The ISIC 2017 dataset was published by the International Skin Imaging Collaboration (ISIC) as a large-scale dataset of dermoscopy images. The Task 3 challenge dataset for lesion classification contains 2,000 images for training including 374 melanoma, 254 seborrheic keratosis and the remainder as benign nevi (1372). Source: https://challenge.isic-archive.com/landing/2017/42 Image Source: https://challenge.isic-archive.com/landing/2017/44

The Kvasir-SEG dataset includes 196 polyps smaller than 10 mm classified as Paris class 1 sessile or Paris class IIa. We have selected it with the help of expert gastroenterologists. We have released this dataset separately as a subset of Kvasir-SEG. We call this subset Kvasir-Sessile. The dataset is publicly available. It can be downloaded from here: https://drive.google.com/drive/folders/1OjsStQh6yuKz0bG6OA3BzmIiXDZILg7V?usp=sharing If you use this dataset, please cite our paper, https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9314114 /https://arxiv.org/pdf/1911.07069.pdf if you use our dataset,

The RITE (Retinal Images vessel Tree Extraction) is a database that enables comparative studies on segmentation or classification of arteries and veins on retinal fundus images, which is established based on the public available DRIVE database (Digital Retinal Images for Vessel Extraction). RITE contains 40 sets of images, equally separated into a training subset and a test subset, the same as DRIVE. The two subsets are built from the corresponding two subsets in DRIVE. For each set, there is a fundus photograph, a vessel reference standard, and a Arteries/Veins (A/V) reference standard. * The fundus photograph is inherited from DRIVE. * For the training set, the vessel reference standard is a modified version of 1st_manual from DRIVE. * For the test set, the vessel reference standard is 2nd_manual from DRIVE. * For the A/V reference standard, four types of vessels are labelled using four colors based on the vessel reference standard. * Arteries are labelled in red; veins are labelled in blue; the overlapping of arteries and veins are labelled in green; the vessels which are uncertain are labelled in white. * The fundus photograph is in tif format. And the vessel reference standard and the A/V reference standard are in png format. The dataset is described in more detail in our paper, which you will cite if you use the dataset in any way: Hu Q, Abràmoff MD, Garvin MK. Automated separation of binary overlapping trees in low-contrast color retinal images. Med Image Comput Comput Assist Interv. 2013;16(Pt 2):436-43. PubMed PMID: 24579170 https://doi.org/10.1007/978-3-642-40763-5_54

Inolves an annotated a large number of cells, including normal epithelial and myoepithelial breast cells (localized in ducts and lobules), invasive carcinomatous cells, fibroblasts, endothelial cells, adipocytes, macrophages and inflammatory cells (lymphocytes and plasmocytes). In total, our data set consists of 50 images with a total of 4022 annotated cells, the maximum number of cells in one sample is 293 and the minimum number of cells in one sample is 5, with an average of 80 cells per sample and a high standard deviation of 58. The annotation was performed by three experts: an expert pathologist and two trained research fellows. Each sample was annotated by one of the annotators, checked by another one and in case of disagreement, a consensus was established by discussion among the 3 experts. Source: https://zenodo.org/record/1175282#.YMisCTZKgow Image source: https://zenodo.org/record/1175282#.YMisCTZKgow

A whole-body FDG-PET/CT dataset with manually annotated tumor lesions (FDG-PET-CT-Lesions) 1,014 studies (900 patients)

MICCAI Challenge on Circuit Reconstruction from Electron Microscopy Images. # About The goal of this challenge is to evaluate algorithms for automatic reconstruction of neurons and neuronal connectivity from serial section electron microscopy data. The comparison is performed not only by evaluating the quality of neuron segmentations, but also by assessing the accuracy of detecting synapses and identifying synaptic partners. The challenge is carried out on three large and diverse datasets from adult Drosophila melanogaster brain tissue, comprising neuron segmentation ground truth and annotations for synaptic connections. A successful solution would demonstrate its efficiency and generalizability, and carry great potential to reduce the time spent on manual reconstruction of neural circuits in electron microscopy volumes. # Description We provide three datasets, each consisting of two (5 μm)3 volumes (training and testing, each 1250 px × 1250 px × 125 px) of serial section EM of the adult fly brain. Each volume has neuron and synapse labelings and annotations for pre- and post-synaptic partners.

