Intestinal parasitic infections remain among the leading causes of morbidity worldwide, especially in tropical and sub-tropical areas with more temperate climates. According to WHO, approximately 1.5 billion people, or 24% of the world’s population, are infected with soil-transmitted helminth infections (STH), and 836 million children worldwide required preventive chemotherapy for STH in 2020. Most infections can cause diarrheal and other symptoms such as malnutrition and anaemia, particularly in children, who may suffer from growth failure. Most infected persons can also shed cysts or eggs in their living environment, and unwittingly cause transmission of parasites to other individuals. An improvement in personal hygiene, better sanitation and a widespread health education campaign have reduced helminthic infections, but protozoa are still present even in asymptomatic hosts, leading to chronic diseases. In developing countries, intestinal protozoa and STH have been recognised as one of the most significant causes of illnesses. Diagnosis of intestinal parasites is usually based on direct examination in the laboratory. However, this method shows low sensitivity, is time-consuming (30 min/sample), requires an experienced and skilled medical laboratory technologist and is impractical for use on-site. This means an automate routine faecal examination for parasitic diseases is essential.

This challenge aims to encourage and highlight novel strategies with a focus on robustness and accuracy in data-driven technologies to automatically detect parasitic eggs and also identify the egg type in compound microscopy images. We expect to gather experts in the fields of image processing, medical imaging and computer vision, which should not be limited to the domain of microscopic imaging as knowledge transfer can benefit the growth of the community. The outcome of the challenge could be further improved and assist diagnosis in real clinical use, or even automate detection and identification of intestinal parasite eggs, which can be used by non-experts.


Our dataset contains 11 types of parasitic eggs from faecal smear samples [more information].

Rules for participation

Participants are subject to the following rules:

  • Participants must register via email for communication. After the registration, the participants will receive instructions and will be granted access to the dataset when released and instructions on how to upload their results to the leaderboard.
  • There should be only one entry per participating team and the maximum team size is 4.
  • Optionally, there can be a paper submission in relation to this challenge. The first submission (22 April 2022) should describe the model and preliminary results. The paper can be updated with the final results, which will be submitted in July. If a paper is not submitted, a short technical report describing the methodology will be required.
  • The participants ranking in the top 5 upon centralising results for all submissions must present a summary of their technology during the dedicated ICIP session.

Evaluation criteria

Participants will upload their results of the testing dataset to the website, where a Mean Intersection-over-Union (mIoU) will be the criteria for evaluation. Each type of parasitic eggs is assessed and assigned an Intersection-over-Union (IoU) score, then all types of parasitic eggs will be calculated for the average of their IoU scores, finally resulting in the mIoU score. The submissions will be ranked according to the criteria and shown on the leaderboard.

Five top-performing teams will be asked to submit their code and models for final checking by the organisers. The organisers will also run the submitted executables on a hidden smaller dataset for further validation. If further comparison is needed, the computational speed will be used as the last criterion.

Winners will be announced at ICIP2022.

Important dates

  • 21 January 2022: Website open for registration
  • 30 January 2022: Training dataset is released
  • 13 February 2022: Testing dataset is released
  • 14 February 2022 12:00 AoE (UTC -12): Submission to leaderboard is open
  • 22 April 2022: Challenge paper submission deadline [Submit your paper here].
  • 31 May 2022 24:00 AoE (UTC -12): Competition closes
  • 20 June 2022 27 June 2022: Top-performing teams announcement
  • 11 July 2022: Final paper/report submission deadline
  • October 2022: Winners announcement at ICIP

Top-performing teams

In alphabetical order:

  • BAD crew, Mahidol University, Thailand
  • NEGU, NCU, China
  • NVLab, National Tsing Hua University, Taiwan
  • Visilab, Universidad de Castilla-La Mancha, Spain
  • ZUSTF4, Zhejiang University of Science and Technology, China

Winners will be announced at ICIP.


  • 1st prize: $1,500
  • 2nd prize: $1,000
  • 3rd prize: $500