 329 Testing images for experiments. Note that these images are of size 512 × 512.
4 PAPERS • 1 BENCHMARK
The complete blood count (CBC) dataset contains 360 blood smear images along with their annotation files splitting into Training, Testing, and Validation sets. The training folder contains 300 images with annotations. The testing and validation folder both contain 60 images with annotations. We have done some modifications over the original dataset to prepare this CBC dataset where some of the image annotation files contain very low red blood cells (RBCs) than actual and one annotation file does not include any RBC at all although the cell smear image contains RBCs. So, we clear up all the fallacious files and split the dataset into three parts. Among the 360 smear images, 300 blood cell images with annotations are used as the training set first, and then the rest of the 60 images with annotations are used as the testing set. Due to the shortage of data, a subset of the training set is used to prepare the validation set which contains 60 images with annotations.
4 PAPERS • NO BENCHMARKS YET
The CHB-MIT dataset is a dataset of EEG recordings from pediatric subjects with intractable seizures. Subjects were monitored for up to several days following withdrawal of anti-seizure mediation in order to characterize their seizures and assess their candidacy for surgical intervention. The dataset contains 23 patients divided among 24 cases (a patient has 2 recordings, 1.5 years apart). The dataset consists of 969 Hours of scalp EEG recordings with 173 seizures. There exist various types of seizures in the dataset (clonic, atonic, tonic). The diversity of patients (Male, Female, 10-22 years old) and different types of seizures contained in the datasets are ideal for assessing the performance of automatic seizure detection methods in realistic settings.
CODA-19 is a human-annotated dataset that denotes the Background, Purpose, Method, Finding/Contribution, and Other for 10,966 English abstracts in the COVID-19 Open Research Dataset.