Click to add a brief description of the dataset (Markdown and LaTeX enabled). Provide: * a high-level explanation of the dataset characteristics * explain motivations and summary of its content * potential use cases of the dataset

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. The validation and test sets consist of 234 chest X-rays from 200 patients and 668 chest X-rays from 500 patients, respectively. The 10 pathologies of interest are Atelectasis, Cardiomegaly, Consolidation, Edema, Enlarged Cardiomediastinum, Lung Lesion, Lung Opacity, Pleural Effusion, Pneumothorax, and Support Devices. For more details, please see our paper, Benchmarking saliency methods for chest X-ray interpretation.

Fetoscopic Placental Vessel Segmentation and Registration (FetReg) is a large-scale multi-centre dataset for the development of generalized and robust semantic segmentation and video mosaicking algorithms for the fetal environment with a focus on creating drift-free mosaics from long duration fetoscopy videos.

GFP-GOWT1 mouse stem cells Dr. E. Bártová. Institute of Biophysics, Academy of Sciences of the Czech Republic, Brno, Czech Republic

HeLa cells stably expressing H2b-GFP Mitocheck Consortium

The dataset contains a Video capsule endoscopy dataset for polyp segmentation. The dataset can be downloaded from here: https://www.kaggle.com/debeshjha1/kvasircapsuleseg https://www.dropbox.com/home/KvasirCapsule-SEG The detail about the dataset can be found from https://arxiv.org/pdf/2104.11138.pdf

The “Medico automatic polyp segmentation challenge” aims to develop computer-aided diagnosis systems for automatic polyp segmentation to detect all types of polyps (for example, irregular polyp, smaller or flat polyps) with high efficiency and accuracy. The main goal of the challenge is to benchmark semantic segmentation algorithms on a publicly available dataset, emphasizing robustness, speed, and generalization. Medico Multimedia Task at MediaEval 2020:Automatic Polyp Segmentation (https://arxiv.org/pdf/2012.15244.pdf)

Polyps in the colon are widely known cancer precursors identified by colonoscopy. Whilst most polyps are benign, the polyp’s number, size and surface structure are linked to the risk of colon cancer. Several methods have been developed to automate polyp detection and segmentation. However, the main issue is that they are not tested rigorously on a large multicentre purpose-built dataset, one reason being the lack of a comprehensive public dataset. As a result, the developed methods may not generalise to different population datasets. To this extent, we have curated a dataset from six unique centres incorporating more than 300 patients. The dataset includes both single frame and sequence data with 3762 annotated polyp labels with precise delineation of polyp boundaries verified by six senior gastroenterologists. To our knowledge, this is the most comprehensive detection and pixel-level segmentation dataset (referred to as PolypGen) curated by a team of computational scientists and expert gastroenterologists. The paper provides insight into data construction and annotation strategies, quality assurance, and technical validation.

The human brain receives nutrients and oxygen through an intricate network of blood vessels. Pathology affecting small vessels, at the mesoscopic scale, represents a critical vulnerability within the cerebral blood supply and can lead to severe conditions, such as Cerebral Small Vessel Diseases. The advent of 7 Tesla MRI systems has enabled the acquisition of higher spatial resolution images, making it possible to visualise such vessels in the brain. However, the lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. To address this, the SMILE-UHURA challenge was organised. This challenge, held in conjunction with the ISBI 2023, in Cartagena de Indias, Colombia, aimed to provide a platform for researchers working on related topics. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. This dataset was created through a combination of automated pre-segmentation and extensive manual refinement.

