Improving the Automated Diagnosis of Breast Cancer with Mesh Reconstruction of Ultrasound Images Incorporating 3D Mesh Features and a Graph Attention Network

Abstract

This study proposes a novel approach for breast tumor classification from ultrasound images into benign and malignant by converting the region of interest (ROI) of a 2D ultrasound image into a 3D representation using the point-e system, allowing for in-depth analysis of underlying characteristics. Instead of relying solely on 2D imaging features, this method extracts 3D mesh features that describe tumor patterns more precisely. Ten informative and medically relevant mesh features are extracted and assessed with two feature selection techniques. Additionally, a feature pattern analysis has been conducted to determine the feature's significance. A feature table with dimensions of 445 × 12 is generated and a graph is constructed, considering the rows as nodes and the relationships among the nodes as edges. The Spearman correlation coefficient method is employed to identify edges between the strongly connected nodes (with a correlation score greater than or equal to 0.7), resulting in a graph containing 56,054 edges and 445 nodes. A graph attention network (GAT) is proposed for the classification task and the model is optimized with an ablation study, resulting in the highest accuracy of 99.34%. The performance of the proposed model is compared with ten machine learning (ML) models and one-dimensional convolutional neural network where the test accuracy of these models ranges from 73 to 91%. Our novel 3D mesh-based approach, coupled with the GAT, yields promising performance for breast tumor classification, outperforming traditional models, and has the potential to reduce time and effort of radiologists providing a reliable diagnostic system.

Keywords: Breast tumor; Feature extraction; Graph attention network (GAT); Mesh; Point cloud; Ultrasound.

Fig. 1

Samples of breast ultrasound images. a Image of a benign tumor and b image of a malignant tumor with their corresponding ground truths

Fig. 2

Overview of the methodology pipeline for breast tumor classification (A: dataset and ROI extraction, B: mesh generation, C: mesh filtering and mesh feature extraction, D: feature selection and graph generation, E: model selection, F: analysis of results)

Fig. 3

Mesh generation from the 2D breast ROI

Fig. 4

Tumor ROIs with their corresponding meshes

Fig. 5

Visualization of the mesh with bounding box and curvature

Fig. 6

MRMR ranking the mesh features based on their relevance with target groups

Fig. 7

Mechanism graph of attention layer processing

Fig. 8

Proposed model architecture after ablation study

Fig. 9

Confusion matrix of proposed model

Fig. 10

Loss and accuracy curve of the proposed GNN model

Fig. 11

Five-fold cross validation for performance analysis