Motivation
Early brain tumor resection can effectively improve the patient’s survival rate. However, resection quality and safety can often be heavily affected by intra-operative brain tissue shift due to factors, such as gravity, drug administration, intracranial pressure change, and tissue removal. Such tissue shift can displace the surgical target and vital structures (e.g., blood vessels) shown in pre-operative images while these displacements may not be directly visible in the surgeon’s field of view.
Intra-operative ultrasound (iUS) is a robust and relatively inexpensive technique to track intra-operative tissue shift and surgical tools. Automatic algorithms for brain tissue segmentation in iUS, especially brain tumors and resection cavity can greatly facilitate the robustness and accuracy of brain shift correction through image registration, and allow easy interpretation of the iUS. This has the potential to improve surgical outcomes and patient survival rate.
The challenge is an extension to the previous CuRIOUS 2018 & CuRIOUS 2019 Challenge that focused on image registration algorithm. It will provide a snapshot of the current and new techniques for iUS segmentation, and provide the opportunity to benchmark the methods on the newly released dataset of iUS brain tumor and resection cavity segmentation.
Early brain tumor resection can effectively improve the patient’s survival rate. However, resection quality and safety can often be heavily affected by intra-operative brain tissue shift due to factors, such as gravity, drug administration, intracranial pressure change, and tissue removal. Such tissue shift can displace the surgical target and vital structures (e.g., blood vessels) shown in pre-operative images while these displacements may not be directly visible in the surgeon’s field of view.
Intra-operative ultrasound (iUS) is a robust and relatively inexpensive technique to track intra-operative tissue shift and surgical tools. Automatic algorithms for brain tissue segmentation in iUS, especially brain tumors and resection cavity can greatly facilitate the robustness and accuracy of brain shift correction through image registration, and allow easy interpretation of the iUS. This has the potential to improve surgical outcomes and patient survival rate.
The challenge is an extension to the previous CuRIOUS 2018 & CuRIOUS 2019 Challenge that focused on image registration algorithm. It will provide a snapshot of the current and new techniques for iUS segmentation, and provide the opportunity to benchmark the methods on the newly released dataset of iUS brain tumor and resection cavity segmentation.
Tasks
The CuRIOUS 2022 Segmentation Challenge will include two tasks:
Task 1: Brain tumor segmentation in intra-operative ultrasound
Task 2: Resection cavity segmentation in intra-operative ultrasound
Important dates
Challenge website launch: April 15, 2022
Team registration: April 1 ~ Aug 10, 2022
Training data release: July 18., 2022
Test data release: Aug 15, 2022
Result submission: Aug 16 ~ Sep 10, 2022 Sep 14, 2022
Methodology paper submission: Aug 13, 2022 Aug 20 2022