Spatial and geometric learning for classification of breast tumors from multi-center ultrasound images: a hybrid learning approach

• Published in: BMC medical imaging Vol. 24; no. 1; pp. 133 - 12
• Main Authors: Ru, Jintao, Zhu, Zili, Shi, Jialin
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 05-06-2024; BioMed Central; BMC
• Subjects: Adult; Analysis; Artificial intelligence; Artificial neural networks; Blended learning; Breast cancer; Breast Neoplasms - diagnostic imaging; Breast tumor classification; Classification; Convolutional neural network; Datasets; Deep Learning; Federated learning; Female; Graph neural network; Graph neural networks; Graph representations; Graphs; Humans; Image Interpretation, Computer-Assisted - methods; Machine learning; Mammography; Methods; Neural networks; Neural Networks, Computer; Ordinary differential equations; Researchers; Spatial discrimination learning; Thyroid gland; Tumors; Ultrasonic imaging; Ultrasonic testing; Ultrasonography, Mammary - methods; Ultrasound; Ultrasound images; Ultrasound images; Federated learning; Breast tumor classification; Artificial intelligence; Convolutional neural network; Graph neural network
• ISSN: 1471-2342; 1471-2342
• DOI: 10.1186/s12880-024-01307-3

Breast cancer is the most common cancer among women, and ultrasound is a usual tool for early screening. Nowadays, deep learning technique is applied as an auxiliary tool to provide the predictive results for doctors to decide whether to make further examinations or treatments. This study aimed to develop a hybrid learning approach for breast ultrasound classification by extracting more potential features from local and multi-center ultrasound data.
We proposed a hybrid learning approach to classify the breast tumors into benign and malignant. Three multi-center datasets (BUSI, BUS, OASBUD) were used to pretrain a model by federated learning, then every dataset was fine-tuned at local. The proposed model consisted of a convolutional neural network (CNN) and a graph neural network (GNN), aiming to extract features from images at a spatial level and from graphs at a geometric level. The input images are small-sized and free from pixel-level labels, and the input graphs are generated automatically in an unsupervised manner, which saves the costs of labor and memory space.
The classification AUC
of our proposed method is 0.911, 0.871 and 0.767 for BUSI, BUS and OASBUD. The balanced accuracy is 87.6%, 85.2% and 61.4% respectively. The results show that our method outperforms conventional methods.
Our hybrid approach can learn the inter-feature among multi-center data and the intra-feature of local data. It shows potential in aiding doctors for breast tumor classification in ultrasound at an early stage.