Histopathological-based brain tumor grading using 2D-3D multi-modal CNN-transformer combined with stacking classifiers

Abstract

Reliability in diagnosing and treating brain tumors depends on the accurate grading of histopathological images. However, limited scalability, adaptability, and interpretability challenge current methods for frequently grading brain tumors to accurately capture complex spatial relationships in histopathological images. This highlights the need for new approaches to overcome these shortcomings. This paper proposes a comprehensive hybrid learning architecture for brain tumor grading. Our pipeline uses complementary feature extraction techniques to capture domain-specific knowledge related to brain tumor morphology, such as texture and intensity patterns. An efficient method of learning hierarchical patterns within the tissue is the 2D-3D hybrid convolution neural network (CNN), which extracts contextual and spatial features. A vision transformer (ViT) additionally learns global relationships between image regions by concentrating on high-level semantic representations from image patches. Finally, a stacking ensemble machine learning classifier is fed concatenated features, allowing it to take advantage of the individual model's strengths and possibly enhance generalization. Our model's performance is evaluated using two publicly accessible datasets: TCGA and DeepHisto. Extensive experiments with ablation studies and cross-dataset evaluation validate the model's effectiveness, demonstrating significant gains in accuracy, precision, and specificity using cross-validation scenarios. In total, our brain tumor grading model outperforms existing methods, achieving an average accuracy, precision, and specificity of 97.1%, 97.1%, and 97.0%, respectively, on the TCGA dataset, and 95%, 94%, and 95% on DeepHisto dataset. Reported results demonstrate how the suggested architecture, which blends deep learning (DL) with domain expertise, can achieve reliable and accurate brain tumor grading.

Keywords: 2D-3D convolutional neural network; Brain tumor grading; Histopathological image analysis; Hybrid deep learning architecture; Stacking classifiers; Vision transformer.

Fig. 1

The proposed framework for grading brain tumor using hybrid feature extraction model.

Fig. 2

The architecture of the hybrid 2D-3D CNN.

Fig. 3

The architectures of (a) Quick Learning Block and (b) Dimension-Reducing Block.

Fig. 4

The ViT architecture.

Fig. 5

The ViT differs from DeepViT in that re-attention is used in place of the self-attention layer inside the transformer block.

Fig. 6

The hybrid model ROC curves for the used datasets: (a) TCGA and (b) DeepHisto.

Fig. 7

Hybrid model confusion matrix for (a) TCGA and (b) DeepHisto Datasets.

Fig. 8

The grad-CAM for the propsed model.