The value of convolutional neural networks-based deep learning model in differential diagnosis of space-occupying brain diseases

Abstract

Objectives: It is still a challenge to differentiate space-occupying brain lesions such as tumefactive demyelinating lesions (TDLs), tumefactive primary angiitis of the central nervous system (TPACNS), primary central nervous system lymphoma (PCNSL), and brain gliomas. Convolutional neural networks (CNNs) have been used to analyze complex medical data and have proven transformative for image-based applications. It can quickly acquire diseases' radiographic features and correct doctors' diagnostic bias to improve diagnostic efficiency and accuracy. The study aimed to assess the value of CNN-based deep learning model in the differential diagnosis of space-occupying brain diseases on MRI.

Methods: We retrospectively analyzed clinical and MRI data from 480 patients with TDLs (n = 116), TPACNS (n = 64), PCNSL (n = 150), and brain gliomas (n = 150). The patients were randomly assigned to training (n = 240), testing (n = 73), calibration (n = 96), and validation (n = 71) groups. And a CNN-implemented deep learning model guided by clinical experts was developed to identify the contrast-enhanced T₁-weighted sequence lesions of these four diseases. We utilized accuracy, sensitivity, specificity, and area under the curve (AUC) to evaluate the performance of the CNN model. The model's performance was then compared to the neuroradiologists' diagnosis.

Results: The CNN model had a total accuracy of 87% which was higher than senior neuroradiologists (74%), and the AUC of TDLs, PCNSL, TPACNS and gliomas were 0.92, 0.92, 0.89 and 0.88, respectively.

Conclusion: The CNN model can accurately identify specific radiographic features of TDLs, TPACNS, PCNSL, and gliomas. It has the potential to be an effective auxiliary diagnostic tool in the clinic, assisting inexperienced clinicians in reducing diagnostic bias and improving diagnostic efficiency.

Keywords: convolutional neural network; diagnosis; differential; magnetic resonance imaging; space-occupying brain lesions; tumefactive demyelinating lesions.

Figure 1

Representative MR images of clipped regions of interest (ROIs) for the four types of diseases. Each row represents a distinct disease, and each image is from a different patient. (A) ROIs from TDLs. (B) ROIs from TPACNS. (C) ROIs from PCNSL. (D) ROIs from gliomas.

Figure 2

Flow chart of the training of the CNN model.

Figure 3

Human-computer interface. (A) ROI select interface. (B) Output interface.

Figure 4

The receiver operating characteristic (ROC) curve of the four different diseases. False positive rate (FPR) = 1-specificity, True positive rate (TPR) = sensitivity.