Lv Cheng, Shu Xu-Jun, Liang Quan, Qiu Jun, Xiong Zi-Cheng, Ye Jing Bo, Li Shang Bo, Liu Cheng Qing, Niu Jing Zhen, Chen Sheng-Bo, Rao Hong
School of Mathematics and Computer Sciences, Nanchang University, Nanchang, Jiangxi, China.
Department of Neurosurgery, General Hospital of Eastern Theater Command, Nanjing, China.
Front Oncol. 2025 May 20;15:1585891. doi: 10.3389/fonc.2025.1585891. eCollection 2025.
Accurate diagnosis of brain tumors significantly impacts patient prognosis and treatment planning. Traditional diagnostic methods primarily rely on clinicians' subjective interpretation of medical images, which is heavily dependent on physician experience and limited by time consumption, fatigue, and inconsistent diagnoses. Recently, deep learning technologies, particularly Convolutional Neural Networks (CNN), have achieved breakthrough advances in medical image analysis, offering a new paradigm for automated precise diagnosis. However, existing research largely focuses on single-task modeling, lacking comprehensive solutions that integrate tumor segmentation with classification diagnosis. This study aims to develop a multi-task deep learning model for precise brain tumor segmentation and type classification.
The study included 485 pathologically confirmed cases, comprising T1-enhanced MRI sequence images of high-grade gliomas, metastatic tumors, and meningiomas. The dataset was proportionally divided into training (378 cases), testing (109 cases), and external validation (51 cases) sets. We designed and implemented BrainTumNet, a deep learning-based multi-task framework featuring an improved encoder-decoder architecture, adaptive masked Transformer, and multi-scale feature fusion strategy to simultaneously perform tumor region segmentation and pathological type classification. Five-fold cross-validation was employed for result verification.
In the test set evaluation, BrainTumNet achieved an Intersection over Union (IoU) of 0.921, Hausdorff Distance (HD) of 12.13, and Dice Similarity Coefficient (DSC) of 0.91 for tumor segmentation. For tumor classification, it attained a classification accuracy of 93.4% with an Area Under the ROC Curve (AUC) of 0.96. Performance remained stable on the external validation set, confirming the model's generalization capability.
The proposed BrainTumNet model achieves high-precision diagnosis of brain tumor segmentation and classification through a multi-task learning strategy. Experimental results demonstrate the model's strong potential for clinical application, providing objective and reliable auxiliary information for preoperative assessment and treatment decision-making in brain tumor cases.
脑肿瘤的准确诊断对患者预后和治疗方案制定有着重大影响。传统诊断方法主要依赖临床医生对医学图像的主观解读，这严重依赖医生经验，且受时间消耗、疲劳以及诊断不一致性的限制。近年来，深度学习技术，尤其是卷积神经网络（CNN），在医学图像分析领域取得了突破性进展，为自动化精确诊断提供了新的范例。然而，现有研究主要集中在单任务建模，缺乏将肿瘤分割与分类诊断相结合的综合解决方案。本研究旨在开发一种用于精确脑肿瘤分割和类型分类的多任务深度学习模型。
本研究纳入485例经病理证实的病例，包括高级别胶质瘤、转移瘤和脑膜瘤的T1增强MRI序列图像。数据集按比例分为训练集（378例）、测试集（109例）和外部验证集（51例）。我们设计并实现了BrainTumNet，这是一个基于深度学习的多任务框架，具有改进的编码器 - 解码器架构、自适应掩码Transformer和多尺度特征融合策略，以同时进行肿瘤区域分割和病理类型分类。采用五折交叉验证进行结果验证。
在测试集评估中，BrainTumNet在肿瘤分割方面的交并比（IoU）为0.921，豪斯多夫距离（HD）为12.13，骰子相似系数（DSC）为0.91。对于肿瘤分类，其分类准确率为93.4%，ROC曲线下面积（AUC）为0.96。在外部验证集上性能保持稳定，证实了模型的泛化能力。
所提出的BrainTumNet模型通过多任务学习策略实现了脑肿瘤分割和分类的高精度诊断。实验结果表明该模型在临床应用中具有强大潜力，为脑肿瘤病例的术前评估和治疗决策提供客观可靠的辅助信息。
