ICIAR 2018

Can you develop a method for automatic detection of cancerous regions in breast cancer histology images?

DRIVE

Develop a system to automatically segment vessels in human retina fundus images.

REFUGE

The goal of the Retinal Fundus Glaucoma Challenge (REFUGE) is to evaluate and compare automated algorithms for glaucoma detection and optic disc/cup segmentation on a common dataset of retinal fundus images.

CHAOS

In this challenge, you segment the liver in CT data, and segment liver, spleen, and kidneys in MRI data.

ACDC-LungHP

Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology

iChallenge-AMD

Age-related Macular Degeneration Challenge

ODIR-2019

北京大学国际眼底图像智能识别竞赛 Peking University International Competition on Ocular Disease Intelligent Recognition

HEROHE

Unlike previous challenges, this proposes to find an image analysis algorithm to identify HER2-positive from HER2-negative breast cancer specimens evaluating only the morphological features present on the HE slide, without the staining patterns of IHC.

EndoCV2020

Endoscopy computer vision challenge (EndoCV2020) introduces two core sub-themes in endoscopy: 1) artefact detection and segmentation (EAD2020) and 2) disease detection and segmentation (EDD2020).

LNDb Challenge

Lung cancer screening and Fleischner follow-up determination in chest CT through nodule detection, segmentation and characterization

VerSe'20

Vertebrae labelling and segmentation on a multi-centre, multi-scanner, and anatomically-diverse CT dataset.

RibFrac

Rib Fracture Detection and Classification Challenge: A large-scale benchmark of 660 CT scans with ~5,000 rib fractures (around 80Gb)

Thyroid Nodule Segmentation and Classification

The main topic of this TN-SCUI2020 challenge is finding automatic algorithms to accurately classify the thyroid nodules in ultrasound images. It will provide the biggest public dataset of thyroid nodule with over 4500 patient cases from different ages, genders, and were collected using different ultrasound machines. Each ultrasound image is provided with its ground truth class (benign or maglinant) and a detailed delineation of the nodule. This challenge will provide a unique opportunity for participants from different backgrounds (e.g. academia, industry, and government, etc.) to compare their algorithms in an impartial way.

Learn2Reg

Challenge on medical image registration addressing: learning from small datasets; estimating large deformations; dealing with multi-modal scans; and learning from noisy annotations

SARAS-ESAD

This challenge is part of Medical Imaging with Deep Learning conference, 2020. The conference is held between 6 ‑ 8 July 2020 in Montréal. The SARAS (Smart Autonomous Robotic Assistant Surgeon) EU consortium, www.saras-project.eu, is working towards replacing the assistant surgeon in MIS with two assistive robotic arms. To accomplish that, an artificial intelligence based system is required which not only can understand the complete surgical scene but also detect the actions being performed by the main surgeon. This information can later be used infer the response required from the autonomous assistant surgeon.

SurgVisDom

CADA

Cerebral aneurysms are local dilations of arterial blood vessels caused by a weakness of the vessel wall. Subarachnoid hemorrhage (SAH) caused by the rupture of a cerebral aneurysm is a life-threatening condition associated with high mortality and morbidity. The mortality rate is above 40%, and even in case of survival cognitive impairment can affect patients for a long time. Major goals in image analysis are the detection and risk assessment of aneurysms. We, therefore, subdivided the challenge into three categories. The first task is finding the aneurysm; the second task is the accurate segmentation to allow for a longitudinal assessment of the development of suspicious aneurysms. The third task is the estimation of the rupture risk of the aneurysm.

Diabetic Foot Ulcer Challenge 2020

Diabetic Foot Ulcer Challenge 2020

CT diagnosis of COVID-19

Coronavirus disease 2019 (COVID-19) has infected more than 1.3 million individuals all over the world and caused more than 106,000 deaths. One major hurdle in controlling the spreading of this disease is the inefficiency and shortage of medical tests. To mitigate the inefficiency and shortage of existing tests for COVID-19, we propose this competition to encourage the development of effective Deep Learning techniques to diagnose COVID-19 based on CT images. The problem we want to solve is to classify each CT image into positive COVID-19 (the image has clinical findings of COVID-19) or negative COVID-19 ( the image does not have clinical findings of COVID-19). It’s a binary classification problem based on CT images.

CADA - Rupture Risk Estimation

Cerebral aneurysms are local dilations of arterial blood vessels caused by a weakness of the vessel wall. Subarachnoid hemorrhage (SAH) caused by the rupture of a cerebral aneurysm is a life-threatening condition associated with high mortality and morbidity. The mortality rate is above 40%, and even in case of survival cognitive impairment can affect patients for a long time. Major goals in image analysis are the detection and risk assessment of aneurysms. We, therefore, subdivided the challenge into three categories. The first task is finding the aneurysm; the second task is the accurate segmentation to allow for a longitudinal assessment of the development of suspicious aneurysms. The third task is the estimation of the rupture risk of the aneurysm.

