Radiomics Group, Vall d'Hebron Institute of Oncology (VHIO), 08035 Barcelona, Spain.
Radiology Department, Bellvitge University Hospital, 08907 Barcelona, Spain; Neuro-Oncology Unit, Institut d'Investigacio Biomedica de Bellvitge (IDIBELL), 08907 Barcelona, Spain.
Cell Rep Med. 2024 Mar 19;5(3):101464. doi: 10.1016/j.xcrm.2024.101464. Epub 2024 Mar 11.
Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on ∼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.
目前，脑肿瘤的无创鉴别诊断基于磁共振成像（MRI）与动态磁敏感对比（DSC）的评估。然而，明确的诊断通常需要神经外科干预，这会影响患者的生活质量。我们在经组织学证实的脑胶质瘤、转移瘤或淋巴瘤患者的 DSC 图像上应用深度学习。在 40 名患者的约 50000 个体素上训练的卷积神经网络提供肿瘤内概率图，从而得出临床级别的诊断。该模型在 400 个额外病例和 128 个外部验证队列中进行了测试。该工具的三分类准确率为 0.78，优于传统的 MRI 指标脑血容量（0.55）和信号恢复百分比（0.59），作为一种支持性诊断工具具有很高的价值。我们的开源软件 Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology（DISCERN），通过使用标准的 MRI 辅助神经肿瘤学中的脑肿瘤诊断，展示了其在辅助医疗决策方面的潜力。
