Medical Image Segmentation

**CrossMoDA is a large and multi-class benchmark for unsupervised cross-modality Domain Adaptation. The goal of the challenge is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are commonly performed using contrast-enhanced T1 (ceT1) MR imaging.

The LIVECell (Label-free In Vitro image Examples of Cells) dataset is a large-scale microscopic image dataset for instance-segmentation of individual cells in 2D cell cultures. LIVECell consists of 5,239 manually annotated, expert-validated, Incucyte HD phase-contrast microscopy images with a total of 1,686,352 individual cells annotated from eight different cell types (average 313 cells per image). The LIVECell images have predefined splits into training (3188), validation (539) and test (1512) sets. Each split is also further subdivided into each of the eight cell types. The training set also has splits of different sizes (2, 4, 5, 25, 50%) to allow dataset size experimentation.

The dataset for this challenge was obtained by carefully annotating tissue images of several patients with tumors of different organs and who were diagnosed at multiple hospitals. This dataset was created by downloading H&E stained tissue images captured at 40x magnification from TCGA archive. H&E staining is a routine protocol to enhance the contrast of a tissue section and is commonly used for tumor assessment (grading, staging, etc.). Given the diversity of nuclei appearances across multiple organs and patients, and the richness of staining protocols adopted at multiple hospitals, the training datatset will enable the development of robust and generalizable nuclei segmentation techniques that will work right out of the box. Source: MoNuSeg

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. Notably, the origin SUN dataset has 113 colonoscopy videos, including 100 positive cases with 49, 136 polyp frames and 13 negative cases with 109, 554 non-polyp frames. It manually trims them into 378 positive and 728 negative short clips, meanwhile maintaining their intrinsic consecutive relationship. Such data pre-processing ensures each clip has around 3~11s duration at a real-time frame rate (i.e., 30 fps), which promotes the fault-tolerant margin for various algorithms and devices. To this end, the re-organized SUN-SEG contains 1, 106 short video clips with 158, 690 video frames totally, offering a solid foundation to build a representative benchmark. As such, it yields the final version of our SUN-SEG dataset, which includes 49,136 polyp frames (i.e., positive part) and 109,554 non-polyp frames (i.e., negative part) taken from different 285 and 728 colonoscopy videos clips, as well as the corresponding annotations.

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. Notably, the origin SUN dataset has 113 colonoscopy videos, including 100 positive cases with 49, 136 polyp frames and 13 negative cases with 109, 554 non-polyp frames. It manually trims them into 378 positive and 728 negative short clips, meanwhile maintaining their intrinsic consecutive relationship. Such data pre-processing ensures each clip has around 3~11s duration at a real-time frame rate (i.e., 30 fps), which promotes the fault-tolerant margin for various algorithms and devices. To this end, the re-organized SUN-SEG contains 1, 106 short video clips with 158, 690 video frames totally, offering a solid foundation to build a representative benchmark. As such, it yields the final version of our SUN-SEG dataset, which includes 49,136 polyp frames (i.e., positive part) and 109,554 non-polyp frames (i.e., negative part) taken from different 285 and 728 colonoscopy videos clips, as well as the corresponding annotations.

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. ## Challenge Tracks DICOM Track: The DICOM benchmarking track uses scanner-generated DICOM images as the input for image segmentation and detection tasks. Raw Data Track: The Raw Data benchmarking track uses raw MRI data (i.e. k-space) as the input for image reconstruction, segmentation and detection tasks.

The ISIC 2017 dataset was published by the International Skin Imaging Collaboration (ISIC) as a large-scale dataset of dermoscopy images. The Task 1 challenge dataset for lesion segmentation contains 2,000 images for training with ground truth segmentations (2000 binary mask images). Source: https://challenge.isic-archive.com/landing/2017/42 Image Source: https://challenge.isic-archive.com/landing/2017/42

A Benchmark for Robust Multi-Hop Spatial Reasoning in Texts

The CELL benchmark is made of fluorescence microscopy images of cell. Source: Multi-Domain Adversarial Learning Image Source: https://arxiv.org/pdf/1903.09239v1.pdf

HyperKvasir dataset contains 110,079 images and 374 videos where it captures anatomical landmarks and pathological and normal findings. A total of around 1 million images and video frames altogether.

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. Source: Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions Image Source: https://challenge2018.isic-archive.com/task3/

The LandCover.ai (Land Cover from Aerial Imagery) dataset is a dataset for automatic mapping of buildings, woodlands, water and roads from aerial images. ### Dataset features * land cover from Poland, Central Europe * three spectral bands - RGB * 33 orthophotos with 25 cm per pixel resolution (~9000x9500 px) * 8 orthophotos with 50 cm per pixel resolution (~4200x4700 px) * total area of 216.27 sq. km ### Dataset format * rasters are three-channel GeoTiffs with EPSG:2180 spatial reference system * masks are single-channel GeoTiffs with EPSG:2180 spatial reference system

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."

