RadboudCOVID

Data from RadboudUMC from Covid-19 (suspected) subjects

LOLA11

55 scans from the LOLA11 challenge

LUNA16

888 CT scans from the LUNA16 challenge

CORADS Score Exam

Assign a CORADS score to 25 cases. You will receive the results of the test by e-mail.

CORADS Score Practice

Practice CORADS scoring with 50 cases. You get instant feedback after every case.

Project AIR - DEMO - Lung nodule detection X-ray

Demonstration reader study to explore what it means to be a reader for Project AIR

Adhesion cine-MRI tutorial

A short 4-case tutorial for adhesion detection on abdominal cine-MRI

Demo educational reader study

Reader study for demo purposes

The PANORAMA Challenge - Reading Interface and Workflow Demo

PANORAMA is an all-new grand challenge with +2000 of carefully curated abdominal CECT exams, and tools to upload, run and validate AI in a secure environment, using standardized consensus-based guidelines.

LOLA11

The goal of LOLA11 (LObe and Lung Analysis 2011) is to compare methods for (semi-)automatic segmentation of the lungs and lobes from chest computed tomography scans. Any team, whether from academia or industry, can join.

LUNA16

The LUNA16 challenge: automatic nodule detection on chest CT

EMPIRE10

Challenge for intra-subject registration of chest CT images.

PROSTATEx

Classification of clinical significance of prostate lesions using multi-parametric MRI data

HC18

Automated measurement of fetal head circumference using 2D ultrasound images

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

Project AIR - commercial AI for bone age prediction on hand XR

Head-to-head performance evaluation of commercially available AI products. This challenge shows the results for bone age prediction on hand radiographs on a multicenter dataset (seven centers) from the Netherlands.

Project AIR - commercial AI for lung nodule detection on CXR

Head-to-head performance evaluation of commercially available AI products. This challenge shows the results for lung nodule detection on chest radiographs on a multicenter dataset (seven centers) from the Netherlands.

Universal Lesion Segmentation Challenge '23

Abdominal Circumference Operator-agnostic UltraSound measurement

The LEOPARD Challenge

MONKEY challenge: Detection of inflammation in kidney biopsies

MONKEY (Machine-learning for Optimal detection of iNflammatory cells in KidnEY)

Challenge Hosting Masterclass

A hands-on workshop designed to provide participants with practical experience in setting up a challenge.

Lung cancer risk estimation on thorax CT scans - DSB2017 grt123

Automatic lung cancer risk estimation from thoracic CT scans

Spleen Segmentation

Automatic spleen segmentation on thorax-abdomen CT scans.

Vertebra segmentation and labeling

Segmentation and labeling of the vertebrae in CT scans with arbitrary field of view.

Tumor Detection in Lymph Nodes

CXR Cardiomegaly Detection

Detect cardiomegaly on chest radiographs through the segmentation of the heart and lungs .

Gleason Grading of Prostate Biopsies

Automated Gleason grading of prostate biopsies following the Gleason Grade Group system.

Pulmonary Lobe Segmentation

Automatic segmentation of pulmonary lobes on CT scans for patients with COPD or COVID-19.

Scaphoid fracture detection

Automatic detection of scaphoid fractures on hand, wrist, and scaphoid x-rays.

CORADS-AI

Segments pulmonary lobes and lesions and computes the CORADS and CT Severity Score from a non-contrast CT scan.

Pulmonary Nodule Malignancy Prediction

Deep Learning for Malignancy Risk Estimation of Low-Dose Screening CT Detected Pulmonary Nodules

HookNet-Breast

Segmentation algorithm for histopathology breast tissue.

Lung Cancer Segmentation

Lung cancer segmentation in H&E stained histopathological images.

Lung cancer risk estimation on thorax CT scans - DSB2017 JulianDaniel

Automatic lung cancer risk estimation from thoracic CT scans

Fluid Segmentation in Retinal Optical Coherence Tomography (OCT)

Segments intraretinal fluid, subretinal fluid, and pigment epithelial detachments in Optical Coherence Tomography scans. Optimized for Spectralis, Cirrus and Topcon scanners.

HookNet-Lung

Segmentation algorithm for histopathology lung tissue.

Femur segmentation in CT

Segments the left and right femur in CT images

Neural Image Compression

Compresses whole slide images into much smaller volumes

CXR Total Lung Volume Measurement

Measurement of total lung volume from chest radiographs using frontal and lateral radiographs

Clinically Significant Prostate Cancer Detection in bpMRI

Deep learning-based 3D detection/diagnosis model trained, validated and tested using 2732 prostate biparametric MRI exams from two centers.

Demo Vessel Segmentation

Demonstrates a vessel segmentation algorithm.

Colon Tissue segmentation

Tissue segmentation network for colon histopathology images

Body composition

Locates L3 in a CT scan and measures the area of subcutaneous, visceral, and intermuscular adipose tissue and smooth muscle. The average Hounsfield Units of each area are also computed.

