From the Computational NeuroSurgery Lab (Jose, Liu, Russo, Di Ieva), Macquarie University, Sydney, Australia.
Australian Institute of Health Innovation, Centre for Health Informatics (Liu), Macquarie University, Sydney, Australia.
Arch Pathol Lab Med. 2023 Aug 1;147(8):916-924. doi: 10.5858/arpa.2021-0518-OA.
CONTEXT.—: Glioma is the most common primary brain tumor in adults. The diagnosis and grading of different pathological subtypes of glioma is essential in treatment planning and prognosis.
OBJECTIVE.—: To propose a deep learning-based approach for the automated classification of glioma histopathology images. Two classification methods, the ensemble method based on 2 binary classifiers and the multiclass method using a single multiclass classifier, were implemented to classify glioma images into astrocytoma, oligodendroglioma, and glioblastoma, according to the 5th edition of the World Health Organization classification of central nervous system tumors, published in 2021.
DESIGN.—: We tested 2 different deep neural network architectures (VGG19 and ResNet50) and extensively validated the proposed approach based on The Cancer Genome Atlas data set (n = 700). We also studied the effects of stain normalization and data augmentation on the glioma classification task.
RESULTS.—: With the binary classifiers, our model could distinguish astrocytoma and oligodendroglioma (combined) from glioblastoma with an accuracy of 0.917 (area under the curve [AUC] = 0.976) and astrocytoma from oligodendroglioma (accuracy = 0.821, AUC = 0.865). The multiclass method (accuracy = 0.861, AUC = 0.961) outperformed the ensemble method (accuracy = 0.847, AUC = 0.933) with the best performance displayed by the ResNet50 architecture.
CONCLUSIONS.—: With the high performance of our model (>80%), the proposed method can assist pathologists and physicians to support examination and differential diagnosis of glioma histopathology images, with the aim to expedite personalized medical care.
脑胶质瘤是成人中最常见的原发性脑肿瘤。不同病理亚型脑胶质瘤的诊断和分级对于治疗计划和预后至关重要。
提出一种基于深度学习的脑胶质瘤组织病理学图像自动分类方法。根据 2021 年发布的第 5 版世界卫生组织中枢神经系统肿瘤分类，我们采用 2 种分类方法，即基于 2 个二分类器的集成方法和使用单个多分类器的多类方法，将脑胶质瘤图像分类为星形细胞瘤、少突胶质细胞瘤和胶质母细胞瘤。
我们测试了 2 种不同的深度神经网络架构（VGG19 和 ResNet50），并基于癌症基因组图谱数据集（n = 700）对提出的方法进行了广泛验证。我们还研究了染色归一化和数据增强对脑胶质瘤分类任务的影响。
使用二分类器，我们的模型可以区分星形细胞瘤和少突胶质细胞瘤（联合）与胶质母细胞瘤，准确率为 0.917（曲线下面积[AUC] = 0.976），星形细胞瘤与少突胶质细胞瘤的准确率为 0.821，AUC 为 0.865。多类方法（准确率 = 0.861，AUC = 0.961）优于集成方法（准确率 = 0.847，AUC = 0.933），其中 ResNet50 架构的性能最佳。
我们的模型性能高（>80%），该方法可以辅助病理学家和医生检查和鉴别脑胶质瘤组织病理学图像，旨在加快个性化医疗。
