{
  "fetched_at": "2026-10-18T13:43:05Z",
  "source_url": "https://www.kaggle.com/competitions/aocr2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Far Eastern Memorial Hospital in New Taipei City, Taiwan has provided the image data and annotations. From this collection, we've chosen contrast-enhanced abdominal and pelvic CT scans from adults over 18 years of age. These scans, taken in the axial section, have a slice thickness of 5mm and cover a span of the last ten years.\n\n- The training dataset comprises 500 CT scans from patients confirmed with acute appendicitis and an additional 500 scans from individuals who exhibited acute abdominal pain but were diagnosed without appendicitis. We've pre-divided the data into Train and Validation sets; adhering to this suggested split is advised.\n- Test data: 200 CT scans from acute abdomen condition, but the composition ratio is unknown.\n- We've created mask files for the CT scans showing acute appendicitis by delineating the affected appendix, as illustrated below in NIfTI format. Annotations were focused on the abnormal appendices, and inflammation in adjacent areas was not marked. We have taken extensive precautions to ensure the accuracy of both the images and annotations. However, in the unlikely event of a minor annotation error, we believe it will not compromise the fairness of the competition.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F6662693%2F220773eed1672c3f4fe6c5e06de57bf7%2FUntitled.png?generation=1698375679755972&alt=media)\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2238168%2F369ac1d079cb0ceb9ab21ee1acbe6e57%2Fdata.jpg?generation=1698823061860686&alt=media)\n\n\n**Evaluation**\n\n- Each CT slice is evaluated to identify the presence of an abnormal appendix indicative of appendicitis. Furthermore, the entire CT scan is assessed to determine a diagnosis of acute appendicitis for that particular scan session. The final score combines evaluations from both slice-level and scan-level assessments.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2238168%2F051221d82e3405c2133b8a318df061b6%2Fevaluation.jpg?generation=1698630943951479&alt=media)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Acute appendicitis is the most common cause of acute abdominal pain. Despite many previous studies, the diagnosis of acute appendicitis remains challenging. Misdiagnosis or delayed diagnosis can increase the incidence of perforation, peritonitis, and complications of laparoscopic surgery, all of which are associated with morbidity and mortality. Therefore, rapid and accurate diagnosis of acute appendicitis is crucial for effective treatment of acute abdominal pain. However, its symptoms are often unclear and overlap with other diseases, making the diagnosis of acute appendicitis difficult even when clinical physicians perform physical examinations and have blood test results. The clinical importance and numerical advantage of acute appendicitis make it the most frequently studied topic in AI-assisted diagnostic processes. \n\nVarious modeling approaches, such as classification, detection, and segmentation, can be used. Rule-based pre- and post-processing methods for calculations are also permitted. Annotations can be manually performed and combined with multiple model calculations. If teams utilize additional data for training, it is necessary to make those data publicly accessible.\n\nPlease also note that it might be beneficial to keep an eye on the discussion board for potential insights.\n\n****Competition Format****\n\nThis competition is organized into two stages:\n\n1. **First Stage:** All participating teams will compete. After this stage, the top 20 teams or the top 20% of the teams (whichever is greater) will be selected based on their performance. Teams that fall into this category must fill out the organizing committee's Google form to facilitate contact and transition into the second stage.\n2. **Second Stage:** The qualified teams from the first stage will compete. The rankings and winners will be determined at the end of this stage.\n\nPlease ensure that you provide accurate and up-to-date contact information in the Google form to avoid any miscommunications or missed opportunities.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Each CT slice is evaluated to identify the presence of an abnormal appendix indicative of appendicitis. Furthermore, the entire CT scan is assessed to determine a diagnosis of acute appendicitis for that particular scan session. \n\nSubmissions will be assessed based on the F1 score, comparing the predictions to the actual targets.\n\nTwo distinct F1 scores will be determined: one for the scan-level predictions and another for the slice-level predictions. The final leaderboard ranking will be derived from a composite of these two F1 scores.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "**One account per participant**\n\nParticipants are limited to one account per user\n\n**Team Limits**\n\nThe maximum team size is 5.\n\nEach participating team must include at least one radiologist.\n\n**No private sharing outside teams**\n\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n**Winning Team Obligations:**\n\n- Make their code publicly available.\n- Produce a brief video outlining their method.\n- Submit the final model/code to the competition organizers.\n\n**Submission Limits**\n\nYou may submit a maximum of 3 entries per day.\n\nYou may select up to 1 final submissions for judging.\n\n**External Data**\n\nParticipants are allowed to use external data for this competition. However, the external data must be publicly available.\n\n**Competition Timeline**\n\nCompetition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s [Overview > Timeline](https://www.kaggle.com/competitions/test22/overview/timeline) page.\n\n**Usage Restrictions for the Provided Data**\n\nThe data is intended exclusively for this competition and is not permitted for clinical or commercial applications. Should you wish to use it for academic publications, obtaining prior consent from Far Eastern Memorial Hospital is mandatory.