Nuclear Pleomorphism Scoring

Scoring nuclear pleomorphism grade in whole-slide breast histopathology images

Hip segmentation in CT

Segments the left and right hip bones in CT images

Vertebral Fracture Assessment

A neural network that assesses vertebral fractures according to the Genant classification

Vertebral Abnormality Scoring

Score from 0 to 100 that expresses how abnormal the shape of a vertebra is

Lobe-Wise Lung Function Estimation from CT

Produces patient-level and lobe-level estimates of DLCO and of FEV1 and FVC pre- and post-bronchodilator

STOIC2021 baseline

Example algorithm for the STOIC2021 COVID-19 AI Challenge

Visceral slide on abdominal cine-MRI

This algorithm calculates the visceral slide along the contour of the abdominal cavity, using segmentation and registration.

Breast Cancer Segmentation and Scoring in H&E

Liver segmentation

Segments the liver and liver tumors using nnUNet

Multi-view scaphoid fracture detection

Automated scaphoid fracture detection on conventional radiographs of the hand, wrist, and scaphoid in any view.

Lung nodule detection for routine clinical CT scans

Deep learning for the detection of pulmonary nodules in chest CT scans

AIROGS Baseline

A baseline algorithm for the AIROGS challenge

Clinically Significant Prostate Cancer Detection in bpMRI using models trained with Report Guided Annotations

Airway Anatomical Labeling

Given an airway segmentation where individual airway branches are extracted, this algorithm will automatically find 18 segmental branches, including 8 from the left lung (LB1+2, LB3, LB4, LB5, LB6, LB7+8, LB9, and LB10) and 10 from the right lung (RB1-10).

Prostate Segmentation

Whole-Gland Prostate Segmentation in bpMRI

Tiger Algorithm Example

example on how to create an algorithm for the tiger challenge

Age-related macular degeneration (AMD) Staging in Optical Coherence Tomography (OCT) with UBIX for Increased Reliability

Deep learning models for optical coherence tomography (OCT) classification often perform well on data from scanners that were also used during training. However, when these models are applied to data from different vendors, their performance tends to drop substantially. Artifacts that only occur within scans from specific scanners are major causes of this poor generalizability. We aimed to improve this generalizability of deep learning models for OCT classifi- cation. To reduce the effect of vendor-specific artifacts, we propose Uncertainty-Based Instance eXclusion (UBIX), of which we define a hard and a soft variant. UBIX aims to suppress the contributions of B-scans with unseen artifacts to the final OCT-level outputs. Suppression is based on out-of-distribution detection of B-scans, which are instances in our multiple instance learning approach.

Breast and fibroglandular tissue segmentation

PI-CAI: Baseline nnU-Net (supervised)

Baseline algorithm submission for PI-CAI based on the nnU-Net framework

Wrist segmentation

Segments the carpal bones and radius and ulna in (dynamic) CT scans of the wrist.

Tibia segmentation in CT

Segments the left and right tibia in CT images

Rib segmentation

Segments and labels the ribs in CT images

PI-CAI: Baseline nnDetection (supervised)

Baseline algorithm submission for PI-CAI based on the nnDetection framework

PI-CAI: Baseline nnU-Net (semi-supervised)

Baseline semi-supervised algorithm submission for PI-CAI based on the nnU-Net framework

PI-CAI: Baseline U-Net (semi-supervised)

PI-CAI: Baseline nnDetection (semi-supervised)

Baseline semi-supervised algorithm submission for PI-CAI based on the nnDetection framework

Endometrial Carcinoma classification

CLAM model that computes the probability of the WSI being (pre)malignant and also outputs an interpretable heatmap.

Colon Budding in IHC

Automatic tumor bud detection in IHC stained slides of CRC

PI-CAI: Baseline nnU-Net (supervised) trained on PI-CAI: Private and Public Training Dataset

Lymphocytes detection in immunohistochemistry

JawFracNet

Segment mandible and mandibular fractures in head CBCT scan

Deep learning to estimate pulmonary nodule malignancy risk using a current and a prior CT image

Deep learning to estimate pulmonary nodule malignancy risk using a prior CT image

PI-CAI: Baseline nnU-Net (semi-supervised) trained on PI-CAI: Private and Public Training Dataset

HookNet-TLS

A model for detection of TLS and GC in histopathology.

PI-CAI: Baseline nnDetection (semi-supervised) trained on PI-CAI: Private and Public Training Dataset

PI-CAI: Baseline U-Net (supervised) trained on PI-CAI: Private and Public Training Dataset

PI-CAI: Baseline U-Net (semi-supervised) trained on PI-CAI: Private and Public Training Dataset

PI-CAI: Baseline nnDetection (supervised) trained on PI-CAI Private and Public Training Dataset

PI-CAI: Baseline nnDetection (supervised) trained on PI-CAI Private and Public Training Dataset

SPIDER Baseline nnU-Net

Carpal instability measurements

Automated AI pipeline for conducting carpal instability measurements on conventional radiographs of the hand and wrist.

SPIDER Baseline IIS

Tumor proportion score in non-small cell lung cancer

Automatic quantification of the tumor proportion score in NSCLC histology

Nuclei detection in immunohistochemistry

Automatic detection of nuclei (hematoxylin positive) in immunohistochemistry WSIs

Neural ODEs for Segmentation of Colon Glands

Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands

PDAC Tumor Segmentation

This algorithm takes an HE histology images of the pancreas, segments the tissue, segments the epithelium and segments the tumor (if present)

Universal Lesion Segmentation [ULS23 Baseline]

Univeral Lesion Segmentation algorithm for Computed Tomography