Details

Autor(en) / Beteiligte

• Hou, Guojie
• Jia, Liye
• Zhang, Yanan
• Wu, Wei
• Zhao, Lin
• Zhao, Juanjuan
• Wang, Long
• Qiang, Yan

Titel

Deep learning approach for predicting lymph node metastasis in non-small cell lung cancer by fusing image–gene data

Ist Teil von

• Engineering applications of artificial intelligence, 2023-06, Vol.122, p.106140, Article 106140

Ort / Verlag

Elsevier Ltd

Erscheinungsjahr

2023

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• The determination of lymph node metastasis is critical to the selection of treatment options for non-small cell lung cancer. Invasive pathological examinations cannot be performed frequently in clinical practice, thus non-invasive and reproducible methods are needed. The current research on non-invasive prediction methods based on image and genetic information has shortcomings such as small data sample size, high data dimension, and poor multimodal fusion effect. In this research, we propose a method for predicting lymph node metastasis in non-small cell lung cancer by fusing imaging data and genetic data to overcome these challenges. An attention-based multimodal information fusion module is designed to fuse image data and genetic data in the mid-fusion, and a bilinear fusion module based on Tucker decomposition is inserted into the model for late fusion, which significantly improves the performance of multimodal fusion. The 3D spiral transformation method is used to extract 2D images from 3D data, and the transformed images inherit and retain the spatial correlation of the original texture and edge information while increasing the image data sample size for subsequent prediction. The random forest method of important measurement is used for feature selection, and redundant data in gene information is eliminated. The experiments are carried out on the NSCLC-Radiogenomics dataset. The accuracy and AUC of the proposed model are 0.968 and 0.963, respectively. The experimental results show that the model is ideal performance in predicting lymph node metastasis, providing a new method for non-invasive lymph node metastasis prediction, which is beneficial to the application of precision medicine.