CADA - Aneurysm Segmentation

Cerebral aneurysms are local dilations of arterial blood vessels caused by a weakness of the vessel wall. Subarachnoid hemorrhage (SAH) caused by the rupture of a cerebral aneurysm is a life-threatening condition associated with high mortality and morbidity. The mortality rate is above 40%, and even in case of survival cognitive impairment can affect patients for a long time. Major goals in image analysis are the detection and risk assessment of aneurysms. We, therefore, subdivided the challenge into three categories. The first task is finding the aneurysm; the second task is the accurate segmentation to allow for a longitudinal assessment of the development of suspicious aneurysms. The third task is the estimation of the rupture risk of the aneurysm.

QUBIQ

Quantification of Uncertainties in Biomedical Image Segmentation Challenge

LoDoPaB-CT

Low-Dose CT reconstruction in the setting of the LoDoPaB-CT dataset.

RIADD (ISBI-2021)

Retinal Image Analysis for multi-Disease Detection

MitoEM

Large-scale 3D mitochondria instance segmentation benchmark

A-AFMA

Prenatal ultrasound (US) measurement of amniotic fluid is an important part of fetal surveillance as it provides a non-invasive way of assessing whether there is oligohydramnios (insufficient amniotic fluid) and polyhydramnios (excess amniotic fluid), which are associated with numerous problems both during pregnancy and after birth. In this Image Analysis Challenge, we aim to attract attention from the image analysis community to work on the problem of automated measurement of the MVP using the predefined ultrasound video clip based on a linear-sweep protocol [1]. We define two tasks. The first task is to automatically detect amniotic fluid and the maternal bladder. The second task is to identify the appropriate points for MVP measurement given the selected frame of the video clip, and calculate the length of the connected line between these points. The data was collected from women in the second trimester of pregnancy, as part of the PURE study at the John Radcliffe Hospital in Oxford, UK.

COVID-19 LUNG CT LESION SEGMENTATION CHALLENGE - 2020

This challenge will create the platform to evaluate emerging methods for the segmentation and quantification of lung lesions caused by SARS-CoV-2 infection from CT images.

Where is VALDO?

Vascular Lesion Detection Challenge at MICCAI 2021

SegPC-2021

This challenge is positioned towards robust segmentation of cells which is the first stage to build such a tool for plasma cell cancer, namely, Multiple Myeloma (MM), which is a type of blood cancer.

EndoCV2021

Endoscopy Computer Vision Challenge 2021

Foot Ulcer Segmentation Challenge

Carotid Artery Vessel Wall Segmentation Challenge

To segment the vessel wall of the carotid artery on black-blood MRI images

Cross-Modality Domain Adaptation Image Segmentation - 2021

The CrossMoDA challenge 2021 introduces the first large and multi-class medical dataset for unsupervised cross-modality Domain Adaptation.

BrainPTM 2021

Brain Pre-surgical Tractography Mapping (BrainPTM) in real clinical scans.

RealNoiseMRI

Brain MRI reconstruction challenge with realistic noise

PAIP2021

PAIP 2021 Challenge; Perineural invasion in multiple organ cancer (colon, prostate and pancreatobiliary tract)

FLARE21

Fast and Low GPU memory Abdominal oRgan sEgmentation Challenge

Breast Cancer Segmentation

Semantic segmentation of histologic regions in scanned FFPE H&E stained slides of triple-negative breast cancer from The Cancer Genome Atlas. See: Amgad M, Elfandy H, ..., Gutman DA, Cooper LAD. Structured crowdsourcing enables convolutional segmentation of histology images. Bioinformatics. 2019. doi: 10.1093/bioinformatics/btz083

FeTA - Fetal Tissue Annotation Challenge

Fetal Tissue Annotation Challenge

fastPET-LD

The purpose of this challenge is the detection of “hot spots” in fast PET scan, that is locations that have an elevated standard uptake value (SUV) and potential clinical significance. Corresponding CT scans are also provided. The ground truth, common to both datasets, was generated by a nuclear medicine expert. It consists of a 3-D segmentation map of the hot spots as well as a text file containing the position and size of 3D cuboid bounding box for each hot spot.

NODE21

NODE21: generate and detect nodules on chest radiographs

WSSS4LUAD

The WSSS4LUAD dataset contains over 10,000 patches of lung adenocarcinoma from whole slide images from Guangdong Provincial People's Hospital and TCGA with image-level annotations. The goal of this challenge is to perform semantic segmentation for differentiating three important types of tissues in the WSIs of lung adenocarcinoma, including cancerous epithelial region, cancerous stroma region and normal region. Paticipants have to use image-level annotations to give pixel-level prediction.

