Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma
Abstract Background To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). Methods Retrospective data from 516 LADC patients, encompassing preoperati...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2024-03-01
|
Series: | BMC Medical Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12880-024-01232-5 |
_version_ | 1797272792487428096 |
---|---|
author | Xiaonan Shao Xinyu Ge Jianxiong Gao Rong Niu Yunmei Shi Xiaoliang Shao Zhenxing Jiang Renyuan Li Yuetao Wang |
author_facet | Xiaonan Shao Xinyu Ge Jianxiong Gao Rong Niu Yunmei Shi Xiaoliang Shao Zhenxing Jiang Renyuan Li Yuetao Wang |
author_sort | Xiaonan Shao |
collection | DOAJ |
description | Abstract Background To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). Methods Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training (n = 404) and test sets (n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values. Results TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849–0.917) in the training set and 0.730 (95%CI = 0.629–0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823–0.919) in the training set and 0.760 (95%CI = 0.638–0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities. Conclusion PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment. |
first_indexed | 2024-03-07T14:34:51Z |
format | Article |
id | doaj.art-eacda03bf80b4cd899c9b73435d7bcea |
institution | Directory Open Access Journal |
issn | 1471-2342 |
language | English |
last_indexed | 2024-03-07T14:34:51Z |
publishDate | 2024-03-01 |
publisher | BMC |
record_format | Article |
series | BMC Medical Imaging |
spelling | doaj.art-eacda03bf80b4cd899c9b73435d7bcea2024-03-05T20:43:47ZengBMCBMC Medical Imaging1471-23422024-03-0124111310.1186/s12880-024-01232-5Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinomaXiaonan Shao0Xinyu Ge1Jianxiong Gao2Rong Niu3Yunmei Shi4Xiaoliang Shao5Zhenxing Jiang6Renyuan Li7Yuetao Wang8Department of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityDepartment of Radiology, The Third Affiliated Hospital of Soochow UniversityInterdisciplinary Institute of Neuroscience and Technology, School of Medicine, Zhejiang UniversityDepartment of Nuclear Medicine, The Third Affiliated Hospital of Soochow UniversityAbstract Background To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). Methods Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training (n = 404) and test sets (n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values. Results TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849–0.917) in the training set and 0.730 (95%CI = 0.629–0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823–0.919) in the training set and 0.760 (95%CI = 0.638–0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities. Conclusion PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment.https://doi.org/10.1186/s12880-024-01232-5Lung adenocarcinomaPositron emission tomography/computed tomographyDeep learning; radiomicsEpidermal growth factor receptor |
spellingShingle | Xiaonan Shao Xinyu Ge Jianxiong Gao Rong Niu Yunmei Shi Xiaoliang Shao Zhenxing Jiang Renyuan Li Yuetao Wang Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma BMC Medical Imaging Lung adenocarcinoma Positron emission tomography/computed tomography Deep learning; radiomics Epidermal growth factor receptor |
title | Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma |
title_full | Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma |
title_fullStr | Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma |
title_full_unstemmed | Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma |
title_short | Transfer learning–based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma |
title_sort | transfer learning based pet ct three dimensional convolutional neural network fusion of image and clinical information for prediction of egfr mutation in lung adenocarcinoma |
topic | Lung adenocarcinoma Positron emission tomography/computed tomography Deep learning; radiomics Epidermal growth factor receptor |
url | https://doi.org/10.1186/s12880-024-01232-5 |
work_keys_str_mv | AT xiaonanshao transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT xinyuge transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT jianxionggao transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT rongniu transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT yunmeishi transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT xiaoliangshao transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT zhenxingjiang transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT renyuanli transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma AT yuetaowang transferlearningbasedpetctthreedimensionalconvolutionalneuralnetworkfusionofimageandclinicalinformationforpredictionofegfrmutationinlungadenocarcinoma |