Autism spectrum disorder (ASD) is characterized by qualitative impairment in social reciprocity, and by repetitive, restricted, and stereotyped behaviors/interests. Previously considered rare, ASD is now recognized to occur in more than 1% of children. Despite continuing research advances, their pace and clinical impact have not kept up with the urgency to identify ways of determining the diagnosis at earlier ages, selecting optimal treatments, and predicting outcomes. For the most part this is due to the complexity and heterogeneity of ASD. To face these challenges, large-scale samples are essential, but single laboratories cannot obtain sufficiently large datasets to reveal the brain mechanisms underlying ASD. In response, the Autism Brain Imaging Data Exchange (ABIDE) initiative has aggregated functional and structural brain imaging data collected from laboratories around the world to accelerate our understanding of the neural bases of autism. With the ultimate goal of facilitating discovery science and comparisons across samples, the ABIDE initiative now includes two large-scale collections: ABIDE I and ABIDE II. Each collection was created through the aggregation of datasets independently collected across more than 24 international brain imaging laboratories and are being made available to investigators throughout the world, consistent with open science principles, such as those at the core of the International Neuroimaging Data-sharing Initiative. For details about these initiatives visit the collection specific pages: ABIDE I and ABIDE II.

We release expert-made scribble annotations for the medical ACDC dataset [1]. The released data must be considered as extending the original ACDC dataset. The ACDC dataset contains cardiac MRI images, paired with hand-made segmentation masks. It is possible to use the segmentation masks provided in the ACDC dataset to evaluate the performance of methods trained using only scribble supervision. References: [1] Bernard, Olivier, et al. "Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved?." IEEE transactions on medical imaging 37.11 (2018): 2514-2525.

The MM-WHS 2017 dataset is a dataset for multi-modality whole heart segmentation. It provides 20 labeled and 40 unlabeled CT volumes, as well as 20 labeled and 40 unlabeled MR volumes. In total there are 120 multi-modality cardiac images acquired in a real clinical environment.

The increasing incidence of melanoma has recently promoted the development of computer-aided diagnosis systems for the classification of dermoscopic images. The PH² dataset has been developed for research and benchmarking purposes, in order to facilitate comparative studies on both segmentation and classification algorithms of dermoscopic images. PH² is a dermoscopic image database acquired at the Dermatology Service of Hospital Pedro Hispano, Matosinhos, Portugal.

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.

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 via segmentation challenges. We anticipate that ATLAS v2.0 will lead to improved algorithms, facilitating large-scale stroke rehabilitation research. Official Paper: https://www.nature.com/articles/s41597-022-01401-7

Echocardiography, or cardiac ultrasound, is the most widely used and readily available imaging modality to assess cardiac function and structure. Combining portable instrumentation, rapid image acquisition, high temporal resolution, and without the risks of ionizing radiation, echocardiography is one of the most frequently utilized imaging studies in the United States and serves as the backbone of cardiovascular imaging. For diseases ranging from heart failure to valvular heart diseases, echocardiography is both necessary and sufficient to diagnose many cardiovascular diseases. In addition to our deep learning model, we introduce a new large video dataset of echocardiograms for computer vision research. The EchoNet-Dynamic database includes 10,030 labeled echocardiogram videos and human expert annotations (measurements, tracings, and calculations) to provide a baseline to study cardiac motion and chamber sizes.

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

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

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 ROBUST-MIS dataset was made available to support the Robust Medical Instrument Segmentation (ROBUST-MIS) Challenge 2019, part of the Endoscopic Vision Challenge associated with MICCAI. The goal of this challenge is the benchmarking of algorithms for medical instrument detection and segmentation with a specific emphasis on robustness and generalization capabilities of the methods. The challenge is based on the biggest annotated data set made available in the field at the time, comprising 10,000 annotated images that have been extracted from a total of 30 surgical procedures from three different surgery types. Data acquisition took place during daily routine procedures in: - rectal resection, - proctocolectomy and - UNKNOWN SURGERY (will be made public after the docker submission deadline) surgeries in the Heidelberg University Hospital, Department of Surgery. The resulting laparoscopic video data was then anonymized by excluding parts of the video displaying parts outside the abdomen. A training case encompasses a 10 second video snippet in form of 250 endoscopic image frames and a reference annotation for the last frame. In the annotated frame a “0” indicates the absence of a medical instrument and numbers “1”, “2“, ... represent different instances of medical instruments. The test cases are identical in format but do not include a reference annotation. UPDATE: While all training and test cases were used for the multiple instance detection task, cases not showing an instrument in the image were removed from training and test sets for the binary and multiple instance segmentation tasks.