QUBIQ2021

Quantification of Uncertainties in Biomedical Image Segmentation Challenge 2021

MIDOG Challenge 2021

Mitosis Domain Generalization Challenge 2021 (part of MICCAI 2021)

STOIC2021 - COVID-19 AI Challenge

COVID-19 Artificial Intelligence Challenge: automated diagnosis, and prognostic evaluation based on computed tomography

Chest XR COVID-19 detection

Build AI models to detect COVID-19 using Chest X-ray images

The PI-CAI Challenge

Artificial Intelligence and Radiologists at Prostate Cancer Detection in MRI

AIROGS

Artificial Intelligence for RObust Glaucoma Screening Challenge

CoNIC 2022

Colon Nuclei Identification and Counting Challenge 2022

MELA2022

MICCAI 2022 MELA Challenge: A Large-Scale Detection Benchmark of 1,100 CT Scans for Mediastinal Lesion Analysis

BCNB

Early Breast Cancer Core-Needle Biopsy WSI Dataset

ATLAS R2.0 - Stroke Lesion Segmentation

Anatomical Tracings of Lesions After Stroke

SynthRAD2023

SynthRAD is the first challenge on automatic generation of synthetic computed tomography (sCT) for radiotherapy

autoPET

Automatic lesion segmentation in whole-body FDG-PET/CT

ACROBAT 2023

The ACROBAT challenge aims to advance the development of WSI registration algorithms that can align WSIs of IHC-stained breast cancer tissue sections to corresponding tissue regions that were stained with H&E. All WSIs originate from routine diagnostic workflows.

Surface Learning for Clinical Neuroimaging

Prediction of developmental phenotypes (age at birth and cognitive test scores) from cortical surface imaging data

Preoperative to Intraoperative Laparoscopy Fusion

Preoperative to Intraoperative Laparoscopy Fusion

Diabetic Retinopathy Analysis Challenge MICCAI2022

Diabetic Retinopathy (DR) lesions segmentation, image quality assessment and classification of proliferatived DR (PDR) and non-PDR in ultra-wide optical coherence tomography angiography mosaic (UW-OCTA-M) images

Multi-Modality Abdominal Multi-Organ Segmentation Challenge 2022

Brain shift with Intraoperative Ultrasound - Segmentation tasks

Multi-site, Multi-Domain Airway Tree Modeling (ATM’22)

Airway segmentation is a crucial step for the analysis of pulmonary diseases including asthma, bronchiectasis, and emphysema. The accurate segmentation based on X-Ray computed tomography (CT) enables the quantitative measurements of airway dimensions and wall thickness, which can reveal the abnormality of patients with chronic obstructive pulmonary disease (COPD). Besides, the extraction of patient-specific airway models from CT images is required for navigatiisted surgery.

Shifts Challenge 2022

The goal of the Shifts Challenge 2022 is to raise awareness among the research community about the problems of distributional shift, robustness, and uncertainty estimation, and to identify new solutions to address them. The competition will consist of two new tracks: White Matter Multiple Sclerosis (MS) lesion segmentation in 3D Magnetic Resonance Imaging (MRI) of the brain and Marine cargo vessel power estimation.

ACMMM MEGC2022: Facial Micro-Expression Grand Challenge

Spotting Facial Macro- and Micro-Expressions in Long Videos

Cell Segmentation in Multi-modality Microscopy Images

Weakly Supervised Cell Segmentation in Multi-modality High-resolution Microscopy Images

PAIP 2023: TC prediction in pancreatic and colon cancer

Tumor cellularity prediction in pancreatic cancer (supervised learning) and colon cancer (transfer learning)

SNEMI3D: 3D Segmentation of neurites in EM images

The challenge is organized in the context of the IEEE International Symposium on Biomedical Imaging, 2013. The old evaluation site (http://brainiac2.snemi3d.org/SNEMI3D/) will be replaced by this one.

Robust Non-rigid Registration Challenge for Expansion Microscopy

Xray Projectomic Reconstruction Extracting Segment with Skeleton

autoPET-II

Automated Lesion Segmentation in PET/CT - Domain Generalization

Ultrasound Image Enhancement challenge 2023

Foundation Model Prompting for Medical Image Classification

The primary objective of this challenge is to promote the development and evaluation of model adaptation techniques for medical image classification to leverage the existing foundation models.

Low-dose Computed Tomography Perceptual Image Quality Assessment

PANORAMA

Artificial Intelligence and Radiologists at Pancreatic Cancer Diagnosis in CT

Justified Referral in AI Glaucoma Screening

The LEOPARD Challenge

AI4Life Microscopy Denoising Challenge

Wellcome to AI4Life-MDC24! In this challenge, we want to focus on an unsupervised denoising of microscopy images. By participating, researchers can contribute to a critical area of scientific research, aiding in interpreting microscopy images and potentially unlocking discoveries in biology and medicine.

Self-supervised learning for 3D light-sheet microscopy image seg

AIROGS Baseline

A baseline algorithm for the AIROGS challenge