The archive contains original images from U2OS cells stained with Hoechst 33342 as PNG files. It also contains images (as Photoshop and GIMP files) showing hand-segmentation of the Hoechst images into regions containing single nuclei.

The Leuven-Haifa dataset contains 240 disc-centered fundus images of 224 unique patients (75 patients with normal tension glaucoma, 63 patients with high tension glaucoma, 30 patients with other eye diseases and 56 healthy controls) from the University Hospitals of Leuven. The arterioles and venules of these images were both annotated by master students in medicine and corrected by a senior annotator. All senior segmentation corrections are provided as well as the junior segmentations of the test set. An open-source toolbox for the parametrization of segmentations was developed. Diagnosis, age, sex, vascular parameters as well as a quality score are provided as metadata. Potential reuse is envisioned as the development or external validation of blood vessels segmentation algorithms or study of the vasculature in glaucoma and the development of glaucoma diagnosis algorithms. The dataset is available on the KU Leuven Research Data Repository (RDR).

The Vocal Folds dataset is a dataset for automatic segmentation of laryngeal endoscopic images. The dataset consists of 8 sequences from 2 patients containing 536 hand segmented in vivo colour images of the larynx during two different resection interventions with a resolution of 512x512 pixels. Source: https://github.com/imesluh/vocalfolds Image Source: https://github.com/imesluh/vocalfolds

The platelet-em dataset contains two 3D scanning electron microscope (EM) images of human platelets, as well as instance and semantic segmentations of those two image volumes. This data has been reviewed by NIBIB, contains no PII or PHI, and is cleared for public release. All files use a multipage uint16 TIF format. A 3D image with size [Z, X, Y] is saved as Z pages of size [X, Y]. Image voxels are approximately 40x10x10 nm

Introduction Iris is considered one of the most accurate and reliable biometric modality. Iris is more stable and distinctive compared with fingerprint, face, voice, etc, and difficult to be replicated for spoof attacks. Although an iris pattern is naturally an ideal identifier, the development of a high-performance iris recognition algorithm and transferring it from laboratory to field application is still a challenging task. In practical applications, the iris recognition system must face various unpredictable iris image degraded. For example, recognition of low-quality iris images, non-cooperative iris images, long-range iris images, and moving iris images are all huge problems in iris recognition. We believe that the first step in solving these problems is to design and develop a database of iris images that includes all of these degraded. # Brief Descriptions and Statistics of the Database CASIA-Iris-Complex contains 22,932 images from 292 Asian subjects. It includes two subsets: CASIA-Iris-CX1 and CASIA-Iris-CX2. All images were collected under NIR illumination and two eyes were captured simultaneously.

The dataset available for download on this webpage represents a 5x5x5µm section taken from the CA1 hippocampus region of the brain, corresponding to a 1065x2048x1536 volume. The resolution of each voxel is approximately 5x5x5nm. The data is provided as multipage TIF files that can be loaded in Fiji. We annotated mitochondria in two sub-volumes. Each sub-volume consists of the first 165 slices of the 1065x2048x1536 image stack. The volume used for training our algorithm in the publications mentionned at the bottom of this page is the top part while the bottom part was used for testing. Although our line of research was primarily motivated by the need to accurately segment mitochondria and synapses, other structures are of interest for neuroscientists such as vesicles or cell boundaries. This dataset was acquired by Graham Knott and Marco Cantoni at EPFL. It is made publicly available in the hope of encouraging similar sharing of useful data amongst researchers and also accelerating neuroscientific research.

A challenge that consists of three tasks, each targeting a different requirement for in-clinic use. The first task involves classifying images from the GI tract into 23 distinct classes. The second task focuses on efficiant classification measured by the amount of time spent processing each image. The last task relates to automatcially segmenting polyps. Source: EndoTect Challenge Please cite "The EndoTect 2020 Challenge: Evaluation andComparison of Classification, Segmentation and Inference Time for Endoscopy" if you use the dataset.

