Balanced transformer: efficient classification of glioblastoma and primary central nervous system lymphoma.

Researchers

Journal

Modalities

Models

Abstract

Primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM) are malignant primary brain tumors with different biological characteristics. Great differences exist between the treatment strategies of PCNSL and GBM. Thus, accurately distinguishing between PCNSL and GBM before surgery is very important for guiding neurosurgery. At present, the spinal fluid of patients is commonly extracted to find tumor markers for diagnosis. However, this method not only causes secondary injury to patients, but also easily delays treatment. Although diagnosis using radiology images is non-invasive, the morphological features and texture features of the two in magnetic resonance imaging (MRI) are quite similar, making distinction with human eyes and image diagnosis very difficult. We proposed the Balanced Transformer, can automatically distinguish between PCNSL and GBM using MRI images based on deep learning to provide an accurate and reliable auxiliary diagnostic basis for radiologists. This model was optimized in terms of data, features, and objective functions. Data enhancement strategy can improve the performance of small sample size. The balanced patch partition can effectively apply the original data information without increasing computing resources, further expand the receptive field and extract high-dimensional data information with high quality. In order to improve the performance of ROC curve prediction, the balanced sample module is proposed. Benefiting from the overall balance design, we conducted an experiment using Balanced Transformer and obtained an accuracy of 99.89%, sensitivity of 99.74%, specificity of 99.73% and AUC of 99.19%, which is far higher than the previous results (accuracy of 89.6% ~ 96.8%, sensitivity of 74.3% ~ 91.3%, specificity of 88.9% ~ 96.02% and AUC of 87.8 % ~ 94.9%). Because GBM is a common type of malignant tumor, the 1% improvement in accuracy has saved many patients and reduced treatment times considerably. Thus,it can provide doctors with a good basis for auxiliary diagnosis.© 2024 Institute of Physics and Engineering in Medicine.