文献速递神经MR

深度学习检测与分割颅内转移瘤中图像预处理技术的系统评估

A Systematic Evaluation of Image Preprocessing in Deep Learning Detection and Segmentation of Intracranial Metastatic Disease.
PubMed 文献 · AJNR Am J Neuroradiol · 2026-07-01

该研究使用nnU-Net在1034例训练集和256例测试集MRI上系统评估了标签制备、偏置校正、归一化、配准和去噪等预处理技术对颅内转移瘤检测与分割的影响。结果显示,仅使用肿瘤核心标签和较少的MRI序列可提高性能,而图像配准会降低小转移灶的检测和分割,偏置校正和去噪无显著影响。

要点

  • 仅用肿瘤核心标签训练可提高检测和分割性能
  • 减少MRI序列数量可能改善分割效果
  • 图像配准可能损害小转移灶的检测和分割

局限性

  • 单中心研究
  • 回顾性设计
  • 样本量有限

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND AND PURPOSE: Image preprocessing is an essential, though often overlooked, part of machine learning, and it is unclear how preprocessing techniques affect metastatic disease segmentation. This is particularly true given the differences between segmentation of primary brain tumors and the detection and segmentation of small metastases. The purpose of this work is to systematically evaluate how preprocessing techniques affect the detection and segmentation of intracranial metastases.

MATERIALS AND METHODS: Using nnU-Net, we evaluated preprocessing techniques on a training data set of 1,034 MRIs and testing set of 256 MRIs. We examined the effects of label preparation, bias correction, normalization, registration, and denoising, as well as the contribution of each MRI sequence. Model performance was compared to the baseline model using paired t-tests, evaluating global Dice scores, lesion detection rate, and per-lesion and per-exam Dice score, surface Dice score, and 95% Hausdorff distance, stratified by lesion volume.

RESULTS: Baseline model performance demonstrated a global Dice score of 0.72 ± 0.28 and a lesion detection rate of 70.8% (1,328/1,877), strongly dependent on lesion size. Including all labels in training, as opposed to only tumor core, resulted in a significant decrease in detection rate to 68.8% (1,292/1,877) (p < 0.001), as well as reduced per-lesion segmentation particularly for smaller lesions. Bias correction and denoising demonstrated no significant effect on performance. Pre-normalization of data led to worse segmentation performance. Image registration reduced both lesion detection and segmentation. Training with fewer MRI sequences, in several cases, improved segmentation.

CONCLUSIONS: Our findings demonstrate that certain preprocessing steps have a significant impact on model performance while others have negligible effects and may not be necessary. With nnU-Net, we observed highest detection and segmentation scores by reducing training labels and MRI sequences to those focused on tumor core, with additional, less relevant data, reducing performance. Several preprocessing steps showed no measurable benefit and image registration may be detrimental to the detection and segmentation of small metastases.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Kamel PI, Naeem A, Shah K, et al. A Systematic Evaluation of Image Preprocessing in Deep Learning Detection and Segmentation of Intracranial Metastatic Disease. AJNR Am J Neuroradiol. 2026. PMID: 42386367. doi:10.3174/ajnr.A9511

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。