Welcome to Digestive-System Pathological Detection and Segmentation Challenge 2019.
Release of training data: Jun. 14th, 2019 Submission start time: Sep. 16th, 2019 11:59 UTC-8 Beijing Time Submission start time extends to: Sep. 19th, 2019 11:59 UTC-8 Beijing Time Submission deadline: Sep. 23th, 2019 11:59 UTC-8 Beijing Time Submission deadline extends to: Sep. 26th, 2019 11:59 UTC-8 Beijing Time Announcement of results: Oct. 1st, 2019
- results site: http://www.digestpath-challenge.org/
Presentation and award ceremony: Oct. 13th, 2019
- Presentation and award ceremony extends to: Oct. 17th, 2019
The goal of the challenge is to set up tasks for evaluating automatic algorithms on signet ring cell detection and colonoscopy tissue screening from digestive system pathological images. This will be the first challenge and first public dataset on signet ring cell detection and colonoscopy tissue screening. Releasing the large quantity of expert-level annotations on digestive-system pathological images will substantially advance the research on automatic pathological object detection and lesion segmentation.
- Task 1: Signet ring cell detection.
- Task 2: Colonoscopy tissue segmentation and classification.
Top-ranking teams on each task will be invited to submit full papers on describing their methods to the special issue on Deep learning for Medical Image Computing of Neurocomputing (IF= 4.072). The guest editors are:
Hongsheng Li (SenseTime Research & CUHK)
Shaoting Zhang (SenseTime Research)
Dimitris N. Metaxas (Rutgers University)
Examination of pathological images is the golden standard for diagnosing and screening cancers in the digestive system. Digital pathology has become increasingly popular in recent years and allows examination of high-resolution whole image (WSI) in remote locations. Such a functionality is convenient for hospitals in rural areas of developing countries, where there are not enough experienced pathologists for accurate diagnosis. However, manual analysis of WSI is still a time-consuming task for the pathologists because the WSI can be up to size 100,000 X 100,000 pixels. This prevents remote examination to be widely adopted in developing countries/regions where there are not enough pathologists. One promising solution is to develop medical models to automatically detect, segment, and classify cells of interests in different pathological images. Such problems attract much attention from the medical imaging community and there is a larger number of existing papers on pathological image segmentation.
In the challenge, participants will be provided with 2 datasets:
- Signet ring cell dataset
A total of 90 patients' 450 pathological images and annotations of 15,000 cells will be provided as the training set. For method evaluation, another 30 patients' 150 images and annotations of 5,000 cells will be utilized. The images are from 2 organs, including gastric mucosa and intestine.
- Colonoscopy tissue segment dataset
A total of 450 patients' 750 tissue slices of an average size of 3000x3000 will be provided as the training set. We will also provide another 150 patients' 250 tissues as the testing set.
The data and annotation are provided by Histo Pathology Diagnostic Center together with cooperated hospitals. (see the Detailed Dataset Description)
Li, J., Yang, S., Huang, X., Da, Q., Yang, X., Hu, Z., ... & Li, H. (2019, June). Signet Ring Cell Detection with a Semi-supervised Learning Framework. In International Conference on Information Processing in Medical Imaging (pp. 842-854). Springer, Cham. (https://arxiv.org/abs/1907.03954)
If you have any questions or comments, please mail to email@example.com.
This challenge is origanized by the following institutions: