Astrocytoma
The newest revision of the WHO classification of tumors of the central nervous system, also known as WHO 5th edition, introduces substantial changes, especially within the glial tumor category, and separates adult-type and pediatric-type glial tumors into different categories for the first time. In addition, another category of glial tumors, “Circumscribed Astrocytic Gliomas” was also created. This group includes pilocytic astrocytoma, pleomorphic xanthoastrocytoma, subependymal giant cell astrocytoma, chordoid glioma, astroblastoma, and the highly nebulous novel entity high-grade astrocytoma with piloid features 1).
Classification
Diffuse astrocytoma MYB or MYBL1 altered
Circumscribed astrocytic gliomas
High-grade astrocytoma with piloid features
Subependymal giant cell astrocytoma
Desmoplastic infantile ganglioglioma / desmoplastic infantile astrocytoma
OLD
see also Cerebellar astrocytoma
Diffuse astrocytic tumor and oligodendroglial tumor
Other astrocytic tumors
Old classification
see Pilocytic astrocytoma 9421/11
see Pilomyxoid astrocytoma 9425/3*
see Subependymal giant cell astrocytoma 9384/1
see Pleomorphic xanthoastrocytoma 9424/3
see Fibrillary astrocytoma 9420/3
see Gemistocytic astrocytoma 9411/3
see Protoplasmic astrocytoma 9410/3
see Anaplastic astrocytoma 9401/3
Pathogenesis
These tumors are characterized by a significant heterogeneity in terms of cytopathological, transcriptional and (epi)genomic features. This heterogeneity has made these cancers one of the most challenging types of cancers to study and treat. To uncover these complexities and to have better understanding of the disease initiation and progression, identification and characterization of underlying cellular and molecular pathways related to (epi)genetics of astrocytic gliomas is crucial 2).
Differential diagnosis
Oligodendroglioma, and glioblastoma.
Glioma is the most common primary brain tumor in adults. The diagnosis and grading of different pathological subtypes of glioma are essential in treatment planning and prognosis.
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.
Jose L et al. 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.
With the binary classifiers, the 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 score = 0.865). The multiclass method (accuracy = 0.861, AUC score = 0.961) outperformed the ensemble method (accuracy = 0.847, AUC = 0.933) with the best performance displayed by the ResNet50 architecture.
With the high performance of the 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 3)