Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer.
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 dat...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2024-01-01
|
Series: | PLoS ONE |
Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297331&type=printable |
_version_ | 1797261753775554560 |
---|---|
author | Yuting Xue Dongxu Zhang Liye Jia Wanting Yang Juanjuan Zhao Yan Qiang Long Wang Ying Qiao Huajie Yue |
author_facet | Yuting Xue Dongxu Zhang Liye Jia Wanting Yang Juanjuan Zhao Yan Qiang Long Wang Ying Qiao Huajie Yue |
author_sort | Yuting Xue |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-24T23:46:14Z |
format | Article |
id | doaj.art-12459b3ccd42423f9c3ffa96325884e1 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-24T23:46:14Z |
publishDate | 2024-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-12459b3ccd42423f9c3ffa96325884e12024-03-15T05:31:15ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-01193e029733110.1371/journal.pone.0297331Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer.Yuting XueDongxu ZhangLiye JiaWanting YangJuanjuan ZhaoYan QiangLong WangYing QiaoHuajie YueKRAS 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.https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297331&type=printable |
spellingShingle | Yuting Xue Dongxu Zhang Liye Jia Wanting Yang Juanjuan Zhao Yan Qiang Long Wang Ying Qiao Huajie Yue Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. PLoS ONE |
title | Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. |
title_full | Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. |
title_fullStr | Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. |
title_full_unstemmed | Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. |
title_short | Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer. |
title_sort | integrating image and gene data with a semi supervised attention model for prediction of kras gene mutation status in non small cell lung cancer |
url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0297331&type=printable |
work_keys_str_mv | AT yutingxue integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT dongxuzhang integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT liyejia integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT wantingyang integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT juanjuanzhao integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT yanqiang integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT longwang integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT yingqiao integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer AT huajieyue integratingimageandgenedatawithasemisupervisedattentionmodelforpredictionofkrasgenemutationstatusinnonsmallcelllungcancer |