\n\n**COMPETITION TITLE**: AOCR2024 AI Challenge: Diagnosis of Acute Appendicitis in Acute Abdomen CT Scans\n\n**COMPETITION SPONSOR**: Taiwan Radiological Society (TRS)\n\n**COMPETITION SPONSOR ADDRESS**: 2F., No.63, Sec. 3, Chong-Qing N. Road, Taipei 103, Taiwan\n\n**COMPETITION WEBSITE**: https://www.kaggle.com/competitions/aocr2024/\n\n**WINNER LICENSE TYPE**: Open Source\n\n**DATA ACCESS AND USE**: Non-Commercial Use, for the competition. Re-distribution or re-identification of any data is strictly prohibited.\n\n**SPONSOR.**\n\nThe Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.\n\n**COMPETITION PERIOD.**\n\nThe Competition Timeline is subject to change, and the Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.\n\n**COMPETITION ENTRY.**\n\nTo enter the Competition, register on the Competition Website before the Entry Deadline and follow the instructions for developing and submitting your Entry through the website. Submissions must be received before the stated deadlines.\n*Submissions must not use or include information from hand labeling or human prediction of the validation dataset or test data records.*\nSubmissions are void if they are illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. The Competition Sponsor can disqualify entrants who do not follow these Rules.\n\n**PUBLICITY.**\n\nYou agree that Competition Sponsor, Kaggle, and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation unless prohibited by law.\n\n**PRIVACY.**\n\nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share, and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). \n\n**WARRANTY, INDEMNITY AND RELEASE.**\n\nYou warrant that your Submission is your original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third-party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights, or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable law.\n\n**GOVERNING LAW.**\n\nUnless otherwise provided in the Rules above, all claims arising out of or relating to these Rules will be governed by Taiwan's law, excluding its conflict of laws rules, and will be litigated exclusively in the Taiwan Taipei District Court. The parties consent to personal jurisdiction in those courts. If any provision of these Rules is held to be invalid or unenforceable, all remaining provisions of the Rules will remain in full force and effect.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Aligned with the 22nd Asia Oceanian Congress of Radiology (AOCR 2024) held in Taipei, Taiwan from March 22-25, this AI challenge explores the significant role of AI in Radiology. The congress, expected to attract around 1,500 attendees, serves as an important platform for discussions and innovation in Radiology. Winning teams of this challenge will have the prestigious opportunity to present their solutions at the AOCR2024 conference. Besides waiving their registration fees, these teams will also receive special recognition and monetary prizes awarded at the AOCR2024 conference.  For more details, please refer to the [AOCR2024 official website](https://www.aocr2024.org/program/ai_challenge.asp).\n\nThis competition focuses on identifying acute appendicitis from CT scans of acute abdomen cases. Participants will engage in a classification task, distinguishing the presence or absence of acute appendicitis using contrast-enhanced CT scans.\n\nYour contributions will aid in predicting if acute appendicitis is responsible for specific acute abdominal pain episodes. Furthermore, it will highlight the critical slices in the CT scan that medical professionals should examine to detect the inflamed appendix.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Submission File",
      "content": "The submission .csv file should contain two columns: \"id\" and \"label\". The \"label\" column should store the prediction results as either 1 or 0. A value of 1 indicates the presence of an inflamed appendix from acute appendicitis, while a value of 0 indicates the absence.\n\n- For scan-level predictions, only enter the filename in the \"id\" column.\n- For slice-level predictions, combine the filename with the slice count in the format: `filename_sliceCount` and enter it in the \"id\" column. Start the slice count at 0 and increment sequentially from the feet to the head direction.\n\nPlease refer to the illustration below.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2238168%2Fdefee0453bf15d2c90368c9b3b2fbc83%2Fsubmission.jpg?generation=1698894171955682&alt=media)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "- **November 1, 2023:** Stage 1 begins.\n- **January 24, 2024:** Stage 1 ends.\n- **January 29, 2024:** Stage 2 begins.\n- **February 4, 2024:** Stage 2 ends & Final submission deadline.\n- **February 21, 2024:** Confirmation deadline for attending the AOCR2024 conference.\n- **March 23, 2024:** AOCR 2024 AI challenge winner presentation and award.\n\nAll deadlines are at 11:59 PM GMT+8 on the specified day, unless otherwise stated. The challenge organizers reserve the right to modify the contest timeline if necessary.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Recognition for winning teams",
      "content": "Following the second stage, up to five leading teams will be offered the unique opportunity to present their solutions at the AOCR2024 conference. For these teams, not only will their conference registration fees be waived, but they will also receive special recognition and benefits that will be detailed on the AOCR2024 official website. Further information can be found on the AOCR2024 official website.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Acknowledgments",
      "content": "**Challenge Organizing Team**\n\nWen-Jeng Lee, MD - National Taiwan University Hospital\n\nKuei-Hong Kuo, MD - Far Eastern Memorial Hospital\n\nWeichung Wang, PhD - National Taiwan University\n\nShu-Huei Shen, MD - Taipei Veterans General Hospital\n\nLi-Jen Wang, MD - Linkou Chang-Gung Memorial Hospital\n\nHong-Jen Chiou, MD - Taipei Veterans General Hospital\n\n**Data Contributor**\nFar Eastern Memorial Hospital in New Taipei City, Taiwan\n\n\n**Special Thanks**\n- The Asian Oceanian Society of Radiology (AOSR) Emerging Trends Committee for their invaluable suggestions.\n- Taiwan Radiological Society (TRS) AI and Imaging Informatics Committee for their continued support.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}