EPISURG is a clinical dataset of $T_1$-weighted magnetic resonance images (MRI) from 430 epileptic patients who underwent resective brain surgery at the National Hospital of Neurology and Neurosurgery (Queen Square, London, United Kingdom) between 1990 and 2018. The NIfTI files are anonymised and the images have been defaced to further protect the patients' identity. The dataset comprises 430 postoperative MRI. The corresponding preoperative MRI is present for 269 subjects. Three human raters segmented the resection cavity on partially overlapping subsets of EPISURG: - Rater 1: 133 subjects (researcher in neuroimaging) - Rater 2: 34 subjects (clinical research fellow) - Rater 3: 33 subjects (neurologist) ## Acknowledgements If you use this dataset for your research please cite the following publications: Pérez-García F., Rodionov R., Alim-Marvasti A., Sparks R., Duncan J.S., Ourselin S. (2020) Simulation of Brain Resection for Cavity Segmentation Using Self-supervised and Semi-supervised Learning. In: Martel A.L. et al. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. Lecture Notes in Computer Science, vol 12263. Springer, Cham. https://doi.org/10.1007/978-3-030-59716-0_12 Pérez-García F., Rodionov R., Alim-Marvasti A., Sparks R., Duncan J.S., Ourselin S. EPISURG: MRI dataset for quantitative analysis of resective neurosurgery for refractory epilepsy. University College London (2020). DOI 10.5522/04/9996158.v1 ## Graphical user interface (GUI) The 3D Slicer extension EPISURG may be used to visualise the dataset. ## Data use agreement The EPISURG data are distributed to the greater scientific community under the following terms: 1. You will not attempt to establish the identity or to make contact with any of the included subjects. 2. You will acknowledge the use of EPISURG data and data derived from EPISURG data when publicly presenting any results or algorithms that benefitted from their use. Papers, book chapters, books, posters, oral presentations, and all other printed and digital presentations of results derived from EPISURG data should cite the publications listed above. 3. You will not further disclose these data beyond the uses outlined in this agreement and understand that redistribution of data in any manner is prohibited. 4. You will require anyone on your team who uses these data, or anyone with whom you share these data to comply with this data use agreement.

Deep learning use for quantitative image analysis is exponentially increasing. However, training accurate, widely deployable deep learning algorithms requires a plethora of annotated (ground truth) data. Image collections must contain not only thousands of images to provide sufficient example objects (i.e. cells), but also contain an adequate degree of image heterogeneity. We present a new dataset, EVICAN-Expert visual cell annotation, comprising partially annotated grayscale images of 30 different cell lines from multiple microscopes, contrast mechanisms and magnifications that is readily usable as training data for computer vision applications. With 4600 images and ∼26 000 segmented cells, our collection offers an unparalleled heterogeneous training dataset for cell biology deep learning application development. The dataset is freely available (https://edmond.mpdl.mpg.de/imeji/collection/l45s16atmi6Aa4sI?q=).

The fetoscopy placenta dataset is associated with our MICCAI2020 publication titled “Deep Placental Vessel Segmentation for Fetoscopic Mosaicking”. The dataset contains 483 frames with ground-truth vessel segmentation annotations taken from six different in vivo fetoscopic procedure videos. The dataset also includes six unannotated in vivo continuous fetoscopic video clips (950 frames) with predicted vessel segmentation maps obtained from the leave-one-out cross-validation of our method. For ground-truth vessel annotation, we selected the non-occluded (no fetus or tool presence) frames through a separate frame-level fetoscopic event identification approach Bano:IJCARS2020. We annotate a binary mask for vessel segmentation using the Pixel Annotation Tool.

Automated measurement of fetal head circumference using 2D ultrasound images

The ISIC 2017 dataset was published by the International Skin Imaging Collaboration (ISIC) as a large-scale dataset of dermoscopy images. The Task 2 challenge dataset for lesion dermoscopic feature extraction contains the original lesion image, a corresponding superpixel mask, and superpixel-mapped expert annotations of the presence and absence of the following features: (a) network, (b) negative network, (c) streaks and (d) milia-like cysts. Source: https://challenge.isic-archive.com/landing/2017/43 Image Source: https://challenge.isic-archive.com/landing/2017/43

This database is provided and maintained by Dr. Gregory C Sharp (Harvard Medical School – MGH, Boston) and his group. The data here provided have been used for the “Head and Neck Auto Segmentation MICCAI Challenge (2015)”. To cite the challenge or the data, please refer to: Raudaschl, P. F., Zaffino, P., Sharp, G. C., Spadea, M. F., Chen, A., Dawant, B. M., … & Jung, F. (2017). Evaluation of segmentation methods on head and neck CT: Auto‐segmentation challenge 2015. Medical Physics, 44(5), 2020-2036. PDDCA version 1.4.1 comprises 48 patient CT images from the Radiation Therapy Oncology Group (RTOG) 0522 study (a multi-institutional clinical trial led by Dr Kian Ang), together with manual segmentation of left and right parotid glands, brainstem, optic chiasm, optic nerves (both left and right), mandible, submandibular glands (both left and right) and manual identification of bony landmarks. We give this data to the community in the hopes that it will be helpful. Any errors in delineation and markup are ours, and are not the fault of participating doctors. Please see pddca.odt for complete information. For practical reasons the database is split in 3 zipped files. Part 3 contains images with some of the above listed structures missing. Details regarding the Challenge Train/Test Splits can be found in the dataset description

The archive contains original images from NIH3T3 cells stained with Hoechst 33342 as PNG files. It also contains images (as Photoshop and GIMP files) showing hand-segmentation of the Hoechst images into regions containing single nuclei.

Glioblastoma-astrocytoma U373 cells on a polyacrylamide substrate Dr. S. Kumar. Department of Bioengineering, University of California at Berkeley, Berkeley CA (USA)

DOI This mouse cerebellar atlas can be used for mouse cerebellar morphometry. We recommend to use Multi Atlas Segmentation and Morphometric analysis toolkit (MASMAT) for mouse brain MRI along with other mouse brain atlases in this repo. ## Reference/citation: - If you're using the this mouse MRI cerebellar atlas in your paper, we ask you to please kindly cite the following papers: - Ma, D., Cardoso, M. J., Zuluaga, M. A., Modat, M., Powell, N. M., Wiseman, F. K., Cleary, J. O., Sinclair, B., Harrison, I. F., Siow, B., Popuri, K., Lee, S., Matsubara, J. A., Sarunic, M. V, Beg, M. F., Tybulewicz, V. L. J., Fisher, E. M. C., Lythgoe, M. F., & Ourselin, S. (2020). Substantially thinner internal granular layer and reduced molecular layer surface in the cerebellum of the Tc1 mouse model of Down Syndrome – a comprehensive morphometric analysis with active staining contrast-enhanced MRI. NeuroImage, 117271. https://doi.org/https://doi.org/10.1016/j.neuroimage.2020.117271 - Ma, D., Cardoso, M. J., Zuluaga, M. A., Modat, M., Powell, N., Wiseman, F., Tybulewicz, V., Fisher, E., Lythgoe, M. F., & Ourselin, S. (2015). Grey Matter Sublayer Thickness Estimation in the Mouse Cerebellum. In Medical Image Computing and Computer Assisted Intervention 2015 (pp. 644–651). https://doi.org/10.1007/978-3-319-24574-4_77

This collection comprises multi-parametric magnetic resonance imaging (mpMRI) scans for de novo Glioblastoma (GBM) patients from the University of Pennsylvania Health System, coupled with patient demographics, clinical outcome (e.g., overall survival, genomic information, tumor progression), as well as computer-aided and manually-corrected segmentation labels of multiple histologically distinct tumor sub-regions, computer-aided and manually-corrected segmentations of the whole brain, a rich panel of radiomic features along with their corresponding co-registered mpMRI volumes in NIfTI format. Scans were initially skull-stripped and co-registered, before their tumor segmentation labels were produced by an automated computational method. These segmentation labels were revised and any label misclassifications were manually corrected/approved by expert board-certified neuroradiologists. The final labels were used to extract a rich panel of imaging features, including intensity, volumetric, morphologic, histogram-based and textural parameters. The segmentation labels enable quantitative computational and clinical studies without the need to repeat manual annotations whilst allowing for comparison across studies. They can also serve as a set of manually-annotated gold standard labels for performance evaluation in computational challenges. The provided panel of radiomic features may facilitate research integrative of the molecular characterization offered, and hence allow associations with molecular markers (radiogenomic biomarker research), clinical outcomes, treatment responses and other endpoints, by researchers without sufficient computational background to extract such features. Additional data accompanying the UPENN-GBM data collection include H&E-stained digitized tissue sections from resected tumor specimens of matched de novo and recurrent cases for a few of the patients in this collection.

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. Brain sections were obtained using a vibratome (Leica VT1000S, Leica Biosystems, Buffalo Grove, IL) and cerebral cortex in 40 μm thick sagittal sections spaced 320 μm apart medial to lateral from brains of each genotype. Staining was performed with rabbit anti-ionized calcium-binding adaptor molecule 1 (Iba-1) IgG (1:125; Wako) with secondary antibody Fluorescein isothiocyanate (FITC). For quantification of Iba-1 stained microglia, cell bodies were counted in the cerebral cortex from three fields of view for three sections each per animal. Between 2 and 3 images were collected per field of view to capture as many cells as possible in sufficient focus for identification. Images were acquired at 10X magnification and pixel resolution 1280x1280 and cropped to 1280x733 pixel area to exclude irregular tissue edges. For more details, please refer to ACCT is a fast and accessible automatic cell counting tool using machine learning for 2D image segmentation. We note that this data repository links to some images gathered in the fluocells (Fluorescent Neuronal Cells) dataset introduced by Morelli et al. which can be found here: https://paperswithcode.com/dataset/fluocells. We provide a link to our automatic cell counting tool that this dataset was used for here at the following Github link: https://github.com/tkataras/Automatic-Cell-Counting-with-TWS.

The AneuX morphology database includes data from 3 different data sources: AneuX, @neurIST and Aneurisk. The AneuX data consists of two portions AneuX1 and AneuX2, which have extracted by two different teams of data curators. The datasets differ in the exact case selection, but represent a very similar patient cohort (patients examined or treated for ruptured or unruptured aneurysms at the The dataset consists of totally 750 aneurysm domes. The geometries were all extracted from 3D rotational angiographies using different vessel lumen segmentation techniques.

A multi-tasking oral ulcer dataset (Autooral dataset) is proposed. Autooral dataset contains two major tasks of disease segmentation and classification. The labeling of the Autooral dataset was done by three experienced dentists. At the end of the annotation, we formed 420 images of oral data with high quality after cropping and removal operations. We standardize the image size to 256*256. The original image is a 24-bit RGB image, the ground truth for the segmentation task is an 8-bit image, and there are five different disease types for the classification task (including cancerous ulcers, traumatic ulcers and traumatic blood blisters, herpes-like aphthous ulcers, mild aphthous ulcers, severe aphthous ulcers). The ratio of the 5 different ulcer types for the classification task was 9:9:15:18:22 (with a few exclusions). Further, by chi-square test, there were significant differences in gender (p=0.04) and age (p=0.01) of the patients among the 5 ulcer types. All-age coverage, a 13-year collection interval, and the presence of 12 underlying diseases, among other things, demonstrated that we had sufficient sample diversity.