Neural Network Classification Algorithm Based on Self-attention Mechanism and Ensemble Learning for MASLD Ultrasound Images

• Published in: Ultrasound in medicine & biology Vol. 50; no. 9; pp. 1361 - 1371
• Main Authors: Guo, Lijuan, Shi, Liling, Wang, Wenjuan, Wang, Xiaotong
• Format: Journal Article
• Language: English
• Published: England Elsevier Inc 01.09.2024
• Subjects: Algorithms; Attention mechanism; Computer-aided diagnosis; Fatty Liver - diagnostic imaging; Humans; Image Interpretation, Computer-Assisted - methods; Liver - diagnostic imaging; Machine Learning; MASLD; Multi-classification; Multi-scale feature aggregation; Neural Networks, Computer; Radiology; Stacking ensemble learning; Ultrasonography - methods; Ultrasound image; VGG16 network; Attention mechanism; VGG16 network; Ultrasound image; Stacking ensemble learning; Multi-classification; Multi-scale feature aggregation; MASLD; Computer-aided diagnosis
• ISSN: 0301-5629; 1879-291X; 1879-291X
• DOI: 10.1016/j.ultrasmedbio.2024.05.011

Ultrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD. We propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images. Our proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection.