Shoushtari Fereshteh Khodadadi, Elahi Reza, Valizadeh Gelareh, Moodi Farzan, Salari Hanieh Mobarak, Rad Hamidreza Saligheh
Quantitative MR Imaging and Spectroscopy Group, Advanced Medical Technologies and Equipment Institute, Tehran University of Medical Sciences, Tehran, Iran; Nuclear Engineering Department, Shiraz University, Shiraz, Iran.
Quantitative MR Imaging and Spectroscopy Group, Advanced Medical Technologies and Equipment Institute, Tehran University of Medical Sciences, Tehran, Iran.
Phys Med. 2025 Jul;135:104988. doi: 10.1016/j.ejmp.2025.104988. Epub 2025 Jun 2.
Multiparametric Magnetic Resonance Imaging (mpMRI) is the gold standard for diagnosing brain tumors, especially gliomas, which are difficult to segment due to their heterogeneity and varied sub-regions. While manual segmentation is time-consuming and error-prone, Deep Learning (DL) automates the process with greater accuracy and speed.
We conducted ablation studies on surveyed articles to evaluate the impact of "add-on" modules-addressing challenges like spatial information loss, class imbalance, and overfitting-on glioma segmentation performance.
Advanced modules-such as atrous (dilated) convolutions, inception, attention, transformer, and hybrid modules-significantly enhance segmentation accuracy, efficiency, multiscale feature extraction, and boundary delineation, while lightweight modules reduce computational complexity. Experiments on the Brain Tumor Segmentation (BraTS) dataset (comprising low- and high-grade gliomas) confirm their robustness, with top-performing models achieving high Dice score for tumor sub-regions.
This survey underscores the need for optimal module selection and placement to balance speed, accuracy, and interpretability in glioma segmentation. Future work should focus on improving model interpretability, lowering computational costs, and boosting generalizability. Tools like NeuroQuant® and Raidionics demonstrate potential for clinical translation. Further refinement could enable regulatory approval, advancing precision in brain tumor diagnosis and treatment planning.
多参数磁共振成像（mpMRI）是诊断脑肿瘤（尤其是胶质瘤）的金标准，由于胶质瘤具有异质性和不同的子区域，因此难以进行分割。虽然手动分割既耗时又容易出错，但深度学习（DL）能够以更高的准确性和速度使分割过程自动化。
我们对调查的文章进行了消融研究，以评估“附加”模块（解决诸如空间信息丢失、类别不平衡和过拟合等挑战）对胶质瘤分割性能的影响。
先进的模块，如实心（扩张）卷积、inception、注意力、Transformer和混合模块，显著提高了分割准确性、效率、多尺度特征提取和边界描绘，而轻量级模块降低了计算复杂度。在脑肿瘤分割（BraTS）数据集（包括低级别和高级别胶质瘤）上的实验证实了它们的鲁棒性，表现最佳的模型在肿瘤子区域获得了较高的Dice分数。
本综述强调了在胶质瘤分割中需要进行最佳模块选择和布局，以平衡速度、准确性和可解释性。未来的工作应集中在提高模型的可解释性、降低计算成本和提高泛化能力上。NeuroQuant®和Raidionics等工具显示了临床转化的潜力。进一步完善可能会获得监管批准，提高脑肿瘤诊断和治疗计划的精准度。
