发表机构
Gachon University; MEDAI（加昌大学; MEDAI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对中重度创伤性脑损伤病变分割难题，利用AIMS-TBI 2025挑战赛推动算法发展，提出基于nnU-Net并采用自适应归一化的方法，有效减少个体差异与伪影，在测试中取得良好成绩，证明该策略对解决病变分割复杂性有效。
AI 中文摘要
中重度创伤性脑损伤（msTBI）中，T1加权MRI图像上病变的分割面临重大临床挑战，因为病变在大小、形状和位置方面具有显著异质性。为应对此挑战，组织了AIMS-TBI 2025挑战赛以推动强大且准确的分割算法发展。本文提出基于深度学习的解决方案，采用nnU-Net框架并对脑实质进行自适应强度归一化，有效减少个体间差异并减轻非脑结构伪影。在最终测试集评估中，该方法在官方排行榜上表现出极具竞争力的性能，总体Dice系数达0.6305，病变分割Dice分数为0.4805，非病变组织为0.9324。结果表明，在nnU-Net流程中纳入解剖学约束归一化是应对msTBI病变分割复杂性的有力有效策略。
英文摘要
The segmentation of lesions in Moderate to Severe Traumatic Brain Injury (msTBI) from T1-weighted MRI presents a significant clinical challenge due to the profound heterogeneity of lesion characteristics in terms of size, shape, and location. To address this, the AIMS-TBI 2025 Challenge was organized to promote the development of robust and accurate segmentation algorithms. In this paper, we present our deep learning-based solution. Our methodology employs the nnU-Net framework with an adaptive intensity normalization strategy confined to the brain parenchyma, effectively reducing inter-subject variability and mitigating artifacts from non-brain structures. Upon final evaluation on the held-out test set, our method demonstrated highly competitive performance on the official leaderboard, achieving an Overall Dice Coefficient of 0.6305. The model obtained a Dice score of 0.4805 for lesion segmentation and 0.9324 for non-lesion tissue. While the lesion Dice reflects the difficulty of detecting highly heterogeneous lesions, the high non-lesion Dice primarily indicates the model's strong ability to correctly identify non-lesion voxels, demonstrating good specificity in differentiating lesion from non-lesion regions. These results demonstrate that incorporating anatomically constrained normalization within the nnU-Net pipeline is a powerful and effective strategy for tackling the complexities of msTBI lesion segmentation.
Comments2nd place, AIMS-TBI Challenge at MICCAI 2025
DOI：10.1007/978-3-032-16370-7_29
