Published March 18, 2020 | Version v1
Other Open

Automatic Lung Cancer Detection and Classification in Whole-slide Histopathology

Creators

  • 1. National University of Defense Technology, China
  • 2. The Radboud University Medical Center in Nijmegen, the Netherlands
  • 3. The Eindhoven University of Technology, the Netherlands
  • 4. Nanjing University of Information Science
  • 5. Memorial Sloan Kettering Cancer Center, USA
  • 6. Inception Institute of Artificial Intelligence, UAE
  • 7. Hunan Lanxi Biotechnology Co. Ltd., China
  • 8. The First Hospital of Changsha, China
  • 9. Hunan Cancer Hospital, the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, China
  • 10. The Second Xiangya Hospital, Central South University, China

Description

This is the challenge design document for the "Automatic Lung Cancer Detection and Classification in Whole-slide Histopathology" Challenge, accepted for MICCAI 2020.

Digital pathology has been gradually introduced in clinical practice. Although the digital pathology scanner could
give very high resolution whole-slide images (WSI) (up to 160nm per pixel), the manual analysis of WSI is still a
time-consuming task for the pathologists. Automatic analysis algorithms offer a way to reduce the burden for
pathologists. Our proposed challenge will focus on automatic detection and classification of lung cancer using
Whole-slide Histopathology. This subject is highly clinical relevant because lung cancer is the top cause of cancerrelated
death in the world. The first stage of the challenge (ACDC2019) was already successfully held in 2019 in
ISBI (https://acdc-lunghp.grand-challenge.org/). ACDC2019 mainly focused on the detection of lung cancer region
in WSIs. ACDC2020 will focus on classifying the main lung cancer subtypes (e.g. squamous carcinoma,
adenocarcinoma) using WSI.

Files

AutomaticLungCancerDetectionandClassificationinWhole-slideHistopathology.pdf

Files (2.6 MB)