Dehghani Farzaneh, Karimian Alireza, Arabi Hossein
Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran.
Department of Medical Imaging, Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland.
J Med Signals Sens. 2024 Apr 8;14:9. doi: 10.4103/jmss.jmss_13_23. eCollection 2024.
Brain tumor segmentation is highly contributive in diagnosing and treatment planning. Manual brain tumor delineation is a time-consuming and tedious task and varies depending on the radiologist's skill. Automated brain tumor segmentation is of high importance and does not depend on either inter- or intra-observation. The objective of this study is to automate the delineation of brain tumors from the Fluid-attenuated inversion recovery (FLAIR), T1-weighted (T1W), T2-weighted (T2W), and T1W contrast-enhanced (T1ce) magnetic resonance (MR) sequences through a deep learning approach, with a focus on determining which MR sequence alone or which combination thereof would lead to the highest accuracy therein.
The BraTS-2020 challenge dataset, containing 370 subjects with four MR sequences and manually delineated tumor masks, is applied to train a residual neural network. This network is trained and assessed separately for each one of the MR sequences (single-channel input) and any combination thereof (dual- or multi-channel input).
The quantitative assessment of the single-channel models reveals that the FLAIR sequence would yield higher segmentation accuracy compared to its counterparts with a 0.77 ± 0.10 Dice index. As to considering the dual-channel models, the model with FLAIR and T2W inputs yields a 0.80 ± 0.10 Dice index, exhibiting higher performance. The joint tumor segmentation on the entire four MR sequences yields the highest overall segmentation accuracy with a 0.82 ± 0.09 Dice index.
The FLAIR MR sequence is considered the best choice for tumor segmentation on a single MR sequence, while the joint segmentation on the entire four MR sequences would yield higher tumor delineation accuracy.
脑肿瘤分割对诊断和治疗规划具有重要意义。手动勾勒脑肿瘤轮廓是一项耗时且繁琐的任务，并且因放射科医生的技术水平而异。自动脑肿瘤分割非常重要，且不依赖于观察者之间或观察者内部的差异。本研究的目的是通过深度学习方法实现从液体衰减反转恢复（FLAIR）、T1加权（T1W）、T2加权（T2W）和T1W对比增强（T1ce）磁共振（MR）序列中自动勾勒脑肿瘤轮廓，重点是确定单独使用哪种MR序列或其哪种组合能在其中实现最高的准确性。
将包含370名受试者的四个MR序列及手动勾勒的肿瘤掩码的BraTS - 2020挑战数据集应用于训练残差神经网络。针对每个MR序列（单通道输入）及其任意组合（双通道或多通道输入）分别训练和评估该网络。
单通道模型的定量评估表明，FLAIR序列相比其他序列能产生更高的分割准确率，其Dice指数为0.77±0.10。至于双通道模型，具有FLAIR和T2W输入的模型产生的Dice指数为0.80±0.10，表现出更高的性能。对全部四个MR序列进行联合肿瘤分割产生了最高的总体分割准确率，Dice指数为0.82±0.09。
FLAIR MR序列被认为是单个MR序列上肿瘤分割的最佳选择，而对全部四个MR序列进行联合分割将产生更高的肿瘤勾勒准确率。
