PROMISE12

The goal of this challenge is to compare interactive and (semi)-automatic segmentation algorithms for MRI of the prostate.

LUNA16

The LUNA16 challenge: automatic nodule detection on chest CT

CAMELYON17

Automated detection and classification of breast cancer metastases in whole-slide images of histological lymph node sections. This task has high clinical relevance and would normally require extensive microscopic assessment by pathologists.

ICIAR 2018

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

IDRiD

This challenge evaluates automated techniques for analysis of fundus photographs. We target segmentation of retinal lesions like exudates, microaneurysms, and hemorrhages and detection of the optic disc and fovea. Also, we seek grading of fundus images according to the severity level of DR and DME.

LUMIC

The LUMIC challenge tests the accuracy in registration between pre- and post-contrast CT chest images for algorithms, using an anthropomophic digital phantom.

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.

PAVES

Peripheral Artery:Vein Enhanced Segmentation (PAVES) is the challenge focussed on providing easily interpretable and relevant images that can be readily understood by clinicians (vascular interventional radiologists & vascular surgeons) from MRA datasets where the venous and arterial vasculature may be equally enhanced. The setting is lower limb arterial occlusive disease where imaging of the below knee arterial vasculature is critical in planning limb salvage interventions. However, the competing demands of the high spatial resolution needed to image small vessels versus imaging time constraints where there is often a very short arteriovenous transit time for contrast passage form arterial to venous compartments makes imaging challenging. While dynamic MRA techniques can usually allow arterial imaging without venous ‘contamination’ these necessarily sacrifice spatial resolution.

CHAOS

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

EAD2019

Endoscopic Artefact Detection (EAD) is a core problem and needed for realising robust computer-assisted tools. The EAD challenge has 3 tasks: 1) Multi-class artefact detection, 2) Region segmentation, 3) Detection generalisation.

ACDC-LungHP

Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology

KiTS19

2019 Kidney and Kidney Tumor Segmentation Challenge

PAIP 2019

PAIP2019: Liver Cancer Segmentation Task 1: Liver Cancer Segmentation Task 2: Viable Tumor Burden Estimation

iChallenge-AMD

Age-related Macular Degeneration Challenge

StructSeg2019

Welcome to Automatic Structure Segmentation for Radiotherapy Planning Challenge 2019. This competition is part of the MICCAI 2019 Challenge.

Lymphocyte Assessment Hackathon

Lymphocyte Assessment Hackathon in conjunction with the MICCAI COMPAY 2019 Workshop on Computational Pathology

AASCE

Accurate Automated Spinal Curvature Estimation

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

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

SurgVisDom

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.

AutoImplant

the MICCAI 2020 Cranial Implant Design Challenge

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.

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.

FLARE21

Fast and Low GPU memory Abdominal oRgan sEgmentation Challenge

NODE21

NODE21: generate and detect nodules on chest radiographs

TIGER

Grand challenge on automate assessment of tumor infiltrating lymphocytes in digital pathology slides of triple negative and Her2-positive breast cancers

The PI-CAI Challenge

Artificial Intelligence and Radiologists at Prostate Cancer Detection in MRI

AIROGS

Artificial Intelligence for RObust Glaucoma Screening Challenge

TDSC-ABUS2023

Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound

SynthRAD2023

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

3D Teeth Scan Segmentation and Labeling Challenge MICCAI2022

Computer-aided design (CAD) tools have become increasingly popular in modern dentistry for highly accurate treatment planning. In particular, in orthodontic CAD systems, advanced intraoral scanners (IOSs) are now widely used as they provide precise digital surface models of the dentition. Such models can dramatically help dentists simulate teeth extraction, move, deletion, and rearrangement and therefore ease the prediction of treatment outcomes. Although IOSs are becoming widespread in clinical dental practice, there are only few contributions on teeth segmentation/labeling available in the literature and no publicly available database. A fundamental issue that appears with IOS data is the ability to reliably segment and identify teeth in scanned observations. Teeth segmentation and labelling is difficult as a result of the inherent similarities between teeth shapes as well as their ambiguous positions on jaws.

MICCAI FLARE 2022

MICCAI 2022 Fast and Low-resource semi-supervised Abdominal oRgan sEgmentation (FLARE) Challenge

AGGC22

autoPET

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

The Head and Neck Organ-at-Risk CT & MR Segmentation Challenge

A semantic multimodal segmentation challenge comprising 30 organs at risk

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.

Universal Lesion Segmentation Challenge '23

Multi-Class Segmentation of Aortic Branches and Zones in CTA

3D Segmentation of Aortic Branches and Zones on Computed Tomography Angiography (CTA)

Deep-Learning-Based CT Lung Registration

Registration of inspiration and expiration lung CT scans using a neural network trained with multiple anatomical constraints.