Overview
Who this competition fits
适合已有 Python 深度学习与 PaddlePaddle 使用经验、想做医学图像语义分割的个人参赛者。参赛者需要能处理环扫 OCT 图像,并理解 RNFL、GCIPL 和脉络膜三类视网膜相关层的分割目标;比赛仅支持个人参赛。
Read the original official blurb
MICCAI2022 Challenge: Glaucoma Oct Analysis and Layer Segmentation (GOALS) Task 1 Official tags: CV. Sign-ups: 523.
Resources
What this competition gives you
There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.
- DataGOALS dataset with 300 circumpapillary OCT scans and segmentation labels.
- BaselineOfficial OCT layer segmentation baseline.
- BaselineOfficial OCT Layer Segmentation baseline.
- BaselineSolution code from GOALS Challenge final teams.
- Reference paperREFUGE challenge review paper.
- Reference paperAGE challenge review paper.
- Reference paperADAM Challenge paper.
- Reference paperGAMMA challenge paper.
- Reference paperREFUGE2 Challenge paper.
Preparation
From registration to a first submission
- 01
PaddlePaddle 2.0+
- 02
OCT医学图像处理
- 03
语义分割模型
- 04
小样本学习
- 05
视网膜层标注理解
- 06
Python深度学习训练
Before you commit: 主要难点是在小规模训练数据上稳定分割三种边界细致的 OCT 层结构:页面明确说明训练部分只有 100 个样本,并鼓励针对小样本训练设计模型。还需按要求使用 PaddlePaddle 2.0 及以上版本训练端到端模型,并提交预测结果和原始代码。
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- Baidu AI Studio
- Last checked
- Not recorded