Liver tumor segmentation method combining multi-axis attention and conditional generative adversarial networks

• Published in: PloS one Vol. 19; no. 12; p. e0312105
• Main Authors: Liao, Jiahao, Wang, Hongyuan, Gu, Hanjie, Cai, Yinghui
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.12.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Analysis; Annotations; Attention; Biology and Life Sciences; Care and treatment; Computational linguistics; Computed tomography; Computer and Information Sciences; Deep Learning; Diagnosis; Engineering and Technology; Generative adversarial networks; Humans; Image enhancement; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Imaging, Three-Dimensional - methods; Information processing; Language processing; Liver; Liver - diagnostic imaging; Liver - pathology; Liver cancer; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - pathology; Liver tumors; Machine learning; Medical diagnosis; Medical imaging; Medicine and Health Sciences; Metric space; Multiaxis; Natural language interfaces; Neural networks; Neural Networks, Computer; Research and Analysis Methods; Segmentation; Social Sciences; Source code; Tomography, X-Ray Computed - methods; Tumors; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0312105

In modern medical imaging-assisted therapies, manual annotation is commonly employed for liver and tumor segmentation in abdominal CT images. However, this approach suffers from low efficiency and poor accuracy. With the development of deep learning, automatic liver tumor segmentation algorithms based on neural networks have emerged, for the improvement of the work efficiency. However, existing liver tumor segmentation algorithms still have several limitations: (1) they often encounter the common issue of class imbalance in liver tumor segmentation tasks, where the tumor region is significantly smaller than the normal tissue region, causing models to predict more negative samples and neglect the tumor region; (2) they fail to adequately consider feature fusion between global contexts, leading to the loss of crucial information; (3) they exhibit weak perception of local details such as fuzzy boundaries, irregular shapes, and small lesions, thereby failing to capture important features. To address these issues, we propose a Multi-Axis Attention Conditional Generative Adversarial Network, referred to as MA-cGAN. Firstly, we propose the Multi-Axis attention mechanism (MA) that projects three-dimensional CT images along different axes to extract two-dimensional features. The features from different axes are then fused by using learnable factors to capture key information from different directions. Secondly, the MA is incorporated into a U-shaped segmentation network as the generator to enhance its ability to extract detailed features. Thirdly, a conditional generative adversarial network is built by combining a discriminator and a generator to enhance the stability and accuracy of the generator’s segmentation results. The MA-cGAN was trained and tested on the LiTS public dataset for the liver and tumor segmentation challenge. Experimental results show that MA-cGAN improves the Dice coefficient, Hausdorff distance, average surface distance, and other metrics compared to the state-of-the-art segmentation models. The segmented liver and tumor models have clear edges, fewer false positive regions, and are closer to the true labels, which plays an active role in medical adjuvant therapy. The source code with our proposed model are available at https : //github . com/jhliao0525/MA-cGAN . git .