The dataset is maintained by VISION AND IMAGE PROCESSING LAB, University of Waterloo. The images of the dataset were extracted from the public databases DermIS and DermQuest, along with manual segmentations of the lesions. The dataset was used in the following journal publication. [1] Glaister, J., A. Wong, and D. A. Clausi, "Automatic segmentation of skin lesions from dermatological photographs using a joint probabilistic texture distinctiveness approach", IEEE Transactions on Biomedical Engineering [2] Amelard, R., J. Glaister, A. Wong, and D. A. Clausi, "High-level intuitive features (HLIFs) for intuitive skin lesion descriptionpdf", IEEE Transactions on Biomedical Engineering, vol. 62, issue 3, pp. 820-831, October, 2015. [3] Glaister, J., R. Amelard, A. Wong, and D. A. Clausi, "MSIM: Multi-Stage Illumination Modeling of Dermatological Photographs for Illumination-Corrected Skin Lesion Analysis", IEEE Transactions on Biomedical Engineering, vol. 60, issue 7, pp. 1873 - 1883, November, 2013.

This dataset is a combination of the following three datasets : figshare, SARTAJ dataset and Br35H This dataset contains 7022 images of human brain MRI images which are classified into 4 classes: glioma - meningioma - no tumor and pituitary.

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.

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. The 2021 Kidney and Kidney Tumor Segmentation Challenge The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge

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. ARCADE: Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs Dataset Phase 1 consists of two datasets of XCA images for each of two tasks of ARCADE challenge. The first task includes in total 1200 coronary vessel tree images, which are divided into train(1000) and validation(200) groups, images for training are followed with annotations, depicting the division of a heart into 26 different regions based on the Syntax Score methodology[1]. Similarly, the second task includes a different set of 1200 images with same train-val division proportion with annotated regions containing atherosclerotic plaques. This dataset, carefully annotated by medical experts, enables scientists to actively contribute towards the advancement of an automated risk assessment system for patients with CAD.

The ISIC 2018 dataset was published by the International Skin Imaging Collaboration (ISIC) as a large-scale dataset of dermoscopy images. The Task 2 dataset is the challenge on lesion attribute detection. It includes 2594 images. The task is to detect the following dermoscopic attributes: pigment network, negative network, streaks, mila-like cysts and globules (including dots). Source: Bi-Directional ConvLSTM U-Net with Densley Connected Convolutions Image Source: https://challenge2018.isic-archive.com/task2/

The dataset contains 33,126 dermoscopic training images of unique benign and malignant skin lesions from over 2,000 patients. Each image is associated with one of these individuals using a unique patient identifier. All malignant diagnoses have been confirmed via histopathology, and benign diagnoses have been confirmed using either expert agreement, longitudinal follow-up, or histopathology. A thorough publication describing all features of this dataset is available in the form of a pre-print that has not yet undergone peer review. The dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Medical University of Vienna, Memorial Sloan Kettering Cancer Center, Melanoma Institute Australia, University of Queensland, and the University of Athens Medical School. The dataset was curated for the SIIM-ISIC Melanoma Classification Challenge hosted on Kaggle during the Summer of 2020. DOI: https://doi.org/10.34970/2020-ds01

The RAD-ChestCT dataset is a large medical imaging dataset developed by Duke MD/PhD Rachel Draelos during her Computer Science PhD supervised by Lawrence Carin. The full dataset includes 35,747 chest CT scans from 19,661 adult patients. The public Zenodo repository contains an initial release of 3,630 chest CT scans, approximately 10% of the dataset. This dataset is of significant interest to the machine learning and medical imaging research communities.

Intracranial hemorrhage (ICH) is a pathological condition characterized by bleeding inside the skull or brain, which can be attributed to various factors. Identifying, localizing and quantifying ICH has important clinical implications, in a bleed-dependent manner. While deep learning techniques are widely used in medical image segmentation and have been applied to the ICH segmentation task, existing public ICH datasets do not support the multi-class segmentation problem. To address this, we develop the Brain Hemorrhage Segmentation Dataset (BHSD), which provides a 3D multi-class ICH dataset containing 192 volumes with pixel-level annotations and 2200 volumes with slice-level annotations across five categories of ICH. To demonstrate the utility of the dataset, we formulate a series of supervised and semi-supervised ICH segmentation tasks. We provide experimental results with state-of-the-art models as reference benchmarks for further model developments and evaluations on this dataset.

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. Source: Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data Image source: Learning to Segment Brain Anatomy from 2D Ultrasound with Less Data

BRATS 2014 is a brain tumor segmentation dataset. Source: Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization Image Source: http://people.csail.mit.edu/menze/papers/proceedings_miccai_brats_2014.pdf

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 existing fully automated techniques for OAR segmentation in the HaN region from CT images that exploit the information of multiple imaging modalities so as to improve the accuracy of segmentation results.