DADFN: dynamic adaptive deep fusion network based on imaging genomics for prediction recurrence of lung cancer

Abstract

Objective. Recently, imaging genomics has increasingly shown great potential for predicting postoperative recurrence of lung cancer patients. However, prediction methods based on imaging genomics have some disadvantages such as small sample size, high-dimensional information redundancy and poor multimodal fusion efficiency. This study aim to develop a new fusion model to overcome these challenges. Approach. In this study, a dynamic adaptive deep fusion network (DADFN) model based on imaging genomics is proposed for predicting recurrence of lung cancer. In this model, the 3D spiral transformation is used to augment the dataset, which better retains the 3D spatial information of the tumor for deep feature extraction. The intersection of genes screened by LASSO, F-test and CHI-2 selection methods is used to eliminate redundant data and retain the most relevant gene features for the gene feature extraction. A dynamic adaptive fusion mechanism based on the cascade idea is proposed, and multiple different types of base classifiers are integrated in each layer, which can fully utilize the correlation and diversity between multimodal information to better fuse deep features, handcrafted features and gene features. Main results. The experimental results show that the DADFN model achieves good performance, and its accuracy and AUC are 0.884 and 0.863, respectively. This indicates that the model is effective in predicting lung cancer recurrence. Significance. The proposed model has the potential to help physicians to stratify the risk of lung cancer patients and can be used to identify patients who may benefit from a personalized treatment option.

Sacroiliitis diagnosis based on interpretable features and multi-task learning

“…Yang et al (2022) reduced the false positive rate through the application of radiomics in DL based segmentation tasks. Jia et al (2023) proposed a method of classification that combined DL and imaging genomics. Therefore, we proposed a new method of classifying sacroiliitis that used both DL features and radiomics features.…”

Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer

“…Since the vast gene dataset contains more than 20,000 gene expression data per patient, the huge amount of gene expression data can significantly increase the computational cost and decrease the prediction accuracy. Therefore, before training the model, we screened the gene expression data from RNA-seq sequencing by the feature selection algorithm [ 29 ] to retain the most relevant genes with KRAS mutations. A total of 115 relevant genes were finally screened.…”

Deep Learning of radiology-genomics integration for computational oncology: A mini review

“… Cancer type Study ID Study Objective Integration method Reference list Gliomas G1 Molecular subtype - Buda, M. et al [108] G2 Molecular subtype - Li, Y. et al [109] Breast cancer B1 Oncotype Dx RS - Ha, R. et al [110] B2 Predicting molecular subtypes - Ha, R. et al [111] B3 Molecular subtypes - Zhang, Y. et al [112] Lung cancer L1 Gene mutation prediction - Hosny, A. et al [113] L2 Gene mutation prediction - Song, Y. [42] L3 Molecular subtype - Yamamoto, S. et al [114] Medulloblastoma M1 Molecular subtypes - Dasgupta, A. et al [115] Renal Cancer R1 Prognosis Prediction Early fusion Schulz, S. et al [44] Colorectal cancer C1 metastasis prediction Early fusion Zhao, J. et al [43] Lung cancer L4 Recurrence prediction Intermediate fusion Jia, L. et al [116] Brain cancer ...…”