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

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

doi:10.1016/j.engappai.2023.106140

Cited by 3 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig 6 shows a visual comparison of the six classification performance metrics after replacing the IntraFC module in I 2 MGAF with addition, concatenation, and AFF Block, respectively. From Fig 6 , we find that the Concatenation fusion method achieves the lowest AUC value, so the [ 5 – 9 ] method cannot fully take advantage of the multimodal information. AFF Block is 5.9% lower than our IntraFC in AUC.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…We compare our S 2 MMAM with current multimodal classification models that have better results. The competing methods include Multimodal Feature Fusion Diagnostic Model (MFFDM) [ 39 ], PLNM [ 9 ]. Note that we reproduce the above methods on the same test set for the sake of fairness.…”

Section: Discussionmentioning

confidence: 99%

“…They used the fusion of radiological features of CT images and clinical information of patients to improve the accuracy of the model to predict KRAS gene mutations. Hou et al [ 9 ] proposed a multimodal information fusion module based on attention that successfully predicted lymph node metastasis using deep learning features of CT images fused with genetic data. Therefore, machine learning and deep learning-based imaging genomics approaches have great potential and application in predicting KRAS gene mutation status in NSCLC.…”

Section: Introductionmentioning

confidence: 99%

“…Although the above model achieved considerable performance, there are still some challenges in the study of deep learning methods based on image and genetic data for predicting KRAS mutation status in NSCLC: 1) Majority of deep learning methods [ 8 , 9 ] that study classification tasks focus only on classification methods. However, these studies did not use the segmentation features generated by the segmentation task to facilitate the classification task to improve the performance and effectiveness of the classification task.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Xue,

Zhang,

Jia

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

KRAS is a pathogenic gene frequently implicated in non-small cell lung cancer (NSCLC). However, biopsy as a diagnostic method has practical limitations. Therefore, it is important to accurately determine the mutation status of the KRAS gene non-invasively by combining NSCLC CT images and genetic data for early diagnosis and subsequent targeted therapy of patients. This paper proposes a Semi-supervised Multimodal Multiscale Attention Model (S2MMAM). S2MMAM comprises a Supervised Multilevel Fusion Segmentation Network (SMF-SN) and a Semi-supervised Multimodal Fusion Classification Network (S2MF-CN). S2MMAM facilitates the execution of the classification task by transferring the useful information captured in SMF-SN to the S2MF-CN to improve the model prediction accuracy. In SMF-SN, we propose a Triple Attention-guided Feature Aggregation module for obtaining segmentation features that incorporate high-level semantic abstract features and low-level semantic detail features. Segmentation features provide pre-guidance and key information expansion for S2MF-CN. S2MF-CN shares the encoder and decoder parameters of SMF-SN, which enables S2MF-CN to obtain rich classification features. S2MF-CN uses the proposed Intra and Inter Mutual Guidance Attention Fusion (I2MGAF) module to first guide segmentation and classification feature fusion to extract hidden multi-scale contextual information. I2MGAF then guides the multidimensional fusion of genetic data and CT image data to compensate for the lack of information in single modality data. S2MMAM achieved 83.27% AUC and 81.67% accuracy in predicting KRAS gene mutation status in NSCLC. This method uses medical image CT and genetic data to effectively improve the accuracy of predicting KRAS gene mutation status in NSCLC.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Xue,

Zhang,

Jia

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The researchers extracted 2D images from 3D data and preserved the spatial correlation of the original texture and edge information. This approach expanded the sample size of the image data to facilitate subsequent prediction [23]. According to reference [7], the researchers utilize an epigenomic tensor, a multidimensional representation of epigenetic data, to analyze complex biological datasets.…”

Section: Tucker Decompositionmentioning

confidence: 99%

Tensor decompositions in cancer study; A comprehensive review

Movahed,

Koleini,

Tabrizi

EPiC Series in Computing

View full text Add to dashboard Cite

Tensor decomposition techniques have gained significant attention in cancer research due to their ability to unravel complex and high-dimensional data structures. In this study, we comprehensively review the research trends from 2013 to 2023. Several themes are dis- cussed, including the problems and challenges regarding cancer datasets, specifically image data and omics data. We also explore proposed tensor decomposition algorithms to tackle these challenges and their applications in different types of cancer, as well as the limita- tions and shortcomings of this field, which call for further research and development. Our objective is to investigate the application of tensor decomposition methods in cancer re- search. We first introduce the concept of tensors as multidimensional arrays and highlight their relevance in modeling cancer data. Subsequently, we discuss various tensor decom- position algorithms, such as Tucker decomposition and Canonical Polyadic decomposition, along with their advantages and limitations. This review aims to assist researchers inter- ested in tensor decomposition techniques, which offer a valuable tool for analyzing complex and heterogeneous cancer data, enabling the discovery of hidden patterns and providing biological